Freezing of Gait Detection in Parkinson's Disease: A Subject-Independent Detector Using Anomaly Scores

• Published in: IEEE transactions on biomedical engineering Vol. 64; no. 11; pp. 2719 - 2728
• Main Authors: Pham, Thuy T., Moore, Steven T., Lewis, Simon John Geoffrey, Nguyen, Diep N., Dutkiewicz, Eryk, Fuglevand, Andrew J., McEwan, Alistair L., Leong, Philip H.W.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accelerometers; Accelerometry - methods; Aged; Algorithms; Ankle; Anomalies; Anomaly score; Australia; Basal ganglia; Central nervous system diseases; Detectors; Diaries; Feature extraction; feature selection; Female; Fog; Gait; Gait Disorders, Neurologic - diagnosis; Gait Disorders, Neurologic - physiopathology; gait freezing; Gait recognition; Humans; Male; Manuals; Middle Aged; Movement disorders; Neurodegenerative diseases; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinson's disease; Reliability analysis; Reproducibility of Results; Sensitivity; Sensitivity and Specificity; Sensors; Signal Processing, Computer-Assisted; Accelerometers; Feature extraction; Parkinson's disease; Australia; Detectors; Manuals
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2017.2665438

Freezing of gait (FoG) is common in Parkinsonian gait and strongly relates to falls. Current clinical FoG assessments are patients' self-report diaries and experts' manual video analysis. Both are subjective and yield moderate reliability. Existing detection algorithms have been predominantly designed in subject-dependent settings. In this paper, we aim to develop an automated FoG detector for subject independent. After extracting highly relevant features, we apply anomaly detection techniques to detect FoG events. Specifically, feature selection is performed using correlation and clusterability metrics. From a list of 244 feature candidates, 36 candidates were selected using saliency and robustness criteria. We develop an anomaly score detector with adaptive thresholding to identify FoG events. Then, using accuracy metrics, we reduce the feature list to seven candidates. Our novel multichannel freezing index was the most selective across all window sizes, achieving sensitivity (specificity) of 96% (79%). On the other hand, freezing index from the vertical axis was the best choice for a single input, achieving sensitivity (specificity) of 94% (84%) for ankle and 89% (94%) for back sensors. Our subject-independent method is not only significantly more accurate than those previously reported, but also uses a much smaller window (e.g., 3 s versus 7.5 s) and/or lower tolerance (e.g., 0.4 s versus 2 s).