AI Science Tracker
EN

University of Guadalajara, Health Sciences University Center, 44340, Guadalajara, Jalisco, Mexico

1 discovery from 2023

Discoveries

MIDO GDM: an innovative artificial intelligence-based prediction model for the development of gestational diabetes in Mexican women.

Source check: Source checked. Not independent scientific confirmation.

Finding: In the described evaluation, the test-set AUC was 0.8471; an independent 50-person external set (27 GDM cases, 23 controls) produced AUC 0.9308, sensitivity 85.19% and specificity 86.96%. The external sample was confirmed separate from the development cohort, but it is small. The reported model-building description also has an unclear sample-count split; do not infer population-wide calibration or clinical benefit.

Technology: An artificial neural network uses nine clinical and demographic variables, selected with machine learning, to estimate GDM risk.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
An artificial neural network uses nine clinical and demographic variables, selected with machine learning, to estimate GDM risk.
Test and result
In the described evaluation, the test-set AUC was 0.8471; an independent 50-person external set (27 GDM cases, 23 controls) produced AUC 0.9308, sensitivity 85.19% and specificity 86.96%.
Limitation / still unknown
The external sample was confirmed separate from the development cohort, but it is small. The reported model-building description also has an unclear sample-count split; do not infer population-wide calibration or clinical benefit.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.nature.com/articles/s41598-023-34126-7

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: The publisher full text describes a clinically specific Mexican gestational-diabetes risk result, with an artificial neural network using nine routinely collected variables and a separate 50-person external validation sample. The result-bearing version located is the publisher article dated 2023-04-28; exact-title/preprint searches found no earlier version. The active/archive catalogs have no same-result entry. The related genotype-informed GDM study uses a different SNP-plus-clinical model and reports distinct genetic findings, so it is related context rather than this model result. The external sample is small, and the paper does not establish improved maternal outcomes..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.