Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
September 10, 2025International journal of research and scientific innovation

A Machine Learning Model for Predicting the Risk of Developing Diabetes - T2DM Using Real-World Data from Kilifi, Kenya

View Full Paper
Ask AI
Bookmark
Share

Authors

IKIsaac Mumo KailuMMMvurya MgalaFMFullgence Mwakondo

Discussion

Loading...

Member takes

Overview

Machine learning identifies risk of type 2 diabetes in low-resource settings, highlighting potential for early detection.

Key Points

  • The XGBoost model achieved a test set accuracy of 91.33%, indicating robust risk prediction for T2DM.
  • Feature selection included statistical methods and algorithm-based approaches, yielding two feature sets for training.
  • A dataset of 2,500 electronic health records was leveraged to enhance the predictive capability of the model.
  • Integrating multi-domain features with machine learning may enable targeted screening in under-resourced healthcare settings.

Cite This Study

Kailu et al. (2025) studied this question.

synapsesocial.com/papers/68c2443bb210217d647a9e31https://doi.org/10.51244/ijrsi.2025.120800026
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. 1A Risk Score Model to Support Early Identification and Prevention of Type 2 Diabetes Incorporating Social Determinants of Health2026
  2. 2Machine learning predicts diabetes risk in high-risk populations: based on the National Health and Nutrition Examination Survey database2025 · 2 citations
  3. 3Application and Challenges of Machine Learning in Prediction of Type 2 Diabetes: A Systematic Review2025
  4. 4A machine learning model for predicting obesity risk in patients with diabetes mellitus: analysis of NHANES 2007–20182025 · 2 citations
  5. 5Diabetes Disease Prediction Using Machine Learning Classification Algorithms2025