(A) low-cost, markerless tailored fall care system for older adults integrating multifactorial fall risk assessment and modular fall interventions

Abstract

With the rapid population aging, falls in older people have become a major public health concern due to their high prevalence and serious adverse effects. Accurate fall risk assessment and effective fall intervention are essential to reduce fall risks and prevent falls. This dissertation aims to develop a low-cost, accurate, and effective fall-care system for older people by integrating multifactorial fall risk assessment and tailored fall interventions utilizing a marker-less Microsoft Kinect. First, a Kinect-based, low-cost multifactorial fall risk assessment system was developed to comprehensively assess major fall risk factors on physiological, psychological, and integrated functions. This system was further tested on 106 Korean older women to examine significant outcome measures and build machine learning-based classification models for predicting prospective fall risk. The system can predict prospective fallers with 84.7% accuracy and the individual's performance was computed as the percentile value of a normative database so that deficiencies can be clearly visualized and targeted for intervention. Second, modularized exergame programs with different difficulty levels were developed to provide tailored fall interventions for the older individuals based on their fall risk assessment results and intervention progress. By seamlessly integrating multifactorial fall risk assessment and tailored fall interventions, a total Kinect-based fall care system was newly developed. A follow-up experiment on 30 new community-dwelling older women was conducted to examine the effectiveness and usability of this developed system for fall prevention. Results showed that the Kinect-based 8-week tailored interactive fall interventions effectively improved older people’s physical and cognitive abilities. The system usability was also excellent regardless of older individuals’ computer skills. Therefore, the developed fall care system can not only accurately screen out older people at fall risk and identify their potential risk factors, but also effectively prevent falls with tailored interventions with a convenient setup for older people.