The risk of delirium or dementia‐related hospitalization among individuals living with dementia after long‐term care entry: A population‐based risk prediction model

INTRODUCTION Identifying individuals with dementia in long‐term care facilities (LTCFs) at risk for delirium or dementia‐related hospitalizations can support individualized risk mitigation. METHODS Using the Registry of Senior Australians (ROSA) Historical National Cohort ( N = 207343 individuals with dementia in 2655 LTCFs), we identified predictors of delirium or dementia‐related hospitalization within 365 days of LTCF entry and developed a risk prediction model using elastic net penalized regression and Fine‐Gray model. Model discrimination using area under the receiver operating characteristics curve (AUC), calibration and clinical utility were assessed. RESULTS Within 365 days, 5.2% ( N = 10709) of individuals had a delirium or dementia‐related hospitalization. Forty predictors were identified, strongest included history of frequent emergency department presentations, physical violence history, being male, and prior delirium. Model AUC was 0.664 (95% confidence interval: 0.650–0.676) with reasonable calibration. DISCUSSION Our risk prediction model for delirium or dementia‐related hospitalizations had moderate discrimination with reasonable calibration and clinical utility. Routinely collected data can inform risk profiling in LTCFs. Highlights Using a large population‐based cohort of people living with dementia, we developed a risk prediction model for delirium or dementia‐related hospitalization within 365 days of long‐term care facility (LTCF) entry. Within 365 days after entry into LTCF, 5.2% of individuals living with dementia had a delirium or dementia‐related hospitalization. The model demonstrated moderate discriminatory performance (area under the curve [AUC] = 0.664, 95% confidence interval [CI]: 0.650–0.676) and reasonable calibration in predicting delirium or dementia‐related hospitalization risk. Our model showed net benefits within 2%–22% risk threshold ranges assessed via decision curve analysis . Risk stratification at LTCF entry may support clinicians and aged care providers in identifying high risk individuals and implementing targeted interventions to reduce delirium or dementia‐related hospitalizations .