JMIR Publications

ABSTRACT

Background:

Early diagnosis is crucial for ensuring that Parkinson's disease (PD) patients receive timely treatment, which can significantly improve their quality of life, and prolong their lifespan. Wearable sensors have recently emerged as promising tools for early PD diagnosis, offering non-invasive, continuous monitoring of symptoms.

Objective:

This systematic review aimed to evaluate the research on wearable sensors in the early diagnosis of PD over the past decade, focusing on the types of sensors, methods, findings, and limitations associated with their use.

Methods:

The systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies were sourced from PubMed, IEEE Xplore, Scopus, and Web of Science, and screened on the inclusion and extract criteria. All the selected studies were assessed for quality using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2), the quality assessment tool recommended by the Cochrane Collaboration.

Results:

A total of 1,888 records were retrieved from the selected databases, with 1,044 records remaining after duplicate removal. Following the screening of titles and abstracts, 949 ineligible records were excluded, leaving 95 articles for eligibility. Eventually, twelve (12/1044, 1.1%) studies met the inclusion criteria, validating the feasibility of wearable sensors in the early diagnosis of PD. Among these studies, 10 (83.3%) were cross-sectional studies, one (8.3%) was a longitudinal study, and one (8.3%) was a mixed study. Additionally, four studies (33.3%) focused on identification diagnosis, two studies (16.7%) addressed the staged diagnosis of PD, and one study focused on the identification of specific symptoms. The main wearable sensors used were IMUs (8/12, 66.7%) and accelerometers (4/12, 33.3%), which primarily captured motion-related data. While initial findings suggest that wearable sensors are feasible for early PD diagnosis, the evidence is still limited by small sample sizes and short study durations.

Conclusions:

Wearable sensors show promise in supporting the early diagnosis of PD, particularly for motor symptom monitoring. However, various limitations persist in validating and applying these technologies for early diagnosis, as the number of relevant studies remains relatively small. More studies of different types are needed to further validate these findings and address existing shortcomings to better advance the use of wearable sensors in the early diagnosis of PD.