Evaluation of Free-Living Motor Symptoms in Patients With Parkinson Disease Through Smartwatches: Protocol for Defining Digital Biomarkers
Bibliographic record
Abstract
BACKGROUND: Monitoring motor symptoms in patients with Parkinson disease (PD) presents significant challenges due to the complex nature of symptom progression, variations in medication responses, and the fluctuations that can occur throughout the day. Traditional neurological visits provide only a limited perspective of a patient's overall condition, with challenges in achieving accurate and objective assessments of symptoms. To bridge this gap, extended monitoring in nonclinical settings could play a critical role in personalizing treatments and improving their efficacy. Wearable devices have emerged as potential tools for assessing PD symptom severity; however, studies integrating both in-clinic and free-living conditions, as well as multiday monitoring, remain scarce. Defining digital biomarkers that provide valuable insights into motor symptoms could enable comprehensive monitoring and tracking of PD in various contexts, facilitating more precise medication adjustments and the implementation of advanced therapeutic strategies. OBJECTIVE: This study aims to collect a dataset to support the proposal and definition of digital biomarkers of PD motor symptoms using wearable devices. Data will be collected both in a supervised setting and continuously in a remote, free-living context during participants' normal daily activities; the study will include patients with PD and healthy controls. The goal is to identify reliable digital biomarkers that can effectively distinguish patients with PD from healthy controls and classify disease severity in both supervised and unsupervised free-living environments. METHODS: This paper outlines a protocol for an observational case-control study aimed at assessing motor symptoms in patients with PD using a smartwatch. The smartwatch will record accelerometer, gyroscope, and physical activity data. Participants will be instructed to perform a series of exercises guided via a smartphone. Measurements will be collected in 2 settings: a supervised clinical environment, with motor symptoms assessments conducted at the beginning and end of the study, and in an unsupervised free-living context for 1 week. In both settings, participants will be required to wear the smartwatch while performing the same set of exercises. In their daily routine, participants will be required to wear the smartwatch continuously throughout the day, removing it only at night for charging. RESULTS: Participant recruitment and data collection started in December 2024 and will continue until spring 2025. The study aims to enroll 20 participants with PD and 20 healthy controls. CONCLUSIONS: It is anticipated that the generation of a dataset of accelerometer and gyroscope signal data recorded from patients with PD at various stages of the disease, alongside data from a control group, will enable robust comparative and impactful analyses. In addition, the study seeks to develop analytical techniques capable of tracking PD symptoms in real-life scenarios, both in everyday settings and clinical environments. TRIAL REGISTRATION: ClinicalTrials.gov NCT06817772; https://clinicaltrials.gov/study/NCT06817772. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/72820.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.021 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.014 | 0.010 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".