To see the other types of publications on this topic, follow the link: EICU Database.
Journal articles on the topic 'EICU Database'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'EICU Database.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Jiang, Hao, Wen Xu, Wenjing Chen, et al. "Value of early critical care transthoracic echocardiography for patients undergoing mechanical ventilation: a retrospective study." BMJ Open 11, no. 10 (2021): e048646. http://dx.doi.org/10.1136/bmjopen-2021-048646.
Full textAbstract:
ObjectivesTo evaluate whether early intensive care transthoracic echocardiography (TTE) can improve the prognosis of patients with mechanical ventilation (MV).DesignA retrospective cohort study.SettingPatients undergoing MV for more than 48 hours, based on the Medical Information Mart for Intensive Care III (MIMIC-III) database and the eICU Collaborative Research Database (eICU-CRD), were selected.Participants2931 and 6236 patients were recruited from the MIMIC-III database and the eICU database, respectively.Primary and secondary outcome measuresThe primary outcome was in-hospital mortality. Secondary outcomes were 30-day mortality from the date of ICU admission, days free of MV and vasopressors 30 days after ICU admission, use of vasoactive drugs, total intravenous fluid and ventilator settings during the first day of MV.ResultsWe used propensity score matching to analyse the association between early TTE and in-hospital mortality and sensitivity analysis, including the inverse probability weighting model and covariate balancing propensity score model, to ensure the robustness of our findings. The adjusted OR showed a favourable effect between the early TTE group and in-hospital mortality (MIMIC: OR 0.78; 95% CI 0.65 to 0.94, p=0.01; eICU-CRD: OR 0.76; 95% CI 0.67 to 0.86, p<0.01). Early TTE was also associated with 30-day mortality in the MIMIC database (OR 0.71, 95% CI 0.57 to 0.88, p=0.001). Furthermore, those who had early TTE had both more ventilation-free days (only in eICU-CRD: 23.48 vs 24.57, p<0.01) and more vasopressor-free days (MIMIC: 18.22 vs 20.64, p=0.005; eICU-CRD: 27.37 vs 28.59, p<0.001) than the control group (TTE applied outside of the early TTE and no TTE at all).ConclusionsEarly application of critical care TTE during MV is beneficial for improving in-hospital mortality. Further investigation with prospectively collected data is required to validate this relationship.
2
Wang, Lu, Jieqing Chen, and Xiang Zhou. "Factors influencing sepsis associated thrombocytopenia (SAT): A multicenter retrospective cohort study." PLOS ONE 20, no. 2 (2025): e0318887. https://doi.org/10.1371/journal.pone.0318887.
Full textAbstract:
Introduction Sepsis associated thrombocytopenia (SAT) is a common complication of sepsis. We designed this study to investigate factors influencing SAT. Methods Patients with sepsis (2984 in Peking union medical college hospital [PUMCH] database, 13165 in eICU Collaborative Research [eICU] database, 11101 in Medical Information Mart for Intensive Care IV [MIMIC-IV] database) were enrolled. Variables included basic information, comorbidities, and organ functions. Multi-variable logistic regression models and artificial neural network model were applied to determine the factors related to SAT. Main results Age and body mass index (BMI) were inversely correlated with the incidence of SAT (p-value 0.175 and 0.049 [PUMCH], p-value 0.000 and 0.000 [eICU], p-value 0.000 and 0.000 [MIMIC-IV]). Hematologic malignancies and other malignancies were positively correlated with the incidence of SAT (p-value 0.000 and 0.000 [PUMCH], p-value 0.000 and 0.000 [eICU], p-value 0.000 and 0.020 [MIMIC-IV]) except other malignancies was inversely correlated with the incidence of SAT in PUMCH database. Norepinephrine (NE) equivalents, total bilirubin (TBIL) and creatinine were positively correlated with the incidence of SAT (p-value 0.000, 0.000 and 0.011 [PUMCH], p-value 0.028, 0.000 and 0.013 [eICU], p-value 0.028, 0.000 and 0.027 [MIMIC-IV]). PaO2 / FiO2 was inversely correlated with the incidence of SAT in PUMCH database (p-value 0.021 [PUMCH]), while it was positively correlated with the incidence of SAT (p-value 0.000 [MIMIC-IV]). PaO2 / FiO2 and SAT was not related (p-value 0.111 [eICU]). TBIL, hematologic malignancies, PaO2 / FiO2 and NE equivalents ranked in the top five significant variables in all three datasets. Conclusions Hematologic malignancies and other malignancies were positively correlated with the incidence of SAT. NE equivalents, TBIL and creatinine were positively correlated with the incidence of SAT. TBIL, hematologic malignancies, PaO2 / FiO2 and NE equivalents ranked in the top significant variables in factors influencing SAT.
3
Kim, Yun Kwan, Won-Doo Seo, Sun Jung Lee, et al. "Early Prediction of Cardiac Arrest in the Intensive Care Unit Using Explainable Machine Learning: Retrospective Study." Journal of Medical Internet Research 26 (September 17, 2024): e62890. http://dx.doi.org/10.2196/62890.
Full textAbstract:
Background Cardiac arrest (CA) is one of the leading causes of death among patients in the intensive care unit (ICU). Although many CA prediction models with high sensitivity have been developed to anticipate CA, their practical application has been challenging due to a lack of generalization and validation. Additionally, the heterogeneity among patients in different ICU subtypes has not been adequately addressed. Objective This study aims to propose a clinically interpretable ensemble approach for the timely and accurate prediction of CA within 24 hours, regardless of patient heterogeneity, including variations across different populations and ICU subtypes. Additionally, we conducted patient-independent evaluations to emphasize the model’s generalization performance and analyzed interpretable results that can be readily adopted by clinicians in real-time. Methods Patients were retrospectively analyzed using data from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) and the eICU-Collaborative Research Database (eICU-CRD). To address the problem of underperformance, we constructed our framework using feature sets based on vital signs, multiresolution statistical analysis, and the Gini index, with a 12-hour window to capture the unique characteristics of CA. We extracted 3 types of features from each database to compare the performance of CA prediction between high-risk patient groups from MIMIC-IV and patients without CA from eICU-CRD. After feature extraction, we developed a tabular network (TabNet) model using feature screening with cost-sensitive learning. To assess real-time CA prediction performance, we used 10-fold leave-one-patient-out cross-validation and a cross–data set method. We evaluated MIMIC-IV and eICU-CRD across different cohort populations and subtypes of ICU within each database. Finally, external validation using the eICU-CRD and MIMIC-IV databases was conducted to assess the model’s generalization ability. The decision mask of the proposed method was used to capture the interpretability of the model. Results The proposed method outperformed conventional approaches across different cohort populations in both MIMIC-IV and eICU-CRD. Additionally, it achieved higher accuracy than baseline models for various ICU subtypes within both databases. The interpretable prediction results can enhance clinicians’ understanding of CA prediction by serving as a statistical comparison between non-CA and CA groups. Next, we tested the eICU-CRD and MIMIC-IV data sets using models trained on MIMIC-IV and eICU-CRD, respectively, to evaluate generalization ability. The results demonstrated superior performance compared with baseline models. Conclusions Our novel framework for learning unique features provides stable predictive power across different ICU environments. Most of the interpretable global information reveals statistical differences between CA and non-CA groups, demonstrating its utility as an indicator for clinical decisions. Consequently, the proposed CA prediction system is a clinically validated algorithm that enables clinicians to intervene early based on CA prediction information and can be applied to clinical trials in digital health.
4
Ziegler, Jennifer, Barret N. M. Rush, Eric R. Gottlieb, Leo Anthony Celi, and Miguel Ángel Armengol de la Hoz. "High resolution data modifies intensive care unit dialysis outcome predictions as compared with low resolution administrative data set." PLOS Digital Health 1, no. 10 (2022): e0000124. http://dx.doi.org/10.1371/journal.pdig.0000124.
Full textAbstract:
High resolution clinical databases from electronic health records are increasingly being used in the field of health data science. Compared to traditional administrative databases and disease registries, these newer highly granular clinical datasets offer several advantages, including availability of detailed clinical information for machine learning and the ability to adjust for potential confounders in statistical models. The purpose of this study is to compare the analysis of the same clinical research question using an administrative database and an electronic health record database. The Nationwide Inpatient Sample (NIS) was used for the low-resolution model, and the eICU Collaborative Research Database (eICU) was used for the high-resolution model. A parallel cohort of patients admitted to the intensive care unit (ICU) with sepsis and requiring mechanical ventilation was extracted from each database. The primary outcome was mortality and the exposure of interest was the use of dialysis. In the low resolution model, after controlling for the covariates that are available, dialysis use was associated with an increased mortality (eICU: OR 2.07, 95% CI 1.75–2.44, p<0.01; NIS: OR 1.40, 95% CI 1.36–1.45, p<0.01). In the high-resolution model, after the addition of the clinical covariates, the harmful effect of dialysis on mortality was no longer significant (OR 1.04, 95% 0.85–1.28, p = 0.64). The results of this experiment show that the addition of high resolution clinical variables to statistical models significantly improves the ability to control for important confounders that are not available in administrative datasets. This suggests that the results from prior studies using low resolution data may be inaccurate and may need to be repeated using detailed clinical data.
5
Sayed, Mohammed, David Riaño, and Jesús Villar. "Predicting Duration of Mechanical Ventilation in Acute Respiratory Distress Syndrome Using Supervised Machine Learning." Journal of Clinical Medicine 10, no. 17 (2021): 3824. http://dx.doi.org/10.3390/jcm10173824.
Full textAbstract:
Background: Acute respiratory distress syndrome (ARDS) is an intense inflammatory process of the lungs. Most ARDS patients require mechanical ventilation (MV). Few studies have investigated the prediction of MV duration over time. We aimed at characterizing the best early scenario during the first two days in the intensive care unit (ICU) to predict MV duration after ARDS onset using supervised machine learning (ML) approaches. Methods: For model description, we extracted data from the first 3 ICU days after ARDS diagnosis from patients included in the publicly available MIMIC-III database. Disease progression was tracked along those 3 ICU days to assess lung severity according to Berlin criteria. Three robust supervised ML techniques were implemented using Python 3.7 (Light Gradient Boosting Machine (LightGBM); Random Forest (RF); and eXtreme Gradient Boosting (XGBoost)) for predicting MV duration. For external validation, we used the publicly available multicenter database eICU. Results: A total of 2466 and 5153 patients in MIMIC-III and eICU databases, respectively, received MV for >48 h. Median MV duration of extracted patients was 6.5 days (IQR 4.4–9.8 days) in MIMIC-III and 5.0 days (IQR 3.0–9.0 days) in eICU. LightGBM was the best model in predicting MV duration after ARDS onset in MIMIC-III with a root mean square error (RMSE) of 6.10–6.41 days, and it was externally validated in eICU with RMSE of 5.87–6.08 days. The best early prediction model was obtained with data captured in the 2nd day. Conclusions: Supervised ML can make early and accurate predictions of MV duration in ARDS after onset over time across ICUs. Supervised ML models might have important implications for optimizing ICU resource utilization and high acute cost reduction of MV.
6
Xu, Yuan, Sheng Chao, and Yulin Niu. "Association between the Predicted Value of APACHE IV Scores and Intensive Care Unit Mortality: A Secondary Analysis Based on EICU Dataset." Computational and Mathematical Methods in Medicine 2022 (April 6, 2022): 1–6. http://dx.doi.org/10.1155/2022/9151925.
Full textAbstract:
Objective. The evidence regarding the relationship between Acute Physiological and Chronic Health Assessment (APACHE) IV scores and emergency intensive care unit (EICU) mortality in patients following organ transplantation remains controversial. The purpose of this study was to investigate the relationship between APACHE IV score and EICU mortality. Methods. Data from 391 American men and women admitted to the EICU after undergoing organ transplants including heart, bone marrow, liver, kidney, lung, and pancreas in the United States. We used this data to analyze the relationship between APACHE IV scores and in-hospital mortality in the postoperative EICU. The primary endpoint was ICU hospitalization mortality after organ transplantation. The entire study data was extracted from the EICU database and uploaded to the DataDryad website. Results. Interaction tests indicate age, respiratory failure, and hormone use can modify the association between APACHE IV and EICU mortality. A stronger association of APACHE and mortality can be observed at <60 years old, no respiratory failure, and no use of hormones. In contrast, there was no association between respiratory failure, hormone use, APACHE, and ICU mortality in patients over 60 years of age. Conclusion. When using the APACHE score for risk stratification of critically ill patients after transplantation, the patient’s age, respiratory failure, and use of hormones should be taken into account.
7
Hu, Tianyang, Wanjun Yao, Yu Li, and Yanan Liu. "Interaction of acute heart failure and acute kidney injury on in-hospital mortality of critically ill patients with sepsis: A retrospective observational study." PLOS ONE 18, no. 3 (2023): e0282842. http://dx.doi.org/10.1371/journal.pone.0282842.
Full textAbstract:
Background The present study aimed to evaluate the synergistic impact of acute heart failure (AHF) and acute kidney injury (AKI) on in-hospital mortality in critically ill patients with sepsis. Methods We undertook a retrospective, observational analysis using data acquired from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and eICU Collaborative Research Database (eICU-CRD). The effects of AKI and AHF on in-hospital mortality were examined using a Cox proportional hazards model. Additive interactions were analyzed using the relative extra risk attributable to interaction. Results A total of 33,184 patients were eventually included, comprising 20,626 patients in the training cohort collected from the MIMIC-IV database and 12,558 patients in the validation cohort extracted from the eICU-CRD database. After multivariate Cox analysis, the independent variables for in-hospital mortality included: AHF only (HR:1.20, 95% CI:1.02–1.41, P = 0.005), AKI only (HR:2.10, 95% CI:1.91–2.31, P < 0.001), and both AHF and AKI (HR:3.80, 95%CI:13.40–4.24, P < 0.001). The relative excess risk owing to interaction was 1.49 (95% CI:1.14–1.87), the attributable percentage due to interaction was 0.39 (95%CI:0.31–0.46), and the synergy index was 2.15 (95%CI:1.75–2.63), demonstrated AHF and AKI had a strong synergic impact on in-hospital mortality. And the findings in the validation cohort indicated identical conclusions to the training cohort. Conclusion Our data demonstrated a synergistic relationship of AHF and AKI on in-hospital mortality in critically unwell patients with sepsis.
8
Tang, Xiao-Wei, Wen-Sen Ren, Shu Huang, et al. "Development and validation of a nomogram for predicting in-hospital mortality of intensive care unit patients with liver cirrhosis." World Journal of Hepatology 16, no. 4 (2024): 625–39. http://dx.doi.org/10.4254/wjh.v16.i4.625.
Full textAbstract:
BACKGROUND Liver cirrhosis patients admitted to intensive care unit (ICU) have a high mortality rate. AIM To establish and validate a nomogram for predicting in-hospital mortality of ICU patients with liver cirrhosis. METHODS We extracted demographic, etiological, vital sign, laboratory test, comorbidity, complication, treatment, and severity score data of liver cirrhosis patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) and electronic ICU (eICU) collaborative research database (eICU-CRD). Predictor selection and model building were based on the MIMIC-IV dataset. The variables selected through least absolute shrinkage and selection operator analysis were further screened through multivariate regression analysis to obtain final predictors. The final predictors were included in the multivariate logistic regression model, which was used to construct a nomogram. Finally, we conducted external validation using the eICU-CRD. The area under the receiver operating characteristic curve (AUC), decision curve, and calibration curve were used to assess the efficacy of the models. RESULTS Risk factors, including the mean respiratory rate, mean systolic blood pressure, mean heart rate, white blood cells, international normalized ratio, total bilirubin, age, invasive ventilation, vasopressor use, maximum stage of acute kidney injury, and sequential organ failure assessment score, were included in the multivariate logistic regression. The model achieved AUCs of 0.864 and 0.808 in the MIMIC-IV and eICU-CRD databases, respectively. The calibration curve also confirmed the predictive ability of the model, while the decision curve confirmed its clinical value. CONCLUSION The nomogram has high accuracy in predicting in-hospital mortality. Improving the included predictors may help improve the prognosis of patients.
9
Yuan, Zhen-nan, Yu-juan Xue, Hai-jun Wang, et al. "A nomogram for predicting hospital mortality of critical ill patients with sepsis and cancer: a retrospective cohort study based on MIMIC-IV and eICU-CRD." BMJ Open 13, no. 9 (2023): e072112. http://dx.doi.org/10.1136/bmjopen-2023-072112.
Full textAbstract:
ObjectiveSepsis remains a high cause of death, particularly in immunocompromised patients with cancer. The study was to develop a model to predict hospital mortality of septic patients with cancer in intensive care unit (ICU).DesignRetrospective observational study.SettingMedical Information Mart for Intensive Care IV (MIMIC IV) and eICU Collaborative Research Database (eICU-CRD).ParticipantsA total of 3796 patients in MIMIC IV and 549 patients in eICU-CRD were included.Primary outcome measuresThe model was developed based on MIMIC IV. The internal validation and external validation were based on MIMIC IV and eICU-CRD, respectively. Candidate factors were processed with the least absolute shrinkage and selection operator regression and cross-validation. Hospital mortality was predicted by the multivariable logistical regression and visualised by the nomogram. The model was assessed by the area under the curve (AUC), calibration curve and decision curve analysis curve.ResultsThe model exhibited favourable discrimination (AUC: 0.726 (95% CI: 0.709 to 0.744) and 0.756 (95% CI: 0.712 to 0.801)) in the internal and external validation sets, respectively, and better calibration capacity than Acute Physiology and Chronic Health Evaluation IV in external validation.ConclusionsDespite that the predicted model was based on a retrospective study, it may also be helpful to predict the hospital morality of patients with solid cancer and sepsis.
10
Wang, Yuxing, Yuhang Tao, Ming Yuan, et al. "Relationship between the albumin-corrected anion gap and short-term prognosis among patients with cardiogenic shock: a retrospective analysis of the MIMIC-IV and eICU databases." BMJ Open 14, no. 10 (2024): e081597. http://dx.doi.org/10.1136/bmjopen-2023-081597.
Full textAbstract:
ObjectivesWe aimed to investigate the association between the albumin-corrected anion gap (ACAG) and the prognosis of cardiogenic shock (CS).DesignA multicentre retrospective cohort study.SettingData were collected from the Medical Information Mart for Intensive Care (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD) datasets.Participants808 and 700 individuals from the MIMIC-IV and eICU-CRD, respectively, who were diagnosed with CS.Primary and secondary outcomesThe primary endpoint was short-term all-cause mortality, including intensive care unit (ICU), in-hospital and 28-day mortality. The secondary endpoints were the 28-day free from the ICU duration and the length of ICU stay.ResultsCS patients were divided into two groups according to the admission ACAG value: the normal ACAG group (≤20 mmol/L) and the high ACAG group (> 20 mmol/L). CS patients with higher ACAG values exhibited increased short-term all-cause mortality rates, including ICU mortality (MIMIC-IV cohort: adjusted HR: 1.43, 95% CI=1.05–1.93, p=0.022; eICU-CRD cohort: adjusted HR: 1.38, 95% CI=1.02–1.86, p=0.036), in-hospital mortality (MIMIC-IV cohort: adjusted HR: 1.31, 95% CI=1.01–1.71, p=0.03; eICU-CRD cohort: adjusted HR: 1.47, 95% CI=1.12–1.94, p=0.006) and 28-day mortality (adjusted HR: 1.42, 95% CI: 1.11 to 1.83, p=0.007). A positive linear correlation was observed between the ACAG value and short-term mortality rates via restricted cubic splines. Compared with the AG, the ACAG presented a larger area under the curve for short-term mortality prediction. In addition, the duration of intensive care was longer, whereas the 28-day free from the ICU duration was shorter in patients with a higher ACAG value in both cohorts.ConclusionThe ACAG value was independently and strongly associated with the prognosis of patients with CS, indicating that the ACAG value is superior to the conventional AG value.
11
Beyer, Sebastian E., Catia Salgado, Ines Garçao, Leo Anthony Celi, and Susana Vieira. "Circadian rhythm in critically ill patients: Insights from the eICU Database." Cardiovascular Digital Health Journal 2, no. 2 (2021): 118–25. http://dx.doi.org/10.1016/j.cvdhj.2021.01.004.
Full text
12
Patel, Sharad, Gurkeerat Singh, Samson Zarbiv, Kia Ghiassi, and Jean-Sebastien Rachoin. "Mortality Prediction Using SaO2/FiO2 Ratio Based on eICU Database Analysis." Critical Care Research and Practice 2021 (November 8, 2021): 1–9. http://dx.doi.org/10.1155/2021/6672603.
Full textAbstract:
Purpose. PaO2 to FiO2 ratio (P/F) is used to assess the degree of hypoxemia adjusted for oxygen requirements. The Berlin definition of Acute Respiratory Distress Syndrome (ARDS) includes P/F as a diagnostic criterion. P/F is invasive and cost-prohibitive for resource-limited settings. SaO2/FiO2 (S/F) ratio has the advantages of being easy to calculate, noninvasive, continuous, cost-effective, and reliable, as well as lower infection exposure potential for staff, and avoids iatrogenic anemia. Previous work suggests that the SaO2/FiO2 ratio (S/F) correlates with P/F and can be used as a surrogate in ARDS. Quantitative correlation between S/F and P/F has been verified, but the data for the relative predictive ability for ICU mortality remains in question. We hypothesize that S/F is noninferior to P/F as a predictive feature for ICU mortality. Using a machine-learning approach, we hope to demonstrate the relative mortality predictive capacities of S/F and P/F. Methods. We extracted data from the eICU Collaborative Research Database. The features age, gender, SaO2, PaO2, FIO2, admission diagnosis, Apache IV, mechanical ventilation (MV), and ICU mortality were extracted. Mortality was the dependent variable for our prediction models. Exploratory data analysis was performed in Python. Missing data was imputed with Sklearn Iterative Imputer. Random assignment of all the encounters, 80% to the training (n = 26690) and 20% to testing (n = 6741), was stratified by positive and negative classes to ensure a balanced distribution. We scaled the data using the Sklearn Standard Scaler. Categorical values were encoded using Target Encoding. We used a gradient boosting decision tree algorithm variant called XGBoost as our model. Model hyperparameters were tuned using the Sklearn RandomizedSearchCV with tenfold cross-validation. We used AUC as our metric for model performance. Feature importance was assessed using SHAP, ELI5 (permutation importance), and a built-in XGBoost feature importance method. We constructed partial dependence plots to illustrate the relationship between mortality probability and S/F values. Results. The XGBoost hyperparameter optimized model had an AUC score of .85 on the test set. The hyperparameters selected to train the final models were as follows: colsample_bytree of 0.8, gamma of 1, max_depth of 3, subsample of 1, min_child_weight of 10, and scale_pos_weight of 3. The SHAP, ELI5, and XGBoost feature importance analysis demonstrates that the S/F ratio ranks as the strongest predictor for mortality amongst the physiologic variables. The partial dependence plots illustrate that mortality rises significantly above S/F values of 200. Conclusion. S/F was a stronger predictor of mortality than P/F based upon feature importance evaluation of our data. Our study is hypothesis-generating and a prospective evaluation is warranted. Take-Home Points. S/F ratio is a noninvasive continuous method of measuring hypoxemia as compared to P/F ratio. Our study shows that the S/F ratio is a better predictor of mortality than the more widely used P/F ratio to monitor and manage hypoxemia.
13
Zheng, Zhuo, Jiawei Luo, Yingchao Zhu, et al. "Development and Validation of a Dynamic Real-Time Risk Prediction Model for Intensive Care Units Patients Based on Longitudinal Irregular Data: Multicenter Retrospective Study." Journal of Medical Internet Research 27 (April 23, 2025): e69293. https://doi.org/10.2196/69293.
Full textAbstract:
Background Timely and accurate prediction of short-term mortality is critical in intensive care units (ICUs), where patients’ conditions change rapidly. Traditional scoring systems, such as the Simplified Acute Physiology Score and Acute Physiology and Chronic Health Evaluation, rely on static variables collected within the first 24 hours of admission and do not account for continuously evolving clinical states. These systems lack real-time adaptability, interpretability, and generalizability. With the increasing availability of high-frequency electronic medical record (EMR) data, machine learning (ML) approaches have emerged as powerful tools to model complex temporal patterns and support dynamic clinical decision-making. However, existing models are often limited by their inability to handle irregular sampling and missing values, and many lack rigorous external validation across institutions. Objective We aimed to develop a real-time, interpretable risk prediction model that continuously assesses ICU patient mortality using irregular, longitudinal EMR data, with improved performance and generalizability over traditional static scoring systems. Methods A time-aware bidirectional attention-based long short-term memory (TBAL) model was developed using EMR data from the MIMIC-IV (Medical Information Mart for Intensive Care) and eICU Collaborative Research Database (eICU-CRD) databases, comprising 176,344 ICU stays. The model incorporated dynamic variables, including vital signs, laboratory results, and medication data, updated hourly, to perform static and continuous mortality risk assessments. External cross-validation and subgroup sensitivity analyses were conducted to evaluate robustness and fairness. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), accuracy, and F1-score. Interpretability was enhanced using integrated gradients to identify key predictors. Results For the static 12-hour to 1-day mortality prediction task, the TBAL model achieved AUROCs of 95.9 (95% CI 94.2-97.5) and 93.3 (95% CI 91.5-95.3) and AUPRCs of 48.5 and 21.6 in MIMIC-IV and eICU-CRD, respectively. Accuracy and F1-scores reached 94.1 and 46.7 in MIMIC-IV and 92.2 and 28.1 in eICU-CRD. In dynamic prediction tasks, AUROCs reached 93.6 (95% CI 93.2-93.9) and 91.9 (95% CI 91.6-92.1), with AUPRCs of 41.3 and 50, respectively. The model maintained high recall for positive cases (82.6% and 79.1% in MIMIC-IV and eICU-CRD). Cross-database validation yielded AUROCs of 81.3 and 76.1, confirming generalizability. Subgroup analysis showed stable performance across age, sex, and severity strata, with top predictors including lactate, vasopressor use, and Glasgow Coma Scale score. Conclusions The TBAL model offers a robust, interpretable, and generalizable solution for dynamic real-time mortality risk prediction in ICU patients. Its ability to adapt to irregular temporal patterns and to provide hourly updated predictions positions it as a promising decision-support tool. Future work should validate its utility in prospective clinical trials and investigate its integration into real-world ICU workflows to enhance patient outcomes.
14
Li, Caifeng, Qian Ren, Zhiqiang Wang, and Guolin Wang. "Early prediction of in-hospital mortality in acute pancreatitis: a retrospective observational cohort study based on a large multicentre critical care database." BMJ Open 10, no. 12 (2020): e041893. http://dx.doi.org/10.1136/bmjopen-2020-041893.
Full textAbstract:
ObjectiveTo develop and validate a prediction model for predicting in-hospital mortality in patients with acute pancreatitis (AP).DesignA retrospective observational cohort study based on a large multicentre critical care database.SettingAll subject data were collected from the eICU Collaborative Research Database (eICU-CRD), which covers 200 859 intensive care unit admissions of 139 367 patients in 208 US hospitals between 2014 and 2015.ParticipantsA total of 746 patients with AP were drawn from eICU-CRD. Due to loss to follow-up (four patients) or incomplete data (364 patients), 378 patients were enrolled in the primary cohort to establish a nomogram model and to conduct internal validation.Primary and secondary outcome measuresThe outcome of the prediction model was in-hospital mortality. All risk factors found significant in the univariate analysis were considered for multivariate analysis to adjust for confounding factors. Then a nomogram model was established. The performance of the nomogram model was evaluated by the concordance index (C-index) and the calibration plot. The nomogram model was internally validated using the bootstrap resampling method. The predictive accuracy of the nomogram model was compared with that of Acute Physiology, Age, and Chronic Health Evaluation (APACHE) IV. Decision curve analysis (DCA) was performed to evaluate and compare the potential net benefit using of different predictive models.ResultsThe overall in-hospital mortality rate is 4.447%. Age, BUN (blood urea nitrogen) and lactate (ABL) were the independent risk factors determined by multivariate analysis. The C-index of nomogram model ABL (0.896 (95% CI 0.825 to 0.967)) was similar to that of APACHE IV (p=0.086), showing a comparable discriminating power. Calibration plot demonstrated good agreement between the predicted and the actual in-hospital mortality. DCA showed that the nomogram model ABL was clinically useful.ConclusionsNomogram model ABL, which used readily available data, exhibited high predictive value for predicting in-hospital mortality in AP.
15
Fong, Nicholas, Jean Feng, Alan Hubbard, Lauren Eyler Dang, and Romain Pirracchio. "IntraCranial pressure prediction AlgoRithm using machinE learning (I-CARE): Training and Validation Study." Critical Care Explorations 6, no. 1 (2023): e1024. http://dx.doi.org/10.1097/cce.0000000000001024.
Full textAbstract:
OBJECTIVES: Elevated intracranial pressure (ICP) is a potentially devastating complication of neurologic injury. Developing an ICP prediction algorithm to help the clinician adjust treatments and potentially prevent elevated ICP episodes. DESIGN: Retrospective study. SETTING: Three hundred thirty-five ICUs at 208 hospitals in the United States. SUBJECTS: Adults patients from the electronic ICU (eICU) Collaborative Research Database was used to train an ensemble machine learning model to predict the ICP 30 minutes in the future. Predictive performance was evaluated using a left-out test dataset and externally evaluated on the Medical Information Mart for Intensive Care-III (MIMIC-III) Matched Waveform Database. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Predictors included age, assigned sex, laboratories, medications and infusions, input/output, Glasgow Coma Scale (GCS) components, and time-series vitals (heart rate, ICP, mean arterial pressure, respiratory rate, and temperature). Each patient ICU stay was divided into successive 95-minute timeblocks. For each timeblock, the model was trained on nontime-varying covariates as well as on 12 observations of time-varying covariates at 5-minute intervals and asked to predict the 5-minute median ICP 30 minutes after the last observed ICP value. Data from 931 patients with ICP monitoring in the eICU dataset were extracted (46,207 timeblocks). The root mean squared error was 4.51 mm Hg in the eICU test set and 3.56 mm Hg in the MIMIC-III dataset. The most important variables driving ICP prediction were previous ICP history, patients’ temperature, weight, serum creatinine, age, GCS, and hemodynamic parameters. CONCLUSIONS: IntraCranial pressure prediction AlgoRithm using machinE learning, an ensemble machine learning model, trained to predict the ICP of a patient 30 minutes in the future based on baseline characteristics and vitals data from the past hour showed promising predictive performance including in an external validation dataset.
16
Chen, Xuanhui, Jiaxin Li, Guangjian Liu, et al. "Identification of Distinct Clinical Phenotypes of Heterogeneous Mechanically Ventilated ICU Patients Using Cluster Analysis." Journal of Clinical Medicine 12, no. 4 (2023): 1499. http://dx.doi.org/10.3390/jcm12041499.
Full textAbstract:
This retrospective study aimed to derive the clinical phenotypes of ventilated ICU patients to predict the outcomes on the first day of ventilation. Clinical phenotypes were derived from the eICU Collaborative Research Database (eICU) cohort via cluster analysis and were validated in the Medical Information Mart for Intensive Care (MIMIC-IV) cohort. Four clinical phenotypes were identified and compared in the eICU cohort (n = 15,256). Phenotype A (n = 3112) was associated with respiratory disease, had the lowest 28-day mortality (16%), and had a high extubation success rate (~80%). Phenotype B (n = 3335) was correlated with cardiovascular disease, had the second-highest 28-day mortality (28%), and had the lowest extubation success rate (69%). Phenotype C (n = 3868) was correlated with renal dysfunction, had the highest 28-day mortality (28%), and had the second-lowest extubation success rate (74%). Phenotype D (n = 4941) was associated with neurological and traumatic diseases, had the second-lowest 28-day mortality (22%), and had the highest extubation success rate (>80%). These findings were validated in the validation cohort (n = 10,813). Additionally, these phenotypes responded differently to ventilation strategies in terms of duration of treatment, but had no difference in mortality. The four clinical phenotypes unveiled the heterogeneity of ICU patients and helped to predict the 28-day mortality and the extubation success rate.
17
O’Halloran, Heather M., Kenneth Kwong, Richard A. Veldhoen, and David M. Maslove. "Characterizing the Patients, Hospitals, and Data Quality of the eICU Collaborative Research Database*." Critical Care Medicine 48, no. 12 (2020): 1737–43. http://dx.doi.org/10.1097/ccm.0000000000004633.
Full text
18
Kang, Sora, Chul Park, Jinseok Lee, and Dukyong Yoon. "Machine Learning Model for the Prediction of Hemorrhage in Intensive Care Units." Healthcare Informatics Research 28, no. 4 (2022): 364–75. http://dx.doi.org/10.4258/hir.2022.28.4.364.
Full textAbstract:
Objectives: Early hemorrhage detection in intensive care units (ICUs) enables timely intervention and reduces the risk of irreversible outcomes. In this study, we aimed to develop a machine learning model to predict hemorrhage by learning the patterns of continuously changing, real-world clinical data.Methods: We used the Medical Information Mart for Intensive Care databases (MIMIC-III and MIMIC-IV). A recurrent neural network was used to predict severe hemorrhage in the ICU. We developed three machine learning models with an increasing number of input features and levels of complexity: model 1 (11 features), model 2 (18 features), and model 3 (27 features). MIMIC-III was used for model training, and MIMIC-IV was split for internal validation. Using the model with the highest performance, external verification was performed using data from a subgroup extracted from the eICU Collaborative Research Database.Results: We included 5,670 ICU admissions, with 3,150 in the training set and 2,520 in the internal test set. A positive correlation was found between model complexity and performance. As a measure of performance, three models developed with an increasing number of features showed area under the receiver operating characteristic (AUROC) curve values of 0.61–0.94 according to the range of input data. In the subgroup extracted from the eICU database for external validation, an AUROC value of 0.74 was observed.Conclusions: Machine learning models that rely on real clinical data can be used to predict patients at high risk of bleeding in the ICU.
19
Glushkov, V. S., E. P. Vdovin, N. V. Ermakov, et al. "An approach for modular database architecture design in the intensive care unit." Medical Doctor and Information Technologies, no. 2 (June 13, 2025): 54–69. https://doi.org/10.25881/18110193_2025_2_54.
Full textAbstract:
This article presents the design of a database intended to optimize the storage and processing of medical data, with a focus on decision support in intensive care and resuscitation. The aim of the study is to develop a logical database model based on advanced principles and methods used in international open database projects, capable of minimizing human error and enhancing the accuracy of real-time patient prognosis. The methodology is founded on a comparative analysis of existing international medical databases, such as MIMIC-IV and eICU. An innovative modular approach was applied in designing the new database, ensuring system flexibility and scalability. The primary outcome is the creation of a logical database model that can be effectively utilized within the Russian healthcare system, including remote and low-resource regions. The logical model was developed taking into account the specifics of medical data, including modules for storing information on hospitalizations, patient condition indicators, laboratory tests, medication prescriptions and other aspects of clinical practice. An important part of the study is the integration of the database with Russian medical information systems and adaptation to national standards and regulatory requirements. The developed architecture of the logical model minimizes the influence of the human factor, automates data analysis and can be used in the development of medical decision support systems. The practical significance lies in improving the quality of medical care and reducing the burden on the staff. The system is applicable in Russian institutions, including remote regions, and contributes to the digitalization of healthcare.
20
Liu, Jialin, Jinfa Wu, Siru Liu, Mengdie Li, Kunchang Hu, and Ke Li. "Predicting mortality of patients with acute kidney injury in the ICU using XGBoost model." PLOS ONE 16, no. 2 (2021): e0246306. http://dx.doi.org/10.1371/journal.pone.0246306.
Full textAbstract:
Purpose The goal of this study is to construct a mortality prediction model using the XGBoot (eXtreme Gradient Boosting) decision tree model for AKI (acute kidney injury) patients in the ICU (intensive care unit), and to compare its performance with that of three other machine learning models. Methods We used the eICU Collaborative Research Database (eICU-CRD) for model development and performance comparison. The prediction performance of the XGBoot model was compared with the other three machine learning models. These models included LR (logistic regression), SVM (support vector machines), and RF (random forest). In the model comparison, the AUROC (area under receiver operating curve), accuracy, precision, recall, and F1 score were used to evaluate the predictive performance of each model. Results A total of 7548 AKI patients were analyzed in this study. The overall in-hospital mortality of AKI patients was 16.35%. The best performing algorithm in this study was XGBoost with the highest AUROC (0.796, p < 0.01), F1(0.922, p < 0.01) and accuracy (0.860). The precision (0.860) and recall (0.994) of the XGBoost model rank second among the four models. Conclusion XGBoot model had obvious advantages of performance compared to the other machine learning models. This will be helpful for risk identification and early intervention for AKI patients at risk of death.
21
Han, Didi, Fengshuo Xu, Luming Zhang, et al. "Early prediction of in-hospital mortality in patients with congestive heart failure in intensive care unit: a retrospective observational cohort study." BMJ Open 12, no. 7 (2022): e059761. http://dx.doi.org/10.1136/bmjopen-2021-059761.
Full textAbstract:
ObjectiveCongestive heart failure (CHF) is a clinical syndrome in which the heart disease progresses to a severe stage. Early diagnosis and risk assessment of death of patients with CHF are critical to prognosis and treatment. The purpose of this study was to establish a nomogram that predicts the in-hospital death of patients with CHF in the intensive care unit (ICU).DesignA retrospective observational cohort study.Setting and participantsData for the study were from 30 411 patients with CHF in the Medical Information Mart for Intensive Care database and the eICU Collaborative Research Database (eICU-CRD).Primary outcomeIn-hospital mortality.MethodsUnivariate logistic regression analysis was used to select risk factors associated with in-hospital mortality of patients with CHF, and multivariate logistic regression was used to build the prediction model. Discrimination, calibration and clinical validity of the model were evaluated by AUC, calibration curve, Hosmer-Lemeshow χ2 test and decision curve analysis, respectively. Finally, data from 15 503 patients with CHF in the multicentre eICU-CRD were used for external validation of the established nomogram.ResultsThe inclusion criteria were met by 15 983 subjects, whose in-hospital mortality rate was 12.4%. Multivariate analysis determined that the independent risk factors were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, hepatic failure (HepF), heart rate, respiratory rate, temperature, systolic blood pressure (SBP), anion gap (AG), blood urea nitrogen (BUN), creatinine, chloride, mean corpuscular volume (MCV), red blood cell distribution width (RDW) and white cell count (WCC). The C-index of the nomogram (0.767, 95% CI 0.759 to 0.779) was superior to that of the traditional Sequential Organ Failure Assessment, Acute Physiology Score III and Get With The Guidelines Heart Failure scores, indicating its discrimination power. Calibration plots demonstrated that the predicted results are in good agreement with the observed results. The decision curves of the derivation and validation sets both had net benefits.ConclusionThe 20 independent risk factors for in-hospital mortality of patients with CHF were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW and WCC. The nomogram, which included these factors, accurately predicted the in-hospital mortality of patients with CHF. The novel nomogram has the potential for use in clinical practice as a tool to predict and assess mortality of patients with CHF in the ICU.
22
Su, Longxiang, Chun Liu, Dongkai Li, et al. "Toward Optimal Heparin Dosing by Comparing Multiple Machine Learning Methods: Retrospective Study." JMIR Medical Informatics 8, no. 6 (2020): e17648. http://dx.doi.org/10.2196/17648.
Full textAbstract:
Background Heparin is one of the most commonly used medications in intensive care units. In clinical practice, the use of a weight-based heparin dosing nomogram is standard practice for the treatment of thrombosis. Recently, machine learning techniques have dramatically improved the ability of computers to provide clinical decision support and have allowed for the possibility of computer generated, algorithm-based heparin dosing recommendations. Objective The objective of this study was to predict the effects of heparin treatment using machine learning methods to optimize heparin dosing in intensive care units based on the predictions. Patient state predictions were based upon activated partial thromboplastin time in 3 different ranges: subtherapeutic, normal therapeutic, and supratherapeutic, respectively. Methods Retrospective data from 2 intensive care unit research databases (Multiparameter Intelligent Monitoring in Intensive Care III, MIMIC-III; e–Intensive Care Unit Collaborative Research Database, eICU) were used for the analysis. Candidate machine learning models (random forest, support vector machine, adaptive boosting, extreme gradient boosting, and shallow neural network) were compared in 3 patient groups to evaluate the classification performance for predicting the subtherapeutic, normal therapeutic, and supratherapeutic patient states. The model results were evaluated using precision, recall, F1 score, and accuracy. Results Data from the MIMIC-III database (n=2789 patients) and from the eICU database (n=575 patients) were used. In 3-class classification, the shallow neural network algorithm performed the best (F1 scores of 87.26%, 85.98%, and 87.55% for data set 1, 2, and 3, respectively). The shallow neural network algorithm achieved the highest F1 scores within the patient therapeutic state groups: subtherapeutic (data set 1: 79.35%; data set 2: 83.67%; data set 3: 83.33%), normal therapeutic (data set 1: 93.15%; data set 2: 87.76%; data set 3: 84.62%), and supratherapeutic (data set 1: 88.00%; data set 2: 86.54%; data set 3: 95.45%) therapeutic ranges, respectively. Conclusions The most appropriate model for predicting the effects of heparin treatment was found by comparing multiple machine learning models and can be used to further guide optimal heparin dosing. Using multicenter intensive care unit data, our study demonstrates the feasibility of predicting the outcomes of heparin treatment using data-driven methods, and thus, how machine learning–based models can be used to optimize and personalize heparin dosing to improve patient safety. Manual analysis and validation suggested that the model outperformed standard practice heparin treatment dosing.
23
Wong, An-Kwok Ian, Paul E. Wischmeyer, Haesung Lee, et al. "Enteral and Parenteral Nutrition Timing in eICU Collaborative Research Database by Race: A Retrospective Observational Study." Journal of Surgical Research 304 (December 2024): 181–89. http://dx.doi.org/10.1016/j.jss.2024.10.021.
Full text
24
Liu, Xianglin, Zhihua Huang, Yizhi Guo, et al. "Identification and Validation of an Explainable Prediction Model of Sepsis in Patients With Intracerebral Hemorrhage: Multicenter Retrospective Study." Journal of Medical Internet Research 27 (April 28, 2025): e71413. https://doi.org/10.2196/71413.
Full textAbstract:
Background Sepsis is a life-threatening condition frequently observed in patients with intracerebral hemorrhage (ICH) who are critically ill. Early and accurate identification and prediction of sepsis are crucial. Machine learning (ML)–based predictive models exhibit promising sepsis prediction capabilities in emergency settings. However, their application in predicting sepsis among patients with ICH is still limited. Objective The aim of the study is to develop an ML-driven risk calculator for early prediction of sepsis in patients with ICH who are critically ill and to clarify feature importance and explain the model using the Shapley Additive Explanations method. Methods Patients with ICH admitted to the intensive care unit (ICU) from the Medical Information Mart for Intensive Care IV database between 2008 and 2022 were divided into training and internal test sets. The external test was performed using the eICU Collaborative Research Database, which includes over 200,000 ICU admissions across the United States between 2014 and 2015. Sepsis following ICU admission was identified using Sepsis-3.0 through clinical diagnosis combining elevation of the Sequential Organ Failure Assessment by ≥2 points with suspected infection. The Boruta algorithm was used for feature selection, confirming 29 features. Nine ML algorithms were used to construct the prediction models. Predictive performance was compared using several evaluation metrics, including the area under the receiver operating characteristic curve (AUC). The Shapley Additive Explanations technique was used to interpret the final model, and a web-based risk calculator was constructed for clinical practice. Results Overall, 2414 patients with ICH were enrolled from the Medical Information Mart for Intensive Care IV database, with 1689 and 725 patients assigned to the training and internal test sets, respectively. An external test set of 2806 patients with ICH from the eICU database was used. Among the 9 ML models tested, the categorical boosting (CatBoost) model demonstrated the best discriminative ability. After reducing features based on their importance, an explainable final CatBoost model was developed using 8 features. The final model accurately predicted sepsis in internal (AUC=0.812) and external (AUC=0.771) tests. Conclusions We constructed a web-based risk calculator with 8 features based on the CatBoost model to assist clinicians in identifying people at high risk for sepsis in patients with ICH who are critically ill.
25
Levi, Riccardo, Francesco Carli, Aldo Robles Arévalo, et al. "Artificial intelligence-based prediction of transfusion in the intensive care unit in patients with gastrointestinal bleeding." BMJ Health & Care Informatics 28, no. 1 (2021): e100245. http://dx.doi.org/10.1136/bmjhci-2020-100245.
Full textAbstract:
ObjectiveGastrointestinal (GI) bleeding commonly requires intensive care unit (ICU) in cases of potentialhaemodynamiccompromise or likely urgent intervention. However, manypatientsadmitted to the ICU stop bleeding and do not require further intervention, including blood transfusion. The present work proposes an artificial intelligence (AI) solution for the prediction of rebleeding in patients with GI bleeding admitted to ICU.MethodsA machine learning algorithm was trained and tested using two publicly available ICU databases, the Medical Information Mart for Intensive Care V.1.4 database and eICU Collaborative Research Database using freedom from transfusion as a proxy for patients who potentially did not require ICU-level care. Multiple initial observation time frames were explored using readily available data including labs, demographics and clinical parameters for a total of 20 covariates.ResultsThe optimal model used a 5-hour observation period to achieve an area under the curve of the receiving operating curve (ROC-AUC) of greater than 0.80. The model was robust when tested against both ICU databases with a similar ROC-AUC for all.ConclusionsThe potential disruptive impact of AI in healthcare innovation is acknowledge, but awareness of AI-related risk on healthcare applications and current limitations should be considered before implementation and deployment. The proposed algorithm is not meant to replace but to inform clinical decision making. Prospective clinical trial validation as a triage tool is warranted.
26
Huang, Tianzhi, Dejin Le, Lili Yuan, Shoujia Xu, and Xiulan Peng. "Machine learning for prediction of in-hospital mortality in lung cancer patients admitted to intensive care unit." PLOS ONE 18, no. 1 (2023): e0280606. http://dx.doi.org/10.1371/journal.pone.0280606.
Full textAbstract:
Backgrounds The in-hospital mortality in lung cancer patients admitted to intensive care unit (ICU) is extremely high. This study intended to adopt machine learning algorithm models to predict in-hospital mortality of critically ill lung cancer for providing relative information in clinical decision-making. Methods Data were extracted from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) for a training cohort and data extracted from the Medical Information Mart for eICU Collaborative Research Database (eICU-CRD) database for a validation cohort. Logistic regression, random forest, decision tree, light gradient boosting machine (LightGBM), eXtreme gradient boosting (XGBoost), and an ensemble (random forest+LightGBM+XGBoost) model were used for prediction of in-hospital mortality and important feature extraction. The AUC (area under receiver operating curve), accuracy, F1 score and recall were used to evaluate the predictive performance of each model. Shapley Additive exPlanations (SHAP) values were calculated to evaluate feature importance of each feature. Results Overall, there were 653 (24.8%) in-hospital mortality in the training cohort, and 523 (21.7%) in-hospital mortality in the validation cohort. Among the six machine learning models, the ensemble model achieved the best performance. The top 5 most influential features were the sequential organ failure assessment (SOFA) score, albumin, the oxford acute severity of illness score (OASIS) score, anion gap and bilirubin in random forest and XGBoost model. The SHAP summary plot was used to illustrate the positive or negative effects of the top 15 features attributed to the XGBoost model. Conclusion The ensemble model performed best and might be applied to forecast in-hospital mortality of critically ill lung cancer patients, and the SOFA score was the most important feature in all models. These results might offer valuable and significant reference for ICU clinicians’ decision-making in advance.
27
Su, Dan, Jiamei Li, Jiajia Ren, et al. "The relationship between serum lactate dehydrogenase level and mortality in critically ill patients." Biomarkers in Medicine 15, no. 8 (2021): 551–59. http://dx.doi.org/10.2217/bmm-2020-0671.
Full textAbstract:
Background: To assess the association between serum lactate dehydrogenase (LDH) levels and mortality in intensive care unit patients. Materials & methods: A total of 1981 patients in the eICU Collaborative Research Database were divided into four groups according to quartiles of LDH levels. Logistic regressions were performed. Results: Elevated LDH levels were significantly associated with higher mortality (intensive care unit mortality: Q2 vs Q1: 1.046 [0.622–1.758]; Q3 vs Q1: 1.667 [1.029–2.699]; and Q4 vs Q1: 1.760 [1.092–2.839]). Similar results persisted in patients with different acute physiology and chronic health evaluation IV scores, and with or without sepsis. Conclusion: The serum LDH level may aid in the early identification of mortality risk in critically ill patients.
28
Xu, Kunyuan, and Yun Huang. "Interpretable Machine Learning for Mortality Prediction in S-AKI Patients Undergoing Hemodialysis." Highlights in Science, Engineering and Technology 119 (December 11, 2024): 879–84. https://doi.org/10.54097/qrvk4c92.
Full textAbstract:
This study developed a machine learning model to predict in-hospital mortality risk among ICU patients with sepsis-associated acute kidney injury (S-AKI) undergoing hemodialysis. A retrospective analysis of 1,467 patients from the MIMIC-IV database and 226 from the eICU-CRD database was conducted, with models evaluated internally and externally. The RF model achieved excellent performance, with AUROCs of 0.798 (95% CI: 0.754–0.843) and 0.790 (95% CI: 0.723–0.857) in internal and external validations, respectively. Decision curve analysis indicated a net benefit of ~0.2 at a 10% mortality threshold, demonstrating good clinical applicability. SHAP analysis identified prothrombin time, APS III, systolic blood pressure, mean arterial pressure, and respiration rate as key predictors, with increased mortality risk associated with prothrombin time >10s, APS III >80, Nibp_systolic <110 mmHg, and Nibp_mean <70 mmHg. This model offers potential for supporting prognosis management and individualized treatment in clinical practice.
29
Safaei, Nima, Babak Safaei, Seyedhouman Seyedekrami, et al. "E-CatBoost: An efficient machine learning framework for predicting ICU mortality using the eICU Collaborative Research Database." PLOS ONE 17, no. 5 (2022): e0262895. http://dx.doi.org/10.1371/journal.pone.0262895.
Full textAbstract:
Improving the Intensive Care Unit (ICU) management network and building cost-effective and well-managed healthcare systems are high priorities for healthcare units. Creating accurate and explainable mortality prediction models helps identify the most critical risk factors in the patients’ survival/death status and early detect the most in-need patients. This study proposes a highly accurate and efficient machine learning model for predicting ICU mortality status upon discharge using the information available during the first 24 hours of admission. The most important features in mortality prediction are identified, and the effects of changing each feature on the prediction are studied. We used supervised machine learning models and illness severity scoring systems to benchmark the mortality prediction. We also implemented a combination of SHAP, LIME, partial dependence, and individual conditional expectation plots to explain the predictions made by the best-performing model (CatBoost). We proposed E-CatBoost, an optimized and efficient patient mortality prediction model, which can accurately predict the patients’ discharge status using only ten input features. We used eICU-CRD v2.0 to train and validate the models; the dataset contains information on over 200,000 ICU admissions. The patients were divided into twelve disease groups, and models were fitted and tuned for each group. The models’ predictive performance was evaluated using the area under a receiver operating curve (AUROC). The AUROC scores were 0.86 [std:0.02] to 0.92 [std:0.02] for CatBoost and 0.83 [std:0.02] to 0.91 [std:0.03] for E-CatBoost models across the defined disease groups; if measured over the entire patient population, their AUROC scores were 7 to 18 and 2 to 12 percent higher than the baseline models, respectively. Based on SHAP explanations, we found age, heart rate, respiratory rate, blood urine nitrogen, and creatinine level as the most critical cross-disease features in mortality predictions.
30
Chen, Junhua, Weifang Huang, and Nan Liang. "Blood glucose fluctuation and in-hospital mortality among patients with acute myocardial infarction: eICU collaborative research database." PLOS ONE 19, no. 4 (2024): e0300323. http://dx.doi.org/10.1371/journal.pone.0300323.
Full textAbstract:
Background To assess the relationship between glycemic variability, glucose fluctuation trajectory and the risk of in-hospital mortality in patients with acute myocardial infarction (AMI). Methods This retrospective cohort study included AMI patients from eICU Collaborative Research Database. In-hospital mortality of AMI patients was primary endpoint. Blood glucose levels at admission, glycemic variability, and glucose fluctuation trajectory were three main study variables. Blood glucose levels at admission were stratified into: normal, intermediate, and high. Glycemic variability was evaluated using the coefficient of variation (CV), divided into four groups based on quartiles: quartile 1: CV≤10; quartile 2: 10<CV≤20; quartile 3: 20<CV≤30; quartile 4: CV>30. Univariate and multivariate Cox regression models to assess the relationship between blood glucose levels at admission, glycemic variability, glucose fluctuation trajectory, and in-hospital mortality in patients with AMI. Results 2590 participants were eventually included in this study. There was a positive relationship between high blood glucose level at admission and in-hospital mortality [hazard ratio (HR) = 1.42, 95%confidence interval (CI): 1.06–1.89]. The fourth quartile (CV>30) of CV was associated with increased in-hospital mortality (HR = 2.06, 95% CI: 1.25–3.40). The findings indicated that only AMI individuals in the fourth quartile of glycemic variability, exhibited an elevated in-hospital mortality among those with normal blood glucose levels at admission (HR = 2.33, 95% CI: 1.11–4.87). Additionally, elevated blood glucose level was a risk factor for in-hospital mortality in AMI patients. Conclusion Glycemic variability was correlated with in-hospital mortality, particularly among AMI patients who had normal blood glucose levels at admission. Our study findings also suggest early intervention should be implemented to normalize high blood glucose levels at admission of AMI.
31
Wang, Yanping, and Yan Xu. "Association between aspartate aminotransferase to alanine aminotransferase ratio and 28-day mortality of ICU patients: A retrospective cohort study from MIMIC-IV database." PLOS One 20, no. 5 (2025): e0324904. https://doi.org/10.1371/journal.pone.0324904.
Full textAbstract:
Background Prior studies have linked the aspartate aminotransferase to alanine aminotransferase ratio (AAR) with negative health outcomes in the elderly and specific populations. However, the impact of AAR on the prognosis of the entire population in the intensive care unit (ICU) remains unclear. This study aimed to determine the correlation between AAR and the mortality among adult ICU patients. Method Patient data were retrieved from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and stratified into quartiles by AAR. Survival analysis using the Kaplan-Meier curves was conducted to compare survival across quartiles. The primary outcome was 28-day mortality, with secondary outcomes including 60-day, 90-day, and 365-day mortality, along with ICU-free, ventilator-free, and vasopressor-free days within the first 28 days. The association between AAR and mortality was evaluated using Cox proportional hazards regression analysis complemented by a restricted cubic spline. Furthermore, the eICU Collaborative Research Database (eICU-CRD) was used as an external validation cohort for sensitivity analysis. Result The study included 20,225 patients with a mean age of 63.7 ± 17.5 years. Kaplan-Meier analysis indicated a higher risk of 28-day mortality for patients with higher AAR (log-rank P < 0.001). After adjusting for confounders, the AAR was significantly related to 28-day mortality (HR = 1.04, 95% CI: 1.03–1.06, P < 0.001) and other mortality benchmarks, exhibiting an inverted L-shaped relationship. The inflection point of the AAR for 28-day mortality was 2.60. Below this threshold, each unit increase in the AAR was associated with a 19% rise in the risk of 28-day mortality (HR = 1.19, 95% CI: 1.11–1.27, P < 0.001), with a plateau observed above this threshold. Subgroup and sensitivity analyses further confirmed the robustness and generalizability of the study. Conclusion AAR demonstrated a significant association with 28-day, 60-day, 90-day, and 365-day mortality, characterized by an inverted L-shaped pattern.
32
Wang, Zichen, Luming Zhang, Shaojin Li, et al. "The relationship between hematocrit and serum albumin levels difference and mortality in elderly sepsis patients in intensive care units—a retrospective study based on two large database." BMC Infectious Diseases 22, no. 1 (2022). http://dx.doi.org/10.1186/s12879-022-07609-7.
Full textAbstract:
Abstract Background Sepsis still threatens the lives of more than 300 million patients annually and elderly patients with sepsis usually have a more complicated condition and a worse prognosis. Existing studies have shown that both Hematocrit (HCT) and albumin (ALB) can be used as potential predictors of sepsis, and their difference HCT-ALB has a significant capacity to diagnose infectious diseases. Currently, there is no relevant research on the relationship between HCT-ALB and the prognosis of elderly sepsis patients. Therefore, this study aims to explore the association between HCT-ALB and mortality in elderly patients with sepsis. Methods This study was a multi-center retrospective study based on the Medical Information Mart for Intensive Care (MIMIC-IV) database and the eICU Collaborative Research Database (eICU-CRD) in elderly patients with sepsis. The optimal HCT-ALB cut-off point for ICU mortality was calculated by the Youden Index based on the eICU-CRD dataset, and multivariate logistic regressions were conducted to explore the association between HCT-ALB and ICU/hospital mortality in the two databases. Subgroup analyses were performed for different parameters and comorbidity status. Results The number of 16,127 and 3043 elderly sepsis patients were selected from two large intensive care databases (eICU-CRD and MIMIC-IV, respectively) in this study. Depending on the optimal cut-off point, patients in both eICU-CRD and MIMIC-IV were independently divided into low HCT-ALB (< 6.7) and high HCT-ALB (≥ 6.7) groups. The odds ratio (95%confidence interval) [OR (95CI%)] of the high HCT-ALB group were 1.50 (1.36,1.65) and 1.71 (1.58,1.87) for ICU and hospital mortality in the eICU-CRD database after multivariable adjustment. Similar trends in the ICU and hospital mortality [OR (95%CI) 1.41 (1.15,1.72) and 1.27 (1.07,1.51)] were observed in MIMIC-IV database. Subgroup analysis showed an interaction effect with SOFA score in the eICU-CRD database however not in MIMIC-IV dataset. Conclusions High HCT-ALB (≥ 6.7) is associated with 1.41 and 1.27 times ICU and hospital mortality risk in elderly patients with sepsis. HCT-ALB is simple and easy to obtain and is a promising clinical predictor of early risk stratification for elderly sepsis patients in ICU.
33
Li, Yun, Lina Zhao, Yang Yu, et al. "Conservative oxygen therapy in critically ill and perioperative period of patients with sepsis-associated encephalopathy." Frontiers in Immunology 13 (October 19, 2022). http://dx.doi.org/10.3389/fimmu.2022.1035298.
Full textAbstract:
ObjectivesSepsis-associated encephalopathy (SAE) patients in the intensive care unit (ICU) and perioperative period are administrated supplemental oxygen. However, the correlation between oxygenation status with SAE and the target for oxygen therapy remains unclear. This study aimed to examine the relationship between oxygen therapy and SAE patients.MethodsPatients diagnosed with sepsis 3.0 in the intensive care unit (ICU) were enrolled. The data were collected from the Medical Information Mart for Intensive Care IV (MIMIC IV) database and the eICU Collaborative Research Database (eICU-CRD) database. The generalized additive models were adopted to estimate the oxygen therapy targets in SAE patients. The results were confirmed by multivariate Logistic, propensity score analysis, inversion probability-weighting, doubly robust model, and multivariate COX analyses. Survival was analyzed by the Kaplan-Meier method.ResultsA total of 10055 patients from eICU-CRD and 1685 from MIMIC IV were included. The incidence of SAE patients was 58.43%. The range of PaO2 (97-339) mmHg, PaO2/FiO2 (189-619), and SPO2≥93% may reduce the incidence of SAE, which were verified by multivariable Logistic regression, propensity score analysis, inversion probability-weighting, and doubly robust model estimation in MIMIC IV database and eICU database. The range of PaO2/FiO2 (189-619) and SPO2≥93% may reduce the hospital mortality of SAE were verified by multivariable COX regression.ConclusionsSAE patients in ICU, including perioperative period, require conservative oxygen therapy. We should maintain SPO2≥93%, PaO2 (97-339) mmHg and PaO2/FiO2 (189-619) in SAE patients.
34
Huang, Xiaxuan, Hongtao Cheng, Shiqi Yuan, et al. "Triglyceride-glucose index as a valuable predictor for aged 65-years and above in critical delirium patients: evidence from a multi-center study." BMC Geriatrics 23, no. 1 (2023). http://dx.doi.org/10.1186/s12877-023-04420-0.
Full textAbstract:
Abstract Background The triglyceride-glucose index (TyG), an established indicator of insulin resistance, is closely correlated with the prognosis of several metabolic disorders. This study aims to investigate the association between the TyG index and the incidence of critical delirium in patients aged 65 years and older. Methods We focused on evaluating patients aged 65 years and older diagnosed with critical delirium. Data were obtained from the Medical Information Database for Intensive Care (MIMIC-IV) and the eICU Collaborative Research Database (eICU-CRD). Multivariate logistic regression and restricted cubic spline (RCS) regression were used to determine the relationship between the TyG index and the risk of delirium. Results Participants aged 65 years and older were identified from the MIMIC-IV (n = 4,649) and eICU-CRD (n = 1,844) databases. Based on optimal thresholds derived from RCS regression, participants were divided into two cohorts: Q1 (< 8.912), Q2 (≥ 8.912). The logistic regression analysis showed a direct correlation between the TyG index and an increased risk of critical delirium among ICU patients aged 65 and older. These findings were validated in the eICU-CRD dataset, and sensitivity analysis further strengthened our conclusions. In addition, the subgroup analysis revealed certain differences. Conclusion This study highlights a clear, independent relationship between the TyG index and the risk of critical delirium in individuals aged 65 years and older, suggesting the importance of the TyG index as a reliable cardio-cerebrovascular metabolic marker for risk assessment and intervention.
35
Zhang, Qitian, Lizhen Xu, Zhiyi Xie, Weibin He, and Xiaohong Huang. "Machine learning-based prediction of mortality in acute myocardial infarction with cardiogenic shock." Frontiers in Cardiovascular Medicine 11 (October 14, 2024). http://dx.doi.org/10.3389/fcvm.2024.1402503.
Full textAbstract:
BackgroundIn the ICU, patients with acute myocardial infarction and cardiogenic shock (AMI-CS) often face high mortality rates, making timely and precise mortality risk prediction crucial for clinical decision-making. Despite existing models, machine learning algorithms hold the potential for improved predictive accuracy.MethodsIn this study, a predictive model was developed using the MIMIC-IV database, with external validation performed on the eICU-CRD database. We included ICU patients diagnosed with AMI-CS. Feature selection was conducted using the Boruta algorithm, followed by the construction and comparison of four machine learning models: Logistic Regression (LR), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Gaussian Naive Bayes (GNB). Model performance was evaluated based on metrics such as AUC (Area Under the Curve), accuracy, sensitivity, specificity, and so on. The SHAP method was employed to visualize and interpret the importance of model features. Finally, we constructed an online prediction model and conducted external validation in the eICU-CRD database.ResultsIn this study, a total of 570 and 391 patients with AMI-CS were included from the MIMIC-IV and eICU-CRD databases, respectively. Among all machine learning algorithms evaluated, LR exhibited the best performance with a validation set AUC of 0.841(XGBoost: 0.835, AdaBoost: 0.839, GNB: 0.826). The model incorporated five variables: prothrombin time, blood urea nitrogen, age, beta-blockers and Angiotensin-Converting Enzyme Inhibitors or Angiotensin II Receptor Blockers. SHAP plots are employed to visualize the importance of model features and to interpret the results. An online prediction tool was developed, externally validated with the eICU-CRD database, achieving an AUC of 0.755.ConclusionEmploying the LR algorithm, we developed a predictive model for assessing the mortality risk among AMI-CS patients in the ICU setting. Through model predictions, this facilitates early detection of high-risk individuals, ensures judicious allocation of healthcare resources.
36
Zhuang, Jinhu, Haofan Huang, Song Jiang, Jianwen Liang, Yong Liu, and Xiaxia Yu. "A generalizable and interpretable model for mortality risk stratification of sepsis patients in intensive care unit." BMC Medical Informatics and Decision Making 23, no. 1 (2023). http://dx.doi.org/10.1186/s12911-023-02279-0.
Full textAbstract:
Abstract Purpose This study aimed to construct a mortality model for the risk stratification of intensive care unit (ICU) patients with sepsis by applying a machine learning algorithm. Methods Adult patients who were diagnosed with sepsis during admission to ICU were extracted from MIMIC-III, MIMIC-IV, eICU, and Zigong databases. MIMIC-III was used for model development and internal validation. The other three databases were used for external validation. Our proposed model was developed based on the Extreme Gradient Boosting (XGBoost) algorithm. The generalizability, discrimination, and validation of our model were evaluated. The Shapley Additive Explanation values were used to interpret our model and analyze the contribution of individual features. Results A total of 16,741, 15,532, 22,617, and 1,198 sepsis patients were extracted from the MIMIC-III, MIMIC-IV, eICU, and Zigong databases, respectively. The proposed model had an area under the receiver operating characteristic curve (AUROC) of 0.84 in the internal validation, which outperformed all the traditional scoring systems. In the external validations, the AUROC was 0.87 in the MIMIC-IV database, better than all the traditional scoring systems; the AUROC was 0.83 in the eICU database, higher than the Simplified Acute Physiology Score III and Sequential Organ Failure Assessment (SOFA),equal to 0.83 of the Acute Physiology and Chronic Health Evaluation IV (APACHE-IV), and the AUROC was 0.68 in the Zigong database, higher than those from the systemic inflammatory response syndrome and SOFA. Furthermore, the proposed model showed the best discriminatory and calibrated capabilities and had the best net benefit in each validation. Conclusions The proposed algorithm based on XGBoost and SHAP-value feature selection had high performance in predicting the mortality of sepsis patients within 24 h of ICU admission.
37
Qi, Zhili, Lei Dong, Jin Lin, and Meili Duan. "Development and validation a nomogram prediction model for early diagnosis of bloodstream infections in the intensive care unit." Frontiers in Cellular and Infection Microbiology 14 (March 4, 2024). http://dx.doi.org/10.3389/fcimb.2024.1348896.
Full textAbstract:
PurposeThis study aims to develop and validate a nomogram for predicting the risk of bloodstream infections (BSI) in critically ill patients based on their admission status to the Intensive Care Unit (ICU).Patients and methodsPatients’ data were extracted from the Medical Information Mart for Intensive Care−IV (MIMIC−IV) database (training set), the Beijing Friendship Hospital (BFH) database (validation set) and the eICU Collaborative Research Database (eICU−CRD) (validation set). Univariate logistic regression analyses were used to analyze the influencing factors, and lasso regression was used to select the predictive factors. Model performance was assessed using area under receiver operating characteristic curve (AUROC) and Presented as a Nomogram. Various aspects of the established predictive nomogram were evaluated, including discrimination, calibration, and clinical utility.ResultsThe model dataset consisted of 14930 patients (1444 BSI patients) from the MIMIC-IV database, divided into the training and internal validation datasets in a 7:3 ratio. The eICU dataset included 2100 patients (100 with BSI) as the eICU validation dataset, and the BFH dataset included 419 patients (21 with BSI) as the BFH validation dataset. The nomogram was constructed based on Glasgow Coma Scale (GCS), sepsis related organ failure assessment (SOFA) score, temperature, heart rate, respiratory rate, white blood cell (WBC), red width of distribution (RDW), renal replacement therapy and presence of liver disease on their admission status to the ICU. The AUROCs were 0.83 (CI 95%:0.81-0.84) in the training dataset, 0.88 (CI 95%:0.88-0.96) in the BFH validation dataset, and 0.75 (95%CI 0.70-0.79) in the eICU validation dataset. The clinical effect curve and decision curve showed that most areas of the decision curve of this model were greater than 0, indicating that this model has a certain clinical effectiveness.ConclusionThe nomogram developed in this study provides a valuable tool for clinicians and nurses to assess individual risk, enabling them to identify patients at a high risk of bloodstream infections in the ICU.
38
Zhang, Yang, Juanjuan Hu, Tianfeng Hua, Jin Zhang, Zhongheng Zhang, and Min Yang. "Development of a machine learning-based prediction model for sepsis-associated delirium in the intensive care unit." Scientific Reports 13, no. 1 (2023). http://dx.doi.org/10.1038/s41598-023-38650-4.
Full textAbstract:
AbstractSeptic patients in the intensive care unit (ICU) often develop sepsis-associated delirium (SAD), which is strongly associated with poor prognosis. The aim of this study is to develop a machine learning-based model for the early prediction of SAD. Patient data were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and the eICU Collaborative Research Database (eICU-CRD). The MIMIC-IV data were divided into a training set and an internal validation set, while the eICU-CRD data served as an external validation set. Feature variables were selected using least absolute shrinkage and selection operator regression, and prediction models were built using logistic regression, support vector machines, decision trees, random forests, extreme gradient boosting (XGBoost), k-nearest neighbors and naive Bayes methods. The performance of the models was evaluated in the validation set. The model was also applied to a group of patients who were not assessed or could not be assessed for delirium. The MIMIC-IV and eICU-CRD databases included 14,620 and 1723 patients, respectively, with a median time to diagnosis of SAD of 24 and 30 h. Compared with Non-SAD patients, SAD patients had higher 28-days ICU mortality rates and longer ICU stays. Among the models compared, the XGBoost model had the best performance and was selected as the final model (internal validation area under the receiver operating characteristic curves (AUROC) = 0.793, external validation AUROC = 0.701). The XGBoost model outperformed other models in predicting SAD. The establishment of this predictive model allows for earlier prediction of SAD compared to traditional delirium assessments and is applicable to patients who are difficult to assess with traditional methods.
39
Cheng, Hongtao, Xiaxuan Huang, Shiqi Yuan, et al. "Can admission Braden skin score predict delirium in older adults in the intensive care unit? Results from a multicenter study." Journal of Clinical Nursing, December 10, 2023. http://dx.doi.org/10.1111/jocn.16962.
Full textAbstract:
AbstractAims and ObjectivesTo investigate whether a low Braden Skin Score (BSS), reflecting an increased risk of pressure injury, could predict the risk of delirium in older patients in the intensive care unit (ICU).BackgroundDelirium, a common acute encephalopathy syndrome in older ICU patients, is associated with prolonged hospital stay, long‐term cognitive impairment and increased mortality. However, few studies have explored the relationship between BSS and delirium.DesignMulticenter cohort study.MethodsThe study included 24,123 older adults from the Medical Information Mart for Intensive Care IV (MIMIC‐IV) database and 1090 older adults from the eICU Collaborative Research Database (eICU‐CRD), all of whom had a record of BSS on admission to the ICU. We used structured query language to extract relevant data from the electronic health records. Delirium, the primary outcome, was primarily diagnosed by the Confusion Assessment Method for the ICU or the Intensive Care Delirium Screening Checklist. Logistic regression models were used to validate the association between BSS and outcome. A STROBE checklist was the reporting guide for this study.ResultsThe median age within the MIMIC‐IV and eICU‐CRD databases was approximately 77 and 75 years, respectively, with 11,195 (46.4%) and 524 (48.1%) being female. The median BSS at enrollment in both databases was 15 (interquartile range: 13, 17). Multivariate logistic regression showed a negative association between BSS on ICU admission and the prevalence of delirium. Similar patterns were found in the eICU‐CRD database.ConclusionsThis study found a significant negative relationship between ICU admission BSS and the prevalence of delirium in older patients.Relevance to Clinical PracticeThe BSS, which is simple and accessible, may reflect the health and frailty of older patients. It is recommended that BSS assessment be included as an essential component of delirium management strategies for older patients in the ICU.No Patient or Public ContributionThis is a retrospective cohort study, and no patients or the public were involved in the design and conduct of the study.
40
Lv, Yinzhen, Jiayi Weng, Jing Li, Wei Chen, He Huang, and Yuzhuo Zhao. "A New Evaluation Model for Traumatic Severe Pneumothorax Based on Interpretable Machine Learning." INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL 20, no. 1 (2025). https://doi.org/10.15837/ijccc.2025.1.6830.
Full textAbstract:
Traumatic pneumothorax is a complex condition that is challenging to diagnose, particularly in hospitals, underdeveloped areas, and during mass casualty events. This study aimed to evaluate the potential of machine learning (ML) for diagnosing and assessing traumatic pneumothorax. We extracted 33 vital signs and blood gas parameters from the MIMIC-IV database, selecting 12 clinically significant features as inputs to four ML algorithms: extreme gradient boosting (XGBoost), artificial neural network (ANN), support vector machine (SVM), and k-nearest neighbors (KNN). Five-fold cross-validation was used to train and test the models, with external validation performed on the EICU database. Model performance was evaluated using AUROC, recall, and accuracy, with SHAP interpretability employed to understand feature importance. In total, 3871 participants from the MIMIC-IV database and 22,022 participants from the EICU database were analyzed. Hemoglobin, Oxygenation Index, and pH were found to be key indicators of severe traumatic pneumothorax. XGBoost exhibited the best performance, achieving an AUROC of 0.979 (95% CI: [0.966, 0.989]) on the MIMIC-IV dataset and 0.806 (95% CI: [0.740, 0.864]) on the EICU dataset. The results suggest that ML, particularly XGBoost, is faster and more convenient than traditional imaging methods, making it well-suited for emergency or mass casualty situations. ML algorithms show promise for initial diagnosis of traumatic pneumothorax, with XGBoost demonstrating strong interpretability and robust external validation.
41
Tang, Hai, Zhuochen Jin, Jiajun Deng, et al. "Development and validation of a deep learning model to predict the survival of patients in ICU." Journal of the American Medical Informatics Association, June 25, 2022. http://dx.doi.org/10.1093/jamia/ocac098.
Full textAbstract:
Abstract Background Patients in the intensive care unit (ICU) are often in critical condition and have a high mortality rate. Accurately predicting the survival probability of ICU patients is beneficial to timely care and prioritizing medical resources to improve the overall patient population survival. Models developed by deep learning (DL) algorithms show good performance on many models. However, few DL algorithms have been validated in the dimension of survival time or compared with traditional algorithms. Methods Variables from the Early Warning Score, Sequential Organ Failure Assessment Score, Simplified Acute Physiology Score II, Acute Physiology and Chronic Health Evaluation (APACHE) II, and APACHE IV models were selected for model development. The Cox regression, random survival forest (RSF), and DL methods were used to develop prediction models for the survival probability of ICU patients. The prediction performance was independently evaluated in the MIMIC-III Clinical Database (MIMIC-III), the eICU Collaborative Research Database (eICU), and Shanghai Pulmonary Hospital Database (SPH). Results Forty variables were collected in total for model development. 83 943 participants from 3 databases were included in the study. The New-DL model accurately stratified patients into different survival probability groups with a C-index of &gt;0.7 in the MIMIC-III, eICU, and SPH, performing better than the other models. The calibration curves of the models at 3 and 10 days indicated that the prediction performance was good. A user-friendly interface was developed to enable the model’s convenience. Conclusions Compared with traditional algorithms, DL algorithms are more accurate in predicting the survival probability during ICU hospitalization. This novel model can provide reliable, individualized survival probability prediction.
42
Yang, Yang, Shengru Liang, Jiangdong Liu, et al. "Triglyceride-glucose index as a potential predictor for in-hospital mortality in critically ill patients with intracerebral hemorrhage: a multicenter, case–control study." BMC Geriatrics 24, no. 1 (2024). http://dx.doi.org/10.1186/s12877-024-05002-4.
Full textAbstract:
Abstract Background The correlation between the triglyceride-glucose index (TyG) and the prognosis of ischemic stroke has been well established. This study aims to assess the influence of the TyG index on the clinical outcomes of critically ill individuals suffering from intracerebral hemorrhage (ICH). Methods Patients diagnosed with ICH were retrospectively retrieved from the Medical Information Mart for Intensive Care (MIMIC-IV) and the eICU Collaborative Research Database (eICU-CRD). Various statistical methods, including restricted cubic spline (RCS) regression, multivariable logistic regression, subgroup analysis, and sensitivity analysis, were employed to examine the relationship between the TyG index and the primary outcomes of ICH. Results A total of 791 patients from MIMIC-IV and 1,113 ones from eICU-CRD were analyzed. In MIMIC-IV, the in-hospital and ICU mortality rates were 14% and 10%, respectively, while in eICU-CRD, they were 16% and 8%. Results of the RCS regression revealed a consistent linear relationship between the TyG index and the risk of in-hospital and ICU mortality across the entire study population of both databases. Logistic regression analysis revealed a significant positive association between the TyG index and the likelihood of in-hospital and ICU death among ICH patients in both databases. Subgroup and sensitivity analysis further revealed an interaction between patients' age and the TyG index in relation to in-hospital and ICU mortality among ICH patients. Notably, for patients over 60 years old, the association between the TyG index and the risk of in-hospital and ICU mortality was more pronounced compared to the overall study population in both MIMIC-IV and eICU-CRD databases, suggesting a synergistic effect between old age (over 60 years) and the TyG index on the in-hospital and ICU mortality of patients with ICH. Conclusions This study established a positive correlation between the TyG index and the risk of in-hospital and ICU mortality in patients over 60 years who diagnosed with ICH, suggesting that the TyG index holds promise as an indicator for risk stratification in this patient population.
43
Fang, Yipeng, Yuan Zhang, and Xin Zhang. "Serum phosphate levels and the development of sepsis associated acute kidney injury: evidence from two independent databases." Frontiers in Medicine 11 (March 22, 2024). http://dx.doi.org/10.3389/fmed.2024.1367064.
Full textAbstract:
ObjectiveWe aimed to investigate the association between serum phosphate levels and the risk for developing sepsis associated acute kidney injury (SAKI).MethodsSeptic patients from the Medical Information Mart for Intensive Care IV (MIMIC IV) and the eICU Collaborative Research Database (eICU-CRD) were enrolled. Restricted cubic spline (RCS) was used to visualize the relationship between phosphate levels and the risk of SAKI. Patients were divided into four categories based on their serum phosphate levels. Logistic regression analysis, receiver operating characteristic (ROC) curve and subgroup analysis were performed to evaluate the predictive value of serum phosphate for SAKI.ResultsA total of 9,244 and 2,124 patients from the MIMIC IV and eICU-CRD database were included in the final analysis. RCS curve revealed a non-linear correlation between phosphate levels and the risk of SAKI (p for non-linearity &lt;0.05). Each 1 mg/dL increase in phosphate levels was associated with a 1.51 to 1.64-fold increased risk of SAKI (OR 2.51–2.64, p &lt; 0.001) in the MIMIC IV cohort and a 0.29 to 0.38-fold increased risk (OR 1.29–1.38, p &lt; 0.001) in the eICU-CRD cohort. Compared to the normal-low category, hyperphosphatemia and normal-high category were independently associated with an increased risk of SAKI, while hypophosphatemia was independently associated with a decreased risk in the MIMIC IV cohort. A similar trend was observed in the eICU-CRD cohort, but statistical significance disappeared in the hypophosphatemia category and the adjusted model of normal high category. These finding was consistent in subgroup analysis.ConclusionElevated serum phosphate, even within the normal range, is an independent risk factor for developing SAKI in septic patients. Abnormal change in serum phosphate levels may be a novel biomarker for early prediction of SAKI occurrence.
44
Ye, Jianfeng, Luming Zhang, Jun Lyu, et al. "Malignant cancer may increase the risk of all-cause in-hospital mortality in patients with acute myocardial infarction: a multicenter retrospective study of two large public databases." Cardio-Oncology 9, no. 1 (2023). http://dx.doi.org/10.1186/s40959-023-00156-3.
Full textAbstract:
Abstract Background Acute myocardial infarction (AMI) and cancer are diseases with high morbidity and mortality worldwide, bringing a serious economic burden, and they share some risk factors. The purpose of this study was to determine the effect of cancer on the all-cause in-hospital mortality of patients with AMI. Methods This multicenter retrospective study analyzed patients with AMI from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and eICU Collaborative Research Database (eICU-CRD) in the United States. Patients were divided into two groups based on whether they had concomitant malignant cancer: cancer and noncancer groups. The outcome was all-cause in-hospital mortality. The association between the two groups and their outcomes were analyzed using Kaplan–Meier and Cox proportional-hazards regression models. Propensity score matching (PSM) and propensity score based inverse probability of treatment weighting (IPTW) were used to further adjust for confounding variables to verify the stability of the results. Results The study included 3,034 and 5,968 patients with AMI from the MIMIC-IV database and the eICU-CRD, respectively. Kaplan–Meier survival curves indicated that the probability of in-hospital survival was lower in patients with cancer than in those without cancer. After adjusting for potential confounding variables using multivariable Cox proportional hazards regression, the risk of all-cause in-hospital mortality was significantly higher in the cancer than the noncancer group, and the HR (95% CI) values for the cancer group were 1.56(1.22,1.98) and 1.35(1.01,1.79) in the MIMIC-IV database and the eICU-CRD, respectively. The same results were obtained after using PSM and IPTW, which further verified the results. Conclusions Among the patients with AMI, the all-cause in-hospital mortality risk of those with cancer was higher than those without cancer. Therefore, when treating such patients, comprehensive considerations should be made from a multidisciplinary perspective involving cardiology and oncology, with the treatment plan adjusted accordingly.
45
Bi, Siwei, Ruiqi Liu, Jingyi Li, Shanshan Chen, and Jun Gu. "The Prognostic Value of Calcium in Post-Cardiovascular Surgery Patients in the Intensive Care Unit." Frontiers in Cardiovascular Medicine 8 (October 5, 2021). http://dx.doi.org/10.3389/fcvm.2021.733528.
Full textAbstract:
Background: Present researches exploring the prognostic value of calcium concentration are undermined by sample size and study design. Our study investigated the association of both total calcium (tCa) and ionized Ca (iCa) to short- and long-term mortality and other outcomes in post-cardiovascular surgery (PCS) patients admitted to intensive care unit (ICU) from two large public data sets.Methods: The Medical Information Mart for Intensive Care III (MIMIC-III) database and the eICU Collaborative Research Database (eICU) were inspected to identify PCS patients. The primary outcome was 28-day mortality. Multivariate regression was used to elucidate the relationship between calcium concentration and outcomes. The propensity score estimation was performed to validate our findings.Results: A total of 6122 and 914 patients were included from the MIMIC III and eICU data sets, respectively. The groups with the most patients were the mild hypo-iCa and hypo-tCa groups. The mild hypo-iCa group showed significant association with worse short-term and long-term prognosis, less use of ventilation, longer ICU and hospital stay, and more incidence of 7-day acute kidney injury.Conclusions: The mild hypo-iCa (0.9–1.15 mmol/L) within the first day of admission to the ICU could serve as an independent prognosis factor for PCS patients.
46
Bi, Siwei, Ruiqi Liu, Jingyi Li, Shanshan Chen, and Jun Gu. "The Prognostic Value of Calcium in Post-Cardiovascular Surgery Patients in the Intensive Care Unit." Frontiers in Cardiovascular Medicine 8 (October 5, 2021). http://dx.doi.org/10.3389/fcvm.2021.733528.
Full textAbstract:
Background: Present researches exploring the prognostic value of calcium concentration are undermined by sample size and study design. Our study investigated the association of both total calcium (tCa) and ionized Ca (iCa) to short- and long-term mortality and other outcomes in post-cardiovascular surgery (PCS) patients admitted to intensive care unit (ICU) from two large public data sets.Methods: The Medical Information Mart for Intensive Care III (MIMIC-III) database and the eICU Collaborative Research Database (eICU) were inspected to identify PCS patients. The primary outcome was 28-day mortality. Multivariate regression was used to elucidate the relationship between calcium concentration and outcomes. The propensity score estimation was performed to validate our findings.Results: A total of 6122 and 914 patients were included from the MIMIC III and eICU data sets, respectively. The groups with the most patients were the mild hypo-iCa and hypo-tCa groups. The mild hypo-iCa group showed significant association with worse short-term and long-term prognosis, less use of ventilation, longer ICU and hospital stay, and more incidence of 7-day acute kidney injury.Conclusions: The mild hypo-iCa (0.9–1.15 mmol/L) within the first day of admission to the ICU could serve as an independent prognosis factor for PCS patients.
47
Peng, Xiulan, Yahong Cai, Huan Huang, Haifeng Fu, Wei Wu, and Lifeng Hong. "A Predictive Model for Acute Kidney Injury Based on Leukocyte‐Related Indicators in Hepatocellular Carcinoma Patients Admitted to the Intensive Care Unit." Mediators of Inflammation 2025, no. 1 (2025). https://doi.org/10.1155/mi/7110012.
Full textAbstract:
Background: This study aimed to develop and validate a straightforward clinical risk model utilizing white blood cell (WBC) counts to predict acute kidney injury (AKI) in critically sick patients with hepatocellular carcinoma (HCC).Methods: Data were taken from the Medical Information Mart for Intensive Care‐IV (MIMIC‐IV) database for the training cohort. Data for an internal validation cohort were obtained from the eICU Collaborative Research Database (eICU‐CRD), while patients from our hospital were utilized for external validation. A risk model was created utilizing significant indicators identified through multivariate logistic regression, following logistic regression analysis to determine the primary predictors of WBC‐related biomarkers for AKI prediction. The Kaplan–Meier curve was employed to evaluate the prognostic efficacy of the new risk model.Results: A total of 1628 critically sick HCC patients were enrolled. Among these, 23 (23.2%) patients at our hospital, 84 (17.9%) patients in the eICU‐CRD database, and 379 (35.8%) patients in the MIMIC‐IV database developed AKI. A unique risk model was developed based on leukocyte‐related indicators following the multivariate logistic regression analysis, incorporating white blood cell to neutrophil ratio (WNR), white blood cell to monocyte ratio (WMR), white blood cell to hemoglobin ratio (WHR), and platelet to lymphocyte ratio (PLR). This risk model exhibited robust predictive capability for AKI, in‐hospital mortality, and ICU mortality across the training set, internal validation set, and external validation set.Conclusion: This risk model seems to have practical consequences as an innovative and accessible tool for forecasting the prognosis of critically ill HCC patients, which may, to some degree, aid in identifying equitable risk assessments and treatment strategies.
48
Zeng, Zhixuan, Shuo Yao, Jianfei Zheng, and Xun Gong. "Development and validation of a novel blending machine learning model for hospital mortality prediction in ICU patients with Sepsis." BioData Mining 14, no. 1 (2021). http://dx.doi.org/10.1186/s13040-021-00276-5.
Full textAbstract:
Abstract Background Early prediction of hospital mortality is crucial for ICU patients with sepsis. This study aimed to develop a novel blending machine learning (ML) model for hospital mortality prediction in ICU patients with sepsis. Methods Two ICU databases were employed: eICU Collaborative Research Database (eICU-CRD) and Medical Information Mart for Intensive Care III (MIMIC-III). All adult patients who fulfilled Sepsis-3 criteria were identified. Samples from eICU-CRD constituted training set and samples from MIMIC-III constituted test set. Stepwise logistic regression model was used for predictor selection. Blending ML model which integrated nine sorts of basic ML models was developed for hospital mortality prediction in ICU patients with sepsis. Model performance was evaluated by various measures related to discrimination or calibration. Results Twelve thousand five hundred fifty-eight patients from eICU-CRD were included as the training set, and 12,095 patients from MIMIC-III were included as the test set. Both the training set and the test set showed a hospital mortality of 17.9%. Maximum and minimum lactate, maximum and minimum albumin, minimum PaO2/FiO2 and age were important predictors identified by both random forest and extreme gradient boosting algorithm. Blending ML models based on corresponding set of predictors presented better discrimination than SAPS II (AUROC, 0.806 vs. 0.771; AUPRC 0.515 vs. 0.429) and SOFA (AUROC, 0.742 vs. 0.706; AUPRC 0.428 vs. 0.381) on the test set. In addition, calibration curves showed that blending ML models had better calibration than SAPS II. Conclusions The blending ML model is capable of integrating different sorts of basic ML models efficiently, and outperforms conventional severity scores in predicting hospital mortality among septic patients in ICU.
49
Zhang, Guo-Guo, Jia-Hui Hao, Qi Yong, et al. "Lactate-to-albumin ratio is associated with in-hospital mortality in patients with spontaneous subarachnoid hemorrhage and a nomogram model construction." Frontiers in Neurology 13 (October 17, 2022). http://dx.doi.org/10.3389/fneur.2022.1009253.
Full textAbstract:
IntroductionSubarachnoid hemorrhage (SAH) is a severe hemorrhagic stroke with high mortality. However, there is a lack of clinical tools for predicting in-hospital mortality in clinical practice. LAR is a novel clinical marker that has demonstrated prognostic significance in a variety of diseases.MethodsCritically ill patients diagnosed and SAH with their data in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and the eICU Collaborative Research Database (eICU-CRD) were included in our study. Multivariate logistic regression was utilized to establish the nomogram.ResultsA total of 244 patients with spontaneous SAH in the MIMIC-IV database were eligible for the study as a training set, and 83 patients in eICU-CRD were included for external validation. Data on clinical characteristics, laboratory parameters and outcomes were collected. Univariate and multivariate logistic regression analysis identified age (OR: 1.042, P-value: 0.003), LAR (OR: 2.592, P-value: 0.011), anion gap (OR: 1.134, P-value: 0.036) and APSIII (OR: 1.028, P-value: &lt; 0.001) as independent predictors of in-hospital mortality and we developed a nomogram model based on these factors. The nomogram model incorporated with LAR, APSIII, age and anion gap demonstrated great discrimination and clinical utility both in the training set (accuracy: 77.5%, AUC: 0.811) and validation set (accuracy: 75.9%, AUC: 0.822).ConclusionLAR is closely associated with increased in-hospital mortality of patients with spontaneous SAH, which could serve as a novel clinical marker. The nomogram model combined with LAR, APSIII, age, and anion gap presents good predictive performance and clinical practicability.
50
Liu, Chao, Xiaoli Liu, Mei Hu, et al. "A simple nomogram for predicting hospital mortality of patients over 80 years in ICU: An International Multicenter Retrospective Study." Journals of Gerontology: Series A, May 10, 2023. http://dx.doi.org/10.1093/gerona/glad124.
Full textAbstract:
Abstract Background This study aimed to develop and validate an easy-to-use ICU illness scoring system to evaluate the in-hospital mortality for very old patients (VOPs, over 80 years old). Methods We performed a multicenter retrospective study based on the eICU Collaborative Research Database (eICU-CRD), Medical Information Mart for Intensive Care Database (MIMIC-III CareVue and MIMIC-IV), and the Amsterdam University Medical Centers Database (AmsterdamUMCdb). Least Absolute Shrinkage and Selection Operator (LASSO) regression was applied to variables selection. The Logistic regression (LR) algorithm was used to develop the risk score and a nomogram was further generated to explain the score. Results We analyzed 23,704 VOPs, including 3,726 deaths (10,183 [13.5% mortality] from eICU-CRD (development set), 12,703 [17.2%] from the MIMIC and 818 [20.8%] from the AmsterdamUMC (external validation sets)). Thirty-four variables were extracted on the first day of ICU admission, and 10 variables were finally chosen including Glasgow Coma Scale, shock index, respiratory rate, partial pressure of carbon dioxide, lactate, mechanical ventilation (yes vs. no), oxygen saturation, Charlson Comorbidity Index, blood urea nitrogen and urine output. The nomogram was developed based on the ten variables (AUC: training of 0.792, testing of 0.788, MIMIC of 0.764 and AmsterdamUMC of 0.808 [external validating]), which consistently outperformed the SOFA, APS-III, and SAPS-II. Conclusions We developed and externally validated a nomogram for predicting mortality in VOPs based on 10 commonly measured variables on the first day of ICU admission. It could be a useful tool for clinicians to identify potentially high risks of VOPs.