Samenvatting

Early identification of the palliative phase in patients with COPD and heart failure remains difficult, often delaying needed care. Since most patients are cared for at home, timely recognition in primary care is crucial. However, screening tools are rarely used, and identification relies on professional judgment. Machine learning may help by analyzing routine health data to support earlier detection. This study aimed to identify and prioritize key signs and symptoms to support timely recognition of palliative care needs.

A mixed-methods study was conducted in four phases: interviews, a literature review, focus groups, and a survey among home-based nursing professionals. Results showed that deterioration is multidimensional, involving physical, psychological, social, and spiritual changes, along with increasing care needs and healthcare use.

These findings provide a foundation for developing a machine learning model to support home-based nurses in recognizing the palliative phase earlier and improving palliative care delivery.