Prediction of the 10-year incidence of type 2 diabetes mellitus based on advanced anthropometric indices using machine learning methods in the Iranian population
Authors' conclusion
BMI, VAI, and LAP were the best predictors of T2DM incidence.
Study context
- Population
- Participants of the Mashhad Stroke and Heart Atherosclerotic Disorder (MASHAD) study, Iranian population; anthropometric indices (Body Mass Index (BMI), Body Adiposity Index (BAI), Abdominal Volume Index (AVI), Visceral Adiposity Index (VAI), WWI, Body Roundness Index (BRI), Body Surface Area (BSA), Conicity Index (C-Index), Lipid Accumulation Product (LAP)) measured in phase I
- Participants
- 1,256 vs 5,193
- Exposure
- People with vs without diabetes mellitus in phase II of the MASHAD study
- With DMn = 1,256
- Without DMn = 5,193reference
- Outcome
- 10-year incidence of T2D predicted by anthropometric indices
- Follow-up
- 10 years (phase II)
Methodological detailslogistic regression and decision tree analysis
- Logistic regression and decision tree analysis
Main finding
As reported in the abstract
Predictors of T2D incidence
Incident rate, BMI < 21.25 kg/m² and VAI ≤ 5.9 vs higher BMI and VAI levels
0.033 vs. 0.967
Chance of diabetes for BMI > 25 kg/m² (rapidly increased), OR
2.27
Observational data: associations, not effects.
Original publication
Prediction of the 10-year incidence of type 2 diabetes mellitus based on advanced anthropometric indices using machine learning methods in the Iranian population. Diabetes Res Clin Pract. Published 25 June 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →