Biomechanical Parameters and Clinical Assessment Scores for Identifying Elderly Fallers Based on Balance and Dynamic Tasks

Abstract

Accidental falls are a major health concern among older adults. Currently, fall prevention programs employ clinical assessment scores for identifying elderly fallers based on cutoff values. Biomechanical parameters provide crucial information differentiating pathological gait and posture and can be used to classify elderly fallers and non-fallers. Pattern recognition models based on biomechanical parameters may provide greater insight for such classification. The purpose of this study was to compare the classification accuracy of different pattern recognition models for identifying elderly fallers using biomechanical parameters measured during balance and gait tasks. Pattern recognition models were also developed using clinical assessment scores and compared to the models based on biomechanical parameters for accurately identifying elderly fallers. Participants included 58 non-fallers (age = 72.3 ± 5.7) and 41 fallers (age = 74.0 ±12.3) who performed balance and gait tasks on a walkway with embedded force plates and pressure mats. The parameters included 2D ground reaction force (GRF), center of pressure (COP), and the plantar pressure (PP). Using this data as input, different classification algorithms were used to build models. Maximum accuracy of 86.02% for classifying faller/non-faller categories was obtained using a classifier based on biomechanical parameters from combined gait and balance tasks. The GRF parameters ranked higher than COP and PP parameters based on F-score ranking suggesting predictor importance of GRF parameters. The classification performance was further improved by adding GRF parameters to the more commonly used COP parameters. However, the classifiers based on clinical assessment scores resulted in a maximum accuracy of 92.93% suggesting that elderly fallers can be accurately classified using pattern recognition models based on clinical assessment scores. INDEX TERMS Balance, biomechanical parameters, classification, clinical assessment tools, fall risk, gait, older adults.

Micro-Doppler Radar Gait Measurement to Detect Age- and Fall Risk-Related Differences in Gait: A Simulation Study on Comparison of Deep Learning and Gait Parameter-Based Approaches

“…For this purpose, gait information that shows differences in fall risks should be effective for screening people with high fall risks. Many studies have verified the significant differences in gait between participant groups with different fall risks, such as young adults, elderly adults, and elderly adults with a history of falls [2]- [4]. In particular, elderly adults with a history of multiple falls have significant fall risks [5], [6], and the detection of such risks via the gait information is important to prevent repeated falls.…”

“…However, participants must wear numerous acceleration sensors in these approaches. Although sensing systems using force plates or pressure mats have also been used [4], [8], their measurement areas are limited to the sensor surface and the measurable gait information is thus limited compared with that obtainable using other sensors. To achieve simple and unconstrained gait measurement, optical remote sensing techniques such as depth sensing and camerabased analysis have been widely used [10]- [12].…”

Bedtime Monitoring for Fall Detection and Prevention in Older Adults

“…Similarly, the work in [ 46 ] focuses on rehabilitation exercises and, more specifically, those exercises performed with the lower limb. In this sense, the work in [ 47 ] points to any task involving gait as a major cause for falls. The works in [ 30 , 31 , 48 , 49 ] focus on the intrinsic factors that cause imbalances, such as muscle strength or the ability to posture control.…”

Survey on Video-Based Biomechanics and Biometry Tools for Fracture and Injury Assessment in Sports

“…Given the aforementioned context, it is clear that smart tools for fracture prevention in sports would benefit greatly the field of sports sciences. The same tool could have important impact in elderly healthcare [66]. A plausible solution for this method is the combination of artificial intelligence (AI) and biomechanics.…”