Tremor Detection Parkinson Sensor — Biomedical Instrumentation & Clinical Sensing

Abstract — Tremor Detection Parkinson Sensor

Creative Commons Attribution (CC BY) license ( http://creativecommons.org/licenses/by/4.0/ ). Figure 1: Diagnostic Medical Waveform & Bio-Potential Clinical Trace for Tremor Detection Parkinson Sensor Tremor is one of the main symptoms of Parkinson’s Disease (PD) that reduces the quality of life. Tremor is measured as part of the Unified Parkinson Disease Rating Scale (UPDRS) part III. However, the assessment is based on onsite physical examinations and does not fully represent the patients’ tremor experience in their day-to-day life. Our objective in this paper was to develop algorithms that, combined with wearable sensors, can estimate total Parkinsonian tremor as the patients performed a variety of free body movements. We developed two methods: an ensemble model based on gradient tree boosting and a deep learning model based on long short-term memory (LSTM) networks. The developed methods were assessed on gyroscope sensor data from 24 PD subjects. Our analysis demonstrated that the method based on gradient tree boosting provided a high correlation ( r = 0.96 using held-out testing and r = 0.93 using subject-based, leave-one-out cross-validation) between the estimated and clinically assessed tremor subscores in comparison to the LSTM-based method with a moderate correlation ( r = 0.84 using held-out testing and r = 0.77 using subject-based, leave-one-out cross-validation).

Sensor Interfacing & Analog Front-End Conditioning

These results indicate that our approach holds great promise in providing a full spectrum of the patients’ tremor from continuous monitoring of the subjects’ movement in their natural environment. Keywords: Parkinsonian tremor, continuous monitoring, wearable sensors, gradient tree boosting, deep learning, LSTM Tremor is an involuntary movement disorder, common in many middle-aged and older adults. It is characterized by approximately rhythmic shaking of hands, head, trunk, voice, or legs . Tremor reduces the quality of life by interrupting the subjects’ activities such as reading, writing, and eating. Tremor can be divided into “resting tremor”, which occurs as subjects relax their muscles and “action tremor”, which happens while the subjects perform voluntary muscle movements. There are two types of action tremors: postural and kinetic tremor. The postural tremor occurs when a person holds his/her hand(s) or leg(s) still, against gravity. The kinetic tremor happens when a person is engaged in different daily activities that involve voluntary movements of the muscles. There are several causes for tremor. Idiopathic Parkinson’s disease (PD) is the most common cause of resting tremor, although it may cause some action tremor as well .

Bio-Signal Waveform Analysis & Simulation Findings

Figure 2: Diagnostic Medical Waveform & Bio-Potential Clinical Trace for Tremor Detection Parkinson Sensor A neurologist typically measures the severity degree of resting and action (postural and kinetic) tremor of PD patients during routine clinical visits. The neurologist performs the Unified Parkinson Disease Rating Scale (UPDRS) Part III assessment during which the patients are asked to perform three tasks: arm resting, arm extending, and touching the tip of their nose with their index finger (finger-to-nose testing) . However, a single clinical examination often fails to capture the complete spectrum of tremor that a PD subject experiences in routine daily life . Wearable sensors, combined with machine learning algorithms, can be used in a patient’s natural living environment to estimate the severity rating of tremor based on the way that it manifests itself in movement patterns [ 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 ].

Scope & Clinical Applications

• Real-time multi-parameter vital signs telemetry (ECG, Heart Rate, SpO2, Temperature, Respiration)
• Low-noise Analog Front-End (AFE) conditioning with active Driven Right Leg (DRL) 50 Hz cancellation
• Digital signal processing in MATLAB: Pan-Tompkins QRS detection, FIR/IIR notch, and Continuous Wavelet Transforms
• Finite element tissue bio-electromagnetics and orthopedic mechanical simulations in COMSOL & ANSYS
• Complete Arduino firmware .INO sketches, circuit schematics, and university dissertation reports