The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific Calculators

Objective:. To compare the performance of the ACS NSQIP “universal” risk calculator (N-RC) to operation-specific RCs. Background:. Resources have been directed toward building operation-specific RCs because of an implicit belief that they would provide more accurate risk estimates than the N-RC. How...

Full description

Saved in:
Bibliographic Details
Main Authors: Mark E. Cohen, PhD, Yaoming Liu, PhD, Bruce L. Hall, MD, PhD, MBA, FACS, Clifford Y. Ko, MD, MS, MSHS, FACS
Format: Article
Language:English
Published: Wolters Kluwer Health 2023-12-01
Series:Annals of Surgery Open
Online Access:http://journals.lww.com/10.1097/AS9.0000000000000358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589716569980928
author Mark E. Cohen, PhD
Yaoming Liu, PhD
Bruce L. Hall, MD, PhD, MBA, FACS
Clifford Y. Ko, MD, MS, MSHS, FACS
author_facet Mark E. Cohen, PhD
Yaoming Liu, PhD
Bruce L. Hall, MD, PhD, MBA, FACS
Clifford Y. Ko, MD, MS, MSHS, FACS
author_sort Mark E. Cohen, PhD
collection DOAJ
description Objective:. To compare the performance of the ACS NSQIP “universal” risk calculator (N-RC) to operation-specific RCs. Background:. Resources have been directed toward building operation-specific RCs because of an implicit belief that they would provide more accurate risk estimates than the N-RC. However, operation-specific calculators may not provide sufficient improvements in accuracy to justify the costs in development, maintenance, and access. Methods:. For the N-RC, a cohort of 5,020,713 NSQIP patient records were randomly divided into 80% for machine learning algorithm training and 20% for validation. Operation-specific risk calculators (OS-RC) and OS-RCs with operation-specific predictors (OSP-RC) were independently developed for each of 6 operative groups (colectomy, whipple pancreatectomy, thyroidectomy, abdominal aortic aneurysm (open), hysterectomy/myomectomy, and total knee arthroplasty) and 14 outcomes using the same 80%/20% rule applied to the appropriate subsets of the 5M records. Predictive accuracy was evaluated using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), and Hosmer-Lemeshow (H-L) P values, for 13 binary outcomes, and mean squared error for the length of stay outcome. Results:. The N-RC was found to have greater AUROC (P = 0.002) and greater AUPRC (P < 0.001) compared to the OS-RC. No other statistically significant differences in accuracy, across the 3 risk calculator types, were found. There was an inverse relationship between the operation group sample size and magnitude of the difference in AUROC (r = −0.278; P = 0.014) and in AUPRC (r = −0.425; P < 0.001) between N-RC and OS-RC. The smaller the sample size, the greater the superiority of the N-RC. Conclusions:. While operation-specific RCs might be assumed to have advantages over a universal RC, their reliance on smaller datasets may reduce their ability to accurately estimate predictor effects. In the present study, this tradeoff between operation specificity and accuracy, in estimating the effects of predictor variables, favors the N-R, though the clinical impact is likely to be negligible.
format Article
id doaj-art-9f37d7cc8e3d4867933d698d0b708a3c
institution Kabale University
issn 2691-3593
language English
publishDate 2023-12-01
publisher Wolters Kluwer Health
record_format Article
series Annals of Surgery Open
spelling doaj-art-9f37d7cc8e3d4867933d698d0b708a3c2025-01-24T09:18:12ZengWolters Kluwer HealthAnnals of Surgery Open2691-35932023-12-0144e35810.1097/AS9.0000000000000358202312000-00023The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific CalculatorsMark E. Cohen, PhD0Yaoming Liu, PhD1Bruce L. Hall, MD, PhD, MBA, FACS2Clifford Y. Ko, MD, MS, MSHS, FACS3From the * Division of Research and Optimal Patient Care, American College of Surgeons, Chicago, ILFrom the * Division of Research and Optimal Patient Care, American College of Surgeons, Chicago, ILFrom the * Division of Research and Optimal Patient Care, American College of Surgeons, Chicago, ILFrom the * Division of Research and Optimal Patient Care, American College of Surgeons, Chicago, ILObjective:. To compare the performance of the ACS NSQIP “universal” risk calculator (N-RC) to operation-specific RCs. Background:. Resources have been directed toward building operation-specific RCs because of an implicit belief that they would provide more accurate risk estimates than the N-RC. However, operation-specific calculators may not provide sufficient improvements in accuracy to justify the costs in development, maintenance, and access. Methods:. For the N-RC, a cohort of 5,020,713 NSQIP patient records were randomly divided into 80% for machine learning algorithm training and 20% for validation. Operation-specific risk calculators (OS-RC) and OS-RCs with operation-specific predictors (OSP-RC) were independently developed for each of 6 operative groups (colectomy, whipple pancreatectomy, thyroidectomy, abdominal aortic aneurysm (open), hysterectomy/myomectomy, and total knee arthroplasty) and 14 outcomes using the same 80%/20% rule applied to the appropriate subsets of the 5M records. Predictive accuracy was evaluated using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), and Hosmer-Lemeshow (H-L) P values, for 13 binary outcomes, and mean squared error for the length of stay outcome. Results:. The N-RC was found to have greater AUROC (P = 0.002) and greater AUPRC (P < 0.001) compared to the OS-RC. No other statistically significant differences in accuracy, across the 3 risk calculator types, were found. There was an inverse relationship between the operation group sample size and magnitude of the difference in AUROC (r = −0.278; P = 0.014) and in AUPRC (r = −0.425; P < 0.001) between N-RC and OS-RC. The smaller the sample size, the greater the superiority of the N-RC. Conclusions:. While operation-specific RCs might be assumed to have advantages over a universal RC, their reliance on smaller datasets may reduce their ability to accurately estimate predictor effects. In the present study, this tradeoff between operation specificity and accuracy, in estimating the effects of predictor variables, favors the N-R, though the clinical impact is likely to be negligible.http://journals.lww.com/10.1097/AS9.0000000000000358
spellingShingle Mark E. Cohen, PhD
Yaoming Liu, PhD
Bruce L. Hall, MD, PhD, MBA, FACS
Clifford Y. Ko, MD, MS, MSHS, FACS
The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific Calculators
Annals of Surgery Open
title The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific Calculators
title_full The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific Calculators
title_fullStr The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific Calculators
title_full_unstemmed The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific Calculators
title_short The Accuracy of the NSQIP Universal Surgical Risk Calculator Compared to Operation-Specific Calculators
title_sort accuracy of the nsqip universal surgical risk calculator compared to operation specific calculators
url http://journals.lww.com/10.1097/AS9.0000000000000358
work_keys_str_mv AT markecohenphd theaccuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators
AT yaomingliuphd theaccuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators
AT brucelhallmdphdmbafacs theaccuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators
AT cliffordykomdmsmshsfacs theaccuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators
AT markecohenphd accuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators
AT yaomingliuphd accuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators
AT brucelhallmdphdmbafacs accuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators
AT cliffordykomdmsmshsfacs accuracyofthensqipuniversalsurgicalriskcalculatorcomparedtooperationspecificcalculators