Adrienne N Cobb1, Taylor R Erickson2, Anai N Kothari1, Emanuel Eguia1, Sarah A Brownlee2, Weiwei Yao3, Hyunyou Choi3, Victoria Greenberg3, Joy Mboya3, Michael Voss3, Daniela Stan Raicu3, Raffaella Settimi-Woods3, Paul C Kuo4. 1. Loyola University Medical Center, Department of Surgery, Maywood, IL; One:MAP Section of Surgical Analytics, Department of Surgery, Loyola University Chicago, Maywood, IL. 2. Loyola University Medical Center, Department of Surgery, Maywood, IL. 3. University of South Florida, Department of Surgery, Tampa, FL. 4. One:MAP Section of Surgical Analytics, Department of Surgery, Loyola University Chicago, Maywood, IL; DePaul University, College of Computing and Digital Media, Chicago, IL . Electronic address: paulkuo@health.usf.edu.
Abstract
BACKGROUND: This study aimed to determine whether publicized hospital rankings can be used to predict surgical outcomes. METHODS: Patients undergoing one of nine surgical procedures were identified, using the Healthcare Cost and Utilization Project State Inpatient Database for Florida and New York 2011-2013 and merged with hospital data from the American Hospital Association Annual Survey. Nine quality designations were analyzed as possible predictors of inpatient mortality and postoperative complications, using logistic regression, decision trees, and support vector machines. RESULTS: We identified 229,657 patients within 177 hospitals. Decision trees were the highest performing machine learning algorithm for predicting inpatient mortality and postoperative complications (accuracy 0.83, P<.001). The top 3 variables associated with low surgical mortality (relative impact) were Hospital Compare (42), total procedure volume (16) and, Joint Commission (12). When analyzed separately for each individual procedure, hospital quality awards were not predictors of postoperative complications for 7 of the 9 studied procedures. However, when grouping together procedures with a volume-outcome relationship, hospital ranking becomes a significant predictor of postoperative complications. CONCLUSION: Hospital quality rankings are not a reliable indicator of quality for all surgical procedures. Hospital and provider quality must be evaluated with an emphasis on creating consistent, reliable, and accurate measures of quality that translate to improved patient outcomes.
BACKGROUND: This study aimed to determine whether publicized hospital rankings can be used to predict surgical outcomes. METHODS:Patients undergoing one of nine surgical procedures were identified, using the Healthcare Cost and Utilization Project State Inpatient Database for Florida and New York 2011-2013 and merged with hospital data from the American Hospital Association Annual Survey. Nine quality designations were analyzed as possible predictors of inpatient mortality and postoperative complications, using logistic regression, decision trees, and support vector machines. RESULTS: We identified 229,657 patients within 177 hospitals. Decision trees were the highest performing machine learning algorithm for predicting inpatient mortality and postoperative complications (accuracy 0.83, P<.001). The top 3 variables associated with low surgical mortality (relative impact) were Hospital Compare (42), total procedure volume (16) and, Joint Commission (12). When analyzed separately for each individual procedure, hospital quality awards were not predictors of postoperative complications for 7 of the 9 studied procedures. However, when grouping together procedures with a volume-outcome relationship, hospital ranking becomes a significant predictor of postoperative complications. CONCLUSION: Hospital quality rankings are not a reliable indicator of quality for all surgical procedures. Hospital and provider quality must be evaluated with an emphasis on creating consistent, reliable, and accurate measures of quality that translate to improved patient outcomes.
Authors: John D Birkmeyer; Andrea E Siewers; Emily V A Finlayson; Therese A Stukel; F Lee Lucas; Ida Batista; H Gilbert Welch; David E Wennberg Journal: N Engl J Med Date: 2002-04-11 Impact factor: 91.245
Authors: Danny Lascano; Julia B Finkelstein; LaMont J Barlow; Daniel Kabat; Arindam RoyChoudhury; Jorge R Caso; G Joel DeCastro; William Gold; James M McKiernan Journal: Urology Date: 2015-09-25 Impact factor: 2.649
Authors: Michael B Rothberg; Elizabeth Morsi; Evan M Benjamin; Penelope S Pekow; Peter K Lindenauer Journal: Health Aff (Millwood) Date: 2008 Nov-Dec Impact factor: 6.301
Authors: J Matthew Austin; Ashish K Jha; Patrick S Romano; Sara J Singer; Timothy J Vogus; Robert M Wachter; Peter J Pronovost Journal: Health Aff (Millwood) Date: 2015-03 Impact factor: 6.301
Authors: Christopher R Friese; Rong Xia; Amir Ghaferi; John D Birkmeyer; Mousumi Banerjee Journal: Health Aff (Millwood) Date: 2015-06 Impact factor: 6.301
Authors: David Metcalfe; Cheryl K Zogg; Elliott R Haut; Timothy M Pawlik; Adil H Haider; Daniel C Perry Journal: Int J Epidemiol Date: 2019-12-01 Impact factor: 7.196