AUTOMATED DIABETES DISEASE PREDICTION SYSTEM BASED ON RISK FACTORS ASSESSMENT: TAKING CHARGE OF YOUR HEALTH

(Received: 7-Sep.-2023, Revised: 4-Nov.-2023 , Accepted: 18-Nov.-2023)

Authors Nawal Sad-Houari, Hicham Reguieg, Chaimaa Bachiri, Marwa Alioua,

Keywords #ANOVA #Diabetes #Feature extraction #Machine learning #Patients #Prediction #RFE

Abstract Diabetes is one of the most common diseases worldwide and its prevalence rate continues to rise. This increase is due to factors related to nutrition and lifestyle on the one hand and to genetic factors on the other hand, thus creating a real public-health problem. Therefore, it is crucial to identify diabetes early in order to allow rapid treatment, capable of slowing down the progression of the disease. The objective of this work is to propose an automatic diabetes-prediction system based on the following machine-learning techniques: SVM, KNN, Decision Tree and Logistic Regression. Using risk factors specific to the Algerian environment, we constructed a new dataset that includes 823 patients, with 418 being diabetic and 405 being non-diabetic. In order to choose the relevant features and identify the most informative risk factors, we combined several feature-extraction methods, such as ANalysis of Variance (ANOVA) and Recursive Feature Elimination (RFE) and we used also the features proposed by the Pima Indian Diabetes Dataset (PIDD). The results of this study provided valuable information on the comparative performance of different machine-learning models in the prediction of diabetes, as well as on the importance of the selected characteristics.

References

[1] S. M. H. Mahmud et al., "Machine Learning Based Unified Framework for Diabetes Prediction," Proc. of the 2018 Int. Conf. on Big Data Engineering and Technology (BDET 2018), pp. 46–50, 2018.

[2] A. Singh, A. Dhillon, N. Kumar, M. S. Hossain, G. Muhammad and M. Kumar, "eDiaPredict: An Ensemble-based Framework for Diabetes Prediction," ACM Transactions on Multimedia Computing, Communications and Applications, vol. 17, no. 2, pp 1–26, 2021.

[3] L. Xu, J. He and Y. Hu, "Early Diabetes Risk Prediction Based on Deep Learning Methods," Proc. of the 4th Int. Conf. on Pattern Recognition and Artificial Intelligence, pp. 282-286, Yibin, China, 2021.

[4] M. Belhadj et al., "BAROMÈTRE Algérie: Enquête Nationale sur la prise en Charge des Personnes Diabétiques," Médecine des Maladies Métaboliques, vol. 13, no. 2, pp. 188-194, 2019.

[5] D. S. Sisodia and R. Agrawal, "Data Imputation-based Learning Models for Prediction of Diabetes," Proc. of the 2020 Int. Conf. on Decision Aid Sciences and Application (DASA), pp. 966-970, 2020.

[6] H. Song and S. Lee, "Implementation of Diabetes Incidence Prediction Using a Multilayer Perceptron Neural Network," Proc. of the IEEE Int. Conf. on Bioinformatics and Biomedicine, pp. 3089-3091, Houston, USA, 2021.

[7] Z. Punthakee, R. Goldenberg and P. Katz, "Definition, Classification and Diagnosis of Diabetes, Prediabetes and Metabolic Syndrome," Canadian Journal of Diabetes, vol. 42, no. 1, pp. 10-15, 2018.

[8] Y. Wei, W. Guo, B.W. Ling, Y. Dai and Q. Liu, "Both Forward Approach and Backward Approach for Performing Both Regressions and Classifications Using the Histogram Information for Predicting the Baseline Screening Scores for Performing the Prognostic of the Diabetes," Signal, Image and Video Processing, vol. 17, pp. 3803–3809, 2023.

[9] A. Al-Sideiri, Z. B. C. Cob and S. B. M. Drus, "Machine Learning Algorithms for Diabetes Prediction: A Review Paper," Proc. of the 2019 Int. Conf. on Artificial Intelligence, Robotics and Control (AIRC ’19), pp. 27–32, 2019.

[10] M. Komi, J. Li, Y. Zhai and X. Zhang, "Application of Data Mining Methods in Diabetes Prediction," Proc. of the 2017 2nd IEEE Int. Conf. on Image, Vision and Computing (ICIVC), pp. 1006-1010, Chengdu, 2017.

[11] A. H. Khan and J. E. Pessin, "Insulin Regulation of Glucose Uptake: A Complex Interplay of Intracellular Signalling Pathways," Diabetologia, vol. 45, pp. 1475–1483, 2002.

[12] S. V. Hemanth, S. Alagarsamy and T. D. Rajkumar, "Convolutional Neural Network-based Sea Lion Optimization Algorithm for the Detection and Classification of Diabetic Retinopathy," Acta Diabetologica, vol. 60, pp. 1377–1389, 2023.

[13] X. Li, M. Curiger, R. Dornberger and T. Hanne, "Optimized Computational Diabetes Prediction with Feature Selection Algorithms," Proc. of the 2023 7th Int. Conf. on Intelligent Systems, Metaheuristics and Swarm Intelligence (ISMSI ’23), pp. 36–43, DOI: 10.1145/3596947.3596948, 2023.

[14] M. M. Hassan, Z. J. Peya, S. Mollick, M. A. Billah, M. M. Hasan Shakil and A. U. Dulla, "Diabetes Prediction in Healthcare at Early Stage Using Machine Learning Approach," Proc. of the 12th Int. Conf. on Computing Communication and Networking Technologies, pp. 01- 05, Kharagpur, India, 2021.

[15] J. M. Ekoé, Z. Punthakee, T. Ransom, A. P. H. Prebtani and R. Goldenberg, "Dépistage du Diabète de Type 1 et de Type 2," Canadian Journal of Diabetes, vol. 37, pp. S373-S376, 2013.

[16] P. J. Shermila, A. Ahilan, M. Shunmugathammal and J. Marimuthu, "DEEPFIC: Food Item Classification with Calorie Calculation Using Dragonfly Deep Learning Network," Signal, Image and Video Processing, vol. 17, pp. 3731–3739, 2023.

[17] S. Brahimi and Y. F. Drioua, Etude Rétrospective des Facteurs de Risques du Diabète au Niveau de l’EPSP EsSenia, M.Sc Thesis, University of Science and Technology of Oran Mohamed Boudiaf, USTO-MB oran, Algeria, 2021.

[18] F. Zafar et al., "Predictive Analytics in Healthcare for Diabetes Prediction," Proc. of the 2019 9th Int. Conf. on Biomedical Engineering and Technology (ICBET’ 19), pp. 253–259, 2019.

[19] S. Mahajan, P. K. Sarangi, A. K. Sahoo and M. Rohra, "Diabetes Mellitus Prediction Using Supervised Machine Learning Techniques," Proc. of the 2023 Int. Conf. on Advancement in Computation and Computer Technologies, pp. 587-592, Gharuan, India, 2023.

[20] M. van der Schaar et al., "How Artificial Intelligence and Machine Learning Can Help Healthcare Systems Respond to COVID-19," Machine Learning, vol. 110, no. 1, pp. 1–14, 2021.

[21] M. H. Arnold, "Teasing out Artificial Intelligence in Medicine: An Ethical Critique of Artificial Intelligence and Machine Learning in Medicine," Journal of Bioethical Inquiry, vol. 18, no. 1, pp. 121–139, 2021.

[22] F. Ali et al., "An Intelligent Healthcare Monitoring Framework Using Wearable Sensors and Social Networking Data," Future Generation Computer Systems, vol. 114, pp. 23–43, 2021.

[23] P. Whig, K. Gupta, N. Jiwani, H. Jupalle, S. Kouser and N. Alam, "A Novel Method for Diabetes Classification and Prediction with Pycaret," Microsystem Technologies, vol. 29, pp. 1479-1487, 2023.

[24] B. Karaagac, K. M. Owolabi and E. Pindza, "A Computational Technique for the Caputo Fractal- fractional Diabetes Mellitus Model without Genetic Factors," Int. Journal of Dynamics and Control, vol. 11, pp. 2161–2178, 2023.

[25] E. Daniel, J. Johnson, U. A. Victor, G. V. Aditya and S. A. Sibby, "An Efficient Diabetes Prediction Model Using Machine Learning," Proc. of the 4th Int. Conf. on Electronics and Sustainable Communication Systems, pp. 1202-1208, Coimbatore, India, 2023.

[26] D. N. Katsarou et al., "Short Term Glucose Prediction in Patients with Type 1 Diabetes Mellitus," Proc. of the 44th Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, pp. 329-332, Glasgow, Scotland, United Kingdom, 2022.

[27] W. Gu, Z. Zhou, Y. Zhou, M. He, H. Zou and L. Zhang, "Predicting Blood Glucose Dynamics with Multi-time-series Deep Learning," Proc. the 15th ACM Conf. on Embedded Network Sensor Systems, pp. 1-2, DOI: 10.1145/3131672.3136965, 2017.

[28] T. Zhu, K. Li, P. Herrero, J. Chen and P. Georgiou, "A Deep Learning Algorithm For Personalized Blood Glucose Prediction," Proc. of the 27th Int. Joint Conf. on Artificial Intelligence and the 23rd European Conf. on Artificial Intelligence, pp. 1-5, 2018.

[29] A. Yahyaoui, A. Jamil, J. Rasheed and M. Yesiltepe, "A Decision Support System for Diabetes Prediction Using Machine Learning and Deep Learning Techniques," Proc. of the 1st Inte. Informatics and Software Engineering Conf. (UBMYK), pp. 1-4, Ankara, Turkey, 2019.

[30] C. Fiarni, E. M. Sipayung and S. Maemunah, "Analysis and Prediction of Diabetes Complication Disease Using Data Mining Algorithm," Procedia Computer Science, vol. 161, pp. 449–457, 2019.

[31] A. Mujumdar and V. Vaidehi, "Diabetes Prediction Using Machine Learning Algorithms," Procedia Computer Science, vol. 165, pp. 292-299, 2019.

[32] P. B. M. Kumar et al., "Type 2: Diabetes Mellitus Prediction Using Deep Neural Networks classifier," Int. Journal of Cognitive Computing in Engineering, vol. 1, pp. 55-61, 2020.

[33] Himanshi, A. Agarwal, Sidharth and K. Middha, "Prediction of Diabetes Using Machine Learning Algorithms," Int. Research Journal of Modernization in Engineering Technology and Science, vol. 3, no. 12, pp. 1778-1782, 2021.

[34] R. Cheheltani et al., "Predicting Misdiagnosed Adult-onset Type 1 Diabetes Using Machine Learning," Diabetes Research and Clinical Practice, vol. 191, p. 110029, 2022.

[35] A. E. Evwiekpaefe and N. Abdulkadir, "A Predictive Model for Diabetes Mellitus Using Machine Learning Techniques (A Study in Nigeria)," The African Journal of Information Systems, vol. 15, no. 1, pp. 1-21, 2023.

[36] Y. Su, C. Huang, W. Yin, X. Lyu, L. Ma and Z. Tao, "Diabetes Mellitus Risk Prediction Using Age Adaptation Models," Biomedical Signal Processing and Control, vol. 80, p. 104381, 2023.

[37] S. C. Gupta and N. Goel, "Predictive Modeling and Analytics for Diabetes Using Hyper-parameter Tuned Machine Learning Techniques," Procedia Computer Science, vol. 218, pp. 1257–1269, 2023.

[38] H. M. Deberneh and I. Kim, "Prediction of Type 2 Diabetes Based on Machine Learning Algorithm," Int. Journal of Environmental Research and Public Health, vol. 18, no. 6, 2021.

[39] H. El Massari, Z. Sabouri, S. Mhammedi and N. Gherabi, "Diabetes Prediction Using Machine Learning Algorithms and Ontology," J. of ICT Standardization, vol. 10, no. 02, pp. 319–338, 2022.

[40] A. Mujumdar and V. Vaidehi, "Diabetes Prediction Using Machine Learning Algorithms," Procedia Computer Science, vol. 165, pp. 292–299, 2019.

[41] H. EL Massari, S. Mhammedi, Z. Sabouri and N. Gherabi, "Ontology-based Machine Learning to Predict Diabetes Patients," Proc. of the Int. Conf. on Information, Communication and Cybersecurity (ICI2C 2021), pp. 437–445, DOI: 10.1007/978-3-030-91738-8_40, 2022.

[42] N. Yuvaraj and K. R. SriPreethaa, "Diabetes Prediction in Healthcare Systems Using Machine Learning Algorithms on Hadoop Cluster," Cluster Computing, vol. 22, no. 1, pp. 1–9, 2019.

[43] M. Kumar et al., "Population-centric Risk Prediction Modeling for Gestational Diabetes Mellitus: A Machine Learning Approach," Diabetes Research and Clinical Practice, vol. 185, no. 01, pp. 01-11, 2022.

[44] M. Kumar et al., "Machine Learning-derived Prenatal Predictive Risk Model to Guide Intervention and Prevent the Progression of Gestational Diabetes Mellitus to Type 2 Diabetes: Prediction Model Development Study," JMIR Diabetes, vol. 07, no. 03, pp. 01-12, 2022.