Background: For advanced cancer patients in palliative care, a crucial phase is the transition from palliative care in the hospital to the home setting, where 24-7 care is not guaranteed any more. To fill this gap after transition, we are evaluating the feasibility of a physical and social activity tracking system consisting of a FDA approved bracelet (Biovotion Everion MD®) collecting vital data, e.g., heart rate, oxygen saturation etc., and an Android smart-phone (Samsung Galaxy S5) collecting patients' self-reports of pain and distress as well as acceleration, GPS and phone call statistics data. When study participants are asked, how they are doing in general, a common answer is "There are good days and there are bad days." Apparently, they order their days into different groups. We argue that these "good" and "bad" days have impact on a patient's behavior and is therefore visible in the collected activity data. Objective: As a part of the study's goals, we aim to show the explanatory power of the collected data: the collected data reflect the health status of a patient. Methods: Data is collected over a study period of 12 weeks as part of a feasibility study with an explorative and descriptive study design. Study participants are enrolled from the wards of the Clinic of Radiation-Oncology at the University Hospital Zurich, including the specialized palliative care ward. The data collection chain consists of the patients' devices, Wi-Fi and internet for secured data upload and a receiving web server. The raw data is preprocessed involving resampling and basic feature extraction. Complex features are extracted using unsupervised machine learning methods, e.g., clustering. Heat maps are used to provide overview visualizations of sensor modalities. Integrated views are generated for multi-modal reconstruction and visualization of patients' daily routines. Results: Data collection started in March 2017 and already 13 study participants have finished their study participation or had to abort their participation due to health reasons. We collected more than 10000 hours of valid bracelet data and about 410000 GPS positions from the smart-phone. The cohort shows a high variability in live circumstances, e.g., some are still working, and others hardly leave their homes. We give examples of two patients with different courses of disease in order to demonstrate our approach. Conclusions: Our remote monitoring system delivers a large amount of data that allows us to reconstruct the daily routines of the patients showing differences between good and bad days.Trial Registration: The local Ethics Committee (Kantonale Ethikkommission Zürich) has approved the study protocol; approval number PB_2016-00895.