Application and Prediction of Machine Learning Algorithm in Predicting Diabetes Mellitus

DOI

10.2991/978-94-6463-540-9_22How to use a DOI?

Keywords

Diabetes Prediction; Machine Learning Algorithms; Random Forest; Logistic Regression; Support Vector Machines

Abstract

Diabetes mellitus (DM) is a major worldwide health problem since it is characterised by persistently elevated blood sugar levels. Predictive analysis of DM is crucial for early detection and prevention, optimal resource allocation, development of personalized treatment plans, cost reduction, and formulation of effective public health strategies. Based on data from Kaggle, this study assesses how well the algorithms Random Forest (RF), Support Vector Machines (SVM), and Logistic Regression (LR) predict diabetes. These machine learning (ML) algorithms are assessed for their accuracy, robustness, and overall utility in identifying diabetes risk factors and early detection of the disease. This paper employed these models to analyze a large dataset from Kaggle, assessing their predictive capabilities based on accuracy, sensitivity, specificity, and generalizability. The results indicated that RF outperformed other models with an Area Under The Curve (AUC) score of 0.96361, highlighting its robust predictive power. Significant predictors across all models included hemoglobin A1c (HbA1c) level, blood glucose level, age, body mass index (BMI), hypertension, and smoking history. Additionally, chronic periodontitis and lipid levels were identified as important factors influencing diabetes risk. This research emphasizes how crucial it is to use a variety of health markers when predicting DM in order to improve early diagnosis and treatment approaches, which will eventually improve patient outcomes and save healthcare expenditures.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Bingyu Ke
PY  - 2024
DA  - 2024/10/16
TI  - Application and Prediction of Machine Learning Algorithm in Predicting Diabetes Mellitus
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 191
EP  - 202
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_22
DO  - 10.2991/978-94-6463-540-9_22
ID  - Ke2024
ER  -