Adaptive Kernel Probability Model (AKPM) for Interpretable and Reliable Diabetes Prediction using Clinical Diagnostic Data

Abstract

Diabetes mellitus poses a growing global health concern, particularly in low- and middle-income countries where early detection remains limited, demanding classification models that balance accuracy, interpretability, and adaptability to heterogeneous clinical data. This study proposes and evaluates the Adaptive Kernel Probability Model (AKPM), a novel nonparametric probabilistic classifier designed to enhance diabetes prediction by performing localized kernel density estimation with adaptive bandwidth selection via k-nearest neighbors. Implemented and tested on the Pima Indians Diabetes Dataset, AKPM outperformed conventional classifiers—Naïve Bayes and Gaussian Mixture Models (GMM)—across all evaluation metrics, achieving 87.5% accuracy, 83.3% precision, 76.9% recall, and an F1-score of 80.0% for the diabetic class, alongside 89.3% precision and 92.6% recall for the normal class. These results surpassed GMM (83.0% accuracy, 71.6% F1-score) and Naïve Bayes (80.0% accuracy, 66.6% F1-score), confirming AKPM’s superior capability to detect diabetic cases while minimizing false negatives. Offering transparent posterior inference and a modular design, AKPM emerges as a reliable and interpretable solution for clinical decision support systems and real-world healthcare applications.

Keywords

Adaptive kernel density estimation; probabilistic classification; diabetes risk prediction; machine learning; decision support.

Full Text:

PDF

References

K. Abnoosian, R. Farnoosh, and M. H. Behzadi, “Prediction of diabetes disease using an ensemble of machine learning multi-classifier models,” BMC Bioinformatics, vol. 24, no. 1, Art. no. 465, Sep. 2023. https://doi.org/10.1186/s12859-023-05465-z

N. W. S. Chew et al., “The global burden of metabolic disease: Data from 2000 to 2019,” Cell Metabolism, vol. 35, no. 3, pp. 414–428.e3, Mar. 2023. https://doi.org/10.1016/j.cmet.2023.02.003

C. George, J. B. Echouffo-Tcheugui, B. G. Jaar, I. G. Okpechi, and A. P. Kengne, “The need for screening, early diagnosis, and prediction of chronic kidney disease in people with diabetes in low- and middle-income countries—A review of the current literature,” BMC Medicine, vol. 20, no. 1, Art. no. 241, Aug. 2022. https://doi.org/10.1186/s12916-022-02438-6

M. D. Butt et al., “A systematic review of the economic burden of diabetes mellitus: Contrasting perspectives from high- and low-middle-income countries,” Journal of Pharmaceutical Policy and Practice, vol. 17, no. 1, Art. no. 41, Apr. 2024. https://doi.org/10.1080/20523211.2024.2322107

I. Golovaty et al., “Two decades of diabetes prevention efforts: A call to innovate and revitalize our approach to lifestyle change,” Diabetes Research and Clinical Practice, vol. 198, Art. no. 110195, Apr. 2023. https://doi.org/10.1016/j.diabres.2022.110195

S. A. Thomas et al., “Transforming global approaches to chronic disease prevention and management across the lifespan: Integrating genomics, behavior change, and digital health solutions,” Frontiers in Public Health, vol. 11, Art. no. 1248254, Oct. 2023. https://doi.org/10.3389/fpubh.2023.1248254

A. Agliata, D. Giordano, F. Bardozzo, S. Bottiglieri, A. Facchiano, and R. Tagliaferri, “Machine learning as a support for the diagnosis of type 2 diabetes,” International Journal of Molecular Sciences, vol. 24, no. 7, Art. no. 6775, Apr. 2023. https://doi.org/10.3390/ijms24076775

K. K. Patro et al., “An effective correlation-based data modeling framework for automatic diabetes prediction using machine and deep learning techniques,” BMC Bioinformatics, vol. 24, no. 1, Art. no. 488, Oct. 2023. https://doi.org/10.1186/s12859-023-05488-6

J. Feng et al., “A hybrid stacked ensemble and Kernel SHAP-based model for intelligent cardiotocography classification and interpretability,” BMC Medical Informatics and Decision Making, vol. 23, no. 1, Art. no. 278, Nov. 2023. https://doi.org/10.1186/s12911-023-02378-y

V. Adarsh, G. R. Gangadharan, U. Fiore, and P. Zanetti, “Multimodal classification of Alzheimer’s disease and mild cognitive impairment using custom MKSCDDL kernel over CNN with transparent decision-making for explainable diagnosis,” Scientific Reports, vol. 14, no. 1, Art. no. 2185, Jan. 2024. https://doi.org/10.1038/s41598-024-52185-2

M. S. Reza, R. Amin, R. Yasmin, W. Kulsum, and S. Ruhi, “Improving diabetes disease patients classification using stacking ensemble method with PIMA and local healthcare data,” Heliyon, vol. 10, no. 2, Art. no. e24536, Jan. 2024. https://doi.org/10.1016/j.heliyon.2024.e24536

S. C. Mackenzie, C. A. R. Sainsbury, and D. J. Wake, “Diabetes and artificial intelligence beyond the closed loop: A review of the landscape, promise and challenges,” Diabetologia, vol. 67, no. 2, pp. 223–235, Nov. 2023. https://doi.org/10.1007/s00125-023-06038-8

D. Wolf et al., “Self-supervised pre-training with contrastive and masked autoencoder methods for dealing with small datasets in deep learning for medical imaging,” Scientific Reports, vol. 13, no. 1, Art. no. 19019, Nov. 2023. https://doi.org/10.1038/s41598-023-46433-0

A. Altamimi et al., “An automated approach to predict diabetic patients using KNN imputation and effective data mining techniques,” BMC Medical Research Methodology, vol. 24, no. 1, Art. no. 234, Sep. 2024. https://doi.org/10.1186/s12874-024-02324-0

P. Sampath et al., “Robust diabetic prediction using ensemble machine learning models with synthetic minority over-sampling technique,” Scientific Reports, vol. 14, no. 1, Art. no. 23457, Nov. 2024. https://doi.org/10.1038/s41598-024-78519-8

M. Kiran, Y. Xie, N. Anjum, G. Ball, B. Pierscionek, and D. Russell, “Machine learning and artificial intelligence in type 2 diabetes prediction: A comprehensive 33-year bibliometric and literature analysis,” Frontiers in Digital Health, vol. 7, Art. no. 1557467, Mar. 2025. https://doi.org/10.3389/fdgth.2025.1557467

Z. Zhang, C. Yan, X. Zhang, S. L. Nyemba, and B. A. Malin, “Forecasting the future clinical events of a patient through contrastive learning,” Journal of the American Medical Informatics Association, vol. 29, no. 9, pp. 1584–1592, May 2022. https://doi.org/10.1093/jamia/ocac086

http://dx.doi.org/10.28989/avitec.v8i1.3689

Article Metrics

Abstract view: 38 times
Download     : 0   times

This work is licensed under a Creative Commons Attribution 4.0 International License.

Refbacks

• There are currently no refbacks.