Derivation and validation of a mortality risk prediction model in older adults needing home care: Updating the RESPECT (Risk Evaluation for Support: Predictions for Elder-Life in their Communities Tool) algorithm for use with data from the interRAI Home Care Assessment System

Background Despite an increasing number of risk prediction models being developed within the healthcare space, few have been widely adopted and evaluated in clinical practice. RESPECT, a mortality risk communication tool powered by a prediction algorithm, has been implemented in the home care setting in Ontario, Canada, to support the identification of palliative care needs among older adults. We sought to re-estimate and validate the RESPECT algorithm in contemporary data. Methods The study and derivation cohort comprised adults living in Ontario aged 50 years and older with at least 1 interRAI Home Care (interRAI HC) record between April 1, 2018 and September 30, 2019. Algorithm validation used 500 bootstrapped samples, each containing a 5% random selection from the total cohort. The primary outcome was mortality within 6 months following an interRAI HC assessment. We used proportional hazards regression with robust standard errors to account for clustering by the individual. Kaplan–Meier survival curves were estimated to derive the observed risk of death at 6 months for assessment of calibration and median survival. Finally, 61 risk groups were constructed based on incremental increases in the observed median survival. Results The study cohort included 247,377 adults and 35,497 deaths (14.3%). The mean predicted 6-month mortality risk was 18.0% and ranged from 1.5% (95% CI 1.0%–1.542%) in the lowest to 96.0 % (95% CI 95.8%–96.2%) in the highest risk group. Estimated median survival spanned from 36 days in the highest risk group to over 3.5 years in the lowest risk group. The algorithm had a c-statistic of 0.76 (95% CI 0.75-0.77) in our validation cohort. Conclusions RESPECT demonstrates good discrimination and calibration. The algorithm, which leverages routinely-collected information, may be useful in home care settings for earlier identification of individuals who might be nearing the end of life.