Perioperative medicine & outcomes
Integrating StEP-COMPAC definition and enhanced recovery after surgery status in a machine-learning-based model for postoperative pulmonary complications in laparoscopic hepatectomy
Authors' conclusion
Logistic regression was identified as the best-performing model. ERAS implementation was associated with a reduction in the number of PPCs.
Study context
- Population
- Adults undergoing laparoscopic hepatectomy at two centres, January 2015–February 2021
- Participants
- 1,022 adults
- Outcome
- PPCs (StEP-COMPAC definition); model performance by AUC
Methodological detailsmachine learning, least absolute shrinkage and selection operator (LASSO) feature selection, temporal external validation, two centres
- Machine learning
- LASSO feature selection
- Temporal external validation
- Two centres
Performance
As reported in the abstract
Model performance (AUC)
Best model: logistic regression (of 7 models); AUC, internal validation
0.745
Logistic regression AUC, temporal external validation
0.680
Further findings
Incidence of postoperative pulmonary complications (PPCs)
- Incidence of PPCs
- 8.7%
Selected predictors (LASSO, lambda.1se)
- Enhanced Recovery after Surgery (ERAS) implementation, serum gamma-glutamyl transferase, malignant tumour, total bilirubin, age-adjusted Charleston Comorbidities Index
Original publication
Integrating StEP-COMPAC definition and enhanced recovery after surgery status in a machine-learning-based model for postoperative pulmonary complications in laparoscopic hepatectomy. Anaesth Crit Care Pain Med. Published 13 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →