Nicholas K Schiltz1,2,3, Mary A Dolansky4,5, David F Warner6, Kurt C Stange5,7,8,9, Stefan Gravenstein10,11,12,13, Siran M Koroukian5,7,9. 1. Frances Payne Bolton School of Nursing , Case Western Reserve University, 10900 Euclid Avenue, Room 459H, Cleveland, OH, 44106-7343, USA. nks8@case.edu. 2. Department of Population & Quantitative Health Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA. nks8@case.edu. 3. Center for Community Health Integration, Case Western Reserve University School of Medicine, Cleveland, OH, USA. nks8@case.edu. 4. Frances Payne Bolton School of Nursing , Case Western Reserve University, 10900 Euclid Avenue, Room 459H, Cleveland, OH, 44106-7343, USA. 5. Department of Population & Quantitative Health Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA. 6. Department of Sociology, University of Alabama at Birmingham, Birmingham, AL, USA. 7. Center for Community Health Integration, Case Western Reserve University School of Medicine, Cleveland, OH, USA. 8. Department of Family & Community Health, Case Western Reserve University School of Medicine, Cleveland, OH, USA. 9. Case Comprehensive Cancer Center, Case Western Reserve University, Cleveland, OH, USA. 10. Department of Health Services, Policy, and Practice, Brown University, Providence, RI, USA. 11. Alpert School of Medicine, Brown University, Providence, RI, USA. 12. Center for Gerontology and Healthcare Research, Brown University, Providence, RI, USA. 13. Providence Veterans Administration Medical Center, Providence, RI, USA.
Abstract
BACKGROUND: Limitations in instrumental activities of daily living (IADL) hinder a person's ability to live independently in the community and self-manage their conditions, but its impact on hospital readmission has not been firmly established. OBJECTIVE: To test the importance of IADL dependency as a predictor of 30-day readmissions and quantify its impact relative to other morbidities. DESIGN: A retrospective cohort study of the population-based Health and Retirement Study linked to Medicare claims data. Random forest was used to rank each predictor variable in terms of its ability to predict readmission. Classification and regression tree (CART) was used to identify complex multimorbidity combinations associated with high or low risk of readmission. Generalized linear regression was used to estimate the adjusted relative risk of readmission for IADL limitations. SUBJECTS: Hospitalizations of adults age 65 and older (n = 20,007), from 6617 unique subjects. MAIN MEASURES: The main outcome was 30-day all-cause unplanned readmission. The main predictor of interest was self-reported IADL limitation. Other key predictors were self-reported complex multimorbidity including chronic diseases, geriatric syndromes, and activities of daily living (ADL) limitations, along with demographic, socioeconomic, and behavioral factors. KEY RESULTS: The overall 30-day readmission rate in the study was 16.4%. Random forest analysis ranked ADLs and IADL limitations as the two most important predictors of 30-day readmission. CART identified hospitalizations of patients with IADL limitations and diabetes as a subgroup at the highest risk of readmission (26% readmitted). Multivariable regression analyses showed that ADL limitations were associated with 1.17 (1.06-1.29) times higher risk of readmission even after adjusting for other patient covariates. Risk prediction was modest though for even the best model (AUC = 0.612). CONCLUSIONS: IADL limitations are key predictors of 30-day readmission as demonstrated using several machine learning methods. Routine assessment of functional abilities in hospital settings could help identify those most at risk.
BACKGROUND: Limitations in instrumental activities of daily living (IADL) hinder a person's ability to live independently in the community and self-manage their conditions, but its impact on hospital readmission has not been firmly established. OBJECTIVE: To test the importance of IADL dependency as a predictor of 30-day readmissions and quantify its impact relative to other morbidities. DESIGN: A retrospective cohort study of the population-based Health and Retirement Study linked to Medicare claims data. Random forest was used to rank each predictor variable in terms of its ability to predict readmission. Classification and regression tree (CART) was used to identify complex multimorbidity combinations associated with high or low risk of readmission. Generalized linear regression was used to estimate the adjusted relative risk of readmission for IADL limitations. SUBJECTS: Hospitalizations of adults age 65 and older (n = 20,007), from 6617 unique subjects. MAIN MEASURES: The main outcome was 30-day all-cause unplanned readmission. The main predictor of interest was self-reported IADL limitation. Other key predictors were self-reported complex multimorbidity including chronic diseases, geriatric syndromes, and activities of daily living (ADL) limitations, along with demographic, socioeconomic, and behavioral factors. KEY RESULTS: The overall 30-day readmission rate in the study was 16.4%. Random forest analysis ranked ADLs and IADL limitations as the two most important predictors of 30-day readmission. CART identified hospitalizations of patients with IADL limitations and diabetes as a subgroup at the highest risk of readmission (26% readmitted). Multivariable regression analyses showed that ADL limitations were associated with 1.17 (1.06-1.29) times higher risk of readmission even after adjusting for other patient covariates. Risk prediction was modest though for even the best model (AUC = 0.612). CONCLUSIONS: IADL limitations are key predictors of 30-day readmission as demonstrated using several machine learning methods. Routine assessment of functional abilities in hospital settings could help identify those most at risk.
Entities:
Keywords:
activities of daily living; health services research; multimorbidity; patient readmission; supervised machine learning
Authors: Siran M Koroukian; Nicholas Schiltz; David F Warner; Jiayang Sun; Paul M Bakaki; Kathleen A Smyth; Kurt C Stange; Charles W Given Journal: J Gen Intern Med Date: 2016-02-22 Impact factor: 5.128
Authors: Amanda Sonnega; Jessica D Faul; Mary Beth Ofstedal; Kenneth M Langa; John W R Phillips; David R Weir Journal: Int J Epidemiol Date: 2014-03-25 Impact factor: 7.196
Authors: Jennifer Meddings; Heidi Reichert; Shawna N Smith; Theodore J Iwashyna; Kenneth M Langa; Timothy P Hofer; Laurence F McMahon Journal: J Gen Intern Med Date: 2016-11-15 Impact factor: 5.128
Authors: Nazima Allaudeen; Jeffrey L Schnipper; E John Orav; Robert M Wachter; Arpana R Vidyarthi Journal: J Gen Intern Med Date: 2011-03-12 Impact factor: 5.128
Authors: Aaron L Leppin; Michael R Gionfriddo; Maya Kessler; Juan Pablo Brito; Frances S Mair; Katie Gallacher; Zhen Wang; Patricia J Erwin; Tanya Sylvester; Kasey Boehmer; Henry H Ting; M Hassan Murad; Nathan D Shippee; Victor M Montori Journal: JAMA Intern Med Date: 2014-07 Impact factor: 21.873
Authors: Nicholas K Schiltz; Megan A Foradori; Andrew P Reimer; Matthew Plow; Mary A Dolansky Journal: J Am Geriatr Soc Date: 2022-04-05 Impact factor: 7.538
Authors: Patricia García-Pérez; María Del Carmen Rodríguez-Martínez; José Pablo Lara; Carlos de la Cruz-Cosme Journal: Int J Environ Res Public Health Date: 2021-12-07 Impact factor: 3.390