Predicting hospice eligibility among dementia patients using language models

Alzheimer's disease and related dementias (ADRD) are increasing in prevalence, and access to potential benefits of hospice care remains challenging. Large language models (LLMs), like GPT-4o, applied to electronic health records (EHRs) could support decisions by estimating mortality risk.

We analyzed patients with ADRD diagnosis from two academic medical centers. GPT-4o was used to estimate 6-month mortality risk from discharge summaries without any retraining or preprocessing. We used Cox regression to assess associations between predictions and time to death.

Of 9872 individuals, 3563 (36%) died within 6 months. GPT-4o predictions stratified risk of death within 6 months (log-rank p < 0.001, area under the curve [AUC] = 0.79); predictions were strongly associated with mortality in Cox regression models (adjusted hazard ratio [aHR] = 31.02 95% confidence interval [CI] 27.44-35.08, p < 0.001) with similar results between sites.

GPT-4o can stratify mortality risk using routinely generated documentation, potentially facilitating hospice referral decisions, but more prospective work is needed.

Large language models (LLMs) can estimate 6-month mortality in patients with dementia. GPT-4o estimates of mortality risk from discharge summaries were highly discriminative (area under the curve [AUC] = 0.79). Predictions may support hospice referral decisions.