Classification of Diabetes using Multilayer Perceptron
S. Sivasankari, J. Surendiran, N. Yuvaraj, M. Ramkumar, C.N. Ravi, R.G. Vidhya
Abstract
The breakthroughs in public healthcare infrastructure have resulted in a large influx of highly sensitive and critical healthcare information. The application of sophisticated data analysis techniques can aid in the early detection and prevention of a variety of fatal diseases. Diabetes can cause heart disease, renal disease, and nerve damage, all of which are life-threatening complications of the disease. The goal of this work is to identify, detect, and forecast the emergence of diabetes in its earliest stages by employing machine learning techniques and algorithms. When it comes to diabetes classification, an MLP is used. The experimental evaluation was carried out using the PIMA Indian Diabetes dataset. According to the study findings, MLP outperforms the competition in terms of accuracy, with an accuracy rate of 86.08%. Following this, a comparison of the suggested technique with the existing state of the art is carried out, proving the flexibility of the proposed approach to a wide range of public healthcare applications.