Article

Evaluation of accelerometer-based fall detection algorithms on real-world falls.

Department of Electronics, Computer Science and Systems, University of Bologna, Bologna, Italy.
PLoS ONE (Impact Factor: 3.53). 05/2012; 7(5):e37062. DOI: 10.1371/journal.pone.0037062
Source: PubMed

ABSTRACT Despite extensive preventive efforts, falls continue to be a major source of morbidity and mortality among elderly. Real-time detection of falls and their urgent communication to a telecare center may enable rapid medical assistance, thus increasing the sense of security of the elderly and reducing some of the negative consequences of falls. Many different approaches have been explored to automatically detect a fall using inertial sensors. Although previously published algorithms report high sensitivity (SE) and high specificity (SP), they have usually been tested on simulated falls performed by healthy volunteers. We recently collected acceleration data during a number of real-world falls among a patient population with a high-fall-risk as part of the SensAction-AAL European project. The aim of the present study is to benchmark the performance of thirteen published fall-detection algorithms when they are applied to the database of 29 real-world falls. To the best of our knowledge, this is the first systematic comparison of fall detection algorithms tested on real-world falls. We found that the SP average of the thirteen algorithms, was (mean ± std) 83.0% ± 30.3% (maximum value = 98%). The SE was considerably lower (SE = 57.0% ± 27.3%, maximum value = 82.8%), much lower than the values obtained on simulated falls. The number of false alarms generated by the algorithms during 1-day monitoring of three representative fallers ranged from 3 to 85. The factors that affect the performance of the published algorithms, when they are applied to the real-world falls, are also discussed. These findings indicate the importance of testing fall-detection algorithms in real-life conditions in order to produce more effective automated alarm systems with higher acceptance. Further, the present results support the idea that a large, shared real-world fall database could, potentially, provide an enhanced understanding of the fall process and the information needed to design and evaluate a high-performance fall detector.

Download full-text

Full-text

Available from: Lorenzo Chiari, Jun 19, 2015
0 Followers
 · 
291 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: Falls represent a significant threat to the health and independence of adults aged 65 years and older. As a wide variety and large number of passive monitoring systems are currently and increasingly available to detect when individuals have fallen, there is a need to analyze and synthesize the evidence regarding their ability to accurately detect falls to determine which systems are most effective. The purpose of this literature review is to systematically assess the current state of design and implementation of fall-detection devices. This review also examines to what extent these devices have been tested in the real world as well as the acceptability of these devices to older adults. A systematic literature review was conducted in PubMed, CINAHL, EMBASE, and PsycINFO from their respective inception dates to June 25, 2013. Articles were included if they discussed a project or multiple projects involving a system with the purpose of detecting a fall in adults. It was not a requirement for inclusion in this review that the system targets persons older than 65 years. Articles were excluded if they were not written in English or if they looked at fall risk, fall detection in children, fall prevention, or a personal emergency response device. Studies were initially divided into those using sensitivity, specificity, or accuracy in their evaluation methods and those using other methods to evaluate their devices. Studies were further classified into wearable devices and nonwearable devices. Studies were appraised for inclusion of older adults in sample and if evaluation included real-world settings. This review identified 57 projects that used wearable systems and 35 projects using nonwearable systems, regardless of evaluation technique. Nonwearable systems included cameras, motion sensors, microphones, and floor sensors. Of the projects examining wearable systems, only 7.1% reported monitoring older adults in a real-world setting. There were no studies of nonwearable devices that used older adults as subjects in either a laboratory or a real-world setting. In general, older adults appear to be interested in using such devices although they express concerns over privacy and understanding exactly what the device is doing at specific times. This systematic review was limited to articles written in English and did not include gray literature. Manual paper screening and review processes may have been subject to interpretive bias. There exists a large body of work describing various fall-detection devices. The challenge in this area is to create highly accurate unobtrusive devices. From this review it appears that the technology is becoming more able to accomplish such a task. There is a need now for more real-world tests as well as standardization of the evaluation of these devices.
    12/2013; DOI:10.1097/JPT.0000000000000000
  • [Show abstract] [Hide abstract]
    ABSTRACT: Wearable telecare and telehealth systems are those which can be worn on the human body and continuously monitor a user’s vital status. Even though these systems have already shown promise in applications for improving medical service quality and reducing medical costs, a short battery life significantly restricts the widespread use of these systems. Low-power technologies (a general name for technologies which use various approaches to reduce the power consumption of the associated electronics) can help alleviate this disadvantage of wearable telecare and telehealth systems. In this paper, we review recent developments and applications of low-power technologies in wearable telecare and telehealth systems, sorting the various approaches into two categories: hardware-based approaches and firmware-based approaches. This paper focuses on illustrating how to realize these approaches but does not provide a quantitative analysis of different approaches, since the intended applications of these approaches are quite different, hence numeric comparison is not meaningful. Given the proliferation of wearable telecare and telehealth systems, there will be a greater emphasis on the development of low-power technologies in this field.
    03/2015; 5(1):1-9. DOI:10.1007/s13534-015-0174-2
  • [Show abstract] [Hide abstract]
    ABSTRACT: Although near-falls (or recoverable imbalances) are common episodes for many older adults, they have received a little attention and were not considered in the previous laboratory-based fall assessments. Hence, this paper addresses near-fall scenarios in addition to the typical falls and activities of daily living (ADLs). First, a novel vertical velocity-based pre-impact fall detection method using a wearable inertial sensor is proposed. Second, to investigate the effect of near-fall conditions on the detection performance and feasibility of the vertical velocity as a fall detection parameter, the detection performance of the proposed method (Method 1) is evaluated by comparing it to that of an acceleration-based method (Method 2) for the following two different discrimination cases: falls vs. ADLs (i.e. excluding near-falls) and falls vs. non-falls (i.e. including near-falls). Our experiment results show that both methods produce similar accuracies for the fall vs. ADL detection case; however Method 1 exhibits a much higher accuracy than Method 2 for the fall vs. non-fall detection case. This result demonstrates the superiority of the vertical velocity over the peak acceleration as a fall detection parameter when the near-fall conditions are included in the non-fall category, in addition to its capability of detecting pre-impact falls.
    IEEE Transactions on Neural Systems and Rehabilitation Engineering 09/2014; 23(2). DOI:10.1109/TNSRE.2014.2357806 · 2.82 Impact Factor