Perioperative medicine & outcomes
Development and validation of a machine learning-based prediction model for intraoperative hypothermia in Chinese patients undergoing gastrointestinal surgery
Authors' conclusion
This study highlights key predictors of intraoperative hypothermia and presents a reliable nomogram for risk prediction in patients undergoing gastrointestinal surgery.
Study context
- Population
- Patients undergoing gastrointestinal surgery, First Hospital of Putian City, China, January–March 2024
- Participants
- 418 patients
- Exposure
- Logistic regression (LR) vs Nomogram
- Outcome
- Intraoperative hypothermia (core temperature < 36.0 °C, deep nasal probe every 15 min)
Methodological detailssingle-centre, machine learning prediction model, nomogram
- Single-centre
- Machine learning prediction model
- Nomogram
Main finding
As reported in the abstract
Prediction of intraoperative hypothermia
| Group | AUC | Accuracy |
|---|---|---|
| LR | 0.872 | 0.808 |
| Nomogram | 0.877 | — not stated in the abstract |
AUC
LR0.872
Nomogram0.877
Accuracy
LR0.808
Nomogram— not stated in the abstract
— not stated in the abstract
Observational data: associations, not effects.
Further findings
Clinical features differing between the two groups
- Clinical features with significant differences (of 25)
- 12
Original publication
Development and validation of a machine learning-based prediction model for intraoperative hypothermia in Chinese patients undergoing gastrointestinal surgery. Perioper Med (Lond). Published 30 September 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →