A Postural Assessment Utilizing Machine Learning Prospectively Identifies Older Adults at a High Risk of Falling

Abstract

Introduction: Falls are the leading cause of accidental death in older adults. Each year, 28.7% of US adults over 65 years experience a fall resulting in over 300,000 hip fractures and $50 billion in medical costs. Annual fall risk assessments have become part of the standard care plan for older adults. However, the effectiveness of these assessments in identifying at-risk individuals remains limited. This study characterizes the performance of a commercially available, automated method, for assessing fall risk using machine learning.Methods: Participants (N = 209) were recruited from eight senior living facilities and from adults living in the community (five local community centers in Houston, TX) to participate in a 12-month retrospective and a 12-month prospective cohort study. Upon enrollment, each participant stood for 60 s, with eyes open, on a commercial balance measurement platform which uses force-plate technology to capture center-of-pressure (60 Hz frequency). Linear and non-linear components of the center-of-pressure were analyzed using a machine-learning algorithm resulting in a postural stability (PS) score (range 1–10). A higher PS score indicated greater stability. Participants were contacted monthly for a year to track fall events and determine fall circumstances. Reliability among repeated trials, past and future fall prediction, as well as survival analyses, were assessed.Results: Measurement reliability was found to be high (ICC(2,1) [95% CI]=0.78 [0.76–0.81]). Individuals in the high-risk range (1-3) were three times more likely to fall within a year than those in low-risk (7–10). They were also an order of magnitude more likely (12/104 vs. 1/105) to suffer a spontaneous fall i.e., a fall where no cause was self-reported. Survival analyses suggests a fall event within 9 months (median) for high risk individuals.Conclusions: We demonstrate that an easy-to-use, automated method for assessing fall risk can reliably predict falls a year in advance. Objective identification of at-risk patients will aid clinicians in providing individualized fall prevention care.

Fall risk classification with posturographic parameters in community-dwelling older adults: a machine learning and explainable artificial intelligence approach

“…As we hypothesized, the discriminating ability varied with different criteria. Using criteria II according to a TUG test scores had good performance, comparable with or even superior to some studies with different study designs and ML methods [ 14 , 15 , 19 ]. It is not surprising because of multifactorial nature of falls, while TUG scores were correlated with balance and could be reflected by static posturographic features.…”

“…There have been several studies combining posturographic data and AI approach for fall risk classification in several populations, including the older adults living in communities or institutes [ 14 – 18 ], osteoporotic elderly [ 19 ], parkinsonism [ 20 ], and multiple sclerosis [ 11 ]. The posturographic data are obtained from force platforms [ 11 , 17 , 20 ], pressure platforms [ 16 ], inertial sensors [ 16 , 21 ], or depth camera [ 18 ].…”

A new approach for fall risk assessment in hospitalized older adults based on gait data

“…In recent years, many scholars have begun to use objective instruments to assess the risk of falls in older adults. These include a triaxial accelerometer and inertial sensor system 17,[33][34][35] , fall risk assessment based on a pressure platform 15,[36][37][38] , gait acquisition system based on marker points 18 , and gait acquisition systems without marking points 20,39 . This study attempted to use a gait analysis instrument to collect objective data and study its reliability, providing a new method for the clinical risk assessment of falls.…”

“…Since the 19th century, instruments have been developed to collect objective data on balance and gait in older adults to assess and predict fall risk. Thapa et al 14 and Forth et al 15 used a pressure-plate-based balancing instrument to measure balance-related indicators and predict the risk of repeated falls in older adults. Three-dimensional accelerometers have been developed to measure balance in older adults 16,17 .…”

Self-Monitoring of Balance Performance can Reduce the Rate of Falls Among Older Adults

“…The numeric score was displayed on a nearby computer display after the test with an associated color denoting fall risk category. Scores ranging 1-3 indicated high fall risk coinciding with a "red" risk group; scores ranging 4-6 indicated moderate fall risk, coinciding with a "yellow" risk group and scores ranging 7-10 indicated low fall risk coinciding with a "green" risk group (Forth et al, 2020). This "balance score" was immediately made available to the participant upon completion of the test and placed within the context of visual imagery depicting less independence and increased frailty for scores in the "red" risk group and increased independence and low frailty for scores in the "green" risk group.…”