Detecting cardiomyopathies in pregnancy and the postpartum period with an electrocardiogram-based deep learning model
Source check: Source checked. Not independent scientific confirmation.
Finding: Among 1,807 women, the model’s AUC was 0.92 for LVEF ≤35%, 0.89 for <45%, and 0.87 for <50%; the strict-threshold AUC exceeded natriuretic peptide and clinical-variable comparators. The primary study includes 1,807 Mayo Clinic-system women with ECG and echocardiography; the model was evaluated against LVEF-defined cardiomyopathy and compared with biomarkers and a multivariable clinical model. Retrospective diagnostic evidence, not prospective outcome benefit.
Technology: An ECG-based deep-learning model screened for cardiomyopathy in pregnant and postpartum women using 12-lead ECGs.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- An ECG-based deep-learning model screened for cardiomyopathy in pregnant and postpartum women using 12-lead ECGs.
- Test and result
- Among 1,807 women, the model’s AUC was 0.92 for LVEF ≤35%, 0.89 for <45%, and 0.87 for <50%; the strict-threshold AUC exceeded natriuretic peptide and clinical-variable comparators.
- Limitation / still unknown
- The primary study includes 1,807 Mayo Clinic-system women with ECG and echocardiography; the model was evaluated against LVEF-defined cardiomyopathy and compared with biomarkers and a multivariable clinical model. Retrospective diagnostic evidence, not prospective outcome benefit.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8715757/
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: Primary source full text Methods and Results; version/date checked against bibliographic record..
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.