2026-04-02
Leming Zhou, Hanshu Qin, Yanmei Yang, Gang Huang, Zhigang Liu
Hypertension is associated with an increased risk of serious complications, and the hazards are very serious. However, current methods for predicting comorbidity risks face the challenge that comorbidity prediction relying solely on data driven may lead to clinically implausible associations and reduce model interpretability. Also, how to capture the fusion features of patient and identify differences among them to facilitate risk prediction needs to be addressed. To overcome these challenges, we propose a Disease Potential-Driven Graph Attention (DP-GA) model for comorbidity risk prediction of hypertension, which has 3-fold ideas: (a) Constructing a fusion mechanism for the correlation among the patients' disease features and the structural, thus integrating feature attention and structural attention effectively; (b) Introducing a similarity-difference balance mechanism to further identify the relationships among patients; and (c) Designing a disease potential-driven attention mechanism to calculate the disease potential and construct masks, thus preserving the effective associations from high-risk patients to low-risk patients. Experimental results demonstrate that our proposed DP-GA model achieves a significant improvement in comorbidity risk prediction for patients with hypertension across three comorbidity datasets collected by the research group, compared with both the baseline and state-of-the-art peer methods. We also analyze the comorbidity network to predict the risk of hypertension comorbidity, thereby improving interpretability and early prediction of such comorbidities.
DOI: 10.3389/fdata.2026.18141572026-03-23
Edossa Merga Terefe, Merga Abdissa Aga
Vehicle insurance claim severity modeling requires accurate and interpretable methods that can handle skewed and heterogeneous loss data. This study provides a structured empirical comparison between classical parametric regression models and tree-based ensemble learning approaches for predicting claim size conditional on claim occurrence. The analysis is conducted within a cross-sectional conditional severity framework using real-world motor insurance data. We implement and compare ordinary least squares (OLS), a Tweedie generalized linear model (GLM), and three ensemble methods: bagging, random forests (RFs), and gradient boosting. Model performance is evaluated using out-of-sample root mean square error (RMSE), and variable importance measures assess the relative contribution of predictors. The results indicate that tree-based ensemble methods achieve modest improvements in predictive accuracy relative to classical parametric models. The Tweedie GLM remains a competitive, flexible parametric benchmark for skewed positive claim amounts. Variable importance analysis consistently identifies premium and insured value as key determinants of claim severity. Overall, the findings suggest that ensemble learning methods can complement traditional actuarial models, offering additional flexibility in capturing non-linear effects while maintaining comparable predictive performance in moderate-complexity severity data.
DOI: 10.3389/fdata.2026.17783632026-03-13
Sara-Jane Bittner, Michael Barz, Daniel Sonntag
Interpreting fundus images is an essential skill for detecting eye diseases, such as diabetic retinopathy (DR), one of the leading causes of visual impairment. However, the training of junior doctors relies on experienced ophthalmologists, who often lack the time for teaching, or on printed training materials that lack variability in examples. In this work, we present FunduScope, an interactive human-centered learning tool for training junior ophthalmologists, which is based on a pre-trained ML model for classifying DR. In a qualitative pre-study, we investigated the needs of junior doctors and identified gaps in recent learning procedures. In the main mixed-methods study, we examined the experience of 10 junior doctors with the tool and its impact on cognitive load, usability, and additional factors relevant to e-learning tools. Despite technical constraints our results confirm the potential of using an ML-based learning tool in medical education, addressing the time constraints of ophthalmologists, and providing learning independence for junior doctors. However, future work could extend the learning tool by using explainable artificial intelligence (XAI) to further support the clinical decision making of learners and exceeding the scope of this proof of concept to other ophthalmic diseases.
DOI: 10.3389/fdata.2026.16769222026-02-04
Arif Mahmud, Ashikur Rahman, Fahmid Al Farid, Jia Uddin, Hezerul Bin Abdul Karim
IntroductionDespite several strategies, Bangladesh has a poor rate of internet of things (IoT) deployment. This study therefore seeks to investigate the factors shaping IoT adoption for residential security in Dhaka and to analyze their respective contributions.MethodHence, this study combined two important theories, namely protection motivation theory (PMT) along with attitude-social influence-self-efficacy (ASE) in which a hybrid PLS-Machine learning approach has been used to identify both linear and nonlinear correlations with high predictive accuracy. Snowball sampling method was utilized to choose 348 valid replies from a survey of household heads. Afterward, partial least squares (PLS) followed by artificial neural networks (ANN) and machine learning (ML) classifiers were the procedures that made up the complete assessment method.ResultsThe variables that affected intention with a variance of 34.9% and accuracy of 74.28% were severity, vulnerability, response efficacy, response cost, and attitude. On the other hand, vulnerability was the most significant predictor, followed by response cost, attitude, response efficacy, self-efficacy, social influence, and severity.DiscussionThe theoretical contribution of this study lies in its novel integration of PMT and ASE models, offering new insights into their combined effect on technology adoption in emerging markets. Besides, the findings contribute to the literature by increasing the public awareness of home security that can enhance Dhaka's overall state of public order and safety. Moreover, the findings may offer valuable insights for companies and entrepreneurs, as incorporating these factors into marketing strategies and investment initiatives is likely to foster greater consumer adoption.
DOI: 10.3389/fdata.2026.17187102026-02-04
Francisco Gumucio, Lu Zhang
Long-term fairness in sequential decision-making is critical yet challenging, as decisions at each time step influence future opportunities and outcomes, potentially exacerbating existing disparities over time. While existing methods primarily achieve fairness by directly adjusting decision models, in this work, we study a complementary perspective based on sequential algorithmic recourse, in which fairness is pursued through actionable interventions for individuals. We introduce Sequential Causal Algorithmic Recourse for Fairness (SCARF), a causally grounded framework that generates temporally coherent recourse trajectories by integrating structural causal modeling with sequential generative modeling. By explicitly incorporating both short-term and long-term fairness constraints, as well as practical budget limitations, SCARF generates personalized recourse plans that effectively mitigate disparities over multiple decision cycles. Through experiments on synthetic and semi-synthetic datasets, we empirically examine how different recourse strategies influence fairness dynamics over time, illustrating the trade-offs between short-term and long-term fairness under sequential interventions. The results demonstrate that SCARF provides a practical and informative framework for analyzing long-term fairness in dynamic decision-making settings.
DOI: 10.3389/fdata.2026.17509062026-01-16
Mayuri Kate, Suresh Neethirajan
The convergence of IoT sensing, edge computing, and machine learning is revolutionizing precision livestock farming. Yet bioacoustic data streams remain underexploited due to computational-complexity and ecological-validity challenges. We present one of the most comprehensive bovine vocalization datasets to date-569 expertly curated clips spanning 48 behavioral classes, recorded across three commercial dairy farms using multi-microphone arrays and expanded to 2,900 samples through domain-informed data augmentation. This FAIR-compliant resource addresses key Big Data challenges: volume (90 h of raw recordings, 65.6 GB), variety (multi-farm, multi-zone acoustic environments), velocity (real-time processing requirements), and veracity (noise-robust feature-extraction pipelines). A modular data-processing workflow combines denoising implemented both in iZotope RX 11 for quality control and an equivalent open-source Python pipeline using noisereduce, multi-modal synchronization (audio-video alignment), and standardized feature engineering (24 acoustic descriptors via Praat, librosa, and openSMILE) to enable scalable welfare monitoring. Preliminary machine-learning benchmarks reveal distinct class-wise acoustic signatures across estrus detection, distress classification, and maternal-communication recognition. The dataset's ecological realism-embracing authentic barn acoustics rather than controlled conditions-ensures deployment-ready model development. This work establishes the foundation for animal-centered AI, where bioacoustic streams enable continuous, non-invasive welfare assessment at industrial scale. By releasing a Zenodo-hosted, FAIR-compliant dataset (restricted access) and an open-source preprocessing pipeline on GitHub, together with comprehensive metadata schemas, we advance reproducible research at the intersection of Big Data analytics, sustainable agriculture, and precision livestock management. The framework directly supports UN SDG 9, demonstrating how data science can transform traditional farming into intelligent, welfare-optimized production systems capable of meeting global food demands while maintaining ethical animal-care standards.
DOI: 10.3389/fdata.2025.17231552026-01-12
M. S. Pavithran, S. M. Vadivel
IntroductionEmployee turnover remains a significant challenge for organizations as it becomes difficult for them to retain the same employees and continue with their operations efficiently. With the assistance of predictive analytics, HR managers will be able to foresee and lower the potential turnover. Conventional research has focused on the effectiveness of technical models, yet there is a lack of studies investigating the interpretability and reliability of managerial forecasts.MethodsThis research used the Employee Attrition dataset and applied various pre-processing methods, including label encoding, feature scaling, and SMOTE for class balancing. Machine learning models were trained and optimized using grid search with stratified cross-validation. The best-performing model was calibrated using the sigmoid method to ensure the accuracy of the predicted probabilities. LIME enabled local interpretability, thus providing practical insights into individual employee attrition-related risks. Permutation feature importance analysis and SHAP summary plots helped in better understanding the model by showing the individual features that contributed to the attrition probability.ResultsThe Random Forest classifier achieved the highest AUC-ROC score of 97.37%. Risk distribution visualizations highlight employees with the highest attrition probability, and calibration is the main reason for the Brier Score reduction from 0.03873 to 0.03480.DiscussionThe study concludes that by prioritizing interventions and increasing the accuracy of retention strategies, a calibrated, interpretable, and risk-stratified model can enhance HR decision-making. This framework aids HR leaders in transitioning from reactive to proactive workforce management by leveraging data-driven insights.
DOI: 10.3389/fdata.2025.1699561