Drug Burden Index is a Modifiable Predictor of 30-Day-Hospitalization in Community-Dwelling Older Adults with Complex Care Needs: Machine Learning Analysis of InterRAI Data

Robert T Olender; Sandipan Roy; Hamish A Jamieson; Sarah N Hilmer; Prasad S Nishtala

doi:10.1093/gerona/glae130

Drug Burden Index is a Modifiable Predictor of 30-Day-Hospitalization in Community-Dwelling Older Adults with Complex Care Needs: Machine Learning Analysis of InterRAI Data

J Gerontol A Biol Sci Med Sci. 2024 May 11:glae130. doi: 10.1093/gerona/glae130. Online ahead of print.

Authors

Robert T Olender¹, Sandipan Roy², Hamish A Jamieson³, Sarah N Hilmer⁴, Prasad S Nishtala⁵

Affiliations

¹ Department of Life Sciences, University of Bath, UK.
² Department of Mathematical Sciences, University of Bath, UK.
³ Department of Medicine, University of Otago, Christchurch, New Zealand.
⁴ Kolling Institute, Faculty of Medicine and Health, Northern Clinical School, The University of Sydney and Northern Sydney Local Health District, St Leonards, New South Wales, Australia.
⁵ Department of Life Sciences & Centre for Therapeutic Innovation, University of Bath, UK.

PMID: 38733108
DOI: 10.1093/gerona/glae130

Abstract

Background: Older adults (≥ 65 years) account for a disproportionately high proportion of hospitalization and in-hospital mortality, some of which may be avoidable. Although machine learning (ML) models have already been built and validated for predicting hospitalization and mortality, there remains a significant need to optimise ML models further. Accurately predicting hospitalization may tremendously impact the clinical care of older adults as preventative measures can be implemented to improve clinical outcomes for the patient.

Methods: In this retrospective cohort study, a dataset of 14,198 community-dwelling older adults (≥ 65 years) with complex care needs from the Inter-Resident Assessment Instrument database was used to develop and optimise three ML models to predict 30-day-hospitalization. The models developed and optimized were Random Forest (RF), XGBoost (XGB), and Logistic Regression (LR). Variable importance plots were generated for all three models to identify key predictors of 30-day-hospitalization.

Results: The area under the receiver operating characteristics curve for the RF, XGB and LR models were 0.97, 0.90 and 0.72, respectively. Variable importance plots identified the Drug Burden Index and alcohol consumption as important, immediately potentially modifiable variables in predicting 30-day-hospitalization.

Conclusions: Identifying immediately potentially modifiable risk factors such as the Drug Burden Index and alcohol consumption is of high clinical relevance. If clinicians can influence these variables, they could proactively lower the risk of 30-day-hospitalization. ML holds promise to improve the clinical care of older adults. It is crucial that these models undergo extensive validation through large-scale clinical studies before being utilized in the clinical setting.

Keywords: Artificial intelligence; Decision tree; Hospitalization; Logistic Regression; Predictive modelling.