Abstract | BACKGROUND: The Predictive Optimal Trees in Emergency Surgery Risk (POTTER) tool is an artificial intelligence-based calculator for the prediction of 30-day outcomes in patients undergoing emergency operations. In this study, we sought to assess the performance of POTTER in the emergency general surgery (EGS) population in particular. METHODS: All patients who underwent EGS in the 2017 American College of Surgeons NSQIP database were included. The performance of POTTER in predicting 30-day postoperative mortality, morbidity, and 18 specific complications was assessed using the c-statistic metric. As a subgroup analysis, the performance of POTTER in predicting the outcomes of patients undergoing emergency laparotomy was assessed. RESULTS: A total of 59,955 patients were included. Median age was 50 years and 51.3% were women. POTTER predicted mortality (c-statistic = 0.93) and morbidity (c-statistic = 0.83) extremely well. Among individual complications, POTTER had the highest performance in predicting septic shock (c-statistic = 0.93), respiratory failure requiring mechanical ventilation for 48 hours or longer (c-statistic = 0.92), and acute renal failure (c-statistic = 0.92). Among patients undergoing emergency laparotomy, the c-statistic performances of POTTER in predicting mortality and morbidity were 0.86 and 0.77, respectively. CONCLUSIONS: POTTER is an interpretable, accurate, and user-friendly predictor of 30-day outcomes in patients undergoing EGS. POTTER could prove useful for bedside counseling of patients and their families and for benchmarking of EGS care.
|
Authors | Majed W El Hechi, Lydia R Maurer, Jordan Levine, Daisy Zhuo, Mohamad El Moheb, George C Velmahos, Jack Dunn, Dimitris Bertsimas, Haytham Ma Kaafarani |
Journal | Journal of the American College of Surgeons
(J Am Coll Surg)
Vol. 232
Issue 6
Pg. 912-919.e1
(06 2021)
ISSN: 1879-1190 [Electronic] United States |
PMID | 33705983
(Publication Type: Journal Article, Validation Study)
|
Copyright | Copyright © 2021 American College of Surgeons. Published by Elsevier Inc. All rights reserved. |
Topics |
- Adult
- Aged
- Artificial Intelligence
- Benchmarking
(methods, statistics & numerical data)
- Databases, Factual
(statistics & numerical data)
- Decision Trees
- Emergency Service, Hospital
(statistics & numerical data)
- Emergency Treatment
(adverse effects, statistics & numerical data)
- Feasibility Studies
- Female
- Hospital Mortality
- Humans
- Laparotomy
(adverse effects, statistics & numerical data)
- Male
- Middle Aged
- Postoperative Complications
(epidemiology, etiology)
- Risk Assessment
(methods, statistics & numerical data)
- Risk Factors
|