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

Objective:

To evaluate the effectiveness of electronic health record (EHR) algorithms in identifying patients with high palliative care needs and facilitating timely interventions.

Key Findings:

• 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).
• Increased do-not-resuscitate documentation (RR, 1.22; 95% CI, 1.17–1.28).
• Marginal effects observed on hospice use and in-hospital mortality.
• No significant effects on ICU admission, length of stay, or family-reported psychological outcomes.

Interpretation:

Implementation of automated EHR algorithms is associated with higher rates of palliative care consultations and advance care planning documentation, indicating potential to improve end-of-life care.

Limitations:

• Data analyzed were extracted from previously published trials.
• Potential variability in algorithm implementation across different settings may affect generalizability.

Conclusion:

Automated EHR algorithms can enhance the timeliness and quality of palliative care interventions.