2025· Proceedings of the 3rd International Conference on Data Science, Advanced Algorithms, and Intelligent Computing· pp. 274-279· 0 citations· 10 references
TL;DR
In the future, it is essential to establish a standardized validation framework, develop interpretable algorithms, integrate wearable non-invasive markers, and implement Bayesian racial modeling to promote early screening and personalized intervention, thereby revolutionizing the clinical prevention paradigm.
Abstract
: Diabetes has become a severe challenge to global public health: in 2023, there are 537 million cases worldwide (expected to rise to 783 million by 2045), with annual medical expenses exceeding $727 billion. Furthermore, 30% to 50% of patients are undiagnosed and asymptomatic, highlighting the urgent need for precise predictive models. The advantages of machine learning are significant: for instance, the random forest model combining HbA1c and FLI achieved an AUC of 0.874, while the cross-population model from the THIN database achieved an AUC ranging from 0.907 to 0.925. The integration of lifestyle data through CATBoost revealed a U-shaped risk association with sleep duration, and the accuracy of the multi-source hybrid model exceeded 98%, confirming the value of multimodal integration. However, current research faces challenges including data heterogeneity, insufficient external validation, poor interpretability of deep learning, and difficulties in multimodal integration. In the future, it is essential to establish a standardized validation framework, develop interpretable algorithms, integrate wearable non-invasive markers, and implement Bayesian racial modeling to promote early screening and personalized intervention, thereby revolutionizing the clinical prevention paradigm.
Six supervised learning models were developed and compared for diabetes prediction using a dataset and compared for diabetes prediction using a 100k patients records with eight clinical features including gender, age, hypertension, smoking history, heart disease, BMI, HbA1c level, and blood glucose level.
It is indicated that a rigorously conducted methodology and interpretability in machine learning development are crucial in creating machine learning solutions in healthcare decision support, which is the pathway to real applications in diabetes risk assessment.
T. Khan, M. Saeed, Majid Hussain et al.· Scientific Reports· 0 citations
Diabetes mellitus is a chronic metabolic disorder whose global prevalence continues to rise, creating an urgent need for scalable, low-cost tools for early risk identification. This study evaluates the effectiveness of five machine learning algorithms (Random Forest, XGBoost, Support Vector Machine [SVM], CatBoost, and TabNet) for predicting diabetes risk from routinely available clinical and lifestyle variables. Using the Pima Indians Diabetes dataset, a preprocessing pipeline was applied that included median imputation of physiologically implausible zero values, standardized (Z-score) feature scaling, Boruta-based feature selection, and class-imbalance handling through class-weight adjustment and the Synthetic Minority Oversampling Technique (SMOTE). Models were trained on an 80/20 train-test split and assessed using accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (ROC-AUC). Random Forest achieved the strongest overall performance (accuracy 0.753; F1-score 0.689; ROC-AUC 0.810), followed by CatBoost, SVM, and XGBoost, whereas TabNet performed worst with very low recall for the diabetic class. The best-performing model (Random Forest) was deployed in a lightweight Flask web application that returns a probability-based diabetes risk assessment, categorising each prediction as low, moderate, or high risk together with a tailored recommendation. The findings confirm that ensemble tree-based methods, particularly Random Forest, provide a reliable, interpretable, and deployable basis for diabetes risk screening, especially in resource-constrained settings. Key limitations include dataset homogeneity, residual class imbalance, and limited feature coverage.
T. Olayinka· FUDMA Journal of Sciences· 0 citations
Background: The increasing prevalence of Type 2 Diabetes Mellitus (T2DM), currently estimated at 462 million individuals, corresponding to 6.28% of the world’s population, highlights the critical need for effective screening strategies that leverage large-scale health surveys and clinical databases for early risk identification and intervention. Machine learning approaches applied to such data have reported near-perfect predictive accuracy such as accuracy of 0.98 on the BRFSS dataset and 0.97 on the PIDD dataset, but the reproducibility of these results under fully specified, independent pipelines remains largely untested.
Objective: T2DM is a public health challenge in which early screening can significantly improve outcomes. The objectives were (i) to develop and validate machine-learning models for diabetes risk using large, survey-based data and (ii) to evaluate reproducibility of previously reported high-performance models, while identifying interpretable risk factors suitable for deployment in screening.
Methods: We performed a cross-sectional retrospective analysis of the 2015 Behavioral Risk Factor Surveillance System (BRFSS) and the Pima Indians Diabetes Database (PIDD). Models included logistic regression, tree-based learners (e.g., XGBoost), and a ConvLSTM deep network. We systematically explored 2,240 configurations spanning preprocessing, scaling, class-imbalance remedies (e.g. SMOTE variants), and regularization. Interpretability relied on SHAP to quantify feature contributions.
Results: Attempts to reproduce a previously published KNN recipe’s near-perfect performance demonstrated significantly lower performance on BRFSS (0.69 accuracy). A similar result was obtained in ConvLSTM architecture replication on PIDD reached ~0.79 test accuracy. In BRFSS, CatBoost achieved the top AUC (0.83), while a tuned logistic regression delivered the most screening-appropriate profile (recall 0.97, AUC 0.82) with transparent coefficients and straightforward deployment. SHAP consistently ranked self-reported general health, BMI, and age as the dominant predictors. A prespecified sensitivity analysis showed the logistic regression model’s discriminative ability was largely stable when subjective or objective self-reported variables were removed individually (ΔAUC ≈ –0.02). Larger, but acceptable, degradation was observed when all self-reported features were excluded or randomly perturbed; recall remained high across scenarios.
Conclusions: There is a gap between headline results in the literature and performance achieved under fully specified and reproducible pipelines. A simple logistic regression – with excellent recall and competitive AUC – appears preferable for population screening, where transparency, robustness to reporting noise, and ease of implementation are paramount. Sensitivity checks reinforce that performance does not hinge on any single subjective domain, supporting clinical utility of logistic regression models in imperfect real-world data.
Shaked Shechter, N. Shomron· Journal of Scientific Innova...· 0 citations
Diabetes is one of the leading causes of morbidity and mortality worldwide. To avoid difficult management of the condition, there is need to predict early onset of the condition. This study investigated the application of machine learning techniques and exploratory data analysis to forecast early-onset of diabetes using the PIMA Indian dataset. Preprocessing included handling missing values and standardization, leading to the development and evaluation of 5 models which include Logistic Regression, K-Nearest Neighbors, Random Forest, Support Vector Machine, and Neural Network. Exploratory analysis identified glucose concentration, body mass index, and age as the most influential features. Random Forest achieved the highest accuracy (0.74%) while both Random Forest and Logistic Regression attained the best ROC-AUC score of 0.81%. Feature importance analysis emphasized the predictive significance of glucose and BMI, aligning with clinical knowledge of diabetes risk factors. Despite the promising results the study acknowledged limitations related to the PIMA dataset's demographic scope and the moderate complexity of neural networks, highlighting areas for future enhancement. Ethical considerations, including data privacy and algorithmic bias, were addressed to ensure responsible model development.
Abdulrahman Nasiru Sada, Eli. A. Jiya, Yahaya Muhammad Umar et al.· Journal of Science Research...· 0 citations
Background: Diabetes mellitus is a major global health burden, and its early detection is essential for preventing serious complications. Machine learning, and eXtreme Gradient Boosting (XGBoost) in particular, performs strongly on routine clinical data; however, reported results are frequently optimistic because of hold-out evaluation and data leakage, and the resulting models are often difficult to interpret.
Objective: To develop and rigorously evaluate an interpretable XGBoost model for predicting the presence of diabetes from eight routine diagnostic measurements, using an unbiased, leakage-controlled evaluation design.
Methods: An openly available dataset of 1,168 patient records (771 non-diabetic and 397 diabetic; an approximately 66:34 class imbalance) with eight clinical features was analysed. Physiologically implausible zero values were treated as missing and imputed with the median inside a processing pipeline. Model selection and performance estimation were separated using a 5×5 nested cross-validation scheme, with all preprocessing confined to the training folds to prevent data leakage. Performance was assessed on out-of-fold predictions using accuracy, sensitivity, specificity, precision, F1 score, the area under the ROC curve (ROC-AUC), and the Brier score; probability calibration was examined; and the contribution of each feature was quantified with SHapley Additive exPlanations (SHAP).
Results: The model achieved an ROC-AUC of 0.823, an accuracy of 0.769, a specificity of 0.859, a sensitivity of 0.595, a precision of 0.684, an F1 score of 0.636, and a Brier score of 0.160. The near-diagonal calibration curve and low Brier score indicated that the predicted probabilities were well calibrated and could be interpreted as reliable risk estimates. SHAP analysis identified glucose, body mass index, and age as the most influential predictors, in agreement with established clinical risk factors for diabetes.
Conclusions: Under a leakage-controlled, unbiased evaluation, XGBoost provided moderate but trustworthy discrimination together with well-calibrated probabilities for diabetes prediction, while SHAP confirmed clinically plausible predictors. The comparatively conservative performance underscores the importance of nested cross-validation over simple hold-out splits for realistic model assessment. External validation and decision-threshold or class-imbalance strategies represent promising directions for future work.
Z. Kucukakcali, I. Cicek· International Journal of Med...· 0 citations