Cost-effectiveness analysis of home-based palliative care for end-stage cancer patients

Global increases in cancer prevalence and the associated financial burden necessitate the development of highly cost-effective care models. Optimally managing scarce healthcare resources is crucial to balance the goals of maximizing survival for curable patients and quality of life for those with terminal illness. This study evaluated the cost-effectiveness of a novel home-based palliative care model for end-stage cancer patients that utilizes Artificial Intelligence (AI) for operational optimization, compared to usual care. This case-control study compared costs and outcomes for two groups of end-stage cancer patients. The intervention group consisted of 94 patients receiving home-based palliative care from an Iranian NGO, Ala, which uses an AI-driven management system for resource planning. The control group included 113 patients receiving usual care, comprising outpatient services and hospitalization as needed. The groups were matched for cancer type, stage, age, and gender. We calculated the costs of inpatient and outpatient clinical and para-clinical services over a 6-month period. Outcome measures were hospital length of stay (LOS) and the proportion of deaths occurring at home. Home-based model demonstrated significant advantages. A higher proportion of deaths occurred at home in the intervention group compared to the control group (45.7% vs. 23.9%; p = 0.001). The mean LOS was lower for the intervention group (14.8 days vs. 20.5 days; p = 0.052). The mean total costs were also significantly lower for the intervention group (\$8,860 vs. \$13,172; p = 0.019). Incremental analysis confirmed home-based care as a dominant strategy, providing better outcomes at a lower cost. Home-based palliative care model proved to be a dominant and cost-effective strategy for end-stage cancer patients, resulting in more home deaths, reduced hospital stays, and lower costs. We recommend the inclusion of such optimized home-based palliative care in health insurance benefits packages and suggest that the integration of AI for demand forecasting and resource planning is a key component for its scalability and efficiency.