Abstract

One of the most common chronic illnesses in the world, diabetes, must be identified early to avoid serious health issues and enhance patient outcomes. Reduced prediction accuracy, duplicated characteristics, and high-dimensional medical data are common problems for traditional diagnostic methods. Principal Component Analysis (PCA) and machine learning techniques are the foundation of this study's optimized early diabetic prediction system. To extract the most important characteristics from the dataset while removing unnecessary and duplicated information, PCA is used as a dimensionality reduction technique. Several machine learning classifiers, such as Random Forest, Support Vector Machine (SVM), and Decision Tree, are then trained and assessed using the altered feature set. Metrics including accuracy, precision, recall, F1-score, and confusion matrix are used to evaluate the suggested system's performance. When compared to traditional machine learning techniques without feature optimization, experimental results show that the incorporation of PCA greatly increases classification efficiency, lowers computing complexity, and improves prediction accuracy. The suggested framework supports medical professionals in prompt diagnostic and decision-making processes by offering a dependable, effective, and scalable approach for the early prediction of diabetes. The results demonstrate how well PCA, and machine learning methods work together to create sophisticated healthcare prediction systems.

References

• A. Pandey and P. Gautam, “Risk of diabetes disease prediction using machine learning approach,” European Journal of Cardiovascular Medicine, vol. 14, no. 6, 2024.
• I. Tasin, T. U. Nabil, S. Islam, and R. Khan, “Diabetes prediction using machine learning and explainable AI techniques,” Healthcare Technology Letters, pp. 1–10, 2022.
• C. C. Olisah, L. Smith, and M. Smith, “Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective,” Computer Methods and Programs in Biomedicine, vol. 220, pp. 1–12, 2022.
• H. M. Deberneh and I. Kim, “Prediction of type 2 diabetes based on machine learning algorithm,” International Journal of Environmental Research and Public Health, vol. 18, pp. 1–14, 2021.
• N. Fazakis, O. Kocsis, E. Dritsas, S. Alexiou, N. Fakotakis, and K. Moustakas, “Machine learning tools for long-term type 2 diabetes risk prediction,” IEEE Access, vol. 9, pp. 1030–1045, 2021.
• N. K. G., V. Rajesh, A. V. A. Reddy, K. Sumedh, and T. R. S. Reddy, “Prediction of diabetes using machine learning classification algorithms,” International Journal of Scientific & Technology Research, vol. 9, no. 1, 2020.
• S. P. Chatrati, G. Hossain, and A. Goyal, “Smart home health monitoring system for predicting type 2 diabetes and hypertension,” Journal of King Saud University – Computer and Information Sciences, vol. 34, no. 3, pp. 862–870, 2020.
• M. K. Hasan, M. A. Alam, D. Das, E. Hossain, and M. Hasan, “Diabetes prediction using ensembling of different machine learning classifiers,” IEEE Access, vol. 8, pp. 76516–76531, 2020.
• B. Pranto, “Evaluating machine learning methods for predicting diabetes among female patients in Bangladesh,” Information, vol. 11, pp. 1–20, 2020.
• N. Mohan and V. Jain, “Performance analysis of support vector machine in diabetes prediction,” in Proc. Int. Conf. Electronics, Communication and Aerospace Technology (ICECA), 2020, pp. 1–3.
• M. A. Sarwar, N. Kamal, W. Hamid, and M. A. Shah, “Prediction of diabetes using machine learning algorithms in healthcare,” in Proc. 24th Int. Conf. Automation & Computing, Newcastle upon Tyne, U.K., Sep. 2019.
• Q. Zou, K. Qu, Y. Luo, D. Yin, Y. Ju, and H. Tang, “Predicting diabetes mellitus with machine learning techniques,” Springer, 2018.
• I. Kavakiotis, O. Tsave, A. Salifoglou, N. Maglaveras, I. Vlahavas, and I. Chouvarda, “Machine learning and data mining methods in diabetes research,” Computational and Structural Biotechnology Journal, vol. 15, pp. 104–116, 2017.
• F. Mercaldo, V. Nardone, and A. Santone, “Diabetes mellitus affected patients classification and diagnosis through machine learning techniques,” Procedia Computer Science, vol. 112, pp. 2519–2528, 2017.
• O. S. Soliman and E. Elhamd, “Classification of diabetes mellitus using modified particle swarm optimization and least squares support vector machine,” in Proc. IEEE Int. Conf., 2014.