ARTICLE Schutz_IEEEJ-BHI_2021/IDIAP A Sensor-Driven Visit Detection System in Older Adults? Homes: Towards Digital Late-Life Depression Marker Extraction Schütz, Narayan Botros, Angela Hassen, Sami Ben Saner, Hugo Buluschek, Philipp Urwyler, Prabitha Pais, Bruno Santschi, Valérie Gatica-Perez, Daniel Müri, René M. Nef, Tobias classifiers digital biomarker domain adaptation late-life depression loneliness pervasive computing self-training support telemonitoring EXTERNAL https://publications.idiap.ch/attachments/papers/2021/Schutz_IEEEJ-BHI_2021.pdf PUBLIC IEEE Journal of Biomedical And Health Informatics 26 4 1560-1569 2168-2194 2168-2208 2021 https://ieeexplore.ieee.org/document/9546690 URL 10.1109/JBHI.2021.3114595 doi Modern sensor technology is increasingly used in older adults to not only provide additional safety but also to monitor health status, often by means of sensor derived digital measures or biomarkers. Social isolation is a known risk factor for late-life depression, and a potential component of social-isolation is the lack of home visits. Therefore, home visits may serve as a digital measure for social isolation and late-life depression. Late-life depression is a common mental and emotional disorder in the growing population of older adults. The disorder, if untreated, can significantly decrease quality of life and, amongst other effects, leads to increased mortality. Late-life depression often goes undiagnosed due to associated stigma and the incorrect assumption that it is a normal part of ageing. In this work, we propose a visit detection system that generalizes well to previously unseen apartments - which may differ largely in layout, sensor placement, and size from apartments found in the semi-annotated training dataset. We find that by using a self-training-based domain adaptation strategy, a robust system to extract home visit information can be built (ROC AUC = 0.773). We further show that the resulting visit information correlates well with the common geriatric depression scale screening tool (rho = -0.87, p = 0.001), providing further support for the idea of utilizing the extracted information as a potential digital measure or even as a digital biomarker to monitor the risk of late-life depression.