Literature DB >> 31067577

Development and Prospective Validation of a Machine Learning-Based Risk of Readmission Model in a Large Military Hospital.

Carly Eckert1, Neris Nieves-Robbins2, Elena Spieker3, Tom Louwers1, David Hazel1, James Marquardt1, Keith Solveson3, Anam Zahid1, Muhammad Ahmad1, Richard Barnhill3, T Greg McKelvey1, Robert Marshall3, Eric Shry3, Ankur Teredesai1.   

Abstract

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.

Entities:  

Mesh:

Year:  2019        PMID: 31067577      PMCID: PMC6506330          DOI: 10.1055/s-0039-1688553

Source DB:  PubMed          Journal:  Appl Clin Inform        ISSN: 1869-0327            Impact factor:   2.342


  33 in total

1.  Assessing model fit by cross-validation.

Authors:  Douglas M Hawkins; Subhash C Basak; Denise Mills
Journal:  J Chem Inf Comput Sci       Date:  2003 Mar-Apr

2.  Can characteristics of a health care system mitigate ethnic bias in access to cardiovascular procedures? Experience from the Military Health Services System.

Authors:  A J Taylor; G S Meyer; R W Morse; C E Pearson
Journal:  J Am Coll Cardiol       Date:  1997-10       Impact factor: 24.094

3.  External validation of new risk prediction models is infrequent and reveals worse prognostic discrimination.

Authors:  George C M Siontis; Ioanna Tzoulaki; Peter J Castaldi; John P A Ioannidis
Journal:  J Clin Epidemiol       Date:  2014-10-23       Impact factor: 6.437

Review 4.  Impact of social factors on risk of readmission or mortality in pneumonia and heart failure: systematic review.

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

Review 5.  Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review.

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

6.  What do we mean by validating a prognostic model?

Authors:  D G Altman; P Royston
Journal:  Stat Med       Date:  2000-02-29       Impact factor: 2.373

7.  International Validity of the HOSPITAL Score to Predict 30-Day Potentially Avoidable Hospital Readmissions.

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

8.  Do Non-Clinical Factors Improve Prediction of Readmission Risk?: Results From the Tele-HF Study.

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

Review 9.  Reducing hospital readmission rates: current strategies and future directions.

Authors:  Sunil Kripalani; Cecelia N Theobald; Beth Anctil; Eduard E Vasilevskis
Journal:  Annu Rev Med       Date:  2013-10-21       Impact factor: 13.739

10.  Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30).

Authors:  John Billings; Ian Blunt; Adam Steventon; Theo Georghiou; Geraint Lewis; Martin Bardsley
Journal:  BMJ Open       Date:  2012-08-10       Impact factor: 2.692

View more
  6 in total

1.  Current Trends in Readmission Prediction: An Overview of Approaches.

Authors:  Kareen Teo; Ching Wai Yong; Joon Huang Chuah; Yan Chai Hum; Yee Kai Tee; Kaijian Xia; Khin Wee Lai
Journal:  Arab J Sci Eng       Date:  2021-08-16       Impact factor: 2.807

2.  Predictive modeling for COVID-19 readmission risk using machine learning algorithms.

Authors:  Mostafa Shanbehzadeh; Azita Yazdani; Mohsen Shafiee; Hadi Kazemi-Arpanahi
Journal:  BMC Med Inform Decis Mak       Date:  2022-05-20       Impact factor: 3.298

3.  Implementation of Artificial Intelligence-Based Clinical Decision Support to Reduce Hospital Readmissions at a Regional Hospital.

Authors:  Santiago Romero-Brufau; Kirk D Wyatt; Patricia Boyum; Mindy Mickelson; Matthew Moore; Cheristi Cognetta-Rieke
Journal:  Appl Clin Inform       Date:  2020-09-02       Impact factor: 2.342

4.  Effect of a Real-Time Risk Score on 30-day Readmission Reduction in Singapore.

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

Review 5.  Application of machine learning in predicting hospital readmissions: a scoping review of the literature.

Authors:  Yinan Huang; Ashna Talwar; Satabdi Chatterjee; Rajender R Aparasu
Journal:  BMC Med Res Methodol       Date:  2021-05-06       Impact factor: 4.615

6.  Assess the Performance and Cost-Effectiveness of LACE and HOSPITAL Re-Admission Prediction Models as a Risk Management Tool for Home Care Patients: An Evaluation Study of a Medical Center Affiliated Home Care Unit in Taiwan.

Authors:  Mei-Chin Su; Yi-Jen Wang; Tzeng-Ji Chen; Shiao-Hui Chiu; Hsiao-Ting Chang; Mei-Shu Huang; Li-Hui Hu; Chu-Chuan Li; Su-Ju Yang; Jau-Ching Wu; Yu-Chun Chen
Journal:  Int J Environ Res Public Health       Date:  2020-02-02       Impact factor: 3.390

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.