Evaluation and Integration of an Automatic Fall Prediction System

Falls among the elderly are a significant cause of morbidity, mortality, and increased end-of-life health care costs. Most falls are related to predispositions to unsteadiness, impaired gait, muscle weakness, impaired cognitive and sensory functioning, and prior fall history. In addition, antipsychotic and antidepressant drugs contribute to fall risk by affecting cognitive and perceptual motor processes. Studies examining fall-risk factors cite the following as the most common: unsteady gait, need for extensive assistance in activities of daily living (ADL), and wandering, all of which relate to patterns in movement. An increase in the variability in stride-to-stride velocity has also been identified as an important risk factor for subsequent falls. Thus, changes in the quality and quantity of movement are prominent features associated with changes in health, medication regimens, cognitive impairment, and other predisposing factors involved in fall risk. 

This project sought to confirm the hypothesis that variability in voluntary movement paths of assisted living facility (ALF) residents would be greater in patients who fell the week preceding their fall as compared to residents who did not fall. To evaluate this hypothesis, a prospective observational study using telesurveillance technology was employed. The research determined if a measure of movement variability called Fractal D path tortuosity (Fractal D) would increase fall predictability beyond estimates provided by a fall.  

The main objectives of this project were to:

• Evaluate the relationship between conventional fall-risk assessment measures using performance on standardized gait and balance (SGB) tests and Fractal D movement tortuosity measures. 
• Evaluate tortuosity changes preceding a fall. 
• Gather requirements for a software module to perform online fall-risk assessment in community-based settings. 

Over a period of a year, the movements of 53 elderly residents in two ALFs were monitored and their falls were recorded. Baseline SGB assessments were completed during this time. The velocity, distance and duration, and changes in direction during the individual's daytime movements in common areas of congregate living settings were tracked. Mean Fractal D during the week preceding a fall in 23 individuals who subsequently fell was statistically significantly higher than for 30 individuals who did not fall. Analysis showed that only Fractal D and a history of one or more previous falls were significant fall predictors. 

The project team determined that the relationship between SGB and subsequent falls is weak, although there is a relationship between some SGB measures and Fractal D. The team was able to demonstrate that an automatic dynamic quantitative assessment of the variability of everyday movements is an independent predictor of fall risk which, when combined with other known risk factors for falls, can significantly improve the accuracy of fall prediction than can other risk factors alone. This work led to the creation of a patented system of hardware and customized software that provides a reliable and automatic assessment of Fractal D and can be used in ALFs and nursing homes.