Social workers require a better understanding of the impact of pandemic measures on the level of physical activity of their clients to better target client activation. In this retrospective tracker-based study (two years of measurement), we examined changes in the physical activity of the elderly population (204 participants with an average age of 84.5 years) in the Czech Republic as a result of measures to prevent the spread of COVID-19. Physical activity was statistically compared according to the physical, demographic and social conditions of the participants. In addition to observing the expected activity decrease during the COVID-19 pandemic, we made several hypotheses based on the sex, age group, body mass index, type of housing (apartment or house) and size of the city of residence. We found that 33% of the 204 participants had increased levels of physical activity in the period following the COVID-19 pandemic outbreak in Central Europe. We found that the size of the city where the seniors lived and the type of housing did not affect the general level of physical activity. When comparing physical acquisition rates in each month of 2019 and 2020, we saw the largest declines in April and May 2020, that is, one month after the start of the lockdown.

Project focuses on the implementation of ICT solutions to health and social services. This paper introduces innovation into senior care system on the city district level. Special attention is given to the use of modern technologies, particularly in the field of senior care in their home environment. Within this framework, the technologies are perceived as complementary to health care, not aiming to fully replace health care altogether. New measures must react to the requirements of both recipients and care providers. The paper contains an analysis of these requirements, attitudes and capacities of main stakeholders in the senior care system. The paper also deals with financial and legislative issues related to the introduction of innovation in such way to ensure the feasibility of the proposed solution. Results of this work are transferable to other city districts in Prague and to other municipalities in the Czech Republic as well.

Background: Understanding the impact of pandemic measures on elderly mobility is crucial for shaping public health responses. This retrospective study assesses the changes in mobility of 216 elderly individuals (average age 84 years) in the Czech Republic before and during COVID-19 restrictions, using two years of GPS tracking data. Methods: We conducted statistical analyses across various physical, demographic, and social factors. Data were analyzed for mobility patterns, SOS alarm usage, and relationships between mobility and factors such as age group, body mass index, sex, city size, and housing type. Results: During the study, 4409 SOS alarms were triggered, with only 16.6% requiring action. Alarms triggered outside the home decreased from 34% pre-COVID-19 to 29% during COVID-19, reflecting reduced outdoor activity. Mobility decreased by 43.9% overall during the pandemic. The largest year-on-year decline in mobility was in May, reaching 57.6%. However, 10% of the participants exhibited increased mobility. Factors such as age group, body mass index, sex, city size, and type of housing were analyzed, and we found that city size and housing type did not significantly influence mobility levels. Conclusions: These findings highlight the substantial decline in elderly mobility during the COVID-19 pandemic and emphasize the need for tailored interventions, such as outdoor mobility programs and telemedicine, to support elderly populations during public health crises.

Falls in older adults are a leading cause of injury, and the time spent on the floor afterwards is the stronger predictor of outcome. We present a low-cost system that detects the sustained lying posture following a fall. An FLIR Lepton 3.1R (160 × 120 px) and an int8-quantized FOMO detector run fully on an OpenMV RT1062 board; no image data leaves the node. Ten healthy adults, none in the training data, followed a structured posture protocol, yielding 3034 labelled frames. No fall, real or simulated, was recorded: lying is a proxy for a post-fall state, and claims are restricted accordingly. The detector produced an output on only 66.3% of labelled frames, with a strong class dependence (75.6% lying, 51.7% standing). End-to-end, binary lying-posture recognition reached a sensitivity of 0.723 (95% CI 0.637–0.812) and an F1 of 0.801. Every sustained lying bout of at least 20 s was flagged, but the deployed alert rule also produced roughly one hundred false alerts per hour of non-lying activity. Low-resolution thermal sensing is therefore a workable basis for long-lie detection; the limiting factors are the detector’s class-dependent miss rate and the alert logic, not the posture classifier.