Exploring Quantitative Timed Up and Go Sensor Data with Statistical Learning Techniques
Anthony A. Wright · Scholarship at UWindsor (University of Windsor) · 2018
Injuries and hospitalizations due to accidental falls among seniors represent a major expense for the Canadian public health system. It is highly desirable to be able to predict risk of falls for senior individuals in order to place them in prevention programs. Recently, sensor technologies have been used to predict risk of falls and levels of frailty of individuals. A commonly used test for assessing risk of falls is known as QTUG (Quantitative `Timed Up and Go'). The QTUG data often consist of a small set of survey answers about the individuals' historic variables (e.g., number of falls in the past twelve months) and a large set of sensor-collected quantitative measurements related to the actual movement of the patient. In this paper, we have explored how well the sensor data predict the risk of falls for seniors by using statistical machine learning techniques. Our modes were better in predicting non-fallers rather than fallers.