OBJECTIVE: Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. DESIGN: Observational cohort study. SETTING: Five hospitals, from November 2008 until January 2013. PATIENTS: Hospitalized ward patients INTERVENTIONS: None MEASUREMENTS AND MAIN RESULTS: Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]). CONCLUSIONS: In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.
OBJECTIVE: Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. DESIGN: Observational cohort study. SETTING: Five hospitals, from November 2008 until January 2013. PATIENTS: Hospitalized ward patients INTERVENTIONS: None MEASUREMENTS AND MAIN RESULTS: Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]). CONCLUSIONS: In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically illpatients on the wards.
Authors: Gabriel J Escobar; Juan Carlos LaGuardia; Benjamin J Turk; Arona Ragins; Patricia Kipnis; David Draper Journal: J Hosp Med Date: 2012-03-22 Impact factor: 2.960
Authors: Gary B Smith; David R Prytherch; Paul Meredith; Paul E Schmidt; Peter I Featherstone Journal: Resuscitation Date: 2013-01-04 Impact factor: 5.262
Authors: Romain Pirracchio; Maya L Petersen; Marco Carone; Matthieu Resche Rigon; Sylvie Chevret; Mark J van der Laan Journal: Lancet Respir Med Date: 2014-11-24 Impact factor: 30.700
Authors: Thomas C Bailey; Yixin Chen; Yi Mao; Chenyang Lu; Gregory Hackmann; Scott T Micek; Kevin M Heard; Kelly M Faulkner; Marin H Kollef Journal: J Hosp Med Date: 2013-02-25 Impact factor: 2.960
Authors: Tessy Badriyah; James S Briggs; Paul Meredith; Stuart W Jarvis; Paul E Schmidt; Peter I Featherstone; David R Prytherch; Gary B Smith Journal: Resuscitation Date: 2013-12-19 Impact factor: 5.262
Authors: Matthew M Churpek; Trevor C Yuen; Christopher Winslow; Ari A Robicsek; David O Meltzer; Robert D Gibbons; Dana P Edelson Journal: Am J Respir Crit Care Med Date: 2014-09-15 Impact factor: 21.405
Authors: Jennifer C Ginestra; Heather M Giannini; William D Schweickert; Laurie Meadows; Michael J Lynch; Kimberly Pavan; Corey J Chivers; Michael Draugelis; Patrick J Donnelly; Barry D Fuchs; Craig A Umscheid Journal: Crit Care Med Date: 2019-11 Impact factor: 7.598
Authors: Gary E Weissman; Rebecca A Hubbard; Lyle H Ungar; Michael O Harhay; Casey S Greene; Blanca E Himes; Scott D Halpern Journal: Crit Care Med Date: 2018-07 Impact factor: 7.598
Authors: L Nelson Sanchez-Pinto; Laura Ruth Venable; John Fahrenbach; Matthew M Churpek Journal: Int J Med Inform Date: 2018-05-21 Impact factor: 4.046
Authors: Emanuel Eguia; Adrienne N Cobb; Marshall S Baker; Cara Joyce; Emily Gilbert; Richard Gonzalez; Majid Afshar; Matthew M Churpek Journal: Am J Surg Date: 2019-03-08 Impact factor: 2.565