Perioperative medicine & outcomes
ACS NSQIP Risk Calculator Performance Across Multiple Domains of Operative Risk and Risk-associated Features
Authors' conclusion
Regardless of a patient population's position on the risk spectrum, the RC provides valuable information with excellent calibration and good discrimination.
Study context
- Population
- ACS-NSQIP patients 2021–2024, partitioned into 21 subsets by combinations of risk, age ≥ 75, ASA class 3, 4, or 5, totally dependent functional status, emergent, and laparotomy or total colectomy operative group21 subsets
- Participants
- 1,085,707 patients
- Exposure
- XGB vs CATB
- Outcome
- Calibration (absolute percentage error; APE) and discrimination (AUC) for mortality and morbidity outcomes
Methodological detailsrisk calculator validation, 21 high-risk subsets
- Risk calculator validation
- 21 high-risk subsets
Main finding
As reported in the abstract
Calibration and discrimination across the 21 subsets
- Calibration always excellent for both XGB and CATB (APE<10%)
- With few exceptions, discrimination at least good for both XGB and CATB (AUC>0.7)
Observational data: associations, not effects.
Further findings
Observed outcome rates across the 21 subsets
- Observed mortality range
- 0.04% to 60.01%
- Observed morbidity range
- 3.33% to 59.17%
Original publication
ACS NSQIP Risk Calculator Performance Across Multiple Domains of Operative Risk and Risk-associated Features. Ann Surg. Published 13 May 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →