Machine learning-based integrated identification of predictive combined diagnostic biomarkers for endometriosis
Source check: Source checked. Not independent scientific confirmation.
Finding: Transcriptomic machine-learning analyses nominated five genes as candidate endometriosis diagnostic biomarkers. A five-gene model reached AUC 0.836 in a test dataset, with checks on additional public datasets. This is dataset-level biomarker evidence rather than a demonstrated clinical diagnostic intervention.
Technology: Methods apply multiple learned feature-selection and classification algorithms to transcriptomic data to identify endometriosis-associated diagnostic genes.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Methods apply multiple learned feature-selection and classification algorithms to transcriptomic data to identify endometriosis-associated diagnostic genes.
- Test and result
- Eleven algorithms were evaluated; candidate genes FOS, EPHX1, DLGAP5, PCSK5 and ADAT1 were assessed using dataset checks.
- Limitation / still unknown
- Retrospective public expression datasets; clinical diagnostic utility was not demonstrated.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2023.1290036/full
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary full text, including Methods and Results; primary publication record or first result-bearing version 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 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.