To see the other types of publications on this topic, follow the link: Predictive risk modeling.
Journal articles on the topic 'Predictive risk modeling'
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 'Predictive risk modeling.'
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
Katreddy, Venkata Senareddy. "Predicting Risks in Healthcare Claims Using Advanced Data Processing and Machine Learning Techniques." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 01 (2025): 1–9. https://doi.org/10.55041/ijsrem40802.
Full textAbstract:
Healthcare providers and insurers face significant challenges in managing claims, particularly in detecting fraudulent activities and predicting high-cost claims. This paper proposes a methodology for predicting risks in healthcare claims using data analysis and machine learning techniques. By processing large-scale claims data, analyzing patterns, and building predictive models, this approach aims to improve risk management, operational efficiency, and cost savings. Keywords: Healthcare Claims, Risk Prediction, Data Analysis, Predictive Modeling
2
Waheed, Shaikh Abdul, and P. Sheik Abdul Khader. "Healthcare Solutions for Children Who Stutter Through the Structural Equation Modeling and Predictive Modeling by Utilizing Historical Data of Stuttering." SAGE Open 11, no. 4 (2021): 215824402110581. http://dx.doi.org/10.1177/21582440211058195.
Full textAbstract:
Earlier studies established the role of demographic and temperamental features (DTFs) in the adaptation of childhood stuttering. However, these studies have been short on examining the latent interrelationships among DTFs and not utilizing them in predicting this disorder. This research article endeavors to examine latent interrelationships among DTFs in relation to childhood-stuttering. The purpose of the present is also to analyze whether DTFs can be utilized in predicting the likely risk of this speech disorder. Historical data on childhood stuttering was utilized for performing the invloved experiments of this research. “Structural-Equation-Modeling” (SEM) was applied to examine latent interrelationships among DTFs in relation to stuttering. The predictive analytics approach was employed to ensure whether DTFs of children can be utilized for predicting the likely risk of childhood-stuttering. SEM-based path analysis explored potential latent interrelationships among DTFs by separating them into categories of background and intermediate. By utilizing the same set of the DTFs, predictive models were able to classify children into stuttering and non-stuttering groups with optimal prediction accuracy. The outcomes of this study showed how the stuttering related historical data can be utilized in offering healthcare solutions for individuals with stuttering disorder. The outcomes of the present study also suggest that historical data on stuttering is a very rich source of hidden trends and patterns concerning this disorder. These hidden trends and patterns can be captured by applying a different type of structural and predictive modeling to understand the cause-and-effect relationship among variables in relation to stuttering. The SEM utilizes the cause-and-effect relationship among variables to explore latent-interrelationships between them. While predictive modeling utilizes the cause-and-effect relationship among variables to predict the possible risk of stuttering with optimal prediction accuracy.
3
Vishwakarma, Saketh Kumar. "AI-Driven Predictive Risk Modelling for Aerospace Supply Chains." International Interdisciplinary Business Economics Advancement Journal 6, no. 5 (2025): 102–34. https://doi.org/10.55640/business/volume06issue05-06.
Full textAbstract:
In the aerospace supply chain, a complex, high-stakes ecosystem is at risk of multiple risk categories such as component shortage, cyber threats, and noncompliance with regulations. Traditional risk mitigation strategies are not enough. They are now offered as measures reactive to risks and static contingency plans. This paper investigates how AI-driven predictive risk modeling can break these limitations of the current risk management practices and allow risk management to change from reactionary to proactive across the aerospace supply chain. These models leverage the power of machine learning by poring over structured and unstructured data (telemetry data, supplier log files) and searching for patterns that predict future disruptions. Core technologies that can ingest and process data in real-time, like Apache Kafka and Apache Spark, support dynamic risk calculation. Combining with the domain expertise, they provide precision to the model and compliance framework (FAA, ITAR, AS9100) for legal compliance. The document also mentions some architectural shifts from monolith to microservice systems and the use of design patterns such as CQRS, the Strangler pattern, and ModelOps in the model deployment. Quantifiable benefits, as shown in a case study in a major aerospace OEM, include reduced downtime, decreased procurement times, and better prediction. Results suggest that stakeholders must be involved, ethical AI governance should be implemented, and iterative validation should be used to build trust and alignment in the system. Edge AI, blockchain, and quantum computing are moving in the right direction in the industry and predictive analytics. The guide is a strategic tool for converting their operation to systems with resilient and intelligent supply chains that the aerospace industry’s professionals aspire to embrace.
4
Sadia Latif, Sami Ullah, Aafia Latif, Ghazanfar Ali, Muhammad Hassnain Azhar, and Salman Ali. "PREDICTIVE MODELING OF CARDIOVASCULAR DISEASE USING MACHINE LEARNING APPROACH." Kashf Journal of Multidisciplinary Research 2, no. 02 (2025): 207–32. https://doi.org/10.71146/kjmr288.
Full textAbstract:
The primary causes of death worldwide are Chronic Cardiac diseases. Accurately diagnose and predicting chronic cardiac disease is important to the proper treatment of cardiac patients before a heart attack occurs. The goal of accurate disease prediction will be achieved using a ML algorithm with health examination data. Early prediction of the risk factors of cardiac disease is critical for preventing heart disease. In our research, this is a follow-up study the statistical analysis will be used to assess the prediction of CCD as many high-risk factors (hypertension, smoking, high blood cholesterol, increasing age, male gender, being overweight) are involved. The heat-map cluster and machine learning algorithm provide interactive visualization for the classification of patients with different CCD stages. Early stages of cardiac patients are grouped into one cluster and advanced staged cardiac patients could be at high risk for the expeditious decline of heart function and should be closely monitored. The clustering heatmap provided a new predictive model for health care management for patients at high risk of rapid CCD progression. This model could help physicians make an accurate diagnosis of this progressive and complex disease.
5
Muthuvel, Dr P. "Predictive Modeling for Cardiovascular Disease Risk Assessment." International Journal for Research in Applied Science and Engineering Technology 12, no. 3 (2024): 3382–86. http://dx.doi.org/10.22214/ijraset.2024.58799.
Full textAbstract:
Abstract: Heart disease remains one of the leading causes of mortality worldwide. Early detection and risk assessment are crucial for effective prevention and management. This research paper presents a novel approach utilizing machine learning techniques, particularly decision trees, for predicting heart disease risk. The study utilizes a dataset sourced from the UCI Machine Learning Repository, encompassing diverse features such as age, gender, height, weight, cholesterol levels, and other relevant attributes. The proposed model aims to accurately classify individuals into risk categories based on their demographic and health-related information. Additionally, a user-friendly web application is developed using Python Flask, enabling users to input their data and receive instant risk assessments. Through rigorous experimentation and evaluation, the efficacy and reliability of the predictive model are demonstrated, offering valuable insights for early intervention and personalized healthcare strategies in the fight against heart disease.
6
Toma, Milan, and Ong Chi Wei. "Predictive Modeling in Medicine." Encyclopedia 3, no. 2 (2023): 590–601. http://dx.doi.org/10.3390/encyclopedia3020042.
Full textAbstract:
Predictive modeling is a complex methodology that involves leveraging advanced mathematical and computational techniques to forecast future occurrences or outcomes. This tool has numerous applications in medicine, yet its full potential remains untapped within this field. Therefore, it is imperative to delve deeper into the benefits and drawbacks associated with utilizing predictive modeling in medicine for a more comprehensive understanding of how this approach may be effectively leveraged for improved patient care. When implemented successfully, predictive modeling has yielded impressive results across various medical specialities. From predicting disease progression to identifying high-risk patients who require early intervention, there are countless examples of successful implementations of this approach within healthcare settings worldwide. However, despite these successes, significant challenges remain for practitioners when applying predictive models to real-world scenarios. These issues include concerns about data quality and availability as well as navigating regulatory requirements surrounding the use of sensitive patient information—all factors that can impede progress toward realizing the true potential impact of predictive modeling on improving health outcomes.
7
T. Benila, Christabel, and K. K. Thanammal. "Predictive modeling for cardiovascular disease risk assessment." i-manager's Journal on Data Science & Big Data Analytics 2, no. 1 (2024): 23. http://dx.doi.org/10.26634/jds.2.1.20811.
Full textAbstract:
Cardiovascular diseases (CVDs) continue to be the world's leading cause of death. It is imperative that accurate risk assessment and early intervention be implemented. This study proposes a predictive modeling framework, termed "HeartGuard," designed to assess an individual's risk of developing cardiovascular disease. Leveraging a diverse dataset comprising demographic information, lifestyle factors, medical history, and biomarker data, advanced machine learning techniques are employed to construct robust predictive models. The developed models incorporate features such as age, gender, blood pressure, cholesterol levels, smoking status, physical activity, and family history to estimate the probability of CVD occurrence within a specified timeframe. The evaluation of the models using cross-validation and independent validation datasets demonstrates their high accuracy, sensitivity, and specificity. HeartGuard offers a reliable tool for clinicians to identify individuals at heightened risk of cardiovascular disease, enabling targeted preventive measures and personalized healthcare interventions to mitigate the burden of CVD morbidity and mortality.
8
Luxhoj, James T. "Predictive Analytics for Modeling UAS Safety Risk." SAE International Journal of Aerospace 6, no. 1 (2013): 128–38. http://dx.doi.org/10.4271/2013-01-2104.
Full text
9
Babalola, Abayomi Danlami, Kayode Francis Akingbade, and Daniel Olakunle. "Predictive Modeling for Cardiovascular Disease in Patients Based on Demographic and Biometric Data." ABUAD Journal of Engineering Research and Development (AJERD) 7, no. 1 (2024): 153–59. http://dx.doi.org/10.53982/ajerd.2024.0701.15-j.
Full textAbstract:
Cardiovascular disease (CVD) remains the leading global cause of death, highlighting the urgent need for accurate risk assessment and prediction tools. Machine learning (ML) has emerged as a promising approach for CVD risk prediction, offering the potential to capture complex relationships between clinical and biometric data and patient outcomes. This study explores the application of support vector machines (SVMs), ensemble learning, and artificial neural networks (NNs) for predictive modeling of CVD in patients. The study utilizes a comprehensive dataset comprising demographic and biometric data of patients, including age, gender, blood pressure, cholesterol levels, and body mass index, features. SVMs, ensemble learning, and NNs are employed to construct predictive models based on these data. The performance of each model is evaluated using metrics such as accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC). The results demonstrate that all three models achieve accuracy performance in predicting CVD events, with AUC values ranging from 0.85 to 0.92. Ensemble learning exhibits the highest overall accuracy, while SVM and ANN demonstrate strengths in specific aspects of prediction. The study concludes that Machine learning algorithms, particularly ensemble learning, hold significant promise for improving CVD risk assessment. The integration of ML-based predictive models into demographic practice can facilitate early intervention, personalized treatment strategies, and improved patient outcomes.
10
Wolff, Patricio, Manuel Graña, Sebastián A. Ríos, and Maria Begoña Yarza. "Machine Learning Readmission Risk Modeling: A Pediatric Case Study." BioMed Research International 2019 (April 15, 2019): 1–9. http://dx.doi.org/10.1155/2019/8532892.
Full textAbstract:
Background. Hospital readmission prediction in pediatric hospitals has received little attention. Studies have focused on the readmission frequency analysis stratified by disease and demographic/geographic characteristics but there are no predictive modeling approaches, which may be useful to identify preventable readmissions that constitute a major portion of the cost attributed to readmissions.Objective. To assess the all-cause readmission predictive performance achieved by machine learning techniques in the emergency department of a pediatric hospital in Santiago, Chile.Materials. An all-cause admissions dataset has been collected along six consecutive years in a pediatric hospital in Santiago, Chile. The variables collected are the same used for the determination of the child’s treatment administrative cost.Methods. Retrospective predictive analysis of 30-day readmission was formulated as a binary classification problem. We report classification results achieved with various model building approaches after data curation and preprocessing for correction of class imbalance. We compute repeated cross-validation (RCV) with decreasing number of folders to assess performance and sensitivity to effect of imbalance in the test set and training set size.Results. Increase in recall due to SMOTE class imbalance correction is large and statistically significant. The Naive Bayes (NB) approach achieves the best AUC (0.65); however the shallow multilayer perceptron has the best PPV and f-score (5.6 and 10.2, resp.). The NB and support vector machines (SVM) give comparable results if we consider AUC, PPV, and f-score ranking for all RCV experiments. High recall of deep multilayer perceptron is due to high false positive ratio. There is no detectable effect of the number of folds in the RCV on the predictive performance of the algorithms.Conclusions. We recommend the use of Naive Bayes (NB) with Gaussian distribution model as the most robust modeling approach for pediatric readmission prediction, achieving the best results across all training dataset sizes. The results show that the approach could be applied to detect preventable readmissions.
11
Vaidya, Ayush. "Predictive Modeling for Heart Diseases Detection." International Journal for Research in Applied Science and Engineering Technology 13, no. 5 (2025): 560–63. https://doi.org/10.22214/ijraset.2025.70225.
Full textAbstract:
In this Research paper focuses on the development and application of predictive modeling techniques for the early detection of heart disease. Heart disease remains a leading cause of death globally, making early diagnosis and prevention essential. This project seeks to develop a reliable system for predicting the risk of heart disease by utilizing modern machine learning and data analysis techniques, drawing on patient data such as demographics, lifestyle habits, medical background, and clinical test results. By applying various predictive algorithms, such as decision trees, support vector machines, and deep learning models, the system is trained to identify patterns and correlations within the dataset that are indicative of potential cardiovascular issues. The project also emphasizes the use of feature selection techniques to enhance model accuracy and efficiency while mitigating overfitting. The end goal is to create an automated, real-time decision support tool for healthcare providers, enabling them to diagnose heart disease risk more effectively and provide timely interventions
12
Lamprecht, Chris B., Abeer Dagra, and Brandon Lucke-Wold. "Predictive modeling for post operative delirium in elderly." World Journal of Gastrointestinal Oncology 16, no. 9 (2024): 3761–64. http://dx.doi.org/10.4251/wjgo.v16.i9.3761.
Full textAbstract:
Delirium, a complex neurocognitive syndrome, frequently emerges following surgery, presenting diverse manifestations and considerable obstacles, especially among the elderly. This editorial delves into the intricate phenomenon of postoperative delirium (POD), shedding light on a study that explores POD in elderly individuals undergoing abdominal malignancy surgery. The study examines pathophysiology and predictive determinants, offering valuable insights into this challenging clinical scenario. Employing the synthetic minority oversampling technique, a predictive model is developed, incorporating critical risk factors such as comorbidity index, anesthesia grade, and surgical duration. There is an urgent need for accurate risk factor identification to mitigate POD incidence. While specific to elderly patients with abdominal malignancies, the findings contribute significantly to understanding delirium pathophysiology and prediction. Further research is warranted to establish standardized predictive for enhanced generalizability.
13
Oluwasola, Emmanuel Adesemoye, C. Chukwuma-Eke Ezinne, Iyabode Lawal Comfort, Joan Isibor Ngozi, Oyeronke Akintobi Abiola, and Sophia Ezeh Florence. "Comprehensive Review of Predictive Modeling and Risk Management Techniques in Financial Services." Engineering and Technology Journal 10, no. 04 (2025): 4626–48. https://doi.org/10.5281/zenodo.15314770.
Full textAbstract:
The financial services industry faces increasing complexities and uncertainties, making effective risk management and predictive modeling critical for ensuring stability and profitability. This comprehensive review explores the role of predictive modeling and risk management techniques in the financial sector, highlighting their applications in forecasting potential risks and optimizing decision-making processes. Predictive modeling, powered by advanced statistical methods and machine learning algorithms, enables financial institutions to forecast trends, detect anomalies, and predict the likelihood of various risk events such as credit defaults, market volatility, and operational disruptions. By analyzing historical data, financial institutions can identify patterns that allow them to make informed predictions about future events, enhancing their ability to mitigate risks proactively. The review covers various predictive modeling techniques, including regression analysis, decision trees, neural networks, and ensemble methods, discussing their strengths, limitations, and applications in risk assessment. It also explores how these models are integrated with risk management frameworks to improve the accuracy of risk identification and the development of appropriate mitigation strategies. A key aspect of this review is the importance of data quality, model calibration, and continuous monitoring in ensuring the reliability of predictive models. Additionally, the review highlights the intersection of predictive modeling and traditional risk management techniques such as Value at Risk (VaR), stress testing, and scenario analysis. The integration of these techniques with machine learning-driven models allows for more comprehensive and dynamic risk assessments. Furthermore, the growing importance of regulatory compliance in financial risk management is examined, with a focus on how predictive models help institutions comply with stringent regulatory requirements, such as those set by Basel III and Dodd-Frank. In conclusion, the integration of predictive modeling with risk management techniques in financial services is a powerful tool for enhancing risk identification, mitigating potential threats, and optimizing resource allocation. As financial markets continue to evolve, adopting advanced predictive modeling techniques will be essential for maintaining financial stability and competitive advantage.
14
Xie, Shengkun, and Anna Lawniczak. "Estimating Major Risk Factor Relativities in Rate Filings Using Generalized Linear Models." International Journal of Financial Studies 6, no. 4 (2018): 84. http://dx.doi.org/10.3390/ijfs6040084.
Full textAbstract:
Predictive modeling is a key technique in auto insurance rate-making and the decision-making involved in the review of rate filings. Unlike an approach based on hypothesis testing, the results from predictive modeling not only serve as statistical evidence for decision-making, they also discover relationships between a response variable and predictors. In this work, we study the use of predictive modeling in auto insurance rate filings. This is a typical area of actuarial practice involving decision-making using industry loss data. The aim of this study was to offer some general guidelines for using predictive modeling in regulating insurance rates. Our study demonstrates that predictive modeling techniques based on generalized linear models (GLMs) are suitable in auto insurance rate filings review. The GLM relativities of major risk factors can serve as the benchmark of the same risk factors considered in auto insurance pricing.
15
Kang, Xue-ran, Bin Chen, Yi-sheng Chen, et al. "A prediction modeling based on SNOT-22 score for endoscopic nasal septoplasty: a retrospective study." PeerJ 8 (September 11, 2020): e9890. http://dx.doi.org/10.7717/peerj.9890.
Full textAbstract:
Background To create a nomogram prediction model for the efficacy of endoscopic nasal septoplasty, and the likelihood of patient benefiting from the operation. Methods A retrospective analysis of 155 patients with nasal septum deviation (NSD) was performed to develop a predictive model for the efficacy of endoscopic nasal septoplasty. Quality of life (QoL) data was collected before and after surgery using Sinonasal Outcome Test-22 (SNOT-22) scores to evaluate the surgical outcome. An effective surgical outcome was defined as a SNOT-22 score change ≥ 9 points after surgery. Multivariate logistic regression analysis was then used to establish a predictive model for the NSD treatment. The predictive quality and clinical utility of the predictive model were assessed by C-index, calibration plots, and decision curve analysis. Results The identified risk factors for inclusion in the predictive model were included. The model had a good predictive power, with a AUC of 0.920 in the training group and a C index of 0.911 in the overall sample. Decision curve analysis revealed that the prediction model had a good clinical applicability. Conclusions Our prediction model is efficient in predicting the efficacy of endoscopic surgery for NSD through evaluation of factors including: history of nasal surgery, preoperative SNOT-22 score, sinusitis, middle turbinate plasty, BMI, smoking, follow-up time, seasonal allergies, and advanced age. Therefore, it can be cost-effective for individualized preoperative assessment.
16
Singh, Dhanjeet, Vishal Kumar, and Robin G. Qiu. "Patients’ Disease Risk Predictive Modeling using MIMIC Data." Procedia Computer Science 168 (2020): 112–17. http://dx.doi.org/10.1016/j.procs.2020.02.271.
Full text
17
Gafarov, F. M., Ya B. Rudneva, and U. Yu Sharifov. "Predictive Modeling in Higher Education: Determining Factors of Academic Performance." Vysshee Obrazovanie v Rossii = Higher Education in Russia 32, no. 1 (2023): 51–70. http://dx.doi.org/10.31992/0869-3617-2023-32-1-51-70.
Full textAbstract:
For several decades in the field of data mining in education (EDM), predictive learning has remained one of the most popular and internationally discussed research topics. Specifically, data mining is used to predict educational outcomes such as academic performance, retention, success, satisfaction, achievement and dropout rates. In the management practice of higher education institutions, on the basis of an operational forecast, measures are developed and implemented to support those students who fall into the risk group.Our study is aimed at substantiating a model for predicting the early departure of students using an artificial neural network and analyzing predictors that increase the accuracy of predicting successful graduation from a Russian university. This work will expand the international practice of comparative research in higher education.The paper confirms the already existing hypotheses about the influence of a number of factors on the prediction of academic performance and suggests the need to test their universality or specificity in a particular institution of higher education. We also proved that an artificial neural network model with a certain set of attributes can be applied in the context of a single higher education institution, regardless of specialization. To determine the potential risk group of students, a binary classification prediction model is used. The overall prediction accuracy of a neural network with combined data reaches 88%. For this neural network model, the basic predictors that affect the accuracy of the forecast are the cumulative average level of achievement (CGPA) and the year of admission to the university.
18
Wisnieski, Lauren, Bo Norby, Steven J. Pierce, Tyler Becker, and Lorraine M. Sordillo. "Prospects for predictive modeling of transition cow diseases." Animal Health Research Reviews 20, no. 1 (2019): 19–30. http://dx.doi.org/10.1017/s1466252319000112.
Full textAbstract:
AbstractTransition cow diseases can negatively impact animal welfare and reduce dairy herd profitability. Transition cow disease incidence has remained relatively stable over time despite monitoring and management efforts aimed to reduce the risk of developing diseases. Dairy cattle disease risk is monitored by assessing multiple factors, including certain biomarker test results, health records, feed intake, body condition score, and milk production. However, these factors, which are used to make herd management decisions, are often reviewed separately without considering the correlation between them. In addition, the biomarkers that are currently used for monitoring may not be representative of the complex physiological changes that occur during the transition period. Predictive modeling, which uses data to predict future or current outcomes, is a method that can be used to combine the most predictive variables and their interactions efficiently. The use of an effective predictive model with relevant predictors for transition cow diseases will result in better targeted interventions, and therefore lower disease incidence. This review will discuss predictive modeling methods and candidate variables in the context of transition cow diseases. The next step is to investigate novel biomarkers and statistical methods that are best suited for the prediction of transition cow diseases.
19
Jeffrey, Chidera Ogeawuchi, Emmanuel Akpe Oyinomomo-emi, Ayodeji Abayomi Abraham, and Aderemi Agboola Oluwademilade. "Advances In Predictive Modeling and Risk Mitigation in Education and Financial Services using Machine Learning and BI Dashboards." Engineering and Technology Journal 10, no. 05 (2025): 5040–50. https://doi.org/10.5281/zenodo.15461633.
Full textAbstract:
This paper examines the integration of predictive modeling and risk mitigation techniques using machine learning (ML) and Business Intelligence (BI) dashboards in the education and financial services sectors. Predictive modeling, powered by ML algorithms, provides valuable insights into student performance, dropout prediction, and risk assessment, thereby enabling educational institutions to intervene proactively. Similarly, in financial services, predictive models enhance credit risk evaluation, fraud detection, and regulatory compliance, ensuring more informed decision-making. However, challenges such as data quality, algorithmic bias, and the cost of implementation present barriers to the widespread adoption of these technologies. This paper explores these challenges while highlighting the practical implications for practitioners in both sectors, emphasizing the need for better data integration, fairness in model outcomes, and the integration of BI dashboards for more effective decision-making. Additionally, the paper discusses future research directions, including the integration of advanced AI techniques and the continued advancement of BI tools to further optimize risk mitigation and predictive capabilities. Overall, the findings underscore the transformative potential of predictive analytics in improving outcomes, operational efficiency, and risk management in education and financial services.
20
Tu, Haibin, Siyi Feng, Lihong Chen, Yujie Huang, Juzhen Zhang, and Xiaoxiong Wu. "Revolutionising hepatocellular carcinoma surveillance: Harnessing contrast-enhanced ultrasound and serological indicators for postoperative early recurrence prediction." Medicine 102, no. 35 (2023): e34937. http://dx.doi.org/10.1097/md.0000000000034937.
Full textAbstract:
This study aimed to develop a noninvasive predictive model for identifying early postoperative recurrence of hepatocellular carcinoma (within 2 years after surgery) based on contrast-enhanced ultrasound and serum biomarkers. Additionally, the model’s validity was assessedthrough internal and external validation. Clinical data were collected from patients who underwent liver resection at the First Hospital of Quanzhou and Mengchao Hepatobiliary Hospital. The data included general information, contrast-enhanced ultrasound parameters, Liver Imaging Reporting and Data System (LI-RADS) classification, and serum biomarkers. The data from Mengchao Hospital were divided into 2 groups, with a ratio of 6:4, to form the modeling and internal validation sets, respectively. On the other hand, the data from the First Hospital of Quanzhou served as the external validation group. The developed model was named the Hepatocellular Carcinoma Early Recurrence (HCC-ER) prediction model. The predictive efficiency of the HCC-ER model was compared with other established models. The baseline characteristics were found to be well-balanced across the modeling, internal validation, and external validation groups. Among the independent risk factors identified for early recurrence, LI-RADS classification, alpha-fetoprotein, and tumor maximum diameter exhibited hazard ratios of 1.352, 1.337, and 1.135 respectively. Regarding predictive accuracy, the HCC-ER, Tumour-Node-Metastasis, Barcelona Clinic Liver Cancer, and China Liver Cancer models demonstrated prediction errors of 0.196, 0.204, 0.201, and 0.200 in the modeling group; 0.215, 0.215, 0.218, and 0.212 in the internal validation group; 0.210, 0.215, 0.216, and 0.221 in the external validation group. Using the HCC-ER model, risk scores were calculated for all patients, and a cutoff value of 50 was selected. This cutoff effectively distinguished the high-risk recurrence group from the low-risk recurrence group in the modeling, internal validation, and external validation groups. However, the calibration curve of the predictive model slightly overestimated the risk of recurrence. The HCC-ER model developed in this study demonstrated high accuracy in predicting early recurrence within 2 years after hepatectomy. It provides valuable information for developing precise treatment strategies in clinical practice and holds considerable promise for further clinical implementation.
21
Holt, Kimberly Long. "Predictive Modeling of Occupational Exposure Using Machine Learning and Environmental Sensor Data." Journal of Exceptional Multidisciplinary Research 2, no. 1 (2025): 82–89. https://doi.org/10.69739/jemr.v2i1.617.
Full textAbstract:
Such working environment exposures to harmful elements carry a great risk to workers of different works in different industries especially where they work with chemicals, airborne dusts, physical stresses. Classic exposure assessment approaches —those which tend to inform by manual sampling and past history, are relatively blunt in terms of temporal resolution and lag of response. The use of low-cost environmental sensors and machine learning (ML) techniques provide a paradigm-changing means of predictive modelling of occupational exposure, and will be able to allow real-time risk assessment and pre-emptive hazard mitigation Environmental sensors are able to monitor such things as temperature, humidity, particulate matter (PM), volatile organic compounds (VOCs), and noise levels at all times. These data are able to serve as the basis for the creation of predictive models using ML algorithms that determine the exposure trends, prediction of the high-risk scenarios, and dynamic decision-making Supervised learning models, such as random forests and gradient boosting machines, have demonstrated valid usage in predicting exposure result based on multi-variate sensor input. These days, deep learning methods, including recurrent neural networks (RNNs), have shown better results in dealing with temporal data, and in identifying complex patterns of exposure over time.
22
Baumeister, Sebastian E., Marcus Dörr, Dörte Radke, et al. "Predictive modeling of health care costs: do cardiovascular risk markers improve prediction?" European Journal of Cardiovascular Prevention & Rehabilitation 17, no. 3 (2009): 355–62. http://dx.doi.org/10.1097/hjr.0b013e328333a0b7.
Full text
23
Goyal, Rajeev. "Mathematics in Finance: Risk Management and Predictive Analytics." Modern Dynamics: Mathematical Progressions 1, no. 3 (2024): 1–5. https://doi.org/10.36676/mdmp.v1.i3.34.
Full textAbstract:
The application of mathematical principles in finance has revolutionized risk management and predictive analytics, enabling more precise modeling, assessment, and mitigation of financial risks. This paper explores the critical role of mathematics in developing robust financial models that enhance decision-making processes and improve the accuracy of financial forecasts. Key mathematical techniques, including probability theory, statistics, stochastic processes, and optimization, are examined in the context of their application to risk management and predictive analytics. the use of probability theory and statistics in modeling financial risks, such as market risk, credit risk, and operational risk. These mathematical tools provide the foundation for quantifying and managing uncertainty in financial markets. Stochastic processes, including Brownian motion and geometric Brownian motion, are explored for their role in modeling asset prices and interest rates, forming the basis of various financial derivatives and options pricing models.
24
Kailash, Alle. "Logistic Regression for Predictive Modeling." Journal of Scientific and Engineering Research 8, no. 9 (2019): 307–14. https://doi.org/10.5281/zenodo.13347981.
Full textAbstract:
Customer retention, loyalty measurement, and recovery strategies have become crucial for businesses aiming to minimize client loss. Instead of focusing solely on acquiring new customers, companies now prioritize preventing the loss of existing ones. The telecommunications industry, with its rapid technological advancements and growing user base, generates vast amounts of data. However, this rapid and uncontrolled expansion leads to significant losses due to fraud and technical issues, necessitating the development of new analytical methodologies. This paper addresses the urgent need for effective analysis techniques to manage and interpret the vast data in the telecommunications sector. The primary objective for many providers is to retain highly profitable customers. By predicting which clients are at greater risk of churning, telecommunications companies can implement proactive measures to reduce customer churn and enhance overall business performance.
25
Qianqian, Zhang, Jinying Zhao, Yating Liu, et al. "Development and Evaluation of a Risk Predictive Model for High Level of Self-Reported Symptom Cluster Distress in Patients with Hematologic Malignancies." Blood 144, Supplement 1 (2024): 7911. https://doi.org/10.1182/blood-2024-206411.
Full textAbstract:
Object To develop and evaluate a risk predictive model for high level of self-reported symptom cluster distress in patients with hematologic malignancies. Methods 354 patients who met the inclusion and exclusion criteria were selected at 5 tertiary hospitals in Beijing，Tianjin，Shandong，Jiangsu，and Anhui provinces in China from June to August 2023．Cases were randomly assigned to a modeling group and a validation group based on 5-old cross-validation method at a ratio of 8：2．The random forest algorithm was used to develop the risk predictive model in the modeling group．The receiver operating characteristic curve，Hosmer-Lemeshow goodness-of-fit test，calibration curve，and decision curve were used to comprehensively evaluate the prediction performance of the model in the validation group．Risk factors were identified based on the order of the importance of each influencing factors． Results The incidence of high symptom cluster distress was 35.37％in the modeling group and 31.29％in the validation group．The area under the receiver operating characteristic curve of the prediction model was 0.91；the sensitivity was 68.6%，the specificity was 94.6％；Hosmer-Lemeshow goodness-of-fit test was insignificant(P=0.1375)；the decision curve was above the reference line． Conclusion The risk predictive model based on random forest algorithm has good predictive performance，which is of great significance to help identify hematologic malignancies subgroups at high risk of symptom cluster distress，and will potentially promote symptom management．
26
Nainar, M. Asan. "Predictive Modeling for Brain Stroke Detection Using Machine Learning M. Asan Nainar." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem35392.
Full textAbstract:
Brain strokes often resulting in severe health complications and mortality are a significant global health concern. Early detection and brain stroke prediction involves assessing risk factors, medical history, diagnostic tests, and predictive models. Aims to identify individuals at risk before stroke occurrence, enabling timely interventions and lifestyle modifications to mitigate the risk. In this research, an in-depth exploration of predictive modeling for brain stroke detection utilizing machine learning algorithms specifically XG Boost, Decision Tree, and K-Nearest Neighbors (KNN) is presented. The proposed methodology encompasses data preprocessing, feature engineering, model selection, and accuracy evaluation. Through extensive experimentation, cross-validation, prediction of the performance of each algorithm focuses on metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). Keywords—Machine learning, XG Boost, Decision Tree, K-Nearest Neighbor (KNN), Accuracy, Brain Stroke.
27
Lang, Yiping, Tianyu Liang, and Fei Li. "Integrated multi-omics analysis and predictive modeling of heart failure using sepsis-related gene signature." PLOS One 20, no. 6 (2025): e0326212. https://doi.org/10.1371/journal.pone.0326212.
Full textAbstract:
Background Heart failure (HF) is characterized by complex molecular alterations, and recent studies suggest a potential role for sepsis-related genes in cardiovascular dysfunction. This study aimed to develop a predictive model for HF based on sepsis-related gene signatures. Methods Three sepsis-related datasets (GSE65682, GSE54514, and GSE95233) were analyzed to identify differentially expressed genes (DEGs) following batch effect correction using the ComBat algorithm. With the use of elastic net regularization and the glmnet package in R, Lasso Cox regression was employed to screen out gene signatures. A predictive model was developed based on the expression of each gene signature and the co-efficient values. In addition, the predictive model was validated on independent HF datasets (GSE57345, GSE141910, and GSE5406). Model performance was assessed through receiver operating characteristic (ROC) analysis and AUC values of each gene signature, and immune infiltration was evaluated using CIBERSORT, IPS, and xCell. Sepsis models of C57BL/6 mice were established by cecal ligation and puncture (CLP). Results We identified 340 up-regulated and 333 down-regulated sepsis-related genes. The predictive model, incorporating six key genes, demonstrated superior performance compared to individual genes across both training and validation datasets with the AUC value of the risk score above 0.9, significantly higher than that of a single gene. Immune infiltration profiles differed significantly between HF patients and controls, with more pronounced alterations observed at higher risk score levels. Finally, the expression of six key genes in sepsis models was confirmed to be consistent with our prediction. Conclusion The model constructed through sepsis-related characteristic genes provides a highly advantageous method for predicting HF, and the characteristic genes we have screened may be potential biomarkers for predicting HF. This model has potential application value in early diagnosis and risk stratification, which can help improve the clinical management of heart failure and provide new ideas for preventing HF.
28
BUCHANAN, ROBERT L., and RICHARD C. WHITING. "Risk Assessment and Predictive Microbiology." Journal of Food Protection 59, no. 13 (1996): 31–36. http://dx.doi.org/10.4315/0362-028x-59.13.31.
Full textAbstract:
ABSTRACT The need and desirability of being able to perform quantitative microbial risk assessments for food processing and preparation operations has been discussed extensively for the past several years. However, there has been little application of this approach in large part due to the need to account for the changes in bacterial populations as a result of food environments and processing. The use of predictive food microbiology models has the potential for overcoming these limitations. Through integration of predictive modeling with risk assessment, it is possible to estimate how changes in unit operations are likely to effect the overall safety of a food. Hypothetical examples of how these techniques could be applied to both single-step and multiple-step food-processing and preparation operations are provided.
29
Samuel Jesupelumi Owoade, Abel Uzoka, Joshua Idowu Akerele, and Pascal Ugochukwu Ojukwu. "Enhancing financial portfolio management with predictive analytics and scalable data modeling techniques." International Journal of Scholarly Research and Reviews 5, no. 2 (2024): 089–102. http://dx.doi.org/10.56781/ijsrr.2024.5.2.0050.
Full textAbstract:
The financial industry faces an increasingly complex landscape for portfolio management, where data-driven insights are crucial for optimizing asset allocation and managing risk. This paper explores the integration of predictive analytics and scalable data modeling techniques in enhancing financial portfolio management. By leveraging machine learning algorithms, big data architectures, and real-time data processing, predictive analytics can forecast asset trends, detect market anomalies, and assess portfolio risk with high precision. We evaluate several predictive models, including time-series forecasting, neural networks, and ensemble methods, for their efficacy in financial prediction. The study also discusses the role of scalable data modeling frameworks, such as Apache Spark and cloud-based data lakes, in handling vast volumes of unstructured data across different markets and asset classes. Findings indicate that predictive analytics, when paired with robust data models, can deliver real-time, actionable insights, enhancing decision-making for fund managers and institutional investors. Furthermore, this paper highlights best practices for implementing scalable models in financial institutions, addressing challenges like data latency, model interpretability, and system scalability. By adopting these advanced analytics frameworks, portfolio managers can achieve improved risk-adjusted returns, better asset diversification, and enhanced adaptability to market volatility.
30
Ibrahim Adedeji Adeniran, Christianah Pelumi Efunniyi, Olajide Soji Osundare, and Angela Omozele Abhulimen. "Advancements in predictive modeling for insurance pricing: Enhancing risk assessment and customer segmentation." International Journal of Management & Entrepreneurship Research 6, no. 8 (2024): 2835–48. http://dx.doi.org/10.51594/ijmer.v6i8.1469.
Full textAbstract:
This review paper explores the significant advancements in predictive modeling for insurance pricing, emphasizing its role in enhancing risk assessment and customer segmentation. The paper begins with an overview of the evolution of predictive modeling in the insurance industry, tracing the shift from traditional methods to modern, data-driven approaches powered by machine learning, artificial intelligence (AI), and big data. It highlights how these advancements have improved the accuracy of risk assessment, enabling insurers to develop more precise pricing strategies. The paper also discusses the importance of customer segmentation and personalization in insurance pricing, showcasing how advanced analytics can lead to more tailored and fair premiums, thereby improving customer satisfaction and retention. Additionally, the review addresses the challenges of implementing these advanced predictive models, including technological integration, ethical concerns, and regulatory compliance. The paper concludes by identifying future trends and potential areas for further research, such as real-time data, explainable AI, and ethical AI practices, which are expected to shape the future of predictive modeling in the insurance industry. Keywords: Predictive Modeling, Insurance Pricing, Risk Assessment, Customer Segmentation, Machine Learning.
31
Batchi-Bouyou, Armel L., Duc Tran, Michael Raddatz, et al. "Predictive Modeling of Clonal Hematopoiesis across Diverse Cohorts." Blood 144, Supplement 1 (2024): 1285. https://doi.org/10.1182/blood-2024-210900.
Full textAbstract:
Background: Clonal hematopoiesis (CH) is associated an increased risk of hematologic malignancy and numerous other adverse events. While there are no established therapeutic approaches to treat CH, clinical trials are underway, many of which use targeted therapeutic approaches for specific CH genes or genetic pathways. Since CH screening is generally not part of routine clinical testing, the identification of CH-positive individuals is a challenge to recruitment. While age is the most important risk factor for CH, CH is also known to be associated with other demographic and clinical risk factors. Blood count and blood parameters are also known to be influenced by CH with gene-specific patterns. Here we sought to understand whether commonly available clinical predictors and blood counts could be used to develop a gene-specific CH risk prediction tool with the goal of facilitating CH research screening strategies. Methods: We constructed a prediction model for CH across three cohorts of participants using LASSO regression. Clinical predictors included clinical/demographic characteristics (smoking history, gender, race) and blood count parameters. The UK Biobank served as the development cohort, consisting of 452,547 participants. We used two separate cohorts for validation, The All of Us (AoU) Research database, consisting of 143,850 participants, and MSK-IMPACT cohort, including 8,150 patients with non-hematologic cancers. We compared models with age alone to models including blood count and other clinical/demographic parameters. The predictive performance was determined based on 2 criteria: discrimination by calculating the area under the curve (AUC) receiver operating characteristic (ROC) and calibration by calculating the calibration slope (slope of 1 indicates perfect calibration) and the intercept. Results: A total of 604,547 participants were included in the study. We observed strong associations between clinical features and gene-specific CH including platelet count with DNMT3A and JAK2, neutrophil count and IDH1/2 mutations, and a strong association between spliceosome CH and age. Overall our model showed excellent discrimination (AUC>0.8) for risk JAK2, ASXL1, PPM1D, SF3B1, SRF2, U2AF1 and modest discrimination (AUC>0.7) for DNMT3A, IDH1/2, TP53 and TET2. Compared to a model with age alone, the addition of blood count and clinical parameters improved the model's performance most notably for JAK2 (AUC = 0.72 vs 0.82) and IDH1/2 (AUC = 0.75 vs 0.78). The calibration slopes for gene-specific models ranged from 0.35-1.65 and were highest for JAK2 (slope=0.9; intercept=0.02 ) and TP53 (slope=0.89; intercept=-0.02) . To better determine how our risk prediction model could be used to inform CH screening strategies, we determined the number of patients that would be required to screen using our CH risk prediction model and the number needed to sequence to identify 100 CH positive individuals across 10 CH genes. Application of our risk prediction model to identify individuals at high risk of CH for screening reduced the number of samples needed to sequence by 4-19 fold. Conclusion: We developed and validated a model for gene-specific CH prediction using blood count parameters and demographic factors with strong discriminative performance. These findings highlight the potential of commonly available clinical data to improve CH prediction, aiding in efficient identification of individuals with CH to facilitate clinical trial design.
32
Mudzramer A. Hayudini, Datu Ansaruddin K. Kiram, Mharcelyn M. Kiram, Abdulkamal H. Abduljalil, Nureeza J. Latorre, and Fahra B. Sahibad. "Predictive Modeling in Cardiovascular Disease: An Investigation of Random Forests." Natural Sciences Engineering and Technology Journal 5, no. 1 (2024): 393–404. https://doi.org/10.37275/nasetjournal.v5i1.60.
Full textAbstract:
Cardiovascular diseases (CVDs) are a leading cause of death worldwide. Early detection and intervention are crucial for improving patient outcomes. Machine learning (ML) offers promising tools for CVD prediction, with random forests (RF) emerging as a robust and versatile algorithm. This study investigates the application of RF in predicting blood pressure categories, a crucial indicator of cardiovascular health, using a comprehensive dataset of patient metrics. This study investigated the application of RF in predicting blood pressure categories, a crucial indicator of cardiovascular health. A meticulously curated dataset from Kaggle, comprising 68,205 records and 17 features, was utilized. Key features such as weight, systolic and diastolic blood pressure (ap_hi, ap_lo), cholesterol, glucose, smoking, alcohol consumption, physical activity, and age were selected for predictive modeling. The RF model was trained and tested using a stratified split, and its performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrix. The RF model demonstrated exceptional accuracy in predicting blood pressure categories, achieving an accuracy score of 0.9999. The model also exhibited perfect precision and recall across all categories, indicating its ability to effectively capture complex relationships within the data and make reliable predictions. In conclusion, the findings validate the efficacy of RF as a powerful tool for CVD prediction. Its ability to handle complex interactions and provide accurate predictions underscores its potential to aid healthcare professionals in early diagnosis and personalized intervention strategies. Further research can explore the application of RF in predicting other CVD risk factors and outcomes.
33
Ji, Jung-Hwan, Sung-Gwe Ahn, Youngbum Yoo, et al. "Prediction of a Multi-Gene Assay (Oncotype DX and Mammaprint) Recurrence Risk Group Using Machine Learning in Estrogen Receptor-Positive, HER2-Negative Breast Cancer—The BRAIN Study." Cancers 16, no. 4 (2024): 774. http://dx.doi.org/10.3390/cancers16040774.
Full textAbstract:
This study aimed to develop a machine learning-based prediction model for predicting multi-gene assay (MGA) risk categories. Patients with estrogen receptor-positive (ER+)/HER2− breast cancer who had undergone Oncotype DX (ODX) or MammaPrint (MMP) were used to develop the prediction model. The development cohort consisted of a total of 2565 patients including 2039 patients tested with ODX and 526 patients tested with MMP. The MMP risk prediction model utilized a single XGBoost model, and the ODX risk prediction model utilized combined LightGBM, CatBoost, and XGBoost models through soft voting. Additionally, the ensemble (MMP + ODX) model combining MMP and ODX utilized CatBoost and XGBoost through soft voting. Ten random samples, corresponding to 10% of the modeling dataset, were extracted, and cross-validation was performed to evaluate the accuracy on each validation set. The accuracy of our predictive models was 84.8% for MMP, 87.9% for ODX, and 86.8% for the ensemble model. In the ensemble cohort, the sensitivity, specificity, and precision for predicting the low-risk category were 0.91, 0.66, and 0.92, respectively. The prediction accuracy exceeded 90% in several subgroups, with the highest prediction accuracy of 95.7% in the subgroup that met Ki-67 <20 and HG 1~2 and premenopausal status. Our machine learning-based predictive model has the potential to complement existing MGAs in ER+/HER2− breast cancer.
34
Rohini, Talekar, and P. Praveen. "An Intuitive Approach on Transfer Learning with an IBF+IHP Model for Stroke Classification and Prediction." Engineering, Technology & Applied Science Research 15, no. 1 (2025): 19655–60. https://doi.org/10.48084/etasr.9031.
Full textAbstract:
A cerebral stroke can have significant health ramifications. Efficient stroke prevention requires precise prevention and prompt detection of risk factors. This study introduces a novel predictive modeling technique that uses uncomplicated spatial filter maps and ensemble approaches to enhance stroke risk prediction. The proposed approach utilizes ensemble approaches along with comprehensible spatial filter maps to uncover significant spatial patterns in brain imaging data. The ensemble approach employs a multitude of prediction models to enhance the accuracy of stroke risk forecasts. The experimental findings demonstrate that spatial filter maps and ensemble techniques surpass traditional models in predicting performance. This study showcases the potential of spatial filters to include several patient data to accurately predict stroke risk with a 98% success rate.
35
Prakash, Somasundaram. "Predictive Intelligence: The Impact of Risk Modeling on Organizational Resilience." International Journal of Innovative Technology and Exploring Engineering (IJITEE) 13, no. 3 (2024): 1–3. https://doi.org/10.35940/ijitee.C9802.13030224.
Full textAbstract:
<strong>Abstract:</strong> The importance of risk modelling in strategic planning and decision-making cannot be emphasized enough in an age where uncertainty is constant. This paper explores the crucial function of risk modelling as a vital resource for people and organizations trying to understand and reduce potential risks. The emergence of big data and technology has made it possible to create complex risk models that offer more insights into possible hazards and improve the efficacy of risk management choices. In order to properly measure and manage risks, this article highlights the value of risk models across a range of industries. Risk models are essential for regulatory compliance, especially in sectors like healthcare, where following laws like GDPR and HIPAA are required. These models offer a consistent method for evaluating risk, guaranteeing adherence and averting costly fines. Additionally covered in the article is how risk models improve decision-making by lowering uncertainty and increasing openness, which in turn fosters stakeholder trust. The paper's main body describes a thorough approach to risk modelling, which begins with identifying potential risks and progresses to risk assessment through the use of methods like fault tree analysis (FTA) and event tree analysis (ETA). It then goes over how to quantify risks using both quantitative and qualitative approaches, and it ends with adding up every potential threat to provide an overall risk profile for the company. This paper concludes by highlighting the need for risk modelling in the intricate corporate world. It offers a thorough process for creating risk models, matching them to organizational goals, and utilizing them as a preventative measure for resilience and long-term performance.
36
VAN DEN MUNCKHOF, SVEN, ALI ASADI NIKOOYAN, and AMIR ABBAS ZADPOOR. "ASSESSMENT OF OSTEOPOROTIC FEMORAL FRACTURE RISK: FINITE ELEMENT METHOD AS A POTENTIAL REPLACEMENT FOR CURRENT CLINICAL TECHNIQUES." Journal of Mechanics in Medicine and Biology 15, no. 03 (2015): 1530003. http://dx.doi.org/10.1142/s0219519415300033.
Full textAbstract:
Femoral fracture risk prediction is a necessary step preceding effective pharmacological intervention or pre-operative planning. Current clinical methods for fracture risk prediction rely on 2D imaging methods and have limited predictive value. Researchers are therefore trying to find improved methods for fracture prediction. During last few decades, many studies have focused on integration of 3D imaging techniques and the finite element (FE) method to improve the accuracy of fracture assessment techniques. In this paper, we review the recent advances in FE and other techniques for predicting the risk of femoral fractures. Based on a number of selected studies, the different steps that are involved in generation of patient-specific FE models are reviewed with particular emphasis on the fracture criteria. The inaccuracies that might arise due to the imperfections of the involved steps are also discussed. It is concluded that compared to image- and geometry-based techniques, FE is a more promising approach for prediction of fracture loads. However, certain technological advancements in FE modeling protocols are required before FE modeling can be recruited in clinical settings.
37
Dareng, Eileen O., Jonathan P. Tyrer, Daniel R. Barnes, et al. "Polygenic risk modeling for prediction of epithelial ovarian cancer risk." European Journal of Human Genetics 30, no. 3 (2022): 349–62. http://dx.doi.org/10.1038/s41431-021-00987-7.
Full textAbstract:
AbstractPolygenic risk scores (PRS) for epithelial ovarian cancer (EOC) have the potential to improve risk stratification. Joint estimation of Single Nucleotide Polymorphism (SNP) effects in models could improve predictive performance over standard approaches of PRS construction. Here, we implemented computationally efficient, penalized, logistic regression models (lasso, elastic net, stepwise) to individual level genotype data and a Bayesian framework with continuous shrinkage, “select and shrink for summary statistics” (S4), to summary level data for epithelial non-mucinous ovarian cancer risk prediction. We developed the models in a dataset consisting of 23,564 non-mucinous EOC cases and 40,138 controls participating in the Ovarian Cancer Association Consortium (OCAC) and validated the best models in three populations of different ancestries: prospective data from 198,101 women of European ancestries; 7,669 women of East Asian ancestries; 1,072 women of African ancestries, and in 18,915 BRCA1 and 12,337 BRCA2 pathogenic variant carriers of European ancestries. In the external validation data, the model with the strongest association for non-mucinous EOC risk derived from the OCAC model development data was the S4 model (27,240 SNPs) with odds ratios (OR) of 1.38 (95% CI: 1.28–1.48, AUC: 0.588) per unit standard deviation, in women of European ancestries; 1.14 (95% CI: 1.08–1.19, AUC: 0.538) in women of East Asian ancestries; 1.38 (95% CI: 1.21–1.58, AUC: 0.593) in women of African ancestries; hazard ratios of 1.36 (95% CI: 1.29–1.43, AUC: 0.592) in BRCA1 pathogenic variant carriers and 1.49 (95% CI: 1.35–1.64, AUC: 0.624) in BRCA2 pathogenic variant carriers. Incorporation of the S4 PRS in risk prediction models for ovarian cancer may have clinical utility in ovarian cancer prevention programs.
38
Marciuc, Monica Andreea. "Predictive modeling for claims in automobile insurance." Virgil Madgearu Review of Economic Studies and Research 17, no. 2 (2024): 79–99. https://doi.org/10.24193/rvm.2024.17.118.
Full textAbstract:
The rise of advanced machine learning methods has revolutionized the landscape of predictive modeling in the automobile insurance sector. This paper presents the relevant literature review on the use of machine learning methods, including gradient boosting, random forests, and decision trees, to model claims in automobile insurance. By synthesizing findings from key studies, we conclude on the predictive performance of these methods compared to traditional actuarial models and identify emerging trends and challenges in this domain. Our analysis highlights how data-driven approaches enhance pricing accuracy, optimize risk assessment, and improve operational efficiency. Furthermore, the paper addresses critical issues such as model interpretability, fairness, and ethical considerations in adopting machine learning technologies. This literature review contributes to the ongoing discourse on improving automobile insurance practices through predictive analytics and provides a foundation for future research.
39
Masconi, Katya L., Justin Basile Echouffo-Tcheugui, Tandi E. Matsha, Rajiv T. Erasmus, and Andre Pascal Kengne. "Predictive modeling for incident and prevalent diabetes risk evaluation." Expert Review of Endocrinology & Metabolism 10, no. 3 (2015): 277–84. http://dx.doi.org/10.1586/17446651.2015.1015989.
Full text
40
Hu, Wei, Yuhuan Wu, and Ziting Yang. "An Analysis of Credit Risk Prediction for Small and Micro Enterprises." Journal of Artificial Intelligence Research 1, no. 2 (2024): 1–21. https://doi.org/10.70891/jair.2024.110004.
Full textAbstract:
Digital inclusive finance has emerged as a significant catalyst for the high-quality development of small and micro enterprises (SMEs). This study, grounded in credit risk prediction theory, develops a comprehensive profiling and predictive model for SMEs, offering insights into innovative mechanisms by which inclusive finance can support their sustainable growth. Utilizing an extensive literature review, along with experimental modeling based on publicly available data, the study explores two approaches to feature construction. By employing diverse algorithms, it builds predictive models and proposes tailored policy recommendations to enhance inclusive financial practices. The credit prediction model facilitates targeted financial support and innovation management strategies for SMEs, contributing a fresh perspective to advancing the quality and effectiveness of digital inclusive finance
41
Gaba, Faiza, Sara Mahvash Mohammadi, Mikhail I. Krivonosov, and Oleg Blyuss. "Predicting Risk of Post-Operative Morbidity and Mortality following Gynaecological Oncology Surgery (PROMEGO): A Global Gynaecological Oncology Surgical Outcomes Collaborative Led Study." Cancers 16, no. 11 (2024): 2021. http://dx.doi.org/10.3390/cancers16112021.
Full textAbstract:
The medical complexity of surgical patients is increasing, and surgical risk calculators are crucial in providing high-value, patient-centered surgical care. However, pre-existing models are not validated to accurately predict risk for major gynecological oncology surgeries, and many are not generalizable to low- and middle-income country settings (LMICs). The international GO SOAR database dataset was used to develop a novel predictive surgical risk calculator for post-operative morbidity and mortality following gynecological surgery. Fifteen candidate features readily available pre-operatively across both high-income countries (HICs) and LMICs were selected. Predictive modeling analyses using machine learning methods and linear regression were performed. The area-under-the-receiver-operating characteristic curve (AUROC) was calculated to assess overall discriminatory performance. Neural networks (AUROC 0.94) significantly outperformed other models (p < 0.001) for evaluating the accuracy of prediction across three groups, i.e., minor morbidity (Clavien–Dindo I-II), major morbidity (Clavien–Dindo III-V), and no morbidity. Logistic-regression modeling outperformed the clinically established SORT model in predicting mortality (AUROC 0.66 versus 0.61, p < 0.001). The GO SOAR surgical risk prediction model is the first that is validated for use in patients undergoing gynecological surgery. Accurate surgical risk predictions are vital within the context of major cytoreduction surgery, where surgery and its associated complications can diminish quality-of-life and affect long-term cancer survival. A model that requires readily available pre-operative data, irrespective of resource setting, is crucial to reducing global surgical disparities.
42
Wang, Jing, Chenhao Zhao, and Zhixia Liu. "Can Historical Accident Data Improve Sustainable Urban Traffic Safety? A Predictive Modeling Study." Sustainability 16, no. 22 (2024): 9642. http://dx.doi.org/10.3390/su16229642.
Full textAbstract:
Traffic safety is a critical factor for the sustainable development of urban transportation systems. This study investigates the impact of historical accident information on the prediction of future traffic accident risks, as well as the interaction between this information and other features, such as driver violations and vehicle attributes. Using a comprehensive dataset of traffic accidents involving passenger vehicles in a western Chinese city, we developed two predictive models: Model 1, which is based on vehicle information and driver violations, and Model 2, which integrates historical accident data. The results indicate that the inclusion of historical accident information significantly enhances the predictive performance of the model, particularly in terms of AUC (Area Under the Curve) and AP (Average Precision) values. Furthermore, through feature importance analysis and SHAP (SHapley Additive exPlanations) value evaluation, this study reveals the interaction effects between historical accident data and other features, and how these interactions influence model decisions. The findings suggest that historical accident data play a positive role in predicting future accident risk, with varying effects on risk mitigation. These insights provide a scientific basis for developing strategies to ensure the sustainable development of urban transportation systems.
43
Peek, N., F. Voorbraak, E. de Jonge, B. A. J. M. de Mol, and M. Verduijn. "Modeling Length of Stay as an Optimized Two-class Prediction Problem." Methods of Information in Medicine 46, no. 03 (2007): 352–59. http://dx.doi.org/10.1160/me0368.
Full textAbstract:
Summary Objectives: To develop a predictive model for the outcome length of stay at the Intensive Care Unit (ICU LOS), including the choice of an optimal dichotomization threshold for this outcome. Reduction of prediction problems of this type of outcome to a two-class problem is a common strategy to identify high-risk patients. Methods: Threshold selection and model development are performed simultaneously. From the range of possible threshold values, the value is chosen for which the corresponding predictive model has maximal precision based on the data. To compare the precision of models for different dichotomizations of the outcome, the MALOR performance statistic is introduced. This statistic is insensitive to the prevalence of positive cases in a two-class prediction problem. Results: The procedure is applied to data from cardiac surgery patients to dichotomize the outcome ICU LOS. The class probabilitytree method is used to develop predictive models. Within our data, the best model precision is found at the threshold of seven days. Conclusions: The presented method extends existing procedures for predictive modeling with optimization of the outcome definition for predictive purposes. The method can be applied to all prediction problems where the outcome variable needs to be dichotomized, and is insensitive to changes in the prevalence of positive cases with different dichotomization thresholds.
44
Pucar, Đorđe, and Vladimir Šimović. "Predictive modeling of stroke occurrence using Python for improved risk assessment." Journal of Process Management and New Technologies 12, no. 1-2 (2024): 110–20. http://dx.doi.org/10.5937/jpmnt12-50921.
Full textAbstract:
This paper examines the use of Machine Learning (ML) techniques, particularly Logistic Regression and Random Forests, to predict the occurrence of strokes. It integrates demographic, clinical, and lifestyle factors. The study uses Python as the primary tool for model development and analysis, focusing on binary classification to categorize individuals as either having had a stroke or not. The dataset includes attributes such as age, gender, hypertension, smoking status, and more, which are used to train and evaluate the models. Through extensive experimentation and evaluation, the paper demonstrates the effectiveness of Logistic Regression and Random Forests in stroke prediction. Logistic Regression provides a straightforward baseline, while Random Forests offer higher predictive accuracy. The findings highlight the importance of ML-based approaches in healthcare risk assessment and showcase Python's versatility in facilitating such analyses.
45
Kuwornu, J. P., L. Lix, J. Quail, E. Wang, M. Osman, and G. Teare. "Assessing The Incremental Predictive Value Of Healthcare Utilization Pathways In Risk Prediction Modeling." Value in Health 18, no. 3 (2015): A16. http://dx.doi.org/10.1016/j.jval.2015.03.101.
Full text
46
Rasmy, Laila, Firat Tiryaki, Yujia Zhou, et al. "Representation of EHR data for predictive modeling: a comparison between UMLS and other terminologies." Journal of the American Medical Informatics Association 27, no. 10 (2020): 1593–99. http://dx.doi.org/10.1093/jamia/ocaa180.
Full textAbstract:
Abstract Objective Predictive disease modeling using electronic health record data is a growing field. Although clinical data in their raw form can be used directly for predictive modeling, it is a common practice to map data to standard terminologies to facilitate data aggregation and reuse. There is, however, a lack of systematic investigation of how different representations could affect the performance of predictive models, especially in the context of machine learning and deep learning. Materials and Methods We projected the input diagnoses data in the Cerner HealthFacts database to Unified Medical Language System (UMLS) and 5 other terminologies, including CCS, CCSR, ICD-9, ICD-10, and PheWAS, and evaluated the prediction performances of these terminologies on 2 different tasks: the risk prediction of heart failure in diabetes patients and the risk prediction of pancreatic cancer. Two popular models were evaluated: logistic regression and a recurrent neural network. Results For logistic regression, using UMLS delivered the optimal area under the receiver operating characteristics (AUROC) results in both dengue hemorrhagic fever (81.15%) and pancreatic cancer (80.53%) tasks. For recurrent neural network, UMLS worked best for pancreatic cancer prediction (AUROC 82.24%), second only (AUROC 85.55%) to PheWAS (AUROC 85.87%) for dengue hemorrhagic fever prediction. Discussion/Conclusion In our experiments, terminologies with larger vocabularies and finer-grained representations were associated with better prediction performances. In particular, UMLS is consistently 1 of the best-performing ones. We believe that our work may help to inform better designs of predictive models, although further investigation is warranted.
47
Hu, Qiong, Miao Cai, Nasrin Mohabbati-Kalejahi, et al. "A Review of Data Analytic Applications in Road Traffic Safety. Part 2: Prescriptive Modeling." Sensors 20, no. 4 (2020): 1096. http://dx.doi.org/10.3390/s20041096.
Full textAbstract:
In the first part of the review, we observed that there exists a significant gap between the predictive and prescriptive models pertaining to crash risk prediction and minimization, respectively. In this part, we review and categorize the optimization/ prescriptive analytic models that focus on minimizing crash risk. Although the majority of works in this segment of the literature are related to the hazardous materials (hazmat) trucking problems, we show that (with some exceptions) many can also be utilized in non-hazmat scenarios. In an effort to highlight the effect of crash risk prediction model on the accumulated risk obtained from the prescriptive model, we present a simulated example where we utilize four risk indicators (obtained from logistic regression, Poisson regression, XGBoost, and neural network) in the k-shortest path algorithm. From our example, we demonstrate two major designed takeaways: (a) the shortest path may not always result in the lowest crash risk, and (b) a similarity in overall predictive performance may not always translate to similar outcomes from the prescriptive models. Based on the review and example, we highlight several avenues for future research.
48
Zhang, Xuhui, Wenyu Yang, Wenjuan Yang, Benxin Huang, Zeyao Wang, and Sihao Tian. "Occupational Risk Prediction for Miners Based on Stacking Health Data Fusion." Applied Sciences 15, no. 6 (2025): 3129. https://doi.org/10.3390/app15063129.
Full textAbstract:
Occupational health risk prediction of miners is a core issue to ensure the safety of high-risk operations. Current risk assessment methodologies face critical limitations, as conventional unimodal prediction systems frequently demonstrate limited efficacy in capturing the multifactorial nature of occupational health deterioration. This study presents a novel stacked ensemble architecture employing dual-phase algorithmic optimization to address these muti-parametric interactions. The proposed framework implements a hierarchical modeling paradigm: (1) a primary predictive layer employing heterogeneous base learners (Random Forest and Logistic Regression classifiers) to establish foundational decision boundaries, and (2) a meta-modeling stratum utilizing regularized logistic regression with hyperparameter optimization via grid search-assisted k-fold cross-validation. Empirical validation through comparative analysis reveals the enhanced ensemble achieves a mean accuracy of 90%. Receiver operating characteristic analysis confirms superior discriminative capacity (AUC = 0.89), surpassing conventional ensemble methods by 23.3 percentile points. The model’s capacity to quantify nonlinear exposure–response relationships while maintaining computational tractability suggests significant utility in occupational health surveillance systems. These findings substantiate that the proposed dual-layer optimization framework substantially advances predictive capabilities in occupational health epidemiology, particularly in addressing the complex synergies between environmental hazards and physiological responses in confined industrial environments.
49
Lozhkina, N. G., Yu E. Voskoboynikov, V. N. Kopylov, O. M. Parkhomenko, and M. I. Voevoda. "Two approaches to modeling the risk of progressive atherosclerosis." Siberian Journal of Clinical and Experimental Medicine 38, no. 2 (2023): 89–97. http://dx.doi.org/10.29001/2073-8552-2023-38-2-89-97.
Full textAbstract:
Progressive or accelerated atherosclerosis is accompanied by unfavorable clinical outcomes. Studying and understanding this process and creating a personalized method for assessing the risk and prognosis of this disease are necessary to optimize approaches to treatment and prevention.Aim: To compare two approaches to the creation of prognostic risk model of progressive atherosclerosis: non-linear regression model of logistic type and free cross-platform visual programming system Orange method.Material and Methods. The retrospective cohort study included 202 patients with confirmed coronary heart disease: 147 men and 55 women. The mean age of the patients was 53.3 ± 7.16 years. Group 1 included patients with myocardial infarction or unstable stenocardia, emergency arterial stenting, stroke, peripheral arterial thrombosis, critical ischemia and lower extremity amputation within 2 years before inclusion in the study. Patients in the comparison group did not have these events. Predictive models of the influence of different studied parameters on the probability of rapid progression of atherosclerosis were built using factor and correlation analysis and free cross-platform Orange visual programming system.Results. The authors’ suggested approaches to the evaluation of the risk of progressive atherosclerosis have a good prognostic accuracy (sensitivity 94.1, specificity 97.0 and accuracy 95.5 coefficients, respectively) for the regression model and 0,950 (95,0%) for the machine learning model. However, the construction of the regression model is a more complex procedure compared to the second approach, where the choice of informative indicators for the prediction model is made by Orange. Nevertheless, the above two approaches can successfully complement each other, allowing to build more accurate predictive risk models.Conclusion. The proposed authors’ approaches to assessing the risk of progressive atherosclerosis have a good prognostic accuracy.
50
Huang, Shu, Motomori O. Lewis, Yuhua Bao, et al. "Predictive Modeling for Suicide-Related Outcomes and Risk Factors among Patients with Pain Conditions: A Systematic Review." Journal of Clinical Medicine 11, no. 16 (2022): 4813. http://dx.doi.org/10.3390/jcm11164813.
Full textAbstract:
Suicide is a leading cause of death in the US. Patients with pain conditions have higher suicidal risks. In a systematic review searching observational studies from multiple sources (e.g., MEDLINE) from 1 January 2000–12 September 2020, we evaluated existing suicide prediction models’ (SPMs) performance and identified risk factors and their derived data sources among patients with pain conditions. The suicide-related outcomes included suicidal ideation, suicide attempts, suicide deaths, and suicide behaviors. Among the 87 studies included (with 8 SPM studies), 107 suicide risk factors (grouped into 27 categories) were identified. The most frequently occurring risk factor category was depression and their severity (33%). Approximately 20% of the risk factor categories would require identification from data sources beyond structured data (e.g., clinical notes). For 8 SPM studies (only 2 performing validation), the reported prediction metrics/performance varied: C-statistics (n = 3 studies) ranged 0.67–0.84, overall accuracy(n = 5): 0.78–0.96, sensitivity(n = 2): 0.65–0.91, and positive predictive values(n = 3): 0.01–0.43. Using the modified Quality in Prognosis Studies tool to assess the risk of biases, four SPM studies had moderate-to-high risk of biases. This systematic review identified a comprehensive list of risk factors that may improve predicting suicidal risks for patients with pain conditions. Future studies need to examine reasons for performance variations and SPM’s clinical utility.