American College of Surgeons National Surgical Quality Improvement Program Surgical Risk Calculator Accuracy When Operative Risk is Represented by the Principal Current Procedural Terminology Code Versus Many Codes
Authors' conclusion
While the current RC, relying on XGB and the principal CPT code, remains a viable approach to routine surgical risk assessment, an advanced version of the RC, based on the CATB algorithm and accommodating multiple CPT codes, may provide more accurate estimates.
Study context
- Population
- Surgical patients in the American College of Surgeons National Surgical Quality Improvement Program, 2016 to 2020
- Participants
- 5,020,713 patients
- Comparison
- XGB vs CatBoost (CATB)
- Outcome
- Predictive accuracy for 13 outcomes: discrimination (AUC of ROC and precision recall curve) and calibration (Hosmer-Lemeshow statistics)
Methodological detailsregistry data, 80% training / 20% validation split, machine learning
- Registry data
- 80% training / 20% validation split
- Machine learning
Performance
As reported in the abstract
Predictive accuracy
XGB slightly worse calibration than CATB in cases with at least one code beyond the principal Current Procedural Terminology (CPT) code
34.8%
Further findings
Accuracy in patients with 4 or more CPTs (subgroup)
- CATB provided meaningfully more accurate estimates than XGB in patients with 4 or more CPTs (about 8% of all patients)
Original publication
American College of Surgeons National Surgical Quality Improvement Program Surgical Risk Calculator Accuracy When Operative Risk is Represented by the Principal Current Procedural Terminology Code Versus Many Codes. Ann Surg. Published 7 February 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →