Preserving Health: Health Technology for Fall Prevention
By Thurmon Lockhart, Locomotion Research Lab, Arizona State University
Market projections indicate significant growth in health monitoring sensors and network technologies in the coming years. This expansion is driven by a fundamental shift in healthcare: moving from treating illness to proactive prevention. Health monitoring systems are also enabling personalized medical care based on continuous physiological data. This transformation is further fueled by advancements in miniature devices, microelectronics, and wireless communication, promising a revolution in healthcare.
This special issue focuses on the vital role of mobile and wearable technology in fall risk assessment, a critical area given the serious challenges falls pose to older adults. Falls are a leading cause of mortality, mobility limitations, and premature nursing home placement. Accurate fall risk assessment can facilitate early intervention and treatment. However, subtle mobility impairments often go unnoticed, leading to increased fall risk. Early detection is paramount for timely interventions.
The Need for Fall Prevention
While many technologies for fall detection exist, they often come into play after a fall has already occurred. Fall prevention, rather than simple detection, is key. Because falls stem from multiple causes, effective solutions must consider a multi-faceted approach. The research presented in this special issue explores fall prevention strategies from multiple levels by simultaneously monitoring a range of functions in older adults and those with specific health conditions. Investigations are underway in the areas of fall risk assessment and prediction, including balance and mobility.
Although biomechanical and physiological factors associated with mobility issues and fall risk have been established at a population level. However, it is still unknown how these features can be used for personalized assessments in various international environments.
This research topic aims to provide models of health assessments utilizing time-varying physiological and biomechanical fall risk characteristics using various subjective and objective techniques.
Research Highlights
One study, “The Developments and Iterations of a Mobile Technology-Based Fall Risk Health Application,” by Hsieh et al., explores a mobile application to assess fall risk, particularly in individuals with Multiple Sclerosis (MS) and those who use wheeled devices. The authors suggest that this technology has the potential to deliver personalized fall risk screening to specific patient populations.
Another study, “Explainable Fall Risk Prediction in Older Adults Using Gait and Geriatric Assessment,” by Mishra et al., used gait parameters and fall history data from 92 older adults to develop a fall risk prediction system using a machine-learning model. This model aims to explain individual fall risk factors, aiding in the development of targeted, effective interventions. Explainable machine learning is particularly critical for fall risk prediction, as it can pinpoint specific areas to address, thereby reducing fall risk.
Subramaniam et al.’s review, “Wearable Sensor Systems for Fall Risk Assessment: A Review,” provides an overview of technology involving inertial measurement units (IMUs) and insole devices to assess gait parameters and postural stability, essential for assessing fall risk. The review identifies key gait stability measures and emphasizes the importance of spatiotemporal parameters, biomechanical gait parameters, and data analysis methods.
Finally, the study “Assessing fall risk in osteoporosis patients: a comparative study of age-matched fallers and nonfallers,” by Hyun Moon et al., investigated gait and postural stability in osteoporosis patients. This research also looked at various biomarkers to establish their relationship to fall risk. This study revealed that fall risk can be assessed using IMUs at home and found that fallers were less active than non-fallers. In addition, this study linked certain biomarkers to increased risk, including low levels of calcium, Vitamin D, and indicators of reduced renal function. This study highlighted the need to assess biomarkers, and gait and postural stability measures to characterize frequent fallers.
Author Contributions: TL: Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Resources, Software, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing.
Conflict of interest: The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher’s note: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers.
Keywords: fall risk assessment, gait and posture, ADL (activities of daily life), osteoporosis, multiple sclerosis, older adults, machine learning algorithms, mobile technology
