Title: Diabetes prediction using optimisation techniques with machine learning algorithms

Authors: Sanjeev Kumar; Harsh Tiwari; Mansi Jaiswal

Addresses: Department of Computer Science and Engineering, ABES Institute of Technology, Ghaziabad, India ' Department of Computer Science and Engineering, ABES Institute of Technology, Ghaziabad, India ' Department of Computer Science and Engineering, ABES Institute of Technology, Ghaziabad, India

Abstract: Diabetes is one of the most severe and widespread diseases globally. It is also the cause of many ailments, including coronary artery disease, blindness, and urinary organ disorder. In this circumstance, patients must attend a diagnostic centre to obtain their reports after consultation. A range of methods is currently used to predict diabetes and diabetic-related illnesses. A diabetes forecasting model relying on machine learning recognises diabetes and provides more accurate results using several algorithms and optimisation strategies. It generates results relying on a collection of essential dataset parameters employed to train and test machine learning algorithms. Our proposed paper aims to design a system that can more accurately estimate a patient's diabetic risk level. Models are built using feature selection strategies, hyperparameter optimisation techniques, and essential classification techniques, including random forest and support vector machine. Our proposed scheme is more accurate and better than other existing diabetic-related schemes.

Keywords: support vector machine; SVM; random forest; dataset; hyperparameter; optimisation; feature selection.

DOI: 10.1504/IJEH.2023.130515

International Journal of Electronic Healthcare, 2023 Vol.13 No.2, pp.158 - 168

Received: 20 May 2022
Accepted: 15 Jan 2023
Published online: 25 Apr 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article