Risk Factors Analysis and Predictive Modelling of Diabetic Neuropathy Using Machine Learning Algorithms

Aminu Abdulmajeed Mikailu, Muhammad Garba, Anas Tukur Balarabe, Anas Ahmed Sabir

Abstract


Diabetic neuropathy is a common and severe complication of diabetes mellitus, requiring early detection for effective management. This study investigated the predictive potential of machine learning algorithms—Naive Bayes, Support Vector Machine (SVM), and Decision Tree (J48)—using clinical and demographic data from 356 patients at Usmanu Danfodiyo University Teaching Hospital, Sokoto, Nigeria. The Decision Tree (J48) model demonstrated superior performance with an accuracy of 95.06%, followed by SVM (91.56%) and Naive Bayes (83.29%). Key predictive factors included poor glycemic control, duration of diabetes, family history, cardiovascular conditions, and neurological symptoms such as burning pain and muscle weakness. The findings highlight the utility of machine learning in supporting early diagnosis and individualized care. Incorporating these models into clinical practice could significantly enhance the management of diabetic neuropathy, reduce long-term complications, and optimize healthcare resources, particularly in low-resource settings.


Full Text:

PDF

References


Abdullah, M., & Abdulazeez, A. M. (2021). Comparative analysis of supervised learning algorithms for predicting diabetes disease. International Journal of Scientific & Engineering Research, 12(4), 57–66.

Ahmed, M., Baashar, Y., & Aslam, N. (2022). A hybrid SVM-ANN model for diabetes prediction. International Journal of Advanced Computer Science and Applications, 13(6), 112–120.

Akinci, B., Yener, O., Demir, T., & Yesilkaya, E. (2020). Ethnic and gender disparities in diabetic neuropathy prevalence. Diabetes & Metabolism, 46(5), 367–374.

Aliyu, U., Ahmed, S. A., & Suleiman, M. (2023). Modifiable risk factors and diabetic complications in northern Nigeria: A cross-sectional study. Nigerian Journal of Endocrinology, 18(1), 45–53.

Azeez, M. A., Olatunji, A. A., & Musa, Y. (2022). Epidemiological insights into diabetic neuropathy among African populations. Pan African Medical Journal, 42, 223.

Baldimtsi, G., et al. (2024). Age-related progression of diabetic neuropathy: Mechanisms and biomarkers. Journal of Diabetes and its Complications, 38, 108459.

Baskozos, G., et al. (2022). Machine learning analysis of pain phenotypes in diabetic peripheral neuropathy. Pain, 163(6), e750–e762.

Bhat, A. A., Khan, A., & Farooq, S. (2022). Comparative study of machine learning algorithms for diabetes prediction. International Journal of Computer Applications, 183(23), 9–14.

Bhaskar, H., Rajalakshmi, R., & Unnikrishnan, R. (2023). Correlational neural network model for type 2 diabetes prediction using breath biomarkers. IEEE Journal of Biomedical and Health Informatics, 27(1), 104–112.

Bondar, R. J., et al. (2021). Pathophysiology and diagnosis of diabetic neuropathy. Journal of Neurological Disorders, 9(2), 234–242.

Carmichael, T. R., et al. (2021). Non-invasive biomarkers for diabetic neuropathy detection. Diabetes Research and Clinical Practice, 179, 108991.

Chaudhary, S., & Tyagi, R. (2018). Mechanistic understanding of diabetes mellitus. Journal of Biomedical Sciences, 5(2), 33–41.

Dubey, S., Meena, Y. K., & Rathi, R. (2020). ANN-based model for diabetic neuropathy risk prediction. International Journal of Advanced Trends in Computer Science and Engineering, 9(3), 4101–4106.

El-Massari, A., Salem, H., & Mahfouz, A. (2022). Ontology-enhanced machine learning model for diabetes prediction. Applied Computing and Informatics, 18(1), 33–45.

Ergun, U., & Ilhan, A. (2021). Comparison of machine learning classifiers for diabetes prediction. PeerJ Computer Science, 7, e673.

Galiero, R., et al. (2023). Shared mechanisms among diabetic microvascular complications. Frontiers in Endocrinology, 14, 1054321.

Ibrahim, M. M., & Abdulazeez, A. M. (2021). Hybrid and ensemble machine learning approaches for healthcare prediction. Journal of Soft Computing and Decision Support Systems, 8(5), 23–30.

Ismail, N., & Ali, M. (2022). Global trends in diabetes prevalence and mortality. World Journal of Diabetes, 13(4), 255–263.

Jain, N., & Devendran, A. (2021). A comprehensive survey on the application of machine learning in healthcare. International Journal of Engineering Research & Technology, 10(2), 96–103.

Jijo, A., & Abdulazeez, A. M. (2021). Performance evaluation of decision tree classifiers in medical diagnosis. Asian Journal of Computer and Information Systems, 9(4), 67–74.

Khaleel, H., & Al-Bakry, R. (2023). Predictive modeling of diabetes using Pima dataset. Journal of Computer Applications, 25(3), 45–52.

Liu, H., Zhang, Q., & Wang, Y. (2022). Oxidative stress markers in diabetic neuropathy. Oxidative Medicine and Cellular Longevity, 2022, 3096129.

Nascimento, O. J., et al. (2016). Diabetic polyneuropathy: Review of pathophysiology and treatment. Arquivos de Neuro-Psiquiatria, 74(5), 366–373.

Olokoba, A. B., et al. (2012). Type 2 diabetes mellitus: A review of current trends. Oman Medical Journal, 27(4), 269–273.

Pastore, D., et al. (2022). Dyslipidemia and microvascular damage in diabetic neuropathy. Metabolism: Clinical and Experimental, 132, 155203.

Ponirakis, G., et al. (2022). Diabetic neuropathy: Epidemiology, diagnosis, and treatment. Diabetes/Metabolism Research and Reviews, 38(6), e3544.

Sadiku, M. N. O., Musa, S. M., & Omotoso, T. (2018). Data mining applications in healthcare. International Journal of Engineering Research and Advanced Technology, 4(3), 17–21.

Sanyaolu, A., Okorie, C., & Marinkovic, A. (2023). Global burden of diabetes and health inequality. Journal of Global Health Reports, 7, e2023073.

Sisodia, D., & Sisodia, D. S. (2018). Prediction of diabetes using classification algorithms. Procedia Computer Science, 132, 1578–1585.

Suryasa, W., Rodriguez-Gamez, M., & Koldoris, T. (2021). Urbanization and lifestyle shifts in global diabetes trends. Global Public Health Journal, 14(1), 22–29.

Tiwari, A. K., et al. (2008). Ensemble machine learning approach to tropical diabetic hand syndrome prediction. Journal of Clinical Bioinformatics, 1(1), 5–12.

Today Study Group. (2022). Demographic influences on type 2 diabetes outcomes. New England Journal of Medicine, 387(4), 322–333.

Wang, Y., Guo, H., & Liu, Q. (2019). Handling imbalanced datasets in diabetes prediction. Journal of Healthcare Engineering, 2019, 2356783.

Xu, Y., Wu, J., & Jin, Y. (2020). Predictive modeling for diabetic neuropathy using machine learning. BMC Medical Informatics and Decision Making, 20(1), 12.

Zhu, X., Lin, Y., & Luo, Y. (2024). Molecular mechanisms of diabetic peripheral neuropathy. Frontiers in Molecular Neuroscience, 17, 1246532


Refbacks

  • There are currently no refbacks.