Advances in Wearable Sensor Technology for Fall Prevention in Alzheimer’s Disease: Evidence, Challenges, and Opportunities: A Narrative Review

Abstract

Background & Purpose

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder which is strongly associated with decline in cognition and motor control, placing patients at high risk of falls. Conventional assessments for fall risk are unable to track real world mobility fluctuations in this population. Wearable sensor technology may offer continuous and objective monitoring to detect subtle gait and balance impairments. However, the pertinent evidence specific to AD remains inconclusive.

Objective & Rationale

To review and synthesize the current evidence on wearable sensors technology for fall prevention in Alzheimer’s disease, address the gap in synthesizing research specific to this population and outline challenges as well as future directions.

Methods

A narrative review was conducted in accordance with PRISMA standards. PubMed/MEDLINE, Scopus, Pedro, CINAHL, and Google Scholar were searched (2015–2025) using terms related to AD, falls, and wearable technologies. Eligible studies included randomized controlled trials, observational studies, systematic reviews, and feasibility trials assessing wearable devices (accelerometers, gyroscopes, inertial measurement units, smart footwear, wristbands, or body-mounted sensors) in populations with AD or mild cognitive impairment. Data extraction focused on sensor type, placement, intervention characteristics, outcomes, and implementation factors.

Results & Outcomes

Twenty-five studies met the inclusion criteria. Wearable devices consistently captured fall related biomarkers which included gait variability, stride length, and errors in motor planning. Sensor guided interventions demonstrated significant improvements in balance and dual task performance. However, the effects on gait and fall incidence were inconsistent. Consumer grade wearables such as wrist worn step trackers showed their caliber for low-cost risk management, while AI enabled systems achieved greater than 95% accuracy in fall detection. Patient adherence, device comfort, data overload, and privacy concerns were significant barriers. Methodological limitations in the studies were their small sample sizes, heterogeneity in outcome measures, and limited long term follow up.

Discussion & Conclusion

Wearable sensors provide valuable and objective insights into fall risk in AD which offers opportunities for establishing proactive and individualized fall prevention strategies. However, the current evidence is preliminary, with limited high-quality trials in AD specific populations. Future research should prioritize standardized protocols, larger clinical trials, and integration of wearable sensor technologies into multidisciplinary fall prevention frameworks.