Construction and comparison of preeclampsia prediction models using logistic regression and machine learning.
Source check: Source checked. Not independent scientific confirmation.
Finding: primary Methods/Results document the AI-enabled result, evaluation and bounded interpretation. The result is reported in the BMC Medical Informatics and Decision Making. It does not establish generalization beyond the reported setting or prospective real-world benefit.
Technology: Logistic regression, support-vector machine, random-forest and extreme-gradient-boosting classifiers used clinical and placental-ultrasound predictors for preeclampsia; random forest had the highest AUC and logistic regression the best calibration.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Logistic regression, support-vector machine, random-forest and extreme-gradient-boosting classifiers used clinical and placental-ultrasound predictors for preeclampsia; random forest had the highest AUC and logistic regression the best calibration.
- Test and result
- In a retrospective cohort of 404 pregnant women (45 with preeclampsia), four classifiers were internally evaluated. Random forest had the highest AUC (0.781), while logistic regression had the best out-of-fold calibration (Brier 0.090). The single-center cohort and event count limit generalization; external validation is still needed.
- Limitation / still unknown
- Independent replication and prospective real-world benefit are not established in the reviewed study.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://link.springer.com/article/10.1186/s12911-026-03412-5
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 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.