Fall algorithm development using kinematic parameters measured from simulated falls performed in a quasi-realistic environment using accelerometry

Fall detection with body-worn sensors : a systematic review

BACKGROUND AND AIMS

Falls among older people remain a major public health challenge. Body-worn sensors are needed to improve the understanding of the underlying mechanisms and kinematics of falls. The aim of this systematic review is to assemble, extract and critically discuss the information available in published studies, as well as the characteristics of these investigations (fall documentation and technical characteristics).

METHODS

The searching of publically accessible electronic literature databases for articles on fall detection with body-worn sensors identified a collection of 96 records (33 journal articles, 60 conference proceedings and 3 project reports) published between 1998 and 2012. These publications were analysed by two independent expert reviewers. Information was extracted into a custom-built data form and processed using SPSS (SPSS Inc., Chicago, IL, USA).

RESULTS

The main findings were the lack of agreement between the methodology and documentation protocols (study, fall reporting and technical characteristics) used in the studies, as well as a substantial lack of real-world fall recordings. A methodological pitfall identified in most articles was the lack of an established fall definition. The types of sensors and their technical specifications varied considerably between studies.

CONCLUSION

Limited methodological agreement between sensor-based fall detection studies using body-worn sensors was identified. Published evidence-based support for commercially available fall detection devices is still lacking. A worldwide research group consensus is needed to address fundamental issues such as incident verification, the establishment of guidelines for fall reporting and the development of a common fall definition.

Fall classification by machine learning using mobile phones

Fall prevention is a critical component of health care; falls are a common source of injury in the elderly and are associated with significant levels of mortality and morbidity. Automatically detecting falls can allow rapid response to potential emergencies; in addition, knowing the cause or manner of a fall can be beneficial for prevention studies or a more tailored emergency response. The purpose of this study is to demonstrate techniques to not only reliably detect a fall but also to automatically classify the type. We asked 15 subjects to simulate four different types of falls-left and right lateral, forward trips, and backward slips-while wearing mobile phones and previously validated, dedicated accelerometers. Nine subjects also wore the devices for ten days, to provide data for comparison with the simulated falls. We applied five machine learning classifiers to a large time-series feature set to detect falls. Support vector machines and regularized logistic regression were able to identify a fall with 98% accuracy and classify the type of fall with 99% accuracy. This work demonstrates how current machine learning approaches can simplify data collection for prevention in fall-related research as well as improve rapid response to potential injuries due to falls.