Fall prediction in neurological gait disorders: differential contributions from clinical assessment, gait analysis, and daily-life mobility monitoring

Abstract

Objective To evaluate the predictive validity of multimodal clinical assessment outcomes and quantitative measures of in- and off-laboratory mobility for fall-risk estimation in patients with different forms of neurological gait disorders. Methods The occurrence, severity, and consequences of falls were prospectively assessed for 6 months in 333 patients with early stage gait disorders due to vestibular, cerebellar, hypokinetic, vascular, functional, or other neurological diseases and 63 healthy controls. At inclusion, participants completed a comprehensive multimodal clinical and functional fall-risk assessment, an in-laboratory gait examination, and an inertial-sensor-based daily mobility monitoring for 14 days. Multivariate logistic regression analyses were performed to identify explanatory characteristics for predicting the (1) the fall status (non-faller vs. faller), (2) the fall frequency (occasional vs. frequent falls), and (3) the fall severity (benign vs. injurious fall) of patients. Results 40% of patients experienced one or frequent falls and 21% severe fall-related injuries during prospective fall assessment. Fall status and frequency could be reliably predicted (accuracy of 78 and 91%, respectively) primarily based on patients' retrospective fall status. Instrumented-based gait and mobility measures further improved prediction and provided independent, unique information for predicting the severity of fall-related consequences. Interpretation Falls- and fall-related injuries are a relevant health problem already in early stage neurological gait disorders. Multivariate regression analysis encourages a stepwise approach for fall assessment in these patients: fall history taking readily informs the clinician about patients' general fall risk. In patients at risk of falling, instrument-based measures of gait and mobility provide critical information on the likelihood of severe fall-related injuries.

Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall

“…The causes of falls are multifactorial (medication use, complex activities, stress, environmental complexities, and sleep quality) [7][8][9]. In addition, individuals that enter in a pre-frail or frail condition experience deterioration and de-harmonization in neuromuscular, sensory, and cognitive functions.…”

“…In addition, individuals that enter in a pre-frail or frail condition experience deterioration and de-harmonization in neuromuscular, sensory, and cognitive functions. Finally, considering the fact that static postural control [10], locomotion, and navigation are tasks that have high cognitive demands, especially in terms of attention [11] as well as executive functioning [12,13], deterioration at the sensorimotor and cognitive levels leads to gait and balance disorders increasing the risk of fall [1,2,8,[10][11][12][13][14][15].…”

Ambient Monitoring of Gait and Machine Learning Models for Dynamic and Short-Term Falls Risk Assessment in People With Dementia

“…Wearable technologies have been used in multiple studies to assess fall risk in older adults [7], [14]- [16]. While prospective fall-risk prediction via wearable sensors is potentially very useful for cognitively healthy older adults, compliance and adherence challenges limit the use of sensors in individuals with the dementia.…”

Ambient Monitoring of Gait and Machine Learning Models for Dynamic and Short-Term Falls Risk Assessment in People With Dementia

“…An important part of a falls prevention plan is determining the level of risk of falling. One of the shortcomings of many existing approaches is that their risk evaluation is solely based on a static baseline assessment of individuals, which identifies the risk of falling over time frames of months to years [7]. By this standard, most LTC residents are accurately categorized as having a high risk of falling, making it difficult for care staff to act upon this information.…”