AI Science Tracker
EN

Machine learning nominates a postpartum microRNA associated with later diabetes

Western Sydney University; University of Sydney; University of Melbourne · 23 Mar 2021 · medicine

Discovery

Machine learning nominates a postpartum microRNA associated with later diabetes

Source check: Source checked. Not independent scientific confirmation.

Finding: LASSO-based screening nominated plasma microRNAs in women with previous gestational diabetes. In a separate 82-person sample set from the same longitudinal cohort, miR-369-3p remained associated with later type 2 diabetes after adjustment and multiple-testing correction. Adding it to clinical factors raised apparent AUC from 0.83 to 0.92, with overlapping confidence intervals. The final prediction model was evaluated after marker selection in that sample; prospective clinical utility remains untested.

Technology: LASSO logistic regression; bootstrap feature selection

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

AI contribution
L1-penalized logistic regression and repeated bootstrap selection prioritize microRNAs for subsequent measurement and outcome-association analysis.
Test and result
Twenty-one-person discovery screening and separate 82-person biomarker measurements within a 103-woman longitudinal cohort.
Limitation / still unknown
Independent-cohort replication, causal microRNA function and frozen-model prospective prediction remain unestablished; final-model performance can be optimistic.
Evidence sources and annotation context

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

Evidence sources: https://link.springer.com/content/pdf/10.1007/s00125-021-05429-z.pdf

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: 21 Nov 2026. Review scope: Primary relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships checked..

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

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.