Academic literature on the topic 'Modelli diagnostici ML'

The overlapping imaging characteristics of COVID-19 viral pneumonia and non-COVID-19 viral pneumonia chest X-rays (CXRs) make differentiation difficult for radiologists. Machine learning (ML) has demonstrated promising outcomes in a range of medical sectors, enhancing diagnostic accuracy through its interaction with radiological tests. The potential contribution of ML models in assisting radiologists in discriminating COVID-19 from non-COVID-19 viral pneumonia from CXRs, on the other hand, deserves further examination and exploration. The goal of this study is to empirically assess ML models' capacity to classify X-ray images into COVID-19, pneumonia, and normal cases. The study evaluates the efficacy of K-nearest Neighbor (KNN), random forest (RF), AdaBoost (AB), and neural networks (NN) with various hidden neuron configurations using a wide range of performance measures. These metrics evaluate the area under the curve (AUC), classification accuracy (CA), F1 score (F1), precision, and recall, resulting in a comprehensive evaluation technique. ROC analysis is used to gain a thorough knowledge of the models' discriminating skills. The results show that NN models, particularly those with 100 and 150 hidden neurons, outperform in all criteria, proving their ability to reliably categorize medical disorders. Notably, the study emphasizes the difficulties in separating COVID-19 from pneumonia, emphasizing the importance of strong classification methods. While the study provides useful insights, its drawbacks include the use of a single dataset, the absence of more sophisticated deep learning architectures, and a lack of interpretability analyses. Nonetheless, the study adds to the developing area of medical picture categorization, directing future attempts to improve diagnosis accuracy and widen the use of machine learning in healthcare. The findings highlight the utility of NN models in medical diagnostics and pave the way for future study in this vital area of technology and healthcare.

Glaucoma is a primary cause of permanent blindness, and early and precise detection is essential to prevent significant visual loss. In the context of diagnosing glaucoma, this abstract focuses on three machine learning techniques: decision trees, linear regression, and support vector machines (SVM). Despite being primarily utilised for predictive modelling, linear regression has been modified to diagnose glaucoma by examining the correlation between continuous risk factors and diagnostic results, which helps identify high-risk patients early on. Because SVMs are good at handling high-dimensional data, they can be used to identify healthy versus glaucomatous eyes by maximising the margin between the two classes in the feature space by identifying the ideal hyperplane. Compared to conventional methods, these ML techniques greatly improve diagnostic accuracy, consistency, and speed; nonetheless, issues like the requirement for big, diverse datasets and guaranteeing with great results.

The incorporation of machine learning (ML) in aircraft engineering has transformed the design, analysis, and operation of intricate aerospace systems. This study examines the present and developing applications of machine learning techniques in critical domains like aircraft design optimisation, defect detection and diagnostics, flight control systems, and predictive maintenance. Utilising extensive information from simulations, sensors, and real-time operations, machine learning models facilitate more efficient decision-making, improved system reliability, and decreased operational costs. Moreover, progress in deep learning, reinforcement learning, and neural networks is being progressively utilised for applications spanning aerodynamic modelling to autonomous flight control. This study emphasises the difficulties related to data quality, interpretability, and model validation in safety-critical aircraft contexts.

Abstract This study investigates the application of machine learning (ML) techniques for virtual flow metering (VFM) in oil wells. To develop a robust and accurate VFM model, Two Different Fields were tested for the new technique, one field offshore Egypt & the other field is onshore Iraq; This comprehensive dataset included detailed production data, well parameters, and operational information. Various ML algorithms, including Random Forest, Support Vector Regression, and Artificial Neural Networks, were rigorously tested and compared to identify the optimal model for VFM. The selected model was then calibrated against production test data to ensure accurate and reliable predictions. The calibrated ML model enables the daily verification of production allocation, providing real-time insights into the performance of individual wells. By continuously monitoring production rates, anomalies such as production declines, unexpected shutdowns, or changes in reservoir behavior can be promptly detected. These timely insights facilitate efficient decision-making, allowing for timely interventions and optimization of production strategies. Additionally, the ML-based VFM model supports accurate reservoir allocation by providing reliable estimates of individual well contributions, enabling informed decisions on production allocation and field development planning. After rigorous calibration, the model's performance was further validated through a blind test, where it was applied to a new set of wells without prior training. The results of the blind test confirmed the model's usability and its ability to provide accurate predictions. Moreover, the daily application of the model has demonstrated reasonable agreement with well test data, further solidifying its reliability and practical value. The findings of this study demonstrate the significant potential of ML-based VFM to enhance the efficiency and effectiveness of oil production operations in Egypt & Iraq Assets. By leveraging advanced ML techniques and a comprehensive dataset, this approach offers a reliable and cost-effective solution for improving production performance diagnostics, optimizing reservoir management, and ultimately maximizing oil recovery

Abstract The petroleum industry is reliant on precise and efficient back allocation, a process that calculates individual well production rates from shared facilities or multi-well platforms. Especially in matured facilities and legacy assets, traditional measurement techniques often fail to provide the necessary accuracy due to a lack of pre-installed flow meters and individual measurement mechanisms. Furthermore, these methods frequently require additional interventions, a factor that could potentially defer production, incur significant costs, and require extensive supply chain management. Despite these challenges, back allocation remains an essential process for effective reservoir, well, and field production performance management, as well as for ensuring accurate revenue allocation throughout a field's economic life cycle. This study explores the application of machine learning (ML) as an advanced, data-driven approach to overcome the complexities of back allocation and streamline the process with increased accuracy and reduced interventions. Three ML models were implemented for this purpose, namely XGBoost, Random Forest, and LightGBM. These models were designed to predict individual well oil rates based on various parameters easily obtainable from wellhead locations, including wellhead pressure, temperature, and choke size. A meticulous preprocessing stage was performed to make sure the data was ideally suited for the ML models. Further, hyperparameter tuning was applied to enhance model accuracy and performance. Of the three models, XGBoost showed remarkable performance, producing high R2 scores of 0.97, 0.98, 0.96, and 0.96 for each well. These scores underscore the model's strong capability to predict individual well oil rates with high precision, highlighting the potential of ML in addressing complex problems in the oil and gas sector. The study's findings present a promising advancement in the application of ML, particularly XGBoost, for accurate back allocation in combined production systems. The model's superior performance and prediction accuracy pave the way for improved decision-making related to reservoir management, well diagnostics, and cost optimization. The utilization of ML for back allocation holds considerable promise for boosting operational efficiency and profitability in oil and gas production systems. Looking ahead, further research will seek to apply the model on a larger scale and test its efficiency across varied field conditions and scenarios. This investigation will help to further validate the substantial advantages of employing ML methodologies in the petroleum industry.

Abstract Numerical simulation results are the basis of numerous oil and gas field developments. We based the numerical simulation models (or dynamic models) on 3D geological models. We constructed a geological model using core and log data obtained from wells as inputs to create a reservoir prototype. This paper describes the applications of artificial intelligence (AI) algorithms for parameterization of static and dynamic modeling processes. Accordingly, a hypothetical 3D geological model was created, and porosity and permeability were distributed using sequential Gaussian simulation. Then, Petro-physical rock types (PRT) were defined in the 3D space as a function of porosity and permeability using a hypothetical Winland's R35 equation. Finally, hypothetical saturation-height functions (SHFs) were defined for different PRTs to populate water saturation in the 3D geological model. Subsequently, some wells were randomly defined in the 3D model to obtain the logs of porosity, permeability, SHF, PRT, repeat formation tester pressure (RFT), and datum pressures that are used in this study. A multivariate Gaussian regression was applied for anomaly detection, while core porosity and permeability were filtered. Subsequently, a fixed window average was used to detect the boundaries of core data stationarity and propose the optimum reservoir zone required to describe the internal heterogeneities of the reservoir. Then, we deployed the k-means clustering algorithm to determine the PRT and saturation height function (SHF) based on the core and log data derived from the hypothetical geological model. Finally, we used the clustering-based pattern recognition to cluster well datum pressures into homogeneous groups and create a connected reservoir region CRR map to be used as an input in the 3D permeability distribution. Our results demonstrate the value of additional diagnostics that can be used in conjunction with the traditional semi-log plot of porosity and permeability. This additional diagnostic approach is a semi-log plot of permeability versus depth, which can help check whether intra-reservoir heterogeneities observable in core data have been preserved in the 3D model. In our case, a 3D model created using the core and log data from the hypothetical model and honoring the internal reservoir architecture resulted in a better history match regarding the hypothetical geo-model's RFT pressure signature. Our results further demonstrate that PRT and SHF derived from k-means clustering are sufficiently similar to those of the hypothetical model. Time series anomaly filtering of pressures helped detect incorrect well data that may otherwise have gone unnoticed. Using the nearest-neighbor property distribution resulted in a geological model whose diagnostic plots indicated an excellent match with core data and allowed a better assessment of modeling uncertainties. The ML approaches presented in this study could help obtain data-derived PRT and SHF to complement Winland's interpretation when Mercury Injection Capillary Pressure (MICP) experiments are limited or unavailable, saving both time and cost. Using the fixed window averaging helps optimize the geological model zone assessment, resulting in a better intra-reservoir architecture. Finally, we derive insights into a more efficient core acquisition plan.

Objectives 1. Establish diagnostic procedures to identify tolerant carrier birds based on a) Isolation of ALV-J from blood, b) Detection of group-specific antigen in cloacal swabs and egg albumen. Application of these procedures to broiler breeder flocks with the purpose of removing virus positive birds from the breeding program. 2. Survey the AL V-J infection status of foundation lines to estimate the feasibility of the eradication program 3. Investigate virus transmission through the embryonated egg (vertical) and between chicks in the early post-hatch period (horizontal). Establish a model for limiting horizontal spread by analyzing parameters operative in the hatchery and brooder house. 4. Compare the pathogenicity of AL V-J isolates for broiler chickens. 5. Determine whether AL V-J poses a human health hazard by examining its replication in mammalian and human cells. Revisions. The: eradication objective had to be terminated in the second year following the closing down of the Poultry Breeders Union (PBU) in Israel. This meant that their foundation flocks ceased to be available for selection. Instead, the following topics were investigated: a) Comparison of commercial breeding flocks with and without myeloid leukosis (matched controls) for viremia and serum antibody levels. b) Pathogenicity of Israeli isolates for turkey poults. c) Improvement of a diagnostic ELISA kit for measuring ALV-J antibodies Background. ALV-J, a novel subgroup of the avian leukosis virus family, was first isolated in 1988 from broiler breeders presenting myeloid leukosis (ML). The extent of its spread among commercial breeding flocks was not appreciated until the disease appeared in the USA in 1994 when it affected several major breeding companies almost simultaneously. In Israel, ML was diagnosed in 1996 and was traced to grandparent flocks imported in 1994-5, and by 1997-8, ML was present in one third of the commercial breeding flocks It was then realized that ALV-J transmission was following a similar pattern to that of other exogenous ALVs but because of its unusual genetic composition, the virus was able to establish an extended tolerant state in infected birds. Although losses from ML in affected flocks were somewhat higher than normal, both immunosuppression and depressed growth rates were encountered in affected broiler flocks and affected their profitability. Conclusions. As a result of the contraction in the number of international primary broiler breeders and exchange of male and female lines among them, ALV-J contamination of broiler breeder flocks affected the broiler industry worldwide within a short time span. The Israeli national breeding company (PBU) played out this scenario and presented us with an opportunity to apply existing information to contain the virus. This BARD project, based on the Israeli experience and with the aid of the ADOL collaborative effort, has managed to offer solutions for identifying and eliminating infected birds based on exhaustive virological and serological tests. The analysis of factors that determine the efficiency of horizontal transmission of virus in the hatchery resulted in the workable solution of raising young chicks in small groups through the brooder period. These results were made available to primary breeders as a strategy for reducing viral transmission. Based on phylogenetic analysis of selected Israeli ALV-J isolates, these could be divided into two groups that reflected the countries of origin of the grandparent stock. Implications. The availability of a simple and reliable means of screening day old chicks for vertical transmission is highly desirable in countries that rely on imported breeding stock for their broiler industry. The possibility that AL V-J may be transmitted to human consumers of broiler meat was discounted experimentally.

The quantification of 99mTc labeled biomarkers can add unique value in many different settings, ranging from clinical trials of investigation new drugs to the treatment of individual patients with marketed therapeutics. For example, goals of precision medicine include using companion radiopharmaceutical diagnostics as just-in-time, predictive biomarkers for selecting patients to receive targeted treatments, customizing doses of internally administered radiotherapeutics, and assessing responses to treatment. This Profile describes quantitative outcome measures that represent proxies of target concentration or target mass in topographically specific volumes of interest (VOIs). These outcome measures are usually expressed as the percent injected dose (i.e., radioactivity) per mL of tissue (%ID/mL), a standard uptake value ratio (SUVr), or a target-to-background ratio (TBR). In this profile, targeting is not limited to any single mechanism of action. Targeting can be based on interaction with a cell surface protein, an intracellular complex after diffusion, protein-mediated transport, endocytosis, or mechanical trapping in a capillary bed, as in the case of transarterial administration of embolic microspheres. Regardless, the profile focuses on quantification in well-defined volumes of interest. Technetium-99m based dopamine transporter imaging agents, such as TRODAT, are nearly direct links with some aspects of the predecessor profile on 123I-ioflupane for neurodegenerative disorders. (See www.qibawiki.rsna.org ) Cancer is often a base case of convenience for new material in this profile, but the intent is to create methods that can be useful in other therapeutic areas where the diseases are characterized by spatially-limited anatomical volumes, such as lung segments, or multifocal aggregations of targets, such as white blood cell surface receptors on pulmonary nodules in patients with sarcoidosis. Neoplastic masses that can be measured with x-ray computed tomography (CT) or magnetic resonance imaging (MRI) are the starting point. However, the intent is to create a profile that can be extrapolated to diseases in other therapeutic areas that are also associated with focal, or multi-focal pathology, such as pulmonary granulomatous diseases of autoimmune or infectious etiology, non-oncological diseases of organs such as polycystic kidney disease, and the like. The criteria for measurability are based on the current resolution of most SPECT-CT systems in clinical practice, and are independent of criteria for measurability in other contexts. For this SPECT profile, conformance requires that a “small” VOI must be greater than 30 mL to be measurable. It is understood that much smaller VOIs can sometimes exhibit high conspicuity on SPECT, but these use cases are beyond the scope of this profile and will not be tested for conformance in this version. It is left to individual stakeholders to show the extent to which they can achieve conformance when measuring VOIs less than 30 mL. The detection of smaller changes during clinical trials of large groups can be achieved by referring to the QIBA companion guidance on powering trials. The Claims (Section 2) asserts that compliance with the specifications described in this Profile will produce cross sectional estimates of the concentration of radioactivity [kBq/mL] in a volume of interest (VOI) or a target-to-background ratio (TBR) within a defined confidence interval (CI), and distinguish true biological change from system variance (i.e., measurement error) in individual patients or clinical trials of many patients who will be studied longitudinally with 99mTc SPECT agents. Both claims are founded on observations that target density varies between patients with the same disease as well as within patients with multi-focal disease. The Activities (Section 3) describes the requirements that are placed on the Actors who need to achieve the Claim. Section 3 specifies what the actors must do in order to estimate the amount of radioactivity in a volume of interest, expressed in kBq/mL (ideal) or as a TBR (acceptable) within a 95% CI surrounding the true value. Measurands such as %ID/mL are targets for nonclinical studies in animal models that use terminal sacrifice to establish ground truth for imaging studies. TBRs can be precarious, as the assumptions that depend on the physiology of the background regions matching the volume of interest can be hard to accept sometimes. It is up to each individual stakeholder to qualify the background regions used in their own use case. This profile qualifies only a few in some very limited contexts as examples. The Assessment Procedures (Section 4) for evaluating specific requirements are defined as needed. The requirements are focused on achieving sufficient accuracy and avoiding unnecessary variability of the measurements. The clinical performance target is to achieve a 95% confidence interval for concentration in units of kBq/mL (kilobequerels per milliliter) or %ID/mL (percent injected dose per milliliter) or TBR with both a reproducibility and a repeatability of +/- 8% within a single individual under zero-biological-change conditions. This document is intended to help clinicians basing decisions on these biomarkers, imaging staffs generating measurements of these biomarkers, vendors who are developing related products, purchasers of such products, and investigators designing trials. Note that this document only states requirements to achieve the claims, not “requirements on standard of care” nor compliance with any particular protocol for treating participants in clinical trial settings. Conformance to this Profile is secondary to properly caring for patients or adhering to the requirements of a protocol. QIBA Profiles addressing other imaging biomarkers using CT, MRI, PET and Ultrasound can be found at www.qibawiki.rsna.org.