The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project addresses the costly and life-altering occurrence of falls among older adults. One in three adults over the age of 65 fall each year, and 31% of those falls are attributed to environmental hazards such as floor clutter, rugs, poor lighting, and low contrast. Costs associated with falls will reach $55 billion by 2020 according to the Centers for Disease Control and Prevention (CDC). The economic, social, and health impacts of falls will only continue to get worse as the older adult demographic increases from 40 million today to 72 million in the next 15 years. Through this project, advances in hazard detection algorithms and decision support approaches will contribute to helping prevent millions of falls among older and disabled Americans each and every year. By expanding access to expert environmental fall hazard assessments, the rate of hospitalizations and costly readmissions attributed to falls can be reduced.
The proposed project will develop and test a proof-of-concept for an automated fall hazard assessment system. In the face of an aging demographic, falls are becoming a national and global issue. A low-cost fall assessment system can facilitate the identification and mitigation of environmental hazards before they cause a fall. This project will research and develop computer vision, machine learning, and sensor fusion software algorithms to implement automated detection of potential environmental fall hazards and a risk-based assessment of those hazards for indoor spaces. A custom sensor suite will be used to detect hazards, while a mathematical model of risk will assess the collection of hazards in the context of the area and resident characteristics to suggest appropriate interventions. The project?s outcomes will advance the state of the art in fall prevention technology for older adults, and will be the first proof-of-concept to test the effectiveness of such methods to supplement expert home assessments.
