Sensitivity of Apple Watch fall detection feature among wheelchair users

Abou, Libak; Fliflet, Alexander; Hawari, Lina; Presti, Peter; Sosnoff, Jacob J.; Mahajan, Harshal P.; Frechette, Mikaela L; Rice, Laura A.

doi:10.1080/10400435.2021.1923087

Cited by 14 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such differences indicate that different pre-trained networks extracted features that contain spatial information distinct in classification performance. (ii) Comparing performance for cases (1,2,3) with cases (4,5,6) and cases (7,8,9), it appears that both multistatic and salient fusion lead to enhanced classification. Comparing the results between cases (4,5,6) indicates there were only minor differences for both tasks (i.e., accuracy in case 4 was only 0.8% higher than in case 5 for fall type classification task).…”

Section: Discussionmentioning

confidence: 99%

“…Regarding the former, commonly used sensors include inertial measurement units (IMUs). The potential of wearable sensors has been explored in fall risk assessment [8] and outdoor fall detection [9]. Fall risk assessment with wearable sensing systems requires a series of instructions under supervision [8], [9], and the need for bodily contact makes it less usable for certain individuals.…”

mentioning

confidence: 99%

“…The potential of wearable sensors has been explored in fall risk assessment [8] and outdoor fall detection [9]. Fall risk assessment with wearable sensing systems requires a series of instructions under supervision [8], [9], and the need for bodily contact makes it less usable for certain individuals. Contactless sensing systems, in contrast, can achieve passive (or ambient) monitoring [10]- [12].…”

mentioning

confidence: 99%

See 2 more Smart Citations

An Indoor Fall Monitoring System: Robust, Multistatic Radar Sensing and Explainable, Feature-Resonated Deep Neural Network

Shen

Tsui

Nussbaum

et al. 2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Indoor fall monitoring is challenging for community-dwelling older adults due to the need for high accuracy and privacy concerns. Doppler radar is promising, given its low cost and contactless sensing mechanism. However, the line-of-sight restriction limits the application of radar sensing in practice, as the Doppler signature will vary when the sensing angle changes, and signal strength will be substantially degraded with large aspect angles. Additionally, the similarity of the Doppler signatures among different fall types makes it extremely challenging for classification. To address these problems, in this paper we first present a comprehensive experimental study to obtain Doppler radar signals under large and arbitrary aspect angles for diverse types of simulated falls and daily living activities. We then develop a novel, explainable, multi-stream, feature-resonated neural network (eMSFRNet) that achieves fall detection and a pioneering study of classifying seven fall types. eMSFRNet is robust to both radar sensing angles and subjects. It is also the first method that can resonate and enhance feature information from noisy/weak Doppler signatures. The multiple feature extractors -including partial pre-trained layers from ResNet, DenseNet, and VGGNet -extracts diverse feature information with various spatial abstractions from a pair of Doppler signals. The feature-resonated-fusion design translates the multi-stream features to a single salient feature that is critical to fall detection and classification. eMSFRNet achieved 99.3% accuracy detecting falls and 76.8% accuracy for classifying seven fall types. Our work is the first effective multistatic robust sensing system that overcomes the challenges associated with Doppler signatures under large and arbitrary aspect angles, via our comprehensible feature-resonated deep neural network. Our work also demonstrates the potential to accommodate different radar monitoring tasks that demand precise and robust sensing.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

An Indoor Fall Monitoring System: Robust, Multistatic Radar Sensing and Explainable, Feature-Resonated Deep Neural Network

Shen

Tsui

Nussbaum

et al. 2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…2.1 Authors of [1] the research delves into the global health concern posed by falls and introduces a framework for detecting wheelchair fall anomalies. This framework combines the Isolation Forest (IF) and threshold-based method (TBM).…”

Section: Literature Surveymentioning

confidence: 99%

Promoting sustainable safety: Integrating fall detection for person and wheelchair safety

Polepaka,

Sangem,

Aleti

et al. 2024

E3S Web of Conf.

View full text Add to dashboard Cite

Fall detection systems are crucial for ensuring the safety of the elderly, especially those who are wheelchair-bound. A potential remedy involves promptly detecting human falls in near real-time to facilitate rapid assistance. While various methods have been suggested for fall detectors, there remains a necessity to create precise and sturdy architectures, methodologies, and protocols for detecting falls, particularly among elderly individuals, especially those using wheelchairs. The objective is to design an affordable and dependable IoT-based system for detecting falls in wheelchair users, alerting nearby individuals for assistance and promote sustainable safety. The setup includes a MEMS Sensor, GSM module, and Arduino UNO microcontroller for detecting falls, with the goal of securing the well-being and promoting independent living for the elderly.

show abstract

“…The availability of digital devices provides an opportunity to explore and adopt digital biomarkers as objective quantifiable measures [ 69 , 70 ]. Although an experimental study of intentional falls from a wheelchair among able-bodied young adults using Apple Watch showed poor sensitivity for fall detection [ 71 ], numerous anecdotes of improved outcomes from hard falls due to detection by Apple Watch consistently make the news. To assess the utility of such devices, a clinical trials (NCT04304495) GAPcare II has been initiated.…”

Section: Reviewmentioning

confidence: 99%

Advances in Traumatic Brain Injury Biomarkers

Nishimura¹,

Cordeiro²,

Ahmed³

et al. 2022

Cureus

View full text Add to dashboard Cite

Traumatic brain injury (TBI) is increasingly a major cause of disability across the globe. The current methods of diagnosis are inadequate at classifying patients and prognosis. TBI is a diagnostic and therapeutic challenge. There is no Food and Drug Administration (FDA)-approved treatment for TBI yet. It took about 16 years of preclinical research to develop accurate and objective diagnostic measures for TBI. Two brain-specific protein biomarkers, namely, ubiquitin C-terminal hydrolase-L1 and glial fibrillary acidic protein, have been extensively characterized. Recently, the two biomarkers were approved by the FDA as the first blood-based biomarker, Brain Trauma Indicator™ (BTI™), via the Breakthrough Devices Program. This scoping review presents (i) TBI diagnosis challenges, (ii) the process behind the FDA approval of biomarkers, and (iii) known unknowns in TBI biomarker biology. The current lag in TBI incidence and hospitalization can be reduced if digital biomarkers such as hard fall detection are standardized and used as a mechanism to alert paramedics to an unresponsive trauma patient.

show abstract

Sensitivity of Apple Watch fall detection feature among wheelchair users

Cited by 14 publications

References 23 publications

An Indoor Fall Monitoring System: Robust, Multistatic Radar Sensing and Explainable, Feature-Resonated Deep Neural Network

An Indoor Fall Monitoring System: Robust, Multistatic Radar Sensing and Explainable, Feature-Resonated Deep Neural Network

Promoting sustainable safety: Integrating fall detection for person and wheelchair safety

Advances in Traumatic Brain Injury Biomarkers

Contact Info

Product

Resources

About