Validation of the artificial intelligence-based trauma outcomes predictor (TOP) in patients 65 years and older.
Journal
Surgery
ISSN: 1532-7361
Titre abrégé: Surgery
Pays: United States
ID NLM: 0417347
Informations de publication
Date de publication:
06 2022
06 2022
Historique:
received:
17
06
2021
revised:
22
10
2021
accepted:
16
11
2021
pubmed:
28
12
2021
medline:
1
6
2022
entrez:
27
12
2021
Statut:
ppublish
Résumé
The Trauma Outcomes Predictor tool was recently derived using a machine learning methodology called optimal classification trees and validated for prediction of outcomes in trauma patients. The Trauma Outcomes Predictor is available as an interactive smartphone application. In this study, we sought to assess the performance of the Trauma Outcomes Predictor in the elderly trauma patient. All patients aged 65 years and older in the American College of Surgeons-Trauma Quality Improvement Program 2017 database were included. The performance of the Trauma Outcomes Predictor in predicting in-hospital mortality and combined and specific morbidity based on incidence of 9 specific in-hospital complications was assessed using the c-statistic methodology, with planned subanalyses for patients 65 to 74, 75 to 84, and 85+ years. A total of 260,505 patients were included. Median age was 77 (71-84) years, 57% were women, and 98.8% had a blunt mechanism of injury. The Trauma Outcomes Predictor accurately predicted mortality in all patients, with excellent performance for penetrating trauma (c-statistic: 0.92) and good performance for blunt trauma (c-statistic: 0.83). Its best performance was in patients 65 to 74 years (c-statistic: blunt 0.86, penetrating 0.93). Among blunt trauma patients, the Trauma Outcomes Predictor had the best discrimination for predicting acute respiratory distress syndrome (c-statistic 0.75) and cardiac arrest requiring cardiopulmonary resuscitation (c-statistic 0.75). Among penetrating trauma patients, the Trauma Outcomes Predictor had the best discrimination for deep and organ space surgical site infections (c-statistics 0.95 and 0.84, respectively). The Trauma Outcomes Predictor is a novel, interpretable, and highly accurate predictor of in-hospital mortality in the elderly trauma patient up to age 85 years. The Trauma Outcomes Predictor could prove useful for bedside counseling of elderly patients and their families and for benchmarking the quality of geriatric trauma care.
Sections du résumé
BACKGROUND
The Trauma Outcomes Predictor tool was recently derived using a machine learning methodology called optimal classification trees and validated for prediction of outcomes in trauma patients. The Trauma Outcomes Predictor is available as an interactive smartphone application. In this study, we sought to assess the performance of the Trauma Outcomes Predictor in the elderly trauma patient.
METHODS
All patients aged 65 years and older in the American College of Surgeons-Trauma Quality Improvement Program 2017 database were included. The performance of the Trauma Outcomes Predictor in predicting in-hospital mortality and combined and specific morbidity based on incidence of 9 specific in-hospital complications was assessed using the c-statistic methodology, with planned subanalyses for patients 65 to 74, 75 to 84, and 85+ years.
RESULTS
A total of 260,505 patients were included. Median age was 77 (71-84) years, 57% were women, and 98.8% had a blunt mechanism of injury. The Trauma Outcomes Predictor accurately predicted mortality in all patients, with excellent performance for penetrating trauma (c-statistic: 0.92) and good performance for blunt trauma (c-statistic: 0.83). Its best performance was in patients 65 to 74 years (c-statistic: blunt 0.86, penetrating 0.93). Among blunt trauma patients, the Trauma Outcomes Predictor had the best discrimination for predicting acute respiratory distress syndrome (c-statistic 0.75) and cardiac arrest requiring cardiopulmonary resuscitation (c-statistic 0.75). Among penetrating trauma patients, the Trauma Outcomes Predictor had the best discrimination for deep and organ space surgical site infections (c-statistics 0.95 and 0.84, respectively).
CONCLUSION
The Trauma Outcomes Predictor is a novel, interpretable, and highly accurate predictor of in-hospital mortality in the elderly trauma patient up to age 85 years. The Trauma Outcomes Predictor could prove useful for bedside counseling of elderly patients and their families and for benchmarking the quality of geriatric trauma care.
Identifiants
pubmed: 34955288
pii: S0039-6060(21)01154-5
doi: 10.1016/j.surg.2021.11.016
pmc: PMC9131296
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1687-1694Informations de copyright
Copyright © 2021 Elsevier Inc. All rights reserved.
Références
J Palliat Med. 2015 Aug;18(8):677-81
pubmed: 25974408
PLoS One. 2018 Dec 18;13(12):e0209099
pubmed: 30562397
Injury. 2016 Sep;47(9):1955-9
pubmed: 27346422
JAMA Intern Med. 2015 Dec;175(12):1986-8
pubmed: 26502331
Ann Surg. 2018 Oct;268(4):574-583
pubmed: 30124479
Br J Surg. 1998 Mar;85(3):379-84
pubmed: 9529498
ScientificWorldJournal. 2001 Aug 08;1:323-36
pubmed: 12806071
Am J Surg. 2016 Jul;212(1):109-15
pubmed: 26414690
J Trauma Acute Care Surg. 2017 Jul;83(1):90-96
pubmed: 28422904
J Trauma Acute Care Surg. 2021 Jul 1;91(1):93-99
pubmed: 33755641
Radiology. 1982 Apr;143(1):29-36
pubmed: 7063747
N Engl J Med. 2017 Jun 29;376(26):2507-2509
pubmed: 28657867
JAMA Intern Med. 2015 Apr;175(4):549-56
pubmed: 25642797
J Gerontol A Biol Sci Med Sci. 2018 Nov 10;73(12):1653-1660
pubmed: 29408961
J Trauma. 1987 Apr;27(4):370-8
pubmed: 3106646
J Trauma. 1974 Mar;14(3):187-96
pubmed: 4814394
Curr Opin Crit Care. 2016 Dec;22(6):584-590
pubmed: 27661439
WMJ. 2001;100(2):57-9
pubmed: 11419374
Support Care Cancer. 2010 Jan;18(1):43-9
pubmed: 19381693
J Trauma. 1989 May;29(5):623-9
pubmed: 2657085
J Trauma Acute Care Surg. 2016 Feb;80(2):204-9
pubmed: 26595708
J Trauma. 2002 Sep;53(3):407-14
pubmed: 12352472