Radar-based Recognition of Activities of Daily Living in the Palliative Care Context Using Deep Learning

The accurate detection and quantification of activities of daily life (ADL) are crucial for assessing the health status of palliative patients to allow an optimized treatment in the last phase of life. Current evaluation methods heavily rely on subjective self-reports or external observations by clinical staff, lacking objectivity. To address this limitation, we propose a radar-based approach for recognizing ADLs in a palliative care context. In our proof of concept study, we recorded five different ADLs relevant to palliative care, all occurring within a hospital bed, from N=14 healthy participants (57% women, aged 28.6 ± 5.3years). All movements were recorded using two frequency-modulated continuous wave radar systems measuring velocity, range, and angle. A convolutional neural network combined with long short-term memory achieved a classification accuracy of 99.8 ± 0.4% across five cross-validation folds. Furthermore, we compare our initial approach, which takes into account all dimensions of the available radar data, to a simplified version, where only velocity information over time is fed into the network. While these results demonstrate the high potential of radar-based sensing to automatically detect and quantify activities in a palliative care context, future work is still necessary to assess the applicability to real-world hospital scenarios.