Bias Correction of Wind Speed Forecasts Using an Explainable Machine Learning Method

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Understanding the Performance of Machine Learning Models to Predict Credit Default: A Novel Approach for Supervisory Evaluation

To enhance the performance of machine learning (ML) models for the post-embolization recanalization of cerebral aneurysms, we evaluated the impact of hemodynamic feature derivation and selection method on six ML algorithms. We utilized computational fluid dynamics (CFD) to simulate hemodynamics in 66 cerebral aneurysms from 65 patients, including 57 stable and nine recanalized aneurysms. We derived a total of 107 features for each aneurysm, encompassing four clinical features, 12 morphological features, and 91 hemodynamic features. To investigate the influence of feature derivation and selection methods on the ML models, we employed two derivation methods, simplified and fully derived, in combination with four selection methods: all features, statistically significant analysis, stepwise multivariate logistic regression analysis (stepwise-LR), and recursive feature elimination (RFE). Model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and precision-recall curve (AUPRC) on both the training and testing datasets. The AUROC values on the testing dataset exhibited a wide-ranging spectrum, spanning from 0.373 to 0.863. Fully derived features and the RFE selection method demonstrated superior performance in intra-model comparisons. The multi-layer perceptron (MLP) model, trained with RFE-selected fully derived features, achieved the best performance on the testing dataset, with an AUROC value of 0.863 (95% CI: 0.684- 1.000). Our study demonstrated the importance of feature derivation and selection in determining the performance of ML models. This enabled the development of accurate decision-making models without the need to invade the patient.

Machine Learning (ML) models have been extensively applied in various fields to enhance prediction. For instance, in cybersecurity, they examine large amounts of data, establish trends in the data, and draw insights from previous events, to enhance detection and respond to cyber threats. Random Forest, Logistic Regression, K-Nearest Neighbor and LSTM are some of the popular ML models vastly used for anomaly detection. The accuracy of these models is therefore the cornerstone of the organization’s information systems security since wrong predictions result to false positives and negatives which significantly reduce employees’ output and may result into workers’ frustrations when interacting with the information systems. Among the many factors that affect ML model performance, data pre-processing has been underscored. Using the various publicly available datasets, this paper examines the impact of data preprocessing techniques on selected ML model architectures’ performance. Training time, Accuracy, Precision, Recall and F1 scores are used for evaluating the ML models’ performance.

MP07-06 EVALUATING THE EFFICACY OF ARTIFICIAL INTELLIGENCE IN PREDICTING OUTCOMES FOR PEDIATRIC HYDRONEPHROSIS: A SYSTEMATIC REVIEW

Optimizing asphalt mix design through predicting effective asphalt content and absorbed asphalt content using machine learning

Background Peripheral Arterial Disease(PAD) is a prevalent cardiovascular condition affecting millions worldwide, and the advent of machine learning(ML) techniques offers promising opportunities to enhance risk prediction and personalise patient management in this complex disease. This systematic review and meta-analysis aimed to evaluate the performance of ML models in predicting adverse outcomes in PAD patients compared to traditional statistical approaches. Methods A comprehensive search of major databases(MEDLINE,EMBASE,CINAHL,Cochrane CENTRAL) was conducted for studies published between 2000 and 2024. Two reviewers independently screened studies, extracted data, and assessed risk of bias using the PROBAST tool. The quality of included studies was also assessed using criteria outlined by Qiao et al. A modified Hierarchical Summary Receiver Operating Characteristic(HSROC) analysis was performed to compare the predictive performance of various ML models and traditional regression methods. Results Thirteen studies met the inclusion criteria. Gradient boosted models demonstrated the highest predictive performance with a diagnostic odds ratio(DOR) of 36.593(95% CI:24.44-54.79), sensitivity of 0.853, and specificity of 0.863. The best performing ML models for outcomes within 2 years, showed a DOR of 34.169(95% CI:22.840-51.117). Traditional regression models consistently underperformed compared to ML approaches, with the lowest DOR of 3.326(95% CI:1.814-6.097). The quality assessment revealed a mix of methodological rigor, with 54% of studies rated as low risk of bias and 46% as unclear. Conclusion Advanced ML techniques demonstrate superior predictive power for adverse outcomes in PAD patients compared to traditional regression methods.

The development of machine learning (ML) approaches in materials science offers the opportunity to exploit existing engineering and developmental alloy datasets, such as Oak Ridge National Laboratory (ORNL)’s consistently measured creep-rupture dataset for alumina-forming austenitic (AFA) alloys, to accelerate their further development. As a first step toward achieving ML insights for improved alloy design, the potential sources of uncertainty and their impacts on ML output are examined. It is observed that the selection of algorithms and features as well as data sampling significantly affects the performance of ML models, either positively or negatively. The performance of various ML models in predicting the creep properties of AFA alloys is compared, with further evaluation by assessment of a small set of new developmental AFA alloys that were not part of the training dataset. The present study demonstrates that uncertainty quantification (UQ) is essential in materials science for evaluating the performance of ML algorithms with specifically selected feature sets and obtaining a comprehensive understanding of their limitations and the resultant capability of effective prediction in complex materials systems.

Machine Learning Models in the Prediction of One-Year Mortality in Patients With Advanced Hepatocellular Cancer on Immunotherapy

Introduction Ensuring equitable performance of sleep-related machine learning (ML) models is vital for public health and health equity. This research sought to determine the impact of sociodemographic and health disparities factors on the performance and characteristics of ML models designed to predict OSA treatment initiation. Methods Our data source was the All-Payer Claims Database (APCD) for the Wisconsin Health Information Organization (WHIO). Inclusion criteria included continuous insurance coverage for >12 months prior and >30 months after OSA diagnosis (defined by OCD code G47.33), and having undergone OSA diagnostic testing (defined by CPT codes). OSA treatment was defined based on durable medical equipment charges for PAP machines and supplies. Sociodemographic variables were extracted from APCD and included race, gender, age, and area socioeconomic deprivation (Area Deprivation Index; ADI). The ADI is a validated marker of health risk based on 17 health disparities factors ranking relative disadvantage across communities. Random Forest ML models were trained to predict OSA treatment initiation using sociodemographic variables and a medication history including 39,712 unique medications codified across 94 medication categories. Results Of N=6,026,463 subjects in the ACPD, n=154,821 underwent OSA diagnostic testing, and n=43,601 were diagnosed with OSA. 10-Fold Cross-Validation training-testing was applied to estimate sensitivity-specificity of ML models for predicting treatment initiation. Receiver operating characteristic curve area-under-the-curve (ROC-AUC) analyses were used to compare relative differences in predictive power of each variable. In ROC-AUC analysis of individual variables, the power for predicting OSA treatment were observed in relative rank order by age (0.568), race (0.547), ADI national-level (0.545), ADI state-level (0.544), gender (0.524), and medication history (0.516). In ROC-AUC analysis of combination variables, the highest ML model performance was observed in the combination of only three-variables (age-gender-race, 0.600), while the combination of all-variables showed an ROC-AUC value of (0.594), and the resulting performance difference was not statistically significant based on comparison of the ROC-AUC measures. Conclusion Demographic and health disparity factors may play an important role in future development of predictive AI/ML models. Population sleep health data represents an important resource to identify and bridge care gaps, reduce sleep health disparities, and achieve health equity. Support (if any)

Background: Coronary Artery Disease (CAD) is one of the biggest causes of mortality worldwide. Risk stratification for early detection is essential for the primary prevention of CAD. QRISK3 is known to overestimate future CAD risk in some populations, resulting in unnecessary preventive treatment and reduced cost-effectiveness and safety. Combining machine learning model with the metaheuristic optimisation approach using the PSO algorithm may outperform QRISK3 in predicting CAD. It improves performance by selecting the best-performing subset of features related to clinical outcomes. Research Question: Does the performance of Machine Learning Models Combined with PSO Algorithm for Feature Selection as a Metaheuristic Optimisation Approach in Predicting Coronary Arterial Disease using the UK Biobank dataset outperform the QRISK3 calculator? Aims: This study is to assess the accuracy of QRISK3 in predicting CAD using the UK Biobank dataset. It aims to evaluate the efficacy of machine learning models on the identical dataset for predicting CAD. The work utilises the PSO algorithm for feature selection to identify the optimal subset of features from the UK Biobank dataset. Methods: This study utilises data from the UK Biobank. The dataset consists of 348,015 participants aged 24-84 with no prior diagnosis of CAD. The performance of both QRISK3 and machine learning models was evaluated separately using ROC analysis. Several machine learning models were employed: Logistic Regression, Decision Tree, Random Forest, Naïve Bayes, and Gradient Boosting. The dataset was split into training and test sets with a ratio of 4:1 for the machine learning models. Each model has been developed by adding a PSO algorithm to enhance the model's classification accuracy. Results: Out of the total 348,015 participants, 23,136 individuals (6.64%) were diagnosed with CAD within 10 years following their first visit, while 324,879 individuals (93.4%) did not develop CAD. The AUC value of the QRISK3 prediction is 0.6113, while the combined machine learning models using the PSO algorithm using the gradient boosting model achieve an AUC of 0.7258, showing better performance. Conclusions: This study shows hybrid machine learning models optimised with the PSO algorithm can better predict CAD than QRISK3. These ML models can effectively identify high-risk CAD patients, allowing for more personalised preventative strategies and supporting policymakers in implementing lifestyle change recommendations.

Transfer learning enables prediction of steel corrosion in concrete under natural environments

Integrating machine learning (ML) models into healthcare systems is a rapidly evolving field with the potential to revolutionize care delivery. This study aimed to classify fertility rates and identify significant predictors using ML models among reproductive women in Ethiopia. This study utilized eight ML models in 5864 reproductive-age women using Ethiopian Demographic Health Survey (EDHS), 2019 data. Phyton programming language was used to develop these models. Predictors of fertility rate were determined using the feature important techniques. The performance of models was evaluated using accuracy, area under the curve (AUC), precision, recall, F1-score, specificity, and sensitivity. The mean age of participants was 32.7 (± 5.6) years. The random forest classifier (accuracy = 0.901 and AUC = 0.961) followed by a one-dimensional convolutional neural network (accuracy = 0.899 and AUC = 0.958), logistic regression (accuracy = 0.874 and AUC = 0.937), and gradient boost classifier (accuracy = 0.851 and AUC 0.927) were the top performing ML models. Family size, age, occupation, and education with an average importance score of 0.198, 0.151, 0.118, and 0.081, respectively were the top significant predictors of the fertility rate. The best ML models to classify and predict fertility rates were random forest, one-dimensional convolutional neural network, logistic regression, and gradient boost classifier. The findings on important factors of fertility rate can inform targeted public health, programs that address disparities related to family size, occupation, education, and other socioeconomic factors.

In recent years, infections and damage caused by malware have increased at exponential rates. At the same time, machine learning (ML) techniques have shown tremendous promise in many domains, often out performing human efforts by learning from large amounts of data. Results in the open literature suggest that ML is able to provide similar results for malware detection, achieving greater than 99% classification accuracy [49]. However, the same detection rates when applied in deployed settings have not been achieved. Malware is distinct from many other domains in which ML has shown success in that (1) it purposefully tries to hide, leading to noisy labels and (2) often its behavior is similar to benign software only differing in intent, among other complicating factors. This report details the reasons for the difficultly of detecting novel malware by ML methods and offers solutions to improve the detection of novel malware. We propose to detect malware by detecting behaviors commonly exhibited by malware such as DLL injection, and process hollowing. This is based on the assumption that there is a set of behaviors that are common to most malware samples and detecting them will generalize to novel malware. Additionally, detected behaviors point analysts toward appropriate handling and mitigation strategies, which is not the case with a binary benign/malicious classification. A behavior labeling method was developed and was used to label an existing malware dataset. Results show that detecting malicious behaviors is much more difficult than simply classifying malware and goodware?achieving 80% accuracy compared to reported 99% accuracy from classifying malware and goodware. This drop is due to several reasons which are detailed in the report. We also propose to evaluate the performance of detecting novel malware by holding out a malware family for testing and training on the other families. Traditional ML evaluation will shuffle the data and then split the data into training and testing. Our method addresses the use-case when novel malware families are encountered and they require more than just a malicious or benign designation. Our results suggest that this type of evaluation is much more difficult than traditional methods and provides more realistic results, albeit, significantly worse. For our behavior detection, accuracy decreases from 80% to 68% across all behaviors when holding out a malware family from training. We show that the degradation in performance is because each malware family has distinct characteristics resulting in high extrapolations by an ML model. Here, an ML model should return an "I do not know" response and request further analysis from an analyst. We run a number of experiments that compare novel malware families to the training data using different feature representations including a genomics-inspired distance measure and features extracted by deep learning. Generally, held-out families are significantly different from the training data, resulting in unpredictable results. This has been observed generally in the ML community [22, 9]. We empirically demonstrate this in the domain of malware detection. In an attempt to improve the detection of malware behaviors, we examine the impact that additional synthetic data has on the performance of an ML model in detecting behaviors in novel malware families. We find that while synthetic data does improve the performance of ML models, often simpler methods perform better than more complicated ones. Two generative modeling techniques were examined to produce synthetic malware samples such that the behaviors present are able to be specified externally. The difficulty is due to finer grained analysis of the executable and modifying the problem from a binary classification problem to a multi-label problem. The addition of synthetic data increases the overall accuracy from 68% to 70%. While far less accurate than measures presented in academic analyses, we believe that this is more representative of real-world performance and allows models to be properly placed within a malware detection system. We suggest that in highly dynamic environments ML pipelines should determine whether an ML model is competent in the area of new data and should involve mechanisms to improve over time with a human in the loop.

The computed tomography-severity score (CT-SS) quantifies the severity of pulmonary involvement and is significantly associated with disease severity, intensive care unit (ICU) admissions, and mortality in coronavirus disease-2019 (COVID-19) patients. There is very limited information on the prognostic value of CT-SS when used in machine learning (ML) models to predict ICU admission in COVID-19 patients. In this study, the prognostic significance of CT-SS in ML model-based prediction of ICU admission among COVID-19 patients was evaluated. In this retrospective study, a hospital-based database from 6,854 COVID-19 patients was reviewed. To evaluate the prognostic significance of CT-SS in predicting ICU admission in patients, seven ML methods were trained separately using the most important features, with and without CT-SS data, and their performances were compared. After applying exclusion criteria, 815 COVID-19 patients remained. Just over half of the patients (54.85%) were male, and the mean age was 57.22±16.76 years. The CT-SS index was the strongest predictor among the parameters examined, and integrating this index into the training dataset enhanced ML model performance. The k-nearest neighbors model with 93.3% accuracy, 97.3% sensitivity, 89.4% specificity, and an area under the curve of approximately 98.8% showed the best performance for predicting ICU admission in COVID-19 patients. The results showed that CT-SS is a key predictor for ML models of ICU admission in COVID-19 patients. The ML models developed using a dataset including CT-SS are efficient risk stratification tools for identifying critical COVID-19 patients, thereby facilitating optimal allocation of limited hospital resources.