Deep-learning models show limited external performance for preterm-birth prediction from cervical ultrasound
Source check: Source checked. Not independent scientific confirmation.
Finding: The study reports internal evaluation and external evaluation on a separate ultrasound machine; the external AUC was 0.52. External discrimination was modest; clinical usefulness and improved pregnancy outcomes are not established. Prospective sample collection does not establish prospective evaluation of a locked model.
Technology: Vision Transformer models analyzed mid-trimester cervical ultrasound images to predict spontaneous preterm birth.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Vision Transformer models analyzed mid-trimester cervical ultrasound images to predict spontaneous preterm birth.
- Test and result
- The study reports internal evaluation and external evaluation on a separate ultrasound machine; the external AUC was 0.52.
- Limitation / still unknown
- External discrimination was modest; clinical usefulness and improved pregnancy outcomes are not established. Prospective sample collection does not establish prospective evaluation of a locked model.
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/s41598-026-73548-x
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 result-bearing material for the stated method, result and evaluation, with bibliographic version information..
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.