Detecting Parkinson’s Disease from Wrist-Worn Accelerometry in the U.K. Biobank

Abstract

Parkinson’s disease (PD) is a chronic movement disorder that produces a variety of characteristic movement abnormalities. The ubiquity of wrist-worn accelerometry suggests a possible sensor modality for early detection of PD symptoms and subsequent tracking of PD symptom severity. As an initial proof of concept for this technological approach, we analyzed the U.K. Biobank data set, consisting of one week of wrist-worn accelerometry from a population with a PD primary diagnosis and an age-matched healthy control population. Measures of movement dispersion were extracted from automatically segmented gait data, and measures of movement dimensionality were extracted from automatically segmented low-movement data. Using machine learning classifiers applied to one week of data, PD was detected with an area under the curve (AUC) of 0.69 on gait data, AUC = 0.84 on low-movement data, and AUC = 0.85 on a fusion of both activities. It was also found that classification accuracy steadily improved across the one-week data collection, suggesting that higher accuracy could be achievable from a longer data collection. These results suggest the viability of using a low-cost and easy-to-use activity sensor for detecting movement abnormalities due to PD and motivate further research on early PD detection and tracking of PD symptom severity.

Clustering Accelerometer Activity Patterns from the UK Biobank Cohort

“…The average level of activity is the most common measure used [36][37][38]. Another study, concerned with Parkinson's disease, used the variation in movement to act as proxies for the subject's gait and lateral movement [39]. Others have used various thresholds based on milli-gravities to identify periods of activity covering a range of levels, from being sedate, through light and moderate, to vigorous activities [16,22,40].…”

Integration of Artificial Intelligence, Blockchain, and Wearable Technology for Chronic Disease Management: A New Paradigm in Smart Healthcare

“…According to the tracking equipment worn by the patient, the patient's three-dimensional image can be reconstructed by AI. The system can combine a health warning and an abnormal analysis of heart rate, pulse, respiration, stride, pace, blood oxygen, step frequency, upper limbs, waist, and lower limbs, according to the patient's rehabilitation movement [49][50][51] .…”

“…With the help of wearable devices, the research on measuring the physiological curvature and posture of the spine in patients with chronic diseases of the motor system is conducted continuously. In spinal surgery, it is often necessary to insert implants such as pedicle screws, Kirschner wires, and artificial intervertebral discs into patients to achieve a satisfactory reset effect [49,50] . In the future, it will be possible to insert instruments with sensors into related structures of the human body, which can carry out real-time monitoring of physiological states [52] .…”

Virtual Exam for Parkinson’s Disease Enables Frequent and Reliable Remote Measurements of Motor Function

“…13 Results suggest that features extracted by digital signal processing can be correlated with clinical outcomes of interest, at least when tests are delivered in a controlled setting and assessments are supervised by a clinician. [14][15][16][17][18][19][20][21][22] Active assessments measure patients' maximum capacity, and can be complementary to passive monitoring, which measures the expression of signs in real life. Though some studies have probed the feasibility of using wearable sensors or smartphones for remote, self-guided active assessments, long-term engagement -which is critical to study disease progression -has been an important challenge.…”