Perioperative medicine & outcomes
Systematic development and validation of a predictive model for major postoperative complications in the Peri‐operative Quality Improvement Project ( PQIP ) dataset
Authors' conclusion
We have developed a novel complications model with good internal accuracy, re-prioritised predictor variables and identified hospital-level variation as an important, but overlooked, source of inaccuracy in existing tools.
Study context
- Population
- Patients undergoing major surgery with complete records, UK Peri-operative Quality Improvement Programme dataset
- Participants
- 24,983 included cases
- Comparison
- Novel complications model vs existing generic and specific prediction models and scores
- Outcome
- Major postoperative complications (Clavien-Dindo grade ≥ 2)
Methodological details75% train:25% test split, Least Absolute Shrinkage and Selection Operators (LASSO) predictor selection, model selection by lowest Akaike's information criterion
- 75% train:25% test split
- LASSO predictor selection
- Model selection by lowest Akaike's information criterion
Performance
As reported in the abstract
Major complications
Patients developing major complications
6389
25.6%
Original publication
Systematic development and validation of a predictive model for major postoperative complications in the Peri‐operative Quality Improvement Project ( PQIP ) dataset. Anaesthesia. Published 18 February 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →