The Comparison of Diabetes Risk Prediction Accuracy Across Different Models

Jing Yang, Ruolan Zheng

2024

Abstract

The integration of machine learning technologies, particularly deep learning models, has significantly advanced disease prediction within the healthcare industry. People have begun leveraging large-scale medical data for research, combining various models aimed at enhancing the accuracy of medical disease prediction. This study focuses on diabetes, a severe disease, and employs four different machine learning algorithms: logistic regression, multilayer perceptron, support vector machine, and random forest. The author utilizes a dataset obtained through direct questionnaire surveys of patients at the Sirhaj Diabetic Hospital in Bangladesh, and conducts systematic data processing and visualization using the Python language to compare the strengths, weaknesses, and effectiveness of these four models in disease prediction. This research aims to provide more accurate and reliable tools for predicting the risk of diabetes in the healthcare field. Not only can this help doctors better understand the health status of patients, but it can also provide crucial reference for personalized treatment plans and preventive measures, thereby improving the cure rate of various major diseases.

Paper Citation

in Harvard Style

Yang J. and Zheng R. (2024). The Comparison of Diabetes Risk Prediction Accuracy Across Different Models. In Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI; ISBN 978-989-758-713-9, SciTePress, pages 697-703. DOI: 10.5220/0012968900004508

in Bibtex Style

@conference{emiti24,
author={Jing Yang and Ruolan Zheng},
title={The Comparison of Diabetes Risk Prediction Accuracy Across Different Models},
booktitle={Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI},
year={2024},
pages={697-703},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012968900004508},
isbn={978-989-758-713-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI
TI - The Comparison of Diabetes Risk Prediction Accuracy Across Different Models
SN - 978-989-758-713-9
AU - Yang J.
AU - Zheng R.
PY - 2024
SP - 697
EP - 703
DO - 10.5220/0012968900004508
PB - SciTePress