Development and validation of a model using routine clinical features to improve diabetes diagnosis.
Machine-learning models can identify which people need glucose tolerance tests using routine lab values and vital signs.
This diagnostic model development and validation study examined development and validation of a model using routine clinical features to improve diabetes diagnosis. The abstract reports that machine-learning models can improve the detection of individuals who would need OGTT assessment to diagnose diabetes using standard nonfasting laboratory values and vital signs with and without FPG.
What the study was
- Study design
- Diagnostic model development and validation study
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- Journal of the Endocrine Society
Why it surfaced
Diagnostic model development and validation study relevant to CBC-based diagnostics and machine learning in hematology; AI/ML in clinical diagnostics and imaging; Cardiovascular-metabolic: GLP-1, SGLT2, cardiometabolic risk; score assigned conservatively from the PubMed abstract and metadata.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.