AI Science Tracker
EN

Dynamic machine-learning model for early prediction of intraoperative hypotension using 5-minute perioperative time-series data: a multicenter retrospective study.

Department of Anesthesiology, The Second Affiliated Hospital of Fujian University of Traditional Chinese Medicine, China; Department of Anesthesiology, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University, China; Department of Pediatrics, Women & Infants Hospital of Rhode Island, Warren Alpert Medical School of Brown University, United States; Department of Anesthesiology, Fujian Maternity and Child Health Hospital College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics, Fujian Medical University, China · 30 Sep 2026 · medicine

Discovery

Dynamic machine-learning model for early prediction of intraoperative hypotension using 5-minute perioperative time-series data: a multicenter retrospective study.

Source check: Source checked. Not independent scientific confirmation.

Finding: A retrospective multicenter study developed and internally validated a dynamic model from perioperative time series in 702 adults, then tested it in an independent 248-patient cohort. Random forest predicted MAP below 65 mmHg at the next scheduled five-minute point with AUROC 0.857 internally and 0.894 externally. Prospective clinical workflow benefit remains untested.

Technology: A dynamic machine-learning model used perioperative time-series data to predict intraoperative hypotension in a multicenter retrospective cohort.

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

AI contribution
A dynamic machine-learning model used perioperative time-series data to predict intraoperative hypotension in a multicenter retrospective cohort.
Test and result
The primary abstract reports 702 development/internal-validation patients and an independent external cohort of 248. Using rolling five-minute perioperative data, random forest had internal AUROC 0.857 (95% CI 0.841–0.868), AUPRC 0.413 and Brier score 0.093; external AUROC was 0.894 (95% CI 0.875–0.907), AUPRC 0.540 and Brier score 0.092. The target was MAP below 65 mmHg at the next scheduled five-minute point. The study calls for prospective workflow evaluation.
Limitation / still unknown
An independent external cohort was evaluated, but prospective use in an anesthesia workflow and improvement in patient outcomes were not tested.
Evidence sources and annotation context

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

Evidence sources: https://doi.org/10.3389/fmed.2026.1884174

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 3/5. 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.