Automated algorithms for identifying patients requiring palliative care: a systematic review and meta‑analysis

Electronic health record (EHR)-based algorithms have been developed to identify patients with high palliative care needs and facilitate timely palliative care interventions. We systematically searched PubMed, Embase, and the Cochrane Library for randomized trials published up to December 2025. Pooled risk ratios (RRs) and weighted mean differences with 95% confidence intervals (CIs) were estimated using random-effects models. Risk of bias was assessed using Cochrane RoB 2.0, and certainty of evidence was rated with GRADE. Seven trials enrolling 125,666 patients were included. Automated EHR algorithms significantly increased palliative care consultations (noncancer: RR, 2.19; 95% CI, 1.12-4.28; cancer: RR, 5.31; 95% CI, 3.49-8.09) and do-not-resuscitate documentation (RR, 1.22; 95% CI, 1.17-1.28). Effects on hospice use and in-hospital mortality were marginal. No significant effects were observed for ICU admission, length of stay, or family-reported psychological outcomes. Implementation of automated EHR algorithms is associated with higher rates of palliative care consultations and advance care planning documentation, suggesting potential to enhance the timeliness and quality of end-of-life care.