Kemmler W (2024)
Publication Type: Authored book
Publication year: 2024
Publisher: Springer Nature
ISBN: 9783031672569
DOI: 10.1007/978-3-031-67256-9_4
Falls are the leading cause of injury, hospitalization, and accidental death in older people. Many studies provide considerable evidence that the majority of health-related aspects of fall risk can be positively affected by physical activity or, even better, dedicated exercise interventions. Artificial Intelligence (AI)-based fall technology is the most advanced fall prevention technology currently available. Sensor-based AI concepts with direct feedback options significantly increase the safety and effectiveness of conventional training concepts or e-exercise programs even in non- or only partially supervised training settings. Smart technologies also provide closer monitoring of performance development, an aspect important for the subsequent alignment of the exercise intervention. However, while the predictive ability of present technology to determine the individual risk of fall is satisfactory, current AI-based approaches do not address the identification of dedicated fall risk factors in a way that would allow a precise response through specific exercise intervention. Future research should focus on interpretable AI-based concepts that provide a deeper insight into the individual risk factor profile in order to generate comprehensive training interventions that address several risk factors in a parallel but prioritized manner.
APA:
Kemmler, W. (2024). Sensors, Internet of Things and Artificial Intelligence for the Diagnosis and Prevention of Falls and Fall-Related Injuries in Older People—An Exercise-Related Perspective. Springer Nature.
MLA:
Kemmler, Wolfgang. Sensors, Internet of Things and Artificial Intelligence for the Diagnosis and Prevention of Falls and Fall-Related Injuries in Older People—An Exercise-Related Perspective. Springer Nature, 2024.
BibTeX: Download