You are here:
This project is co-financed by the European Regional Development Fund [ERDF].
One of the most common nursing phenomena is the fall event. More than a third of all people over 65 in Germany are acutely at risk of falling. The consequences of a fall can be not only physical (injuries) but also psychological (fear of further falls). This can lead to considerable impairment of the quality of life. The recognition of the fall risk and the resulting initiation of prophylactic measures is essential to avoid falls.
Aims and Procedure
The aim is to develop easy-to-use software that provides formal and informal carers and other health care professionals with a digital and effective tool for identifying the risk of falling and making decisions on preventive and mobility-preserving measures.
The research and development project addresses the following sub-segments:
- Fall risk identification
- Longer term fall prediction
- Automated recommendations for fall prevention/prophylaxis
Within the project applied for, the Research Group Geriatrics is mainly responsible for the research, identification and classification of general and specific fall risk factors from different data sources as well as the final evaluation of the individual digital applications developed in this R&D project for fall risk identifying gait analysis and fall prediction.
Using a smartphone/tablet camera, gait sequences are recorded and recognised as such. The generated data will be fed into a fall risk model (motion model) to be developed, thus training a neural network. With the help of an artificial intelligence (AI) these are calculated and their deviations from the healthy gait pattern are analysed and interpreted.
Innovations und Prospects
The individual fall risk of a person should be determined holistically with the help of artificial intelligence combined with biomechanical models of the human gait. From this, the risk of falling is determined and intervention measures are to be addressed individually and according to need. Digital solutions can relieve the burden on skilled workers and contribute to improving the quality of care. Both fall prediction and fall prevention deal with complex multifactorial problems due to the interaction between physiological, behavioural and environmental factors contributing to falls; the degree of innovation of the planned project is correspondingly high.