An observational study in PARKINSON DISEASE (Disorder), sponsored by The Hong Kong Polytechnic University. Not yet recruiting at 2 sites in 2 countries. Open to participants aged 45 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-10-21.
Sponsored by The Hong Kong Polytechnic University · Observational
The goal of this prospective observational study is to investigate whether oculomotor-pupillary abnormalities detected using a novel edge-AI eye-tracking device can serve as objective and quantitative biomarkers for the early screening and clinical evaluation of Parkinson's disease (PD). The study will include individuals with early-to-moderate PD and healthy controls. The main question it aims to answer is:
Can oculomotor-pupillary abnormalities detected by a novel edge-AI eye-tracking device serve as objective and quantitative biomarkers for the early screening of Parkinson's disease?
Researchers will compare oculomotor-pupillary parameters between participants with PD and healthy controls and evaluate the ability of these parameters to distinguish PD from healthy controls. Participants with PD will also be followed for 12 months to assess longitudinal changes in eye-tracking measures and their associations with clinical changes.
Participants will:
The study will also evaluate the feasibility and clinical application of the independently developed edge-AI eye-tracking system and develop and validate lightweight real-time models for PD classification and prediction of disease progression.
4,583 studies on the registry are indexed under Parkinson Disease; 1,097 are open to participants now.
This study's planned enrollment of 128 is above the median of 97 across 1,081 observational studies indexed under Parkinson Disease.
Browse Parkinson Disease studies →The Hong Kong Polytechnic University is the lead sponsor of 676 studies on the registry; 254 are open to participants now.
Counted across the registry records on this site, refreshed daily.
The study population will consist of adults aged 45 years or older, including participants with early-to-moderate Parkinson's disease and age-comparable healthy controls. Participants with Parkinson's disease will be recruited from clinical populations and will undergo baseline eye-tracking and clinical assessments followed by longitudinal assessments over 12 months. Healthy controls without Parkinson's disease or other major neurological disorders will undergo baseline assessments for comparison with the Parkinson's disease group. All participants must be able to complete the required eye-tracking tasks and clinical assessments.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
PD Group:
HC Group:
Exclusion Criteria:
Device: Edge-AI Eye-Tracking Assessment
Device: Edge-AI Eye-Tracking Assessment
Participants will undergo standardized oculomotor and pupillary assessments using the study-developed edge-AI eye-tracking device. The assessment includes standardized visual tasks designed to evaluate fixation, saccadic eye movements, smooth pursuit, and pupillary responses. Eye movement and pupil data will be recorded and analyzed to identify oculomotor-pupillary biomarkers associated with Parkinson's disease. The device is used for research assessment only and does not alter participants' routine clinical treatment.
Differences in mean prosaccade gain between early-to-moderate PD patients and healthy controls.
Prosaccade gain is defined as the ratio of the primary saccade amplitude to the target displacement amplitude, measured using a head-mounted infrared eye-tracking device. The mean gain across valid trials will be calculated for each participant. Mean prosaccade gain will be compared between patients with early-to-moderate PD and healthy controls.
Time frame: Baseline
Differences in antisaccade directional error rate between early-to-moderate PD patients and healthy controls.
Antisaccade directional error rate is defined as the percentage of valid antisaccade trials in which the initial saccade is incorrectly directed toward the visual target rather than in the opposite direction, measured using a head-mounted infrared eye-tracking device. The error rate will be calculated for each participant as the number of directional error trials divided by the total number of valid antisaccade trials, multiplied by 100. Antisaccade directional error rate will be compared between patients with early-to-moderate PD and healthy controls.
Time frame: Baseline
Differences in mean prosaccade peak velocity between early-to-moderate PD patients and healthy controls.
Prosaccade peak velocity is defined as the maximum angular eye velocity during the primary prosaccade, measured in degrees per second (°/s) using a head-mounted infrared eye-tracking device. The mean peak velocity across valid trials will be calculated for each participant. Mean prosaccade peak velocity will be compared between patients with early-to-moderate PD and healthy controls.
Time frame: Baseline
Correlation Between Changes in Prosaccade Gain and MDS-UPDRS Part III Scores Over 12 Months
The correlation between changes in mean prosaccade gain and changes in motor symptom severity will be assessed in patients with PD over 12 months. Mean prosaccade gain will be measured using a head-mounted infrared eye-tracking device, while motor symptom severity will be assessed using the Movement Disorder Society-Unified Parkinson's Disease Rating Scale Part III (MDS-UPDRS III). Changes in both measures will be calculated from baseline to 12 months, and their association will be quantified using a correlation coefficient (r).
Time frame: Baseline to 12 months
Correlation Between Changes in Antisaccade Directional Error Rate and MoCA Scores Over 12 Months
The correlation between changes in antisaccade directional error rate and changes in cognitive function will be assessed in patients with PD over 12 months. Antisaccade directional error rate is defined as the percentage of valid antisaccade trials in which the initial saccade is incorrectly directed toward the visual target, measured using a head-mounted infrared eye-tracking device. Cognitive function will be assessed using the Montreal Cognitive Assessment (MoCA). Changes in both measures from baseline to 12 months will be calculated, and their association will be quantified using a correlation coefficient (r).
Time frame: Baseline to 12 months
Area Under the Receiver Operating Characteristic Curve (AUC) for PD Classification
The diagnostic performance of an edge-AI model based on oculomotor-pupillary features measured using a head-mounted infrared eye-tracking device will be evaluated for distinguishing patients with PD from healthy controls. Model performance will be assessed using AUC, with values ranging from 0 to 1, where higher values indicate better discriminative performance.
Time frame: Baseline
Start is estimated for Nov 2026; primary completion for Dec 2027, 13 months later.
Of 381 non-industry observational studies under Parkinson Disease, half reached primary completion within 48 months of starting (the median), counting those still running; a quarter within 22 and three quarters within 133. This study's planned 13 months is below that.
Counting every sponsor, half of 440 studies reached it within 48 months; a quarter within 21 and three quarters within 112.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is not yet recruiting, as verified in Sep 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
The Hong Kong Polytechnic University →