Accurate fall detection for patients with Parkinson's disease based on a data event algorithm and wireless sensor nodes. (May 2020)

• Record Type: Journal Article
• Authors: Ali Hashim, Huda; Mohammed, Saleem Latteef; Gharghan, Sadik Kamel
• Is Part Of: Measurement. Volume 156(2020)
• Publication Date: 2020-05
• Subjects: Accelerometer sensor -- Data event algorithm -- Fall detection -- Myoware sensor -- Parkinson's disease -- Wireless sensor network; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2020.107573
• Languages: English
• ISSNs: 0263-2241

Abstract

Graphical abstract: Highlights: WFDS achieves a high-performance accuracy, sensitivity, and specificity. Fall in PD was accurately determined based on a proposed DEA. DFE accurately distinguished between direction fall and the patient's activities. Selecting of Mg_th = 2 g is enough to avoid all false alarms. Distinguish between falls and ADLs is achieved when Mg_th = 2 and 3 g. Abstract: Elderly fall detection in Parkinson's disease (PD) and epilepsy can cause broken bones or other injuries, decreasing the quality of life and possibly resulting in death. However, such fall-detection systems suffer from certain limitations and challenges such as fall-detection accuracy. This work aims to design and implement a wearable fall-detection system (WFDS) for PD patients based on the low-power ZigBee wireless sensor network (WSN). Patient falls were accurately detected based on the data event algorithm (DEA) results of two wireless sensor nodes an accelerometer and Myoware mounted on the patient's body. The fall direction of the PD was accurately determined based on a direction fall event (DFE) algorithm in the receiver node. The experimental results show that the WFDS achieved 100% accuracy, sensitivity, and specificity in detecting the patient's fall. The experimental WFDS appears to outperform existing modalities in terms of fall detection sensitivity, accuracy, and specificity.