Assessment of Tremor Activity in the Parkinson's Disease Using a Set of Wearable Sensors

• Published in: IEEE journal of biomedical and health informatics 2012-05, Vol.16 (3), p.478-487
• Main Authors: Rigas, G., Tzallas, A. T., Tsipouras, M. G., Bougia, P., Tripoliti, E. E., Baga, D., Fotiadis, D. I., Tsouli, S. G., Konitsiotis, S.
• Format: Article
• Language: English
• Subjects: Accelerometers; Aged; Algorithms; Case-Control Studies; Feature extraction; Hidden Markov models; Hidden Markov models (HMMs); Humans; Legged locomotion; Levodopa-induced dyskinesia (LID); Markov Chains; Middle Aged; Monitoring, Ambulatory - instrumentation; Monitoring, Ambulatory - methods; Movement - physiology; Parkinson Disease - physiopathology; Parkinson's disease; Parkinson's disease (PD); Posture - physiology; posture recognition; Sensor phenomena and characterization; tremor; Tremor - classification; Tremor - diagnosis; Tremor - physiopathology
• ISSN: 1089-7771; 2168-2194; 1558-0032; 2168-2208
• DOI: 10.1109/TITB.2011.2182616

Tremor is the most common motor disorder of Parkinson's disease (PD) and consequently its detection plays a crucial role in the management and treatment of PD patients. The current diagnosis procedure is based on subject-dependent clinical assessment, which has a difficulty in capturing subtle tremor features. In this paper, an automated method for both resting and action/postural tremor assessment is proposed using a set of accelerometers mounted on different patient's body segments. The estimation of tremor type (resting/action postural) and severity is based on features extracted from the acquired signals and hidden Markov models. The method is evaluated using data collected from 23 subjects (18 PD patients and 5 control subjects). The obtained results verified that the proposed method successfully: 1) quantifies tremor severity with 87 % accuracy, 2) discriminates resting from postural tremor, and 3) discriminates tremor from other Parkinsonian motor symptoms during daily activities.