A Novel Explainable Multimodal Machine Learning Framework for Accurate Diabetes Classification Using Clinical and Behavioral Data

Mohammad Shafeeq; Monika Tripathi

doi:10.55524/ijircst.2026.14.4.3

Abstract

The worldwide health issue of diabetes mellitus is growing at an alarming rate and needs proper detection methods that can identify the disease before it leads to dangerous health outcomes. The research introduces a new machine learning system which uses multiple data sources to explain its diabetes diagnosis process by combining clinical data with patient behavioral patterns. The system applies depth wise separable convolutional technology to extract features and uses various feature types to detect both physical health risks and behavioral health risks. The system employs SHAP (Shapley Additive Explanations) which delivers both global and local model prediction explanations to assist users in understanding system operations while establishing confidence with medical experts. The proposed model is tested against baseline methods which include Logistic Regression Support Vector Machine (SVM) Random Forest and XGBoost using standard performance metrics which include accuracy precision recall F1-score and ROC-AUC. The experimental results demonstrate that the proposed framework achieves superior performance compared to all baseline models by achieving 96% accuracy 95% precision 94% recall 94% F1-score and 0.96 AUC. The model's strength and ability to differentiate between classes are validated through both confusion matrix analysis and ROC analysis. The analysis of explainability shows that multimodal data integration is essential because it shows that diabetes prediction relies on clinical glucose and BMI and insulin data and on physical activity and food choices and sleep patterns that people display. The system enables clinical decision-making through its use of multimodal data which enhances prediction accuracy while maintaining complete system visibility. The research demonstrates an AI-based system that delivers precise diabetes categorization through its intelligent healthcare analytics and customized treatment solutions which show interpretable results and expandable capabilities.

Keywords

Diabetes Classification, Machine Learning, Explainable AI, Multimodal Data, Clinical Data, Behavioral Data, SHAP.

References

O. Vershinina et al., “Explainable artificial intelligence model predicting the risk of all-cause mortality in patients with type 2 diabetes mellitus,” Frontiers in Endocrinology, vol. 16, Art. no. 1689312, Oct. 2025. Available from: https://doi.org/10.3389/fendo.2025.1689312
G. Dharmarathne et al., “Self-explainable ML interface for diabetes diagnosis,” Healthcare Analytics, vol. 5, Jun. 2024. Available from: https://doi.org/10.1016/j.health.2024.100301
Pang et al., “SHAP-based explainable ML for diabetes prediction,” Healthcare Analytics, vol. 7, Jun. 2025. Available from: https://doi.org/10.1016/j.health.2025.100390
R. Hasan et al., “Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights,” Information, vol. 16, no. 1, Art. no. 7, 2025. Available from: https://doi.org/10.3390/info16010007
Maimaitijiang, M. Aihaiti, and Y. Mamatjan, “An Explainable AI Framework for Online Diabetes Risk Prediction with a Personalized Chatbot Assistant,” Electronics, vol. 14, Art. no. 3738, 2025. Available from: https://doi.org/10.3390/electronics14183738
M. M. Islam, H. R. Rifat, M. S. B. Shahid, A. Akhter, M. A. Uddin, and K. M. M. Uddin, “Explainable Machine Learning for Efficient Diabetes Prediction Using Hyperparameter Tuning, SHAP Analysis, Partial Dependency, and LIME,” Engineering Reports, vol. 7, Art. no. e13080, 2025. Available from: https://doi.org/10.1002/eng2.13080
S. A. Tanim et al., “Explainable deep learning for Diabetes Diagnosis with (DeepNetX2),” Biomedical Signal Processing and Control, vol. 99, Jan. 2025. Available from: https://doi.org/10.1016/j.bspc.2024.106902
Rustam et al., “Enhanced detection of diabetes mellitus using novel ensemble feature engineering approach and machine learning model,” Scientific Reports, vol. 14, Art. no. 23274, Oct. 2024. Available from: https://doi.org/10.1038/s41598-024-74357-w
P. Netayawijit, W. Chansanam, and K. Sorn-In, “Interpretable Machine Learning Framework for Diabetes Prediction: Integrating SMOTE Balancing with SHAP Explainability for Clinical Decision Support,” Healthcare, vol. 13, Art. no. 2588, 2025. Available from: https://doi.org/10.3390/healthcare13202588
Barman, H. K. Choudhury, and B. Jajodia, “Interpretable machine learning for diabetes risk prediction: A large-scale analysis of Indian national survey data,” Discover Public Health, vol. 22, Art. no. 832, 2025. Available from: https://doi.org/10.1186/s12982-025-01236-8
M. Mutawa, K. Al Sabti, S. Raizada, and S. Sruthi, “Explainable AI for Diabetic Retinopathy: Utilizing YOLO Model on a Novel Dataset,” AI, vol. 6, Art. no. 301, 2025. Available from: https://doi.org/10.3390/ai6120301
Tasin et al., “Diabetes prediction using machine learning and explainable AI techniques,” Healthcare Technology Letters, vol. 10, no. 1–2, pp. 1–10, 2022. Available from: https://doi.org/10.1049/htl2.12039
Y. Huang et al., “Machine learning models predict mortality risk in diabetic neuropathy patients using MIMIC-IV data,” Scientific Reports, vol. 15, Art. no. 38702, Nov. 2025. Available from: https://doi.org/10.1038/s41598-025-22363-x
Y. Mao et al., “Value of machine learning algorithms for predicting diabetes risk: A subset analysis from a real-world retrospective cohort study,” Journal of Diabetes Investigation, vol. 14, no. 2, pp. 309–320, 2023. Available from: https://doi.org/10.1111/jdi.13937
Y. Ghazizadeh, S. Salehi, and M. Mirsaeid Ghazi, “Machine learning-based diabetes prediction: A comprehensive study on predictive modeling and risk assessment,” Journal of Clinical Images and Medical Case Reports, vol. 6, no. 5, Art. no. 3578, 2025. Available from: https://doi.org/10.52768/2766-7820/3578
Pandey and P. Gautam, “Risk of Diabetes Disease Prediction Using Machine Learning Approach,” European Journal of Cardiovascular Medicine, vol. 14, no. 6, pp. 391–399, Nov.–Dec. 2024. Available from: https://doi.org/10.5083/ejcm
V. Nguyen, Y. Choi, and H. Byeon, “An explainable hybrid deep learning model for prediabetes prediction in men aged 30 and above,” Journal of Men's Health, vol. 20, no. 10, pp. 52–72, Oct. 2024. Available from: https://doi.org/10.22514/jomh.2024.166
P. N. Srinivasu et al., “An explainable Artificial Intelligence software system for predicting diabetes,” Heliyon, vol. 10, Art. no. e36112, 2024. Available from: https://doi.org/10.1016/j.heliyon.2024.e36112
M. Chandra Sekhar, P. N. Kavitha, B. N. V. Uma Shankar, A. Aakula, and D. Boya, “MedFusionAI: A Deep Learning Framework for Multi-Modal Health Data Fusion to Predict Chronic Disease Risks,” International Journal of Computational and Experimental Science and Engineering, vol. 11, no. 2, 2025. Available from: https://doi.org/10.22399/ijcesen.2159
H. Zuberi, A. Anees, N. Anjum, A. H. Warsi, P. R. Khan, S. K. Singh, N. K. Singh, R. Singh, S. H. Abbas, and R. Ranjan, “Efficacy of structured exercise protocol on functional capacity, HbA1c, and waist-hip ratio in post-myocardial infarction subjects with diabetes mellitus,” Journal of Neonatal Surgery, vol. 14, no. 5S, pp. 396–405, 2025. Available from: https://doi.org/10.52783/jns.v14.2058
S. K. Singh, P. Verma, and P. Kumar, “Sentiment analysis using machine learning techniques on Twitter: A critical review,” Advances in Mathematics: Scientific Journal, vol. 9, no. 9, pp. 7085–7092, 2020. Available from: https://doi.org/10.37418/amsj.9.9.58
S. K. Singh, P. Verma, and P. Kumar, “Sentiment analysis of COVID-19 epidemic using machine learning algorithm on Twitter,” Journal of Critical Reviews, vol. 7, no. 18, pp. 2565–2572, 2020.
S. Joshi, P. Gupta, R. Kumar, A. Dwivedi, and S. K. Singh, “Privacy by Design: User-Centric Control in Online Photo Sharing,” in Proc. 2025 International Conference on Intelligent and Secure Engineering Solutions (CISES), Greater Noida, India, 2025, pp. 1287–1290. Available from: https://doi.org/10.1109/CISES66934.2025.11265161
M. Mishra, M. S. Hussain, and S. K. Singh, “Protecting Against Social Engineering Using Wireshark: Effective Strategies With Real-World Examples,” in Effective Strategies for Combatting Social Engineering in Cybersecurity. Hershey, PA, USA: IGI Global, 2025. Available from: https://doi.org/10.4018/979-8-3693-6665-3.CH008
Mishra, H. Dev, and S. K. Singh, “Comparative Analysis of Pre-Trained CNN and Feature Selection Algorithms for Plant Leaf Disease Identification,” in 2024 IEEE 11th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), Lucknow, India, 2024, pp. 1–7. Available from: https://doi.org/10.1109/UPCON62832.2024.10983102
G. Mishra, H. Dev, and S. K. Singh, “Evolutionary Algorithms and Deep Learning Techniques for Plant Disease Identification: A Comprehensive Review,” in V. K. Jain, O. P. Sinha, A. Verma, R. Srivastava, M. Hooda, and S. K. Sharma, Eds., Recent Advancements in Semiconductor Technologies, Lecture Notes in Electrical Engineering, vol. 1491. Singapore: Springer, 2026. Available from: https://doi.org/10.1007/978-981-95-3305-3_27
Singh, H. Agarwal, A. P. Singh, A. Kumar, S. Srivastava, and S. K. Singh, “Deep learning and red deer optimiser for automatic cardiovascular disease identification on magnetic resonance images,” Scientific Reports, 2026. Available from: https://doi.org/10.1038/s41598-026-55595-6

Cites this article as

M. Shafeeq, M. Tripathi, "A Novel Explainable Multimodal Machine Learning Framework for Accurate Diabetes Classification Using Clinical and Behavioral Data", International Journal of Innovative Research in Computer Science and Technology (IJIRCST), Vol-14, Issue-4, Page No-19-36, 2026. Available from: https://doi.org/10.55524/ijircst.2026.14.4.3

Corresponding Author

Mohammad Shafeeq

Department of Computer Science and Engineering, P K University, Shivpuri, Madhya Pradesh, India

Download Full Paper

Download PDF

No. of Downloads: 3 | No. of Views: 34

A Novel Explainable Multimodal Machine Learning Framework for Accurate Diabetes Classification Using Clinical and Behavioral Data

Citations

Total View 34

Total Download 3