Improving Machine Learning Classification Predictions through SHAP and Features Analysis Interpretation.

Backgroundand objectives: Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine learning-based models have showed potential as virtual quality assurance tools, being capable of accurately predicting the dose verification results of fixed-beam intensity-modulated radiation therapy (IMRT) or volumetric modulated arc therapy (VMAT) plans, thereby ensuring safe and efficient treatment for patients. However, there has been no research yet that simultaneously integrates different IMRT techniques to predict the gamma pass rate (GPR) and explain the model.Methods: Retrospective analysis of the 3D dosimetric verification results based on measurements with gamma pass rate criteria of 3%/2 mm and 10% dose threshold of 409 pelvic IMRT and VMAT plans was carried out. Radiomics features were extracted from the dose files, from which the XGBoost algorithm based on SHapley Additive exPlanations (SHAP) values was used to select the optimal feature subset as the input for the prediction model. The study employed four different machine learning algorithms, namely, random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), to construct predictive models. Sensitivity, specificity, F1 score, and AUC value were calculated to evaluate the classification performance of these models. The SHAP values were utilized to perform a related interpretive analysis on the best performing model.Results: The sensitivities and specificities of the RF, AdaBoost, XGBoost, and LightGBM models were 0.96, 0.82, 0.93, and 0.89, and 0.38, 0.54, 0.62, and 0.62, respectively. The F1 scores and area under the curve (AUC) values were 0.86, 0.81, 0.88, and 0.86, and 0.81, 0.77, 0.85, and 0.83, respectively. The explanation of the model output based on SHAP values can provide a reference basis for medical physicists when adjusting the plan, thereby improving the efficiency and quality of treatment plans.Conclusion: It is feasible to use a machine learning method based on radiomics to establish a gamma pass rate classification prediction model for IMRT and VMAT plans in the pelvis. The XGBoost model performs better in classification than the other three tree-based ensemble models, and global explanations and single-sample explanations of the model output through SHAP values may offer reference for medical physicists to provide high-quality plans, promoting the clinical application and implementation of GPR prediction models, and providing safe and efficient personalized QA management for patients.

Breast cancer remains the most common cancer among women globally highlighting the importance of early and reliable diagnostic methods. While previous studies have applied association rules mining (ARM) to explore factors contributing to breast cancer, many lacked robust validation of the extracted rules. To address this gap and deepen our understanding of the key biological markers linked to the disease, this study proposes a hybrid framework that integrates Class Association Rule Mining (CARM) with SHapley Additive exPlanations (SHAP) values based on Random Forest (RF) and Gradient Boost (GB) models to uncover and validate meaningful diagnostic patterns. Using the Breast Cancer Coimbra (BCC) dataset comprising 116 patient samples and nine biological markers, a total of 723,938 association rules (AR) were generated with 17,720 significant class association rules (CAR) were extracted. These rules were pruned using lift, leverage and conviction to retain the most relevant ones. Among the healthy group, combinations involving low glucose, low insulin, low resistin and low Homeostatic Model Assessment (HOMA) were consistently observed, while high BMI appeared particularly among younger individuals. These features were associated with negative SHAP values validating their contribution to healthy classifications. In contrast, common patterns such as high glucose, medium resistin and medium Monocyte Chemoattractant Protein-1 (MCP.1) among middle aged individuals highlighting their influence in predicting patient classification. These features consistently showed strong positive SHAP values across both classifiers highlighting their influence in predicting patient outcomes. By combining rule extraction of CARM with feature contribution using SHAP, this study provides a validated and interpretable approach for breast cancer diagnosis. The findings highlight the importance of feature interactions and offer promising directions for personalized risk assessment and early detection.

Prediction of gully erosion susceptibility through the lens of the SHapley Additive exPlanations (SHAP) method using a stacking ensemble model.

e13539 Background: In The US Oncology Network (The Network), about one-third of new patients with a cancer diagnosis started intravenous (IV) treatment after their first visit. The rest of the patients either came in for a consult only or might have received other treatments such as radiation, surgery, or oral therapy. We developed a machine learning model to predict IV treatment initiation among new patients and discovered features associated with the patient’s decision. This model could suggest interventions to improve patient’s access to care. Methods: A retrospective cohort was formed by identifying new patients with cancer from 27 practices in The Network between July 1, 2021 and June 30, 2022. Structured data were extracted and processed from the electronic health records, claims, physician referrals, and the American Community Survey. Patient characteristics included demographics, clinical information, payor types, and socioeconomic status. The referral pattern and the geographic region of practices, and the provider workload were considered as well. Gradient-boosted decision trees, random forest, neural network, and logistic regression models were developed to predict the probability of starting IV treatment within 90 days of the first visit. Model performance was evaluated based on the area under the receiver operating characteristic (AUROC) curve using cross-valuation and 4:1 training/validation random split. Shapley Additive Explanations (SHAP) values were applied to the model to explain feature importance. Results: A total of 117,340 new patients with a cancer diagnosis were included in the study, of whom 35% initiated IV treatment within 90 days of the first visit. A gradient-boosted decision tree algorithm with control of the imbalanced label was chosen as the final model because of the performance and the ability to handle missing values. The model achieved an AUROC of 0.80 on the validation dataset with both cross-valuation and 4:1 training/validation random split. Based on the SHAP values (log odds), we found that clinical information including diagnosis and stage is the most important feature to predict the initiation of IV treatment (mean absolute SHAP = 0.31 and 1.03, respectively). Medicaid contributes least to treatment initiation among all insurance types (mean absolute SHAP = 0.01). In addition, younger age and male patients have a higher chance to start IV treatment (Pearson correlation = -0.41, p-value < 0.01 for age versus SHAP values; p-value < 0.01, two-sided T-test for SHAP values by gender). Conclusions: This study reports a machine learning model to predict IV treatment initiation among new patients with cancer. Clinical features impact the treatment decision more than others. This model could guide patient service and direct personalized care navigation. Further, the model sheds light on future interventions that could enhance patient access to treatment promptly.

Forecasting Hematological Activity in Antiphospholipid Syndrome Using Predictive Models

Background and Objectives: The rising prevalence of myopia is a significant global health concern. Atropine eye drops are commonly used to slow myopia progression in children, but their long-term use raises concern about intraocular pressure (IOP). This study uses SHapley Additive exPlanations (SHAP) to improve the interpretability of machine learning (ML) model predicting end IOP, offering clinicians explainable insights for personalized patient management. Materials and Methods: This retrospective study analyzed data from 1191 individual eyes of 639 boys and 552 girls with myopia treated with atropine. The average age of the whole group was 10.6 ± 2.5 years old. The refractive error of spherical equivalent (SE) in myopia degree was base SE at 2.63D and end SE at 3.12D. Data were collected from clinical records, including demographic information, IOP measurements, and atropine treatment details. The patients were divided into two subgroups based on a baseline IOP of 14 mmHg. ML models, including Lasso, CART, XGB, and RF, were developed to predict the end IOP value. Then, the best-performing model was further interpreted using SHAP values. The SHAP module created a personalized and dynamic graphic to illustrate how various factors (e.g., age, sex, cumulative duration, and dosage of atropine treatment) affect the end IOP. Results: RF showed the best performance, with superior error metrics in both subgroups. The interpretation of RF with SHAP revealed that age and the recruitment duration of atropine consistently influenced IOP across subgroups, while other variables had varying effects. SHAP values also offer insights, helping clinicians understand how different factors contribute to predicted IOP value in individual children. Conclusions: SHAP provides an alternative approach to understand the factors affecting IOP in children with myopia treated with atropine. Its enhanced interpretability helps clinicians make informed decisions, improving the safety and efficacy of myopia management. This study demonstrates the potential of combining SHAP with ML models for personalized care in ophthalmology.

BackgroundIschemic heart disease (IHD) and type 2 diabetes mellitus (T2DM) are leading causes of disability-adjusted life years globally among adults aged 55 years and older. Although both diseases share common risk factors and pathophysiological pathways, previous research has predominantly addressed these conditions in isolation. The co-occurrence patterns and regional variations of IHD and T2DM burden remain poorly understood. We aimed to characterize the global co-occurrence patterns of IHD and T2DM from a spatial perspective and to identify the corresponding risk factors distinguishing different burden regions.MethodsUsing data from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2021 database, we extracted age-standardized disability-adjusted life year (DALY) rates for IHD and T2DM among individuals aged 55 years and older from 204 countries and territories. Based on quartile distributions of global DALY rates for both diseases, we classified countries into four distinct burden regions: Low-Burden Regions (56 countries), T2DM-Dominant Regions (46 countries), IHD-Dominant Regions (46 countries), and Dual-Burden Regions (56 countries). We examined temporal trends from 1990-2021, computed population attributable fractions for major risk factors, and used machine learning-based SHAP (Shapley Additive Explanations) analysis to screen and quantify the effects of corresponding risk factors distinguishing regional classifications.ResultsDual-Burden Regions were distributed across multiple geographic areas including the Caribbean and Central America, Persian Gulf states, Balkan Peninsula, Southeast Asia, West Africa, Eastern Mediterranean, and Northern Europe. The spatial distribution revealed distinct geographic clustering, with higher IHD rates in Eastern Europe and Central Asia, and elevated T2DM rates in Pacific Island nations and parts of the Middle East. Countries and territories with the highest burden for both diseases included North African countries (eg, Morocco: IHD 25,193.1/100,000 and T2DM 32,197.24/100,000) and Pacific Island nations such as Fiji exhibiting IHD burden of 24,758.17 per 100,000 and T2DM burden of 32,197.24 per 100,000. Marshall Islands showed IHD burden of 25,107.72/100,000 and T2DM burden of 22,122.46/100,000, while Nauru demonstrated the highest IHD burden (39,483.92/100,000). High systolic blood pressure contributed most to IHD burden globally (49.79%), while high body-mass index dominated T2DM burden (51.89%). Environmental factors demonstrated clear regional gradients, with household air pollution ranging from 4·58% in Low-Burden to 14.43% in Dual-Burden Regions for IHD. High body-mass index contributed 51.89% to T2DM burden globally, with regional variation from 40.61% in IHD-Dominant to 51.36% in Low-Burden Regions. SHAP analysis identified sociodemographic index (SDI2021) as the primary factor distinguishing Low-Burden from Dual-Burden Regions for both IHD (mean |SHAP| = 1.245) and T2DM (mean |SHAP| = 1.317). Diet high in processed meat consistently showed strong discriminatory power across multiple regional comparisons for T2DM (SHAP values 0.923-1.721), while secondhand smoke emerged as a critical differentiator with SHAP values exceeding 1.0 across various regional distinctions. Diet low in vegetables served as a primary differentiator between Low-Burden and T2DM-Dominant Regions (mean |SHAP| = 1.188).ConclusionThe co-occurrence of IHD and T2DM exhibits pronounced global heterogeneity, with Pacific Island nations and multiple geographic regions including Gulf states, North Africa, and other areas bearing disproportionate dual-burden. Socioeconomic development level fundamentally characterizes dual-burden status, while dietary and environmental factors serve as key regional differentiators. Intervening in modifiable risk factors, particularly processed meat consumption, vegetable intake, and environmental exposures, can fundamentally reduce the global burden of these co-occurring diseases.

Data-driven shear strength prediction of steel reinforced concrete composite shear wall

In the context of high-dimensional credit card fraud data, researchers and practitioners commonly utilize feature selection techniques to enhance the performance of fraud detection models. This study presents a comparison in model performance using the most important features selected by SHAP (SHapley Additive exPlanations) values and the model’s built-in feature importance list. Both methods rank features and choose the most significant ones for model assessment. To evaluate the effectiveness of these feature selection techniques, classification models are built using five classifiers: XGBoost, Decision Tree, CatBoost, Extremely Randomized Trees, and Random Forest. The Area under the Precision-Recall Curve (AUPRC) serves as the evaluation metric. All experiments are executed on the Kaggle Credit Card Fraud Detection Dataset. The experimental outcomes and statistical tests indicate that feature selection methods based on importance values outperform those based on SHAP values across classifiers and various feature subset sizes. For models trained on larger datasets, it is recommended to use the model’s built-in feature importance list as the primary feature selection method over SHAP. This suggestion is based on the rationale that computing SHAP feature importance is a distinct activity, while models naturally provide built-in feature importance as part of the training process, requiring no additional effort. Consequently, opting for the model’s built-in feature importance list can offer a more efficient and practical approach for larger datasets and more intricate models.

The leaf area index (LAI) serves as a critical parameter for assessing wetland ecosystem functions, and accurate LAI retrieval holds substantial significance for wetland conservation and ecological monitoring. To address the spatial constraints of traditional ground-based measurements and the limited accuracy of single-source remote sensing data, this study utilized unmanned aerial vehicle (UAV)-borne hyperspectral and LiDAR sensors to acquire high-quality multi-source remote sensing data of coastal wetlands in the Yellow River Delta. Three machine learning algorithms—random forest (RF), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost)—were employed for LAI retrieval modeling. A total of 38 vegetation indices (VIs) and 12-point cloud features (PCFs) were extracted from hyperspectral imagery and LiDAR point cloud data, respectively. Pearson correlation analysis and the Shapley Additive Explanations (SHAP) method were integrated to identify and select the most informative VIs and PCFs. The performance of LAI retrieval models built on single-source features (VIs or PCFs) or multi-source feature fusion was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). The main findings are as follows: (1) Multi-source feature fusion significantly improved LAI retrieval accuracy, with the RF model achieving the highest performance (R2 = 0.968, RMSE = 0.125). (2) LiDAR-derived structural metrics and hyperspectral-derived vegetation indices were identified as critical factors for accurate LAI retrieval. (3) The feature selection method integrating mean absolute SHAP values (|SHAP| values) with Pearson correlation analysis enhanced model robustness. (4) The intertidal zone exhibited pronounced spatial heterogeneity in the vegetation LAI distribution.

BackgroundA better understanding of the relationships between insomnia and anxiety, mood, eating, and alcohol-use disorders is needed given its prevalence among young adults. Supervised machine learning provides the ability to evaluate which mental disorder is most associated with heightened insomnia among U.S. college students. Combined with Bayesian network analysis, probable directional relationships between insomnia and interacting symptoms may be illuminated.MethodsThe current exploratory analyses utilized a national sample of college students across 26 U.S. colleges and universities collected during population-level screening before entering a randomized controlled trial. We used a 4-step statistical approach: (1) at the disorder level, an elastic net regularization model examined the relative importance of the association between insomnia and 7 mental disorders (major depressive disorder, generalized anxiety disorder, social anxiety disorder, panic disorder, post-traumatic stress disorder, anorexia nervosa, and alcohol use disorder); (2) This model was evaluated within a hold-out sample. (3) at the symptom level, a completed partially directed acyclic graph (CPDAG) was computed via a Bayesian hill-climbing algorithm to estimate potential directionality among insomnia and its most associated disorder [based on SHAP (SHapley Additive exPlanations) values)]; (4) the CPDAG was then tested for generalizability by assessing (in)equality within a hold-out sample using structural hamming distance (SHD).ResultsOf 31,285 participants, 20,597 were women (65.8%); mean (standard deviation) age was 22.96 (4.52) years. The elastic net model demonstrated clinical significance in predicting insomnia severity in the training sample [R2 = .44 (.01); RMSE = 5.00 (0.08)], with comparable performance in the hold-out sample (R2 = .33; RMSE = 5.47). SHAP values indicated that the presence of any mental disorder was associated with higher insomnia scores, with major depressive disorder as the most important disorder associated with heightened insomnia (mean |SHAP|= 3.18). The training CPDAG and hold-out CPDAG (SHD = 7) suggested depression symptoms presupposed insomnia with depressed mood, fatigue, and self-esteem as key parent nodes.ConclusionThese findings provide insights into the associations between insomnia and mental disorders among college students and warrant further investigation into the potential direction of causality between insomnia and depression.Trial registrationTrial was registered on the National Institute of Health RePORTER website (R01MH115128 || 23/08/2018).

There is an increased exploration of the potential of wireless communication networks in the automation of daily human tasks via the Internet of Things. Such implementations are only possible with the proper design of networks. Path loss prediction is a key factor in the design of networks with parameters such as cell radius, antenna heights, and the number of cell sites that can be set. As path loss is affected by the environment, satellite images of network locations are used in developing path loss prediction models such that environmental effects are captured. We developed a path loss model based on the Extreme Gradient Boosting (XGBoost) algorithm, whose inputs are numeric (non-image) features that influence path loss and features extracted from images composed of four tiled satellite images of points along the transmitter to receiver path. The model can predict path loss for multiple frequencies, antenna heights, and environments such that it can be incorporated into Radio Planning Tools. Various feature extraction methods that included CNN and hand-crafted and their combinations were applied to the images in order to determine the best input features, which, when combined with non-image features, will result in the best XGBoost model. Although hand-crafted features have the advantage of not requiring a large volume of data as no training is involved in them, they failed in this application as their use led to a reduction in accuracy. However, the best model was obtained when image features extracted using CNN and GLCM were combined with the non-image features, resulting in an RMSE improvement of 9.4272% against a model with non-image features only without satellite images. The XGBoost model performed better than Random Forest (RF), Extreme Learning Trees (ET), Gradient Boosting, and K Nearest Neighbor (KNN) based on the combination of CNN, GLCM, and non-image features. Further analysis using the Shapley Additive Explanations (SHAP) revealed that features extracted from the satellite images using CNN had the highest contribution toward the XGBoost model’s output. The variation in values of features with output path loss values was presented using SHAP summary plots. Interactions were also observed between some features based on their dependence plots from the computed SHAP values. This information, when further explored, could serve as the basis for the development of an explainable/glass box path loss model.

This investigation aims to establish and substantiate a machine learning-driven predictive framework designed to precisely distinguish between pediatric bronchopneumonia and lobar pneumonia. This endeavor seeks to elevate the accuracy of early clinical support, refine treatment decision-making, and curtail superfluous medical interventions. This study was executed at Siyang Hospital, enrolling 2304 pediatric patients diagnosed with either bronchopneumonia or lobar pneumonia from January 2020 to December 2024. Participants were randomized in a 7:3 ratio into training (n = 1612) and testing (n = 692) sets, supplemented by an external validation set (n = 454) to evaluate the model's generalizability. Hematological and serum biochemical parameters were gathered, with feature selection conducted using eXtreme Gradient Boosting (XGBoost), Support Vector Machine-Recursive Feature Elimination (SVM-RFE), and Random Forest algorithms. A suite of twelve machine learning models-including Random Forest, Gradient Boosting, and Support Vector Machines-was developed, with parameters fine-tuned through five-fold cross-validation. Model efficacy was assessed via receiver operating characteristic (ROC) curves, area under the curve (AUC), sensitivity, specificity, and F1 score, while feature significance was quantified using SHAP values. A nomogram was formulated based on critical features, its clinical value affirmed through calibration curves, and decision curve analysis (DCA). Statistical evaluations incorporated Mann-Whitney U tests, chi-square tests, and DeLong tests, with a threshold of P < 0.05 denoting significance. Notable disparities emerged between the bronchopneumonia (n = 1868) and lobar pneumonia (n = 436) cohorts across several hematological markers, such as large platelet count (P-LCT), Lymphocyte percentage (LYM%), and creatinine (CREA) (P < 0.01). Feature selection pinpointed P-LCT, LYM%, and CREA as key predictors. The Gradient Boosting model demonstrated exemplary performance, yielding an AUC of 0.947 (95% CI 0.934-0.960) in the training set, 0.968 (95% CI 0.954-0.982) in the testing set, and 0.989 (95% CI 0.981-0.997) in the external validation set, underscoring its outstanding discriminative prowess and robust generalizability. SHapley Additive exPlanations (SHAP) analysis underscored P-LCT (Mean Absolute SHAP: 0.057) and LYM% (0.065) as predominant predictors, exhibiting a strong correlation with disease severity. The nomogram attained an AUC of 0.962, with impeccable calibration (C-index = 0.962), and DCA substantiated considerable net benefit at moderate risk thresholds. The Gradient Boosting model, as delineated in this study, markedly advances the differential diagnosis of pediatric bronchopneumonia and lobar pneumonia, delivering high precision and resilience. It serves as an efficacious and dependable clinical decision-support instrument. By incorporating pivotal biomarkers like P-LCT and LYM%, this model illuminates pathophysiological traits, enhances antibiotic stewardship, and guides hospitalization choices, thereby diminishing healthcare resource wastage and ameliorating patient outcomes. These insights furnish vital backing for precision medicine and acute care management.

BackgroundDepressive disorder, particularly major depressive disorder (MDD), significantly impact individuals and society. Traditional analysis methods often suffer from subjectivity and may not capture complex, non-linear relationships between risk factors. Machine learning (ML) offers a data-driven approach to predict and diagnose depression more accurately by analyzing large and complex datasets.MethodsThis study utilized data from the National Health and Nutrition Examination Survey (NHANES) 2013–2014 to predict depression using six supervised ML models: Logistic Regression, Random Forest, Naive Bayes, Support Vector Machine (SVM), Extreme Gradient Boost (XGBoost), and Light Gradient Boosting Machine (LightGBM). Depression was assessed using the Patient Health Questionnaire (PHQ-9), with a score of 10 or higher indicating moderate to severe depression. The dataset was split into training and testing sets (80% and 20%, respectively), and model performance was evaluated using accuracy, sensitivity, specificity, precision, AUC, and F1 score. SHAP (SHapley Additive exPlanations) values were used to identify the critical risk factors and interpret the contributions of each feature to the prediction.ResultsXGBoost was identified as the best-performing model, achieving the highest accuracy, sensitivity, specificity, precision, AUC, and F1 score. SHAP analysis highlighted the most significant predictors of depression: the ratio family income to poverty (PIR), sex, hypertension, serum cotinine and hydroxycotine, BMI, education level, glucose levels, age, marital status, and renal function (eGFR).ConclusionWe developed ML models to predict depression and utilized SHAP for interpretation. This approach identifies key factors associated with depression, encompassing socioeconomic, demographic, and health-related aspects.

An explainable model for the mass appraisal of residences: The application of tree-based Machine Learning algorithms and interpretation of value determinants