Demographic change in Germany and across Europe is placing immense pressure on healthcare and care systems. An increasing number of people are living with dementia – a condition that pushes not only those directly affected, but also their families and professional caregivers to the limits of their capacity. At the same time, there is a growing desire among those affected to remain in their own homes for as long as possible. The future of care must therefore become smarter, more anticipatory and less burdensome – for everyone involved.
This is precisely the challenge that the research and development project HoCaMo addresses. Within the framework of the Central Innovation Programme SME (ZIM) of the German Federal Ministry for Economic Affairs and Climate Action (BMWK), an interdisciplinary consortium of companies and research institutions is developing a modular, scalable monitoring system for use in domestic environments. The goal is to automatically, continuously, and above all contactlessly capture and assess the psychological and physiological states of well-being of people living with dementia.
At the heart of the HoCaMo system is a functionalised mirror that can be seamlessly integrated into the home environment. By embedding optical and acoustic sensors, the mirror is capable of contactlessly capturing a wide range of biometric and behavioural parameters. These include respiratory rate and heart rate, as well as the analysis of facial expressions, posture and paralinguistic features such as pitch and speech rhythm. The mirror integrates discreetly into the daily lives of its users – without intrusive body-worn sensors or disruptive interference with established routines.
The captured data are analysed by a self-learning system developed at the FZI Research Center for Information Technology. Over time, this system learns the individual behavioural patterns and baseline states of each user, enabling it to detect deviations and anomalies at an early stage. On the basis of this data, automated emotion and stress assessments are performed, alongside continuous evaluation of dementia progression. The system distinguishes between group-specific, individual and temporal characteristics, progressively building a precise, personalised user profile that updates continuously.
Particular attention is paid to clinically relevant events: changes in behaviour or vital parameters that may indicate comorbidities or acute health crises are detected early and immediately communicated to authorised recipients – such as care staff, treating physicians or family members. This enables timely medical intervention and can, in the best case, prevent hospitalisation or a deterioration in health.