BACKGROUND: Thirty-day hospital readmissions are a quality metric for health care systems. Predictive models aim to identify patients likely to readmit to more effectively target preventive strategies. Many risk of readmission models have been developed on retrospective data, but prospective validation of readmission models is rare. To the best of our knowledge, none of these developed models have been evaluated or prospectively validated in a military hospital. OBJECTIVES: The objectives of this study are to demonstrate the development and prospective validation of machine learning (ML) risk of readmission models to be utilized by clinical staff at a military medical facility and demonstrate the collaboration between the U.S. Department of Defense's integrated health care system and a private company. METHODS: We evaluated multiple ML algorithms to develop a predictive model for 30-day readmissions using data from a retrospective cohort of all-cause inpatient readmissions at Madigan Army Medical Center (MAMC). This predictive model was then validated on prospective MAMC patient data. Precision, recall, accuracy, and the area under the receiver operating characteristic curve (AUC) were used to evaluate model performance. The model was revised, retrained, and rescored on additional retrospective MAMC data after the prospective model's initial performance was evaluated. RESULTS: Within the initial retrospective cohort, which included 32,659 patient encounters, the model achieved an AUC of 0.68. During prospective scoring, 1,574 patients were scored, of whom 152 were readmitted within 30 days of discharge, with an all-cause readmission rate of 9.7%. The AUC of the prospective predictive model was 0.64. The model achieved an AUC of 0.76 after revision and addition of further retrospective data. CONCLUSION: This work reflects significant collaborative efforts required to operationalize ML models in a complex clinical environment such as that seen in an integrated health care system and the importance of prospective model validation. Georg Thieme Verlag KG Stuttgart · New York.
BACKGROUND: Thirty-day hospital readmissions are a quality metric for health care systems. Predictive models aim to identify patients likely to readmit to more effectively target preventive strategies. Many risk of readmission models have been developed on retrospective data, but prospective validation of readmission models is rare. To the best of our knowledge, none of these developed models have been evaluated or prospectively validated in a military hospital. OBJECTIVES: The objectives of this study are to demonstrate the development and prospective validation of machine learning (ML) risk of readmission models to be utilized by clinical staff at a military medical facility and demonstrate the collaboration between the U.S. Department of Defense's integrated health care system and a private company. METHODS: We evaluated multiple ML algorithms to develop a predictive model for 30-day readmissions using data from a retrospective cohort of all-cause inpatient readmissions at Madigan Army Medical Center (MAMC). This predictive model was then validated on prospective MAMC patient data. Precision, recall, accuracy, and the area under the receiver operating characteristic curve (AUC) were used to evaluate model performance. The model was revised, retrained, and rescored on additional retrospective MAMC data after the prospective model's initial performance was evaluated. RESULTS: Within the initial retrospective cohort, which included 32,659 patient encounters, the model achieved an AUC of 0.68. During prospective scoring, 1,574 patients were scored, of whom 152 were readmitted within 30 days of discharge, with an all-cause readmission rate of 9.7%. The AUC of the prospective predictive model was 0.64. The model achieved an AUC of 0.76 after revision and addition of further retrospective data. CONCLUSION: This work reflects significant collaborative efforts required to operationalize ML models in a complex clinical environment such as that seen in an integrated health care system and the importance of prospective model validation. Georg Thieme Verlag KG Stuttgart · New York.
Authors: Linda Calvillo-King; Danielle Arnold; Kathryn J Eubank; Matthew Lo; Pete Yunyongying; Heather Stieglitz; Ethan A Halm Journal: J Gen Intern Med Date: 2012-10-06 Impact factor: 5.128
Authors: Benjamin A Goldstein; Ann Marie Navar; Michael J Pencina; John P A Ioannidis Journal: J Am Med Inform Assoc Date: 2016-05-17 Impact factor: 4.497
Authors: Jacques D Donzé; Mark V Williams; Edmondo J Robinson; Eyal Zimlichman; Drahomir Aujesky; Eduard E Vasilevskis; Sunil Kripalani; Joshua P Metlay; Tamara Wallington; Grant S Fletcher; Andrew D Auerbach; Jeffrey L Schnipper Journal: JAMA Intern Med Date: 2016-04 Impact factor: 21.873
Authors: Harlan M Krumholz; Sarwat I Chaudhry; John A Spertus; Jennifer A Mattera; Beth Hodshon; Jeph Herrin Journal: JACC Heart Fail Date: 2015-12-02 Impact factor: 12.035
Authors: John Billings; Ian Blunt; Adam Steventon; Theo Georghiou; Geraint Lewis; Martin Bardsley Journal: BMJ Open Date: 2012-08-10 Impact factor: 2.692
Authors: Christine Xia Wu; Ernest Suresh; Francis Wei Loong Phng; Kai Pik Tai; Janthorn Pakdeethai; Jared Louis Andre D'Souza; Woan Shin Tan; Phillip Phan; Kelvin Sin Min Lew; Gamaliel Yu-Heng Tan; Gerald Seng Wee Chua; Chi Hong Hwang Journal: Appl Clin Inform Date: 2021-05-19 Impact factor: 2.342