Machine Learning Prediction of Fall Risk in Older Adults Using Timed Up and Go Test Kinematics

Falls among the elderly population cause detrimental physical, mental, financial problems and, in the worst case, death. The increasing number of people entering the higher risk age-range has increased clinicians’ attention to intervene. Clinical tools, e.g., the Timed Up and Go (TUG) test, have been created for aiding clinicians in fall-risk assessment. Often simple to evaluate, these assessments are subject to a clinician’s judgment. Wearable sensor data with machine learning algorithms were introduced as an alternative to precisely quantify ambulatory kinematics and predict prospective falls. However, they require a long-term evaluation of large samples of subjects’ locomotion and complex feature engineering of sensor kinematics. Therefore, it is critical to build an objective fall-risk detection model that can efficiently measure biometric risk factors with minimal costs. We built and studied a sensor data-driven convolutional neural network model to predict older adults’ fall-risk status with relatively high sensitivity to geriatrician’s expert assessment. The sample in this study is representative of older patients with multiple co-morbidity seen in daily medical practice. Three non-intrusive wearable sensors were used to measure participants’ gait kinematics during the TUG test. This data collection ensured convenient capture of various gait impairment aspects at different body locations.

[1]  L. Maxim,et al.  Screening tests: a review with examples , 2014, Inhalation toxicology.

[2]  Fabien Buisseret,et al.  Timed Up and Go and Six-Minute Walking Tests with Wearable Inertial Sensor: One Step Further for the Prediction of the Risk of Fall in Elderly Nursing Home People , 2020, Sensors.

[3]  M. Woollacott,et al.  Predicting the probability for falls in community-dwelling older adults using the Timed Up & Go Test. , 2000, Physical therapy.

[4]  K. Hill,et al.  The impact of care recipient falls on caregivers. , 2013, Australian health review : a publication of the Australian Hospital Association.

[5]  L. Shrestha,et al.  Life expectancy in the United States. , 1983, Statistical bulletin.

[6]  Richard W. Bohannon,et al.  Reference Values for the Timed Up and Go Test: A Descriptive Meta‐Analysis , 2006, Journal of geriatric physical therapy.

[7]  A. Odibo,et al.  Statistical Analysis and Interpretation of Prenatal Diagnostic Imaging Studies, Part 1 , 2011, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[8]  Takehiko Doi,et al.  Development and validity of methods for the estimation of temporal gait parameters from heel-attached inertial sensors in younger and older adults. , 2017, Gait & posture.

[9]  N. A. Zakaria,et al.  Quantitative analysis of fall risk using TUG test , 2015, Computer methods in biomechanics and biomedical engineering.

[10]  M. Wolf,et al.  The cost and frequency of hospitalization for fall-related injuries in older adults. , 1992, American journal of public health.

[11]  S. Studenski,et al.  Functional reach: a new clinical measure of balance. , 1990, Journal of gerontology.

[12]  Sang Gi Hong,et al.  Gait event detection algorithm based on smart insoles , 2020 .

[13]  W. Hayes,et al.  Impact near the hip dominates fracture risk in elderly nursing home residents who fall , 1993, Calcified Tissue International.

[14]  Predicting the probability of falls in geriatrics using traditional timed up and go test and dual-task constraint timed up and go test: An observational study , 2017 .

[15]  J. Stevens,et al.  Development of STEADI , 2013, Health promotion practice.

[16]  Kamiar Aminian,et al.  Gait and Foot Clearance Parameters Obtained Using Shoe-Worn Inertial Sensors in a Large-Population Sample of Older Adults , 2013, Sensors.

[17]  Wayne Dite,et al.  A clinical test of stepping and change of direction to identify multiple falling older adults. , 2002, Archives of physical medicine and rehabilitation.

[18]  Keith D. Hill,et al.  A new test of dynamic standing balance for stroke patients : Reliability, validity and comparison with healthy elderly , 1996 .

[19]  K. Berg Measuring balance in the elderly: preliminary development of an instrument , 1989 .

[20]  Daniel A. Sterling,et al.  Geriatric falls: injury severity is high and disproportionate to mechanism. , 1998 .

[21]  Yoshihisa Hirakawa,et al.  Falls of the elderly are associated with burden of caregivers in the community , 2006, International journal of geriatric psychiatry.

[22]  Salvatore Sessa,et al.  A Methodology for the Performance Evaluation of Inertial Measurement Units , 2013, J. Intell. Robotic Syst..

[23]  Barry R. Greene,et al.  Quantitative Falls Risk Assessment Using the Timed Up and Go Test , 2010, IEEE Transactions on Biomedical Engineering.

[24]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Jeffrey M. Hausdorff,et al.  An instrumented timed up and go: the added value of an accelerometer for identifying fall risk in idiopathic fallers , 2011, Physiological measurement.

[26]  R. Faulkner,et al.  The history of falls and the association of the timed up and go test to falls and near-falls in older adults with hip osteoarthritis , 2007, BMC geriatrics.

[27]  H B Weiss,et al.  Traumatic brain injuries evaluated in U.S. emergency departments, 1992-1994. , 2000, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[28]  Diane Podsiadlo,et al.  The Timed “Up & Go”: A Test of Basic Functional Mobility for Frail Elderly Persons , 1991, Journal of the American Geriatrics Society.

[29]  Robert L. Berg,et al.  Falls in Older Persons: Risk Factors and Prevention , 1992 .