Perioperative medicine & outcomes
Performance and usability of pre‐operative prediction models for 30‐day peri‐operative mortality risk: a systematic review
Authors' conclusion
The SORT showed the best combination of predictive performance and clinical usability and has been externally validated in several heterogeneous cohorts.
Study context
- Population
- Non-cardiac surgical cohorts; studies of pre-operative prediction models for 30-day mortality (PubMed and Embase to December 2022)15 studies · 10 models
- Comparison
- Pre-operative prediction models for 30-day mortality
- Outcome
- Predictive performance (discrimination and calibration) and clinical usability of models predicting 30-day postoperative mortality
- Follow-up
- 30-day
Methodological detailsRisk of bias assessed with a tool for risk of bias and applicability of prediction model studies
- Risk of bias assessed with a tool for risk of bias and applicability of prediction model studies
Pooled result
As reported in the abstract
Predictive performance and clinical usability
Discrimination (c-statistic), lowest: MySurgeryRisk
0.82
Discrimination (c-statistic), highest: extreme gradient boosting machine learning model
0.96
Studies reporting calibration
6
Original publication
Performance and usability of pre‐operative prediction models for 30‐day peri‐operative mortality risk: a systematic review. Anaesthesia. Published 23 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →