S Ariane Christie1, Alan E Hubbard, Rachael A Callcut, Morad Hameed, Fanny Nadia Dissak-Delon, David Mekolo, Arabo Saidou, Alain Chichom Mefire, Pierre Nsongoo, Rochelle A Dicker, Mitchell Jay Cohen, Catherine Juillard. 1. From the Department of Surgery (S.A.C., R.A.C., C.J.), University of California San Francisco, San Francisco, California; Department of Biostatistics (A.E.H.), University of California Berkeley, Berkeley, California; Division of General Surgery (M.H.), Vancouver General Hospital, University of British Columbia, Vancouver, British Columbia, Canada; Littoral Regional Delegation of the Ministry of Public Health, Cameroon (F.N.D.-D.), Douala, Cameroon; Laquintinie Hospital of Douala, Douala, Cameroon (D.M., A.S.); Regional Hospital of Limbe, Limbe, Cameroon (A.C.M.); Catholic Hospital of Pouma, Pouma, Cameroon (P.N.); Department of Surgery (R.A.D.), University of California Los Angeles, Los Angeles, California; and Denver Health Medical Center and the University of Colorado, Denver, Colorado (M.J.C.).
Abstract
BACKGROUND: Mortality prediction aids clinical decision making and is necessary for quality improvement initiatives. Validated metrics rely on prespecified variables and often require advanced diagnostics, which are unfeasible in resource-constrained contexts. We hypothesize that machine learning will generate superior mortality prediction in both high-income and low- and middle-income country cohorts. METHODS: SuperLearner, an ensemble machine-learning algorithm, was applied to data from three prospective trauma cohorts: a highest-activation cohort in the United States, a high-volume center cohort in South Africa (SA), and a multicenter registry in Cameroon. Cross-validation was used to assess model discrimination of discharge mortality by site using receiver operating characteristic curves. SuperLearner discrimination was compared with standard scoring methods. Clinical variables driving SuperLearner prediction at each site were evaluated. RESULTS: Data from 28,212 injured patients were used to generate prediction. Discharge mortality was 17%, 1.3%, and 1.7% among US, SA, and Cameroonian cohorts. SuperLearner delivered superior prediction of discharge mortality in the United States (area under the curve [AUC], 94-97%) and vastly superior prediction in Cameroon (AUC, 90-94%) compared with conventional scoring algorithms. It provided similar prediction to standard scores in the SA cohort (AUC, 90-95%). Context-specific variables (partial thromboplastin time in the United States and hospital distance in Cameroon) were prime drivers of predicted mortality in their respective cohorts, whereas severe brain injury predicted mortality across sites. CONCLUSIONS: Machine learning provides excellent discrimination of injury mortality in diverse settings. Unlike traditional scores, data-adaptive methods are well suited to optimizing precise site-specific prediction regardless of diagnostic capabilities or data set inclusion allowing for individualized decision making and expanded access to quality improvement programming. LEVEL OF EVIDENCE: Prognostic and therapeutic, level II and III.
BACKGROUND: Mortality prediction aids clinical decision making and is necessary for quality improvement initiatives. Validated metrics rely on prespecified variables and often require advanced diagnostics, which are unfeasible in resource-constrained contexts. We hypothesize that machine learning will generate superior mortality prediction in both high-income and low- and middle-income country cohorts. METHODS: SuperLearner, an ensemble machine-learning algorithm, was applied to data from three prospective trauma cohorts: a highest-activation cohort in the United States, a high-volume center cohort in South Africa (SA), and a multicenter registry in Cameroon. Cross-validation was used to assess model discrimination of discharge mortality by site using receiver operating characteristic curves. SuperLearner discrimination was compared with standard scoring methods. Clinical variables driving SuperLearner prediction at each site were evaluated. RESULTS: Data from 28,212 injured patients were used to generate prediction. Discharge mortality was 17%, 1.3%, and 1.7% among US, SA, and Cameroonian cohorts. SuperLearner delivered superior prediction of discharge mortality in the United States (area under the curve [AUC], 94-97%) and vastly superior prediction in Cameroon (AUC, 90-94%) compared with conventional scoring algorithms. It provided similar prediction to standard scores in the SA cohort (AUC, 90-95%). Context-specific variables (partial thromboplastin time in the United States and hospital distance in Cameroon) were prime drivers of predicted mortality in their respective cohorts, whereas severe brain injury predicted mortality across sites. CONCLUSIONS: Machine learning provides excellent discrimination of injury mortality in diverse settings. Unlike traditional scores, data-adaptive methods are well suited to optimizing precise site-specific prediction regardless of diagnostic capabilities or data set inclusion allowing for individualized decision making and expanded access to quality improvement programming. LEVEL OF EVIDENCE: Prognostic and therapeutic, level II and III.
Authors: Alan Hubbard; Ivan Diaz Munoz; Anna Decker; John B Holcomb; Martin A Schreiber; Eileen M Bulger; Karen J Brasel; Erin E Fox; Deborah J del Junco; Charles E Wade; Mohammad H Rahbar; Bryan A Cotton; Herb A Phelan; John G Myers; Louis H Alarcon; Peter Muskat; Mitchell J Cohen Journal: J Trauma Acute Care Surg Date: 2013-07 Impact factor: 3.313
Authors: Tyler J Loftus; Patrick J Tighe; Amanda C Filiberto; Philip A Efron; Scott C Brakenridge; Alicia M Mohr; Parisa Rashidi; Gilbert R Upchurch; Azra Bihorac Journal: JAMA Surg Date: 2020-02-01 Impact factor: 14.766
Authors: Robert T van Kooten; Renu R Bahadoer; Bouwdewijn Ter Buurkes de Vries; Michel W J M Wouters; Rob A E M Tollenaar; Henk H Hartgrink; Hein Putter; Johan L Dikken Journal: J Surg Oncol Date: 2022-05-03 Impact factor: 2.885