Interpretable Machine Learning Models Research Articles

Predicting the compressive strength of high-performance concrete using an interpretable machine learning model.

Reliable predictions of concrete strength can reduce construction time and labor costs, providing strong support for building construction quality inspection. To enhance the accuracy of concrete strength prediction, this paper introduces an interpretable framework for machine learning (ML) models to predict the compressive strength of high-performance concrete (HPC). By leveraging information from a concrete dataset, an additional six features were added as inputs in the training process of the random forest (RF), AdaBoost, XGBoost and LightGBM models, and the optimal hyperparameters of the models were determined using 5-fold cross-validation and random search methods. Four interpretable ML models for predicting the compressive strength of HPC, including the RF, AdaBoost, XGBoost and LightGBM models, which combine feature derivation and random search, were constructed. In addition, the SHapley Additive exPlanations (SHAP) method was applied to analyze the effects of the input features on the prediction results of the LightGBM model, which combines feature derivation and random search. The results showed that input features such as age, water/cement ratio, slag, and water were the key influences for predicting the compressive strength of HPC. Input features such as the superplastic/cement ratio, slag/cement ratio, and ash/cement ratio had nonsignificant impacts on the predicted compressive strength.

An interpretable (explainable) model based on machine learning and SHAP interpretation technique for mapping wind erosion hazard.

Soil erosion by wind poses a significant threat to various regions across the globe, such as drylands in the Middle East and Iran. Wind erosion hazard maps can assist in identifying the regions of highest wind erosion risk and are a valuable tool for the mitigation of its destructive consequences. This study aims to map wind erosion hazards by developing an interpretable (explainable) model based on machine learning (ML) and Shapley additive exPlanation (SHAP) interpretation techniques. Four ML models, namely random forest (RF), support vector machine (SVM), extreme gradient boosting (XGB), and quadratic discriminant analysis (QDA) were used. Thirteen features associated with wind erosion were mapped spatially and then subjected to a multivariate adaptive regression spline (MARS) feature selection algorithm, and then, tolerance coefficient (TC) and variance inflation factor (VIF) statistical tests were used to explore multicollinearity among the variables. MARS analysis shows that eight features consisting of elevation (or DEM), soil bulk density, precipitation, aspect, slope, soil sand content, vegetation cover (or NDVI), and lithology were the most effective for wind erosion, while no collinearity existed among these variables. The ML models were used for ranking the effective features, and the research introduces the application of an interpretable ML model for the interpretation of predictive model's output. The ranking of effective features by RF-as the most typical ML model-revealed that elevation and soil bulk density were the two most important features. According to the area under the receiver operating characteristic curve (AUROC) (with a value > 90%) and precision-recall (PR) (with a value > 90%) curves, all four ML models performed with great accuracy. According to the PR curve, the SVM model performed slightly better than others, and its results revealed that 20.9%, 23%, and 16.6% of the total area in Hormozgan Province is characterized by moderate, high, and very high hazard classes to wind erosion, respectively. SHAP revealed that soil sand content and elevation are the most important variables contributing to the predictive model output. Overall, our research is one of the pioneering applications of interpretable ML models in mapping wind erosion hazards in Southern Iran. We recommend that future research should address the aspect of interpretability in order to better understand predictive model outputs.

Predictive models for secondary epilepsy in patients with acute ischemic stroke within one year.

Post-stroke epilepsy (PSE) is a critical complication that worsens both prognosis and quality of life in patients with ischemic stroke. An interpretable machine learning model was developed to predict PSE using medical records from four hospitals in Chongqing. Medical records, imaging reports, and laboratory test results from 21,459 ischemic stroke patients were collected and analyzed. Univariable and multivariable statistical analyses identified key predictive factors. The dataset was split into a 70% training set and a 30% testing set. To address the class imbalance, the Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors was employed. Nine widely used machine learning algorithms were evaluated using relevant prediction metrics, with SHAP (SHapley Additive exPlanations) used to interpret the model and assess the contributions of different features. Regression analyses revealed that complications such as hydrocephalus, cerebral hernia, and deep vein thrombosis, as well as specific brain regions (frontal, parietal, and temporal lobes), significantly contributed to PSE. Factors such as age, gender, NIH Stroke Scale (NIHSS) scores, and laboratory results like WBC count and D-dimer levels were associated with increased PSE risk. Tree-based methods like Random Forest, XGBoost, and LightGBM showed strong predictive performance, achieving an AUC of 0.99. The model accurately predicts PSE risk, with tree-based models demonstrating superior performance. NIHSS score, WBC count, and D-dimer were identified as the most crucial predictors. The research is funded by Central University basic research young teachers and students research ability promotion sub-projec t(2023CDJYGRH-ZD06), and by Emergency Medicine Chongqing Key Laboratory Talent Innovation and development joint fund project (2024RCCX10).

Improved prognostication of overall survival after radiotherapy in lung cancer patients by an interpretable machine learning model integrating lung and tumor radiomics and clinical parameters.

Accurate prognostication of overall survival (OS) for non-small cell lung cancer (NSCLC) patients receiving definitive radiotherapy (RT) is crucial for developing personalized treatment strategies. This study aims to construct an interpretable prognostic model that combines radiomic features extracted from normal lung and from primary tumor with clinical parameters. Our model aimed to clarify the complex, nonlinear interactions between these variables and enhance prognostic accuracy. We included 661 stage III NSCLC patients from three multi-national datasets: a training set (N = 349), test-set-1 (N = 229), and test-set-2 (N = 83), all undergoing definitive RT. A total of 104 distinct radiomic features were separately extracted from the regions of interest in the lung and the tumor. We developed four predictive models using eXtreme gradient boosting and selected the top 10 features based on the Shapley additive explanations (SHAP) values. These models were the tumor radiomic model (Model-T), lung radiomic model (Model-L), a combined radiomic model (Model-LT), and an integrated model incorporating clinical parameters (Model-LTC). Model performance was evaluated through Harrell's concordance index, Kaplan-Meier survival curves, time-dependent area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Interpretability was assessed using the SHAP framework. Model-LTC exhibited superior performance, with notable predictive accuracy (C-index: training set, 0.87; test-set-2, 0.76) and time-dependent AUC above 0.75. Complex nonlinear relationships and interactions were evident among the model's variables. The integration of radiomic and clinical factors within an interpretable framework significantly improved OS prediction. The SHAP analysis provided insightful interpretability, enhancing the model's clinical applicability and potential for aiding personalized treatment decisions.

Machine Learning in Genomics: Applications in Whole Genome Sequencing, Whole Exome Sequencing, Single-Cell Genomics, and Spatial Transcriptomics

The application of machine learning (ML) to genomics has transformed the process of analyzing and interpreting large-scale, complex datasets, leading to important breakthroughs in our knowledge of biological systems. This review provides a comprehensive overview of ML applications in key genomic areas: Whole Genome Sequencing (WGS), Whole Exome Sequencing (WES), single-cell genomics, and spatial transcriptomics. In WGS and WES, ML techniques are employed for variant calling, genome-wide association studies, rare variant analysis, and the prediction of pathogenicity. In single-cell genomics, ML facilitates clustering, trajectory inference, and cell type identification, while in spatial transcriptomics, it aids in deciphering spatial patterns of gene expression and tissue heterogeneity. This review further explores the application of ML in related omics fields, including proteomics, transcriptomics, metagenomics, epigenomics, and microbiome research. These applications encompass protein structure prediction, functional annotation, microbial community profiling, and the analysis of epigenetic modifications. We address the challenges caused by high dimensionality, variability in the data, and the requirement for interpretable machine learning models when dealing with genomic data. Emerging technologies like explainable AI and federated learning are highlighted for their potential to address these challenges. Additionally, the review addresses ethical considerations, data privacy issues, and the necessity for standardized protocols in ML applications. This comprehensive examination underscores the transformative impact of ML in genomics and highlights its potential to drive future innovations in personalized medicine and biological research.

Development and external validation of an interpretable machine learning model for the prediction of intubation in the intensive care unit

Given the limited capacity to accurately determine the necessity for intubation in intensive care unit settings, this study aimed to develop and externally validate an interpretable machine learning model capable of predicting the need for intubation among ICU patients. Seven widely used machine learning (ML) algorithms were employed to construct the prediction models. Adult patients from the Medical Information Mart for Intensive Care IV database who stayed in the ICU for longer than 24 h were included in the development and internal validation. The model was subsequently externally validated using the eICU-CRD database. In addition, the SHapley Additive exPlanations method was employed to interpret the influence of individual parameters on the predictions made by the model. A total of 11,988 patients were included in the final cohort for this study. The CatBoost model demonstrated the best performance (AUC: 0.881). In the external validation set, the efficacy of our model was also confirmed (AUC: 0.750), which suggests robust generalization capabilities. The Glasgow Coma Scale (GCS), body mass index (BMI), arterial partial pressure of oxygen (PaO2), respiratory rate (RR) and length of stay (LOS) before ICU were the top 5 features of the CatBoost model with the greatest impact. We developed an externally validated CatBoost model that accurately predicts the need for intubation in ICU patients within 24 to 96 h of admission, facilitating clinical decision-making and has the potential to improve patient outcomes. The prediction model utilizes readily obtainable monitoring parameters and integrates the SHAP method to enhance interpretability, providing clinicians with clear insights into the factors influencing predictions.

Reliable Autism Spectrum Disorder Diagnosis for Pediatrics Using Machine Learning and Explainable AI

Background: As the demand for early and accurate diagnosis of autism spectrum disorder (ASD) increases, the integration of machine learning (ML) and explainable artificial intelligence (XAI) is emerging as a critical advancement that promises to revolutionize intervention strategies by improving both accuracy and transparency. Methods: This paper presents a method that combines XAI techniques with a rigorous data-preprocessing pipeline to improve the accuracy and interpretability of ML-based diagnostic tools. Our preprocessing pipeline included outlier removal, missing data handling, and selecting pertinent features based on clinical expert advice. Using R and the caret package (version 6.0.94), we developed and compared several ML algorithms, validated using 10-fold cross-validation and optimized by grid search hyperparameter tuning. XAI techniques were employed to improve model transparency, offering insights into how features contribute to predictions, thereby enhancing clinician trust. Results: Rigorous data-preprocessing improved the models’ generalizability and real-world applicability across diverse clinical datasets, ensuring a robust performance. Neural networks and extreme gradient boosting models achieved the best performance in terms of accuracy, precision, and recall. XAI techniques demonstrated that behavioral features significantly influenced model predictions, leading to greater interpretability. Conclusions: This study successfully developed highly precise and interpretable ML models for ASD diagnosis, connecting advanced ML methods with practical clinical application and supporting the adoption of AI-driven diagnostic tools by healthcare professionals. This study’s findings contribute to personalized intervention strategies and early diagnostic practices, ultimately improving outcomes and quality of life for individuals with ASD.

Predictions of the Optical Properties of Brown Carbon Aerosol by Machine Learning with Typical Chromophores.

The linkages between BrC optical properties and chemical composition remain inadequately understood, with quantified chromophores explaining less than 25% of ambient aerosol light absorption. This study characterized 38 typical chromophores in aerosols collected in Xi'an, with light absorption contributions to BrC ranging from 1.6 ± 0.3 to 5.8 ± 2.6% at 365 nm. Based on these quantified chromophores, an interpretable machine learning model and the Shapley Additive Explanation (SHAP) method were employed to explore the relationships between BrC optical properties and chemical composition. The model attained high accuracy with Pearson correlation coefficients (r) exceeding 0.93 for the absorption coefficient (Absλ) and surpassing 0.57 for mass absorption efficiency (MAEλ) of BrC. It explains more than 80% of the variance in Abs and over 50% in MAE, significantly improving the understanding of BrC light absorption. Polycyclic aromatic hydrocarbons (PAHs) and oxygenated PAHs (OPAHs) with four and five rings exhibit significant positive effects on Absλ, suggesting that similar unidentified chromophores may also notably impact BrC optical characteristics. The model based on chromophore mass concentrations further simplifies studying BrC optical characteristics. This study advances understanding of the relationship between BrC composition and optical properties and guides the investigation of unrecognized chromophores.

Exploring interactive effects of environmental and microbial factors on food waste anaerobic digestion performance: Interpretable machine learning models

Biogas yield in anaerobic digestion (AD) involves continuous and complex biological reactions. The traditional linear models failed to quantitatively assess the interactive effects of these factors on AD performance. To further explore the internal relationship between target variables and AD performance, this study developed four machine learning models to predict biogas yield and consider the interaction among various factors. Results indicated that the highest prediction accuracy of AD performance was achieved by adding bacterial genera dataset with environmental factors. Random forest model exhibited the highest accuracy, with the testing coefficient of determination equal to 0.9879. Among two types of input features, the bacterial genera accounted for 89.9 % of the impact on biogas yield, followed by environmental factors. The results revealed Keratinibaculum and Acetomicrobium as critical bacteria. The volatile fatty acid controlled below 2000 mg/L and the improved stirring system in AD process were recommended to achieve maximum biogas yield.

Uncovering the features of industrial odors-derived environmental complaints and proactive countermeasures by using machine-learning

Industrial odor-derived environmental complaints pose an emerging and far-reaching challenge in cities worldwide with intensive industries. Developing effective odor complaint management strategies is essential for mitigating the public impact of industrial odors. Based on a typical case of persistent tire manufacturing odors affecting local communities, we proposed an environmental complaint risks (ECR) prediction model using machine-learning (ML) approaches, which combined complaints with temporal-resolution manufacturing-meteorology-environment data. Through intensive match-making between ML algorithms and multi-source parameters, Random Forest models can achieve a reliable ECR-prediction model performance with an average ROC-AUC of 0.79at a monthly timescale, indicating the effectiveness of ML-based ECR prediction models. The interpretable ML model quantitively depicted the underlying mechanisms of ECR prediction, driven by process emission behaviors, local wind direction, and historical high-risk period. Furthermore, to mitigate predictable ECR within a future period, we designed a model framework that integrated ECR prediction models with an adaptive optimization genetic algorithm. This enabled the proactive management by precisely and dynamically allocating limited resources of emission regulatory to high-ECR periods in advance. The strategy was proven effective, achieving a significant 24.7% average reduction in the overall ECR forecast during a period with intensive complaints. Overall, this study proposed a data-driven model framework that efficiently helps the multi-stakeholders shift from passive response to proactive ECR management, thereby enhancing the environmental and social sustainability.

Enhancing financial fraud detection using adaptive machine learning models and business analytics

Financial fraud continues to be a critical threat to businesses and economies worldwide, necessitating advanced detection techniques. This paper reviews the role of adaptive machine learning (ML) models and business analytics in enhancing fraud detection systems. Traditional fraud detection methods often fall short in addressing the complexity and evolving nature of fraudulent activities, making adaptive ML models, such as decision trees and neural networks, more effective in identifying subtle patterns in large datasets. Organizations can refine ML models by integrating business analytics, ensuring real-time detection and continuous improvement of fraud detection systems. The paper also explores the challenges in deploying these technologies, including data privacy concerns and model accuracy, as well as the potential impact of emerging technologies such as blockchain and quantum computing. Future directions emphasize improving the interpretability of ML models and leveraging multi-modal data for a more holistic approach to fraud prevention. The synergy between adaptive machine learning and business analytics promises a more resilient and effective framework for combating financial fraud.

Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study

BackgroundNew-onset atrial fibrillation (NOAF) is the most common arrhythmia in critically ill patients admitted to intensive care and is associated with poor prognosis and disease burden. Identifying high-risk individuals early is crucial. This study aims to create and validate a NOAF prediction model for critically ill patients using machine learning (ML).MethodsThe data came from two non-overlapping datasets from the Medical Information Mart for Intensive Care (MIMIC), with MIMIC-IV used for training and subset of MIMIC-III used as external validation. LASSO regression was used for feature selection. Eight ML algorithms were employed to construct the prediction model. Model performance was evaluated based on identification, calibration, and clinical application. The SHapley Additive exPlanations (SHAP) method was used for visualizing model characteristics and individual case predictions.ResultsAmong 16,528 MIMIC-IV patients, 1520 (9.2%) developed AF post-ICU admission. A model with 23 variables was built, with XGBoost performing best, achieving an AUC of 0.891 (0.873–0.888) in validation and 0.769 (0.756–0.782) in external validation. Key predictors included age, mechanical ventilation, urine output, sepsis, blood urea nitrogen, percutaneous arterial oxygen saturation, continuous renal replacement therapy and weight. A risk probability greater than 0.6 was defined as high risk. A friendly user interface had been developed for clinician use.ConclusionWe developed a ML model to predict the risk of NOAF in critically ill patients without cardiac surgery and validated its potential as a clinically reliable tool. SHAP improves the interpretability of the model, enables clinicians to better understand the causes of NOAF, helps clinicians to prevent it in advance and improves patient outcomes.

A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study

ObjectiveTo develop a computed tomography (CT) radiomics-based interpretable machine learning (ML) model to preoperatively predict human epidermal growth factor receptor 2 (HER2) status in bladder cancer (BCa) with multicenter validation.MethodsIn this retrospective study, 207 patients with pathologically confirmed BCa were enrolled and divided into the training set (n = 154) and test set (n = 53). Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in the training set. Five radiomics-based ML models, namely logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), eXtreme Gradient Boosting (XGBoost) and random forest (RF), were developed. The predictive performance of established ML models was evaluated by the area under the receiver operating characteristic curve (AUC). The Shapley additive explanation (SHAP) was used to analyze the interpretability of ML models.ResultsA total of 1218 radiomics features were extracted from the nephrographic phase CT images, and 11 features were filtered for constructing ML models. In the test set, the AUCs of LR, SVM, KNN, XGBoost, and RF were 0.803, 0.709, 0.679, 0.794, and 0.815, with corresponding accuracies of 71.7%, 69.8%, 60.4%, 75.5%, and 75.5%, respectively. RF was identified as the optimal classifier. SHAP analysis showed that texture features (gray level size zone matrix and gray level co-occurrence matrix) were significant predictors of HER2 status.ConclusionsThe radiomics-based interpretable ML model provides a noninvasive tool to predict the HER2 status of BCa with satisfactory discriminatory performance.Critical relevance statementAn interpretable radiomics-based machine learning model can preoperatively predict HER2 status in bladder cancer, potentially aiding in the clinical decision-making process.Key PointsThe CT radiomics model could identify HER2 status in bladder cancer.The random forest model showed a more robust and accurate performance.The model demonstrated favorable interpretability through SHAP method.Graphical

Predicting High-Flow Nasal Cannula Oxygen Therapy Failure in Patients With Acute Hypoxaemic Respiratory Failure Using Machine Learning: Model Development and External Validation.

To develop and validate a prediction model for high-flow nasal cannula (HFNC) failure in patients with acute hypoxaemic respiratory failure (AHRF). AHRF accounts for a major proportion of intensive care unit (ICU) admissions and is associated with high mortality. HFNC is a non-invasive respiratory support technique that can improve patient oxygenation. However, HFNC failure, defined as the need for escalation to invasive mechanical ventilation, can lead to delayed intubation, prolonged mechanical ventilation and increased risk of mortality. Timely and accurate prediction of HFNC failure has important clinical implications. Machine learning (ML) can improve clinical prediction. Multicentre observational study. This study analysed 581 patients from an academic medical centre in Boston and 180 patients from Guangzhou, China treated with HFNC for AHRF. The Boston dataset was randomly divided into a training set (90%, n = 522) and an internal validation set (10%, n = 59), and the model was externally validated using the Guangzhou dataset (n = 180). A random forest (RF)-based feature selection method was used to identify predictive factors. Nine machine learning algorithms were selected to build the predictive model. The area under the receiver operating characteristic curve (AUC) and performance evaluation parameters were used to evaluate the models. The final model included 38 features selected using the RF method, with additional input from clinical specialists. Models based on ensemble learning outperformed other models (internal validation AUC: 0.83; external validation AUC: 0.75). Important predictors of HFNC failure include Glasgow Coma Scale scores and Sequential Organ Failure Assessment scores, albumin levels measured during HFNC treatment, ROX index at ICU admission and sepsis. This study developed an interpretable ML model that accurately predicts the risk of HFNC failure in patients with AHRF. Clinicians and nurses can use ML models for early risk assessment and decision support in AHRF patients receiving HFNC. TRIPOD checklist for prediction model studies was followed in this study. Patients were involved in the sample of the study.

Interpretable machine learning model for predicting long-term cardiovascular mortality risk in chronic kidney disease patients using SHAP explainers

Abstract Background Patients with chronic kidney disease (CKD) exhibited a pronounced burden of cardiac mortality. However, early prediction of cardiovascular mortality risk in CKD patients remains an unmet medical need. Purpose This study aimed to evaluate the performance of machine learning (ML) algorithms and identify the most influential factors in predicting long-term cardiac mortality among CKD patients. Methods Six ML models were developed, with the most effective one chosen for predicting and categorising patients into high-risk and low-risk groups based on the maximal Youden’s index. Differences in survival rates were assessed using the log-rank test on Kaplan-Meier curves. Cox regression analysis was employed to investigate the relationship between ML-predicted risk scores and mortality. Furthermore, the SHapley Additive exPlanations (SHAP) method was implemented to provide personalised explanations for model decisions. Results The auto-encoder (AE) model achieved the highest AUC of 0.94, with a sensitivity of 80.95% and specificity of 96.34%. Compared to individuals in low-risk group, those in high-risk group exhibited a significantly elevated risk of cardiovascular mortality (adjusted hazard ratio [HR]: 48.24; P <0.001). According to the SHAP model, age, C-reactive protein, blood urea nitrogen and hypertension were identified as the four most influential factors in the AE model. Conclusions Our study successfully developed an AE machine learning model for predicting 10-year cardiovascular mortality among CKD patients. The combination of ML model and SHAP aids doctors in understanding key features in the model, improving their insight into decision-making related to disease severity assessment, thus facilitating early preventive strategies in clinical practice.

On the interpretability of the SVM model for predicting infant mortality in Bangladesh

BackgroundAlthough machine learning (ML) models are well-liked for their outperformance in prediction, greatly avoided due to the lack of intuition and explanation of their predictions. Interpretable ML is, therefore, an emerging research field that combines the performance and interpretability of ML models to create comprehensive solutions for complex decision-making analysis. Conversely, infant mortality is a global public health concern affecting health, social well-being, socio-economic development, and healthcare services. The study employs advanced interpretable ML techniques to anticipate and understand the factors affecting infant mortality in Bangladesh, overcoming the shortcomings of the conventional logistic regression (LR) model.MethodsBy utilizing the global surrogate model and local individual conditional expectation (ICE) interpretability technique, the interpretable support vector machine (SVM) has been used in this study to reveal significant characteristics of infant mortality using data from the Bangladesh Demographic and Health Survey (BDHS) 2017–18. To investigate intricate decision-making analysis of infant mortality, we adapted SVM and LR techniques with the hyperparameter tuning parameters. These models’ performances were initially assessed using the receiver operating characteristics (ROC) curve, run-time, and confusion matrix parameters with 100 permutations. Afterward, the SVM model’s model-agnostic explanation and the LR model’s interpretation were compared to enhance advanced comprehension for further insights.ResultsThe results of the 100 permutations demonstrated that the LR model (Average: accuracy = 0.9105, precision = NaN, sensitivity = 0, specificity = 1, F1-score = 0, area under the ROC curve (AUC) = 0.6780, run-time = 0.0832) outperformed the SVM model (Average: accuracy = 0.8470, precision = 0.1062, sensitivity = 0.0949, specificity = 0.9209, F1-score = 0.1000, AUC = 0.5632, run-time = 0.0254) in predicting infant mortality, but the LR model had a slower run-time and it was unable to predict any positive cases. The interpretation of LR analysis revealed that infant mortality rates decrease when mothers give birth after over two years, with higher educational attainment, overweight or obese mothers, working mothers, and families with polluted cooking fuel having lower rates. The local ICE interpretability technique, which depicts individual influences on the average likelihood of dying within the first birthday, explores the interpretable SVM model that mothers with normal BMIs, giving birth within two years, using less polluted cooking fuel, working mothers, and having male infant were more likely to experience infant death. The interpretable SVM model based on the global surrogate model also reveals that working mothers who used polluted cooking fuel at home and working women who used less polluted cooking fuel but had a longer period between pregnancies than two years would have higher infant death rates. Even among non-working mothers who used polluted cooking fuel and gave birth within two years of the preceding one, infant death rates were higher.ConclusionsThe interpretable SVM model reveals global interpretations help clinicians understand the entire conditional distribution, while local interpretations focus on specific instances, providing different insights into model behavior. Interpretable ML models aid policymakers, stakeholders, and families in understanding and preventing infant deaths by improving policy-making strategies and establishing effective family counseling services.

Impact of sampling for landslide susceptibility assessment using interpretable machine learning models

Impact of sampling for landslide susceptibility assessment using interpretable machine learning models

Forecasting Bank Default Risk with Interpretable Machine Learning: The Study of Chinese Banks

ABSTRACT Bank occupies an important position in the financial system. The stable operation of the banking industry is not only one of the important factors in achieving sustainable economic growth but also related to the stability of the entire financial system. This research collects data from 507 banks in China from 2000 to 2021, uses the non-performing loan ratio as the measurement indicator of bank risk, and selects indicators from five levels (macroeconomic environment, industry economic environment, economic policy uncertainty, financial openness and bank financial status) On this basis, we use interpretable machine learning models to predict the bank’s default risk, analyze and compare the interpretable machine learning model and the post-hoc explainable methods. The results indicate that Provision Coverage (PC), Loan Provision Coverage (LPC), Liquidity Ratio (LR), and KOF Financial Globalization Index (KOFFiGI) have strong predictive capability for bank default risk. Our research can provide a reference for banks, government and financial regulatory authorities to construct the prediction model and indicator monitoring platform for bank default risk.

Interpretable Machine Learning: A Case Study on Predicting Fuel Consumption in VLGC Ship Propulsion

The integration of machine learning (ML) in marine engineering has been increasingly subjected to stringent regulatory scrutiny. While environmental regulations aim to reduce harmful emissions and energy consumption, there is also a growing demand for the interpretability of ML models to ensure their reliability and adherence to safety standards. This research highlights the need to develop models that are both transparent and comprehensible to domain experts and regulatory bodies. This paper underscores the importance of transparency in machine learning through a use case involving a VLGC ship two-stroke propulsion engine. By adhering to the CRISP-DM standard, we fostered close collaboration between marine engineers and machine learning experts to circumvent the common pitfalls of automated ML. The methodology included comprehensive data exploration, cleaning, and verification, followed by feature selection and training of linear regression and decision tree models that are not only transparent but also highly interpretable. The linear model achieved an RMSE of 23.16 and an MRAE of 14.7%, while the accuracy of decision trees ranged between 96.4% and 97.69%. This study demonstrates that machine learning models for predicting propulsion engine fuel consumption can be interpretable, adhering to regulatory requirements, while still achieving adequate predictive performance.

Developing a Wearable Sensor-Based Digital Biomarker of Opioid Dependence.

Repeated opioid exposure leads to a variety of physiologic adaptations that develop at different rates and may foreshadow risk of opioid-use disorder (OUD), including dependence and withdrawal. Digital pharmacovigilance strategies that use noninvasive sensors to identify physiologic adaptations to opioid use represent a novel strategy to facilitate safer opioid prescribing. This study aims to identify wearable sensor-derived features associated with opioid dependence by comparing opioid-naïve individuals to chronic opioid users with acute pain and developing a machine-learning model to distinguish between the 2 groups. Using a longitudinal observational study design, continuous physiologic data were collected on participants with acute pain receiving opioid analgesia. Monitoring continued throughout hospitalization and for up to 7 days posthospital discharge. Opioid administration data were obtained from electronic health record (EHR) and participant self-report. Participants were classified as belonging to 1 of 3 categories based on opioid use history: naïve, occasional, or chronic use. Thirty features were derived from sensor data, and an additional 9 features were derived from participant demographic and treatment characteristics. Physiologic feature behavior immediately postopioid use was compared among naïve and chronic participants, and subsequently features were used to generate machine learning models which were validated using cross-validation and holdout data. Forty-one participants with a combined total of 169 opioid administrations were ultimately included in the final analysis. Four interpretable decision tree-based machine learning models with 14 sensor-based and 5 clinical features were developed to predict class membership on the level of a given observation (dose) and on the participant level. Ranges for model metrics on the participant level were as follows: accuracy 70% to 90%, sensitivity 67% to 100%, and specificity 67% to 100%. Wearable sensor-derived digital biomarkers can be used to predict opioid use status (naïve versus chronic) and the differentiating features may be detecting opioid dependence. Future work should be aimed at further delineating the phenomenon identified in these models (including opioid dependence and/or withdrawal) and at identifying transition states where an individual changes from 1 profile to another with repetitive opioid exposure.