Objective: This study aims to develop and validate a technological set up for the objective assessment and continuous monitoring of axial symptoms in Parkinson’s Disease (PD), including Freezing of Gait (FoG), postural instability, Postural Abnormalities (PA), speech impairment, and dysphagia.

Background: Axial symptoms in PD significantly impact patients’ life quality. Current assessments rely on subjective rating scales, lacking accuracy in capturing real-life challenges. Advances in technology provide opportunities for continuous, ecological monitoring to improve axial symptom detection and characterization.

Method: This multicenter, observational study involves 40 PD patients (Hoehn & Yahr stage 2.5–4) from two Italian Movement Disorders Centers (Turin and Rome). Patients will undergo a screening evaluation with clinical rating scales to characterize axial, motor and non-motor symptoms, disease severity, and functional impairment. The study includes two evaluation phases: (T1) supervised laboratory assessment and (T2) home-like environment testing. Participants will be assessed using wearable inertial sensors, surface electromyography, smartphone-embedded microphone and markerless optical tracking systems. Data from supervised assessment (eg, gait tasks, posture, voice, and swallowing tests) will be processed using machine learning algorithms to 1) refine detection of FoG, postural instability, PA, speech impairment, and dysphagia, 2) identify the most relevant features associated with disability, and 3) generate a symptom-specific and total axial score.

Results: The expected outcomes include the validation of a minimally intrusive setup for monitoring axial symptoms, the identification of correlations between different objective outcomes, and the development of machine learning models for their accurate quantification. The integration of multimodal data will allow a more objective classification of PD severity. Additionally, the study will assess the feasibility of a standardized axial symptoms evaluation tool for both research and clinical practice.

Conclusion: By deploying Artificial Intelligence-driven multimodal assessment tools, this study aims to bridge the gap between qualitative clinical evaluations and quantitative real-life symptom monitoring. Findings may improve disease monitoring in home settings.

« Back to 2025 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/objective-monitoring-of-axial-symptoms-in-parkinsons-disease-omnia-park-the-study-protocol/