Adrienne N Cobb1, Witawat Daungjaiboon2, Sarah A Brownlee3, Anthony J Baldea4, Arthur P Sanford5, Michael M Mosier6, Paul C Kuo7. 1. Loyola University Medical Center, Department of Surgery, 2160 S. 1st Avenue, Maywood, IL 60153, USA; One:MAP Section of Surgical Analytics, Department of Surgery, Loyola University Chicago, 2160 S. 1st Avenue, Maywood, IL 60153, USA. Electronic address: adcobb@lumc.edu. 2. DePaul University, College of Computing and Digital Media, Department of Predictive Analytics, 243 South Wabash Avenue, Chicago, IL 60604, USA. Electronic address: dwitawat@gmail.com. 3. One:MAP Section of Surgical Analytics, Department of Surgery, Loyola University Chicago, 2160 S. 1st Avenue, Maywood, IL 60153, USA. Electronic address: sbrownlee@luc.edu. 4. Loyola University Medical Center, Department of Surgery, 2160 S. 1st Avenue, Maywood, IL 60153, USA. Electronic address: abaldea@lumc.edu. 5. Loyola University Medical Center, Department of Surgery, 2160 S. 1st Avenue, Maywood, IL 60153, USA. Electronic address: asanford@lumc.edu. 6. Loyola University Medical Center, Department of Surgery, 2160 S. 1st Avenue, Maywood, IL 60153, USA. Electronic address: mmosier@lumc.edu. 7. Loyola University Medical Center, Department of Surgery, 2160 S. 1st Avenue, Maywood, IL 60153, USA; One:MAP Section of Surgical Analytics, Department of Surgery, Loyola University Chicago, 2160 S. 1st Avenue, Maywood, IL 60153, USA. Electronic address: paul.kuo@luhs.org.
Abstract
BACKGROUND: This study aims to identify predictors of survival for burn patients at the patient and hospital level using machine learning techniques. METHODS: The HCUP SID for California, Florida and New York were used to identify patients admitted with a burn diagnosis and merged with hospital data from the AHA Annual Survey. Random forest and stochastic gradient boosting (SGB) were used to identify predictors of survival at the patient and hospital level from the top performing model. RESULTS: We analyzed 31,350 patients from 670 hospitals. SGB (AUC 0.93) and random forest (AUC 0.82) best identified patient factors such as age and absence of renal failure (p < 0.001) and hospital factors such as full time residents (p < 0.001) and nurses (p = 0.004) to be associated with increased survival. CONCLUSIONS: Patient and hospital factors are predictive of survival in burn patients. It is difficult to control patient factors, but hospital factors can inform decisions about where burn patients should be treated.
BACKGROUND: This study aims to identify predictors of survival for burn patients at the patient and hospital level using machine learning techniques. METHODS: The HCUP SID for California, Florida and New York were used to identify patients admitted with a burn diagnosis and merged with hospital data from the AHA Annual Survey. Random forest and stochastic gradient boosting (SGB) were used to identify predictors of survival at the patient and hospital level from the top performing model. RESULTS: We analyzed 31,350 patients from 670 hospitals. SGB (AUC 0.93) and random forest (AUC 0.82) best identified patient factors such as age and absence of renal failure (p < 0.001) and hospital factors such as full time residents (p < 0.001) and nurses (p = 0.004) to be associated with increased survival. CONCLUSIONS:Patient and hospital factors are predictive of survival in burn patients. It is difficult to control patient factors, but hospital factors can inform decisions about where burn patients should be treated.
Authors: Saul Blecker; Keith Goldfeld; Naeun Park; Daniel Shine; Jonathan S Austrian; R Scott Braithwaite; Martha J Radford; Marc N Gourevitch Journal: Am J Med Date: 2013-12-11 Impact factor: 4.965
Authors: Kathleen S Romanowski; Alura Barsun; Tina L Pamlieri; David G Greenhalgh; Soman Sen Journal: J Burn Care Res Date: 2015 Jan-Feb Impact factor: 1.845
Authors: Luke M Funk; Atul A Gawande; Marcus E Semel; Stuart R Lipsitz; William R Berry; Michael J Zinner; Ashish K Jha Journal: Ann Surg Date: 2011-05 Impact factor: 12.969
Authors: William J Kostis; Kitaw Demissie; Stephen W Marcella; Yu-Hsuan Shao; Alan C Wilson; Abel E Moreyra Journal: N Engl J Med Date: 2007-03-15 Impact factor: 91.245
Authors: Xinsong Du; Jae Min; Chintan P Shah; Rohit Bishnoi; William R Hogan; Dominick J Lemas Journal: Int J Med Inform Date: 2020-04-15 Impact factor: 4.046
Authors: Paulina B Szklanna; Haidar Altaie; Shane P Comer; Sarah Cullivan; Sarah Kelliher; Luisa Weiss; John Curran; Emmet Dowling; Katherine M A O'Reilly; Aoife G Cotter; Brian Marsh; Sean Gaine; Nick Power; Áine Lennon; Brian McCullagh; Fionnuala Ní Áinle; Barry Kevane; Patricia B Maguire Journal: Front Med (Lausanne) Date: 2021-07-16