Diabetes Prediction System Using Machine Learning

Abstract

Healthcare is one of the most significant application domains of Machine Learning, where early disease prediction can help improve patient outcomes and support clinical decision-making. This dissertation presents a Diabetes Prediction and Analysis System Using Machine Learning that predicts the likelihood of a disease based on various patient health parameters and medical records. The system utilizes a healthcare dataset containing attributes such as glucose level, blood pressure, body mass index (BMI), insulin level, age, and other relevant medical factors. The collected data is pre-processed through missing value handling, feature normalization, and data partitioning to enhance prediction performance. Multiple Machine Learning algorithms, including Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Decision Tree, and Random Forest, are employed to develop predictive models. The performance of these models is evaluated using metrics such as accuracy, precision, recall, F1-score, and confusion matrix. Comparative analysis is carried out to identify the most suitable algorithm for disease prediction. The implementation of the proposed system is carried out in MATLAB, utilizing its Machine Learning and data analysis tools for model training, testing, performance evaluation, and result visualization. Experimental results demonstrate that Machine Learning techniques can effectively predict disease occurrence with high accuracy, thereby assisting healthcare professionals in early diagnosis and treatment planning. The proposed system provides an efficient and reliable approach for disease prediction and analysis, contributing to improved healthcare management and decision support.

Introduction

The text presents a Machine Learning-based Diabetes Prediction and Analysis System designed to support early detection of diabetes and assist healthcare professionals in decision-making. Traditional disease diagnosis mainly depends on doctors’ expertise and laboratory reports, which may be affected by human error, limited resources, and accessibility issues. The integration of Artificial Intelligence (AI) and Machine Learning (ML) enables automated disease prediction by analyzing large volumes of patient health data and identifying hidden patterns.

The proposed system predicts diabetes using patient health parameters such as glucose level, BMI, blood pressure, insulin level, age, and number of pregnancies. Three machine learning algorithms—Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Decision Tree—are implemented and compared to determine the most effective prediction model.

Machine learning plays an important role in healthcare by enabling systems to learn from historical medical datasets and predict diseases without explicit programming. Common algorithms used in healthcare prediction include SVM, Decision Tree, Random Forest, Logistic Regression, KNN, Naïve Bayes, and Artificial Neural Networks. These models are evaluated using performance measures such as accuracy, precision, recall, sensitivity, and specificity.

The literature review highlights various AI-based healthcare systems developed for predicting diseases such as diabetes, heart disease, kidney disease, and liver disease. Previous studies have demonstrated that ML algorithms, deep learning models, and IoT-enabled healthcare systems can improve diagnostic accuracy and provide remote healthcare support.

The proposed diabetes prediction system is developed using MATLAB and follows several stages:

1. Dataset Collection – The system uses the PIMA Indian Diabetes Dataset, containing medical attributes such as pregnancies, glucose, blood pressure, insulin, BMI, diabetes pedigree function, age, and diabetes outcome.
2. Data Preprocessing – Missing values are handled, features are normalized using Z-score normalization, and data quality is improved.
3. Dataset Splitting – The dataset is divided into 80% training data and 20% testing data.
4. Model Training – SVM, KNN, and Decision Tree algorithms are trained using patient health information.
5. Prediction and Evaluation – Models are tested using confusion matrices and performance comparison graphs to identify the most accurate algorithm.
6. New Patient Prediction – The selected model can predict whether a new patient is diabetic or non-diabetic.

Conclusion

This chapter presented the implementation and results of the proposed AI-based diabetes disease prediction system using machine learning algorithms in MATLAB. The system was trained and tested using the diabetes dataset and evaluated using accuracy analysis and confusion matrices. Experimental results showed that the Support Vector Machine classifier achieved better prediction accuracy compared to KNN and Decision Tree algorithms. The proposed system demonstrates the effectiveness of machine learning techniques for intelligent healthcare applications and disease prediction systems.

References

[1] P. Gandhi and S. Gayathri, “Diabetes Prediction Using Machine Learning Techniques,” International Journal of Research Publication and Reviews, vol. 3, no. 2, pp. 77-82, 2022. [2] M. Manimekalai, S. Divya, “Prediction of Diabetes using Artificial Neural Network Classification Technique”, in Journal of Emerging Technology and Innovative Research, vol. 6, issue 6, 2019, pp. 9-13. [3] N. Samer and S. Naser, “Diabetes Prediction Using Artificial Neural Network”, International Journal of Advanced Science and Technology, vol.124 , pp. 1-10, 2018. [4] K. S. Charan and K. S. Mahendranath, “Heart Disease Prediction Using Random Forest Algorithm,” International Research Journal of Engineering and Technology, vol. 9, no. 3, pp. 1191-1194, 2022. [5] V. Chaurasia and S. Pal, ““Early Prediction of Heart Diseases Using Data Mining Techniques,” Caribbean Journal of Science and Technology, vol. 1, pp. 208-217, 2013. [6] R. Detrano et al., “International Application of a New Probability Algorithm Algorithm for the Diagnosis of Coronary Artery Disease ,” American Journal of Cardiology, vol. 64 no. 5, pp. 304–310, 1989. [7] S. Reshma, S. Shaji, A. Janisha “Chronic Kidney Disease Prediction Using Machine Learning,” International Journal of Engineering Research and Technology, vol. 9, no. 7, pp. 137-140, 2020. [8] M. Komi, Jun Li, Yongxin Zhai and Xianguo Zhang, \"Application of data mining methods in diabetes prediction,\" 2017 2nd International Conference on Image, Vision and Computing (ICIVC), Chengdu, 2017, pp. 1006-1010, doi: 10.1109/ICIVC.2017.7984706.. [9] T. Mohanapriya, M. Priyadarshini, H. Sirajudeen and N. Angayarkanni “Liver Disease Prediction Using Classification Techniques,” International Journal of Computer Science and Information Technologies, vol. 15, no. 3, pp. 19–22, 2024. [10] Velu, S.R., Ravi, V. & Tabianan, K. Data mining in predicting liver patients using classification model.Disease Diagnosis”, Health Technol 12, 1211–1235 (2022). https://doi.org/10.1007/s12553-022-00713-3 [11] M. Chen, Y. Hao, K. Hwang, L. Wang, and L. Wang, “Disease Prediction by Machine Learning over Big Data from Healthcare Communities,” IEEE Access, vol. 5, pp. 8869– 8879, 2017. [12] J. Jiang et al., “Artificial Intelligence in Healthcare: Past, Present and Future”, Stroke and Vascular Neurology, vol. 2, no. 4, pp. 230–243, 2017. [13] B. J. Sunday et al., “A Comparative Study of Machine Learning Algorithms for Predictive Health care Systems,” International Journal of Engineering and Information Systems, vol. 9, no. 5, pp. 82-877, 2025. [14] L. P. Sharan et al., “Disease Prediction Using Machine Learning Algorithms,” International Journal of Advance Research in Science Communication and Technology , vol. 3, no. 1, pp. 5-12, 2023. [15] K. A. Parane, N. C. Patil, S. R. Poojara and T. S. Kamble, \"Cloud based Intelligent Healthcare Monitoring System,\" 2014 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), Ghaziabad, India, 2014, pp. 697-701, doi: 10.1109/ICICICT.2014.6781365. [16] B. Godi, S. Viswanadham, A. S. Muttipati, O. P. Samantray and S. R. Gadiraju, \"EHealthcare Monitoring System using IoT with Machine Learning Approaches,\" 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA), Gunupur, India, 2020, pp. 1-5, doi: 10.1109/ICCSEA49143.2020.9132937.. [17] D. Tomar and S. Agarwal, “A Survey on Data Mining Approaches for Healthcare,” International Journal of Bio-Technology, vol. 5, pp. 241-266, 2013. [18] S. A. Tanim et al, “Explainable deep learning for diabetes diagnosis with DeepNetX2,” Biomedical Signal Processing and Control, Springer Nature, vol. 99, 106902, ISSN 17468094, 2025.

Copyright

Copyright © 2026 Sunidhi ., Mr. Rahul, Mr. Parmod Kumar, Mr. Upasna Setia. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.