Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Comparative Study of Diabetes Prediction Based on Lifestyle Factors Using Machine Learning

Bruce Nguyen, Yan Zhang

TL;DR

The paper tackles diabetes risk prediction using lifestyle data from the BRFSS 2015 survey and compares three classifiers—Decision Tree, KNN, and Logistic Regression—on a balanced binary task derived from a 3-class target (no diabetes vs. prediabetes/diabetes). Feature preprocessing includes min-max normalization for numeric attributes and a dataset split of 80/20 for training and testing, with model-specific hyperparameter tuning via grid search and cross-validation. Results show Logistic Regression achieving the highest accuracy of $0.751$, followed by Decision Tree at $0.741$ and KNN at $0.721$, with LR offering the most balanced precision-recall performance. The study demonstrates the feasibility of ML-based diabetes risk stratification from lifestyle factors and points to enhancements through expanded feature sets and ensemble methods to improve predictive robustness and interpretability.

Abstract

Diabetes is a prevalent chronic disease with significant health and economic burdens worldwide. Early prediction and diagnosis can aid in effective management and prevention of complications. This study explores the use of machine learning models to predict diabetes based on lifestyle factors using data from the Behavioral Risk Factor Surveillance System (BRFSS) 2015 survey. The dataset consists of 21 lifestyle and health-related features, capturing aspects such as physical activity, diet, mental health, and socioeconomic status. Three classification models, Decision Tree, K-Nearest Neighbors (KNN), and Logistic Regression, are implemented and evaluated to determine their predictive performance. The models are trained and tested using a balanced dataset, and their performances are assessed based on accuracy, precision, recall, and F1-score. The results indicate that the Decision Tree, KNN, and Logistic Regression achieve an accuracy of 0.74, 0.72, and 0.75, respectively, with varying strengths in precision and recall. The findings highlight the potential of machine learning in diabetes prediction and suggest future improvements through feature selection and ensemble learning techniques.

A Comparative Study of Diabetes Prediction Based on Lifestyle Factors Using Machine Learning

TL;DR

The paper tackles diabetes risk prediction using lifestyle data from the BRFSS 2015 survey and compares three classifiers—Decision Tree, KNN, and Logistic Regression—on a balanced binary task derived from a 3-class target (no diabetes vs. prediabetes/diabetes). Feature preprocessing includes min-max normalization for numeric attributes and a dataset split of 80/20 for training and testing, with model-specific hyperparameter tuning via grid search and cross-validation. Results show Logistic Regression achieving the highest accuracy of , followed by Decision Tree at and KNN at , with LR offering the most balanced precision-recall performance. The study demonstrates the feasibility of ML-based diabetes risk stratification from lifestyle factors and points to enhancements through expanded feature sets and ensemble methods to improve predictive robustness and interpretability.

Abstract

Diabetes is a prevalent chronic disease with significant health and economic burdens worldwide. Early prediction and diagnosis can aid in effective management and prevention of complications. This study explores the use of machine learning models to predict diabetes based on lifestyle factors using data from the Behavioral Risk Factor Surveillance System (BRFSS) 2015 survey. The dataset consists of 21 lifestyle and health-related features, capturing aspects such as physical activity, diet, mental health, and socioeconomic status. Three classification models, Decision Tree, K-Nearest Neighbors (KNN), and Logistic Regression, are implemented and evaluated to determine their predictive performance. The models are trained and tested using a balanced dataset, and their performances are assessed based on accuracy, precision, recall, and F1-score. The results indicate that the Decision Tree, KNN, and Logistic Regression achieve an accuracy of 0.74, 0.72, and 0.75, respectively, with varying strengths in precision and recall. The findings highlight the potential of machine learning in diabetes prediction and suggest future improvements through feature selection and ensemble learning techniques.

Paper Structure

This paper contains 13 sections, 2 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Datasets and Preprocessing
  4. Methodologies
  5. Decision Tree Classification
  6. K-Nearest Neighbors (KNN)
  7. Logistic Regression
  8. Experimental Results and Discussion
  9. Decision Tree Training and Evaluation
  10. KNN Training and Evaluation
  11. Logistic Regression Training and Evaluation
  12. Model Comparison and Discussion
  13. Conclusion

Figures (2)

  • Figure 1: Decision Tree Cross Validation
  • Figure 2: KNN Cross Validation