Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 5, 2026Machine Learning ResearchOpen Access

Investigation on Machine Learning Models for Predicting Diabetes Risk in Indian Populations

View Full Paper
Ask AI
Bookmark
Share

Authors

GSGajendra Singh

Discussion

Loading...

Member takes

Overview

Cross-sectional study demonstrates high predictive accuracy of gradient boosting models for diabetes risk in Indian cohorts, highlighting the value of metabolic features for early screening.

Key Points

  • To evaluate and compare the performance of seven supervised machine learning algorithms for predicting diabetes risk and to identify the primary clinical and demographic predictors.
  • Analyzed demographic, physiological, and behavioral predictors—including age, BMI, blood glucose, blood pressure, insulin, and physical activity—from a cross-sectional dataset divided into 70% training and 30% testing subsets.
  • Evaluated seven supervised algorithms (Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors, XGBoost, and Artificial Neural Network) using accuracy, precision, recall, F1-score, and AUC-ROC metrics.
  • XGBoost achieved the highest performance, with an accuracy of 89.2%, precision of 0.88, recall of 0.87, F1-score of 0.87, and an AUC-ROC of 0.93.
  • Artificial Neural Network and Random Forest also demonstrated strong discrimination, yielding accuracies of 88.5% and 87.6% and AUC-ROCs of 0.92 and 0.91, respectively.
  • Blood glucose level emerged as the most influential predictor of diabetes risk, followed by body mass index and age.

Cite This Study

Gajendra Singh (2026) studied this question.

synapsesocial.com/papers/6a9bd4346b95aff0620ebb96https://doi.org/10.11648/j.mlr.20261102.12
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine learning-based classification of diabetes mellitus using sociodemographic, behavioral, and clinical predictor2026
  2. 2Leveraging Machine Learning to Assess Risk of Type 2 Diabetes and Cardiovascular Diseases in the North Indian Cohort2026
  3. 3Comparative Analysis of Machine Learning Models for Diabetes Risk Prediction Using Clinical Health Indicators2026
  4. 4Comparative Analysis of Machine Learning Models for Diabetes Risk Prediction Using Clinical Health Indicators2026
  5. 5Machine Learning-Based Prediction of Type 2 Diabetes in Indian Population2026