Machine learning for targeted advance care planning in cancer patients: a quality improvement study.

CONTEXT: Prognostication challenges contribute to delays in advance care planning (ACP) for patients with cancer near the end of life (EOL). OBJECTIVES: Examine a quality improvement mortality prediction algorithm intervention's impact on ACP documentation and EOL care. METHODS: We implemented a validated mortality risk prediction machine learning model for solid malignancy patients admitted from the emergency department (ED) to a dedicated solid malignancy unit at Duke University Hospital. Clinicians received an email when a patient was identified as high-risk. We compared ACP documentation and EOL care outcomes before and after the notification intervention. We excluded patients with intensive care unit (ICU) admission in the first 24 hours. Comparisons involve chi-square/Fisher's exact tests and Wilcoxon rank sum tests; comparisons stratified by physician specialty employ Cochran-Mantel-Haenszel tests. RESULTS: Pre-intervention and post-intervention cohorts comprised 88 and 77 patients, respectively. Most were White, non-Hispanic/Latino, and married. ACP conversations were documented for 2.3% of hospitalizations pre-intervention vs. 80.5% post-intervention (p<0.001), and if the attending physician notified was a palliative care specialist (4.1% vs. 84.6%) or oncologist (0% vs. 76.3%) (p<0.001). There were no differences between groups in length of stay (LOS), hospice referral, code status change, ICU admissions or LOS, 30-day readmissions, 30-day ED visits, and inpatient and 30-day deaths. CONCLUSION: Identifying patients with cancer and high mortality risk via machine learning elicited a substantial increase in documented ACP conversations but did not impact EOL care. Our intervention showed promise in changing clinician behavior. Further integration of this model in clinical practice is ongoing.

Hospice Use Among Patients With Cancer: Trends, Barriers, and Future Directions.

Patients with advanced cancer and their families frequently encounter clinical and logistical challenges related to end-of-life care. Hospice provides interdisciplinary and holistic care to meet patients' biomedical, psychosocial, and spiritual needs in the last phases of life. Despite increasing general acceptance and use among patients with cancer, hospice remains underused. Underuse stems from ongoing misconceptions regarding hospice and its purpose, coupled with the rapid development of novel anticancer treatments, such as immunotherapies and targeted therapies, that have changed the landscape of possibilities. Furthermore, rapid evolutions in how end-of-life care is structured and reimbursed for will affect how oncology patients will intersect with hospice care. In this review, we explore the current and future challenges to greater integration of hospice care in the care of patients with advanced cancer and propose five recommendations as part of the path forward.