Objective: This study evaluated the potential of wearables and AI-driven continuous monitoring to assess motor symptoms in Parkinson’s disease (PD). We aimed to determine their potential in identifying patients suitable for device-aided therapy (DAT).

Background: Advanced treatments like deep brain stimulation and continuous drug delivery help manage motor symptoms in advanced stages of PD [1]. However, identifying eligible patients remains difficult. The standard 5-2-1 [2] criteria rely on subjective reports prone to biases [3]. Wearable sensors enable continuous, objective symptom assessment, potentially enhancing treatment decisions [4].

Method: This single-center, parallel-group study was conducted at the Movement Disorder Clinic at Rigshospitalet, Denmark. Inclusion criteria targeted advanced PD with idiopathic PD, motor fluctuations, and ≥5 daily levodopa doses. Exclusion criteria included atypical parkinsonism, prior DAT, or wheelchair dependency. 16 eligible patients were screened; 11 completed the study. Participants were first categorized by an independent specialist as either ready or not yet ready for DAT, then wore a wrist sensor for at least 3 weeks. The device recorded raw motion data, processed by an AI algorithm to quantify bradykinesia, ON time, and dyskinesia severity minute-by-minute [5, 6]. Algorithmic output was retrospectively compared with clinical decision-making.

Results: ON and OFF times significantly differed between study groups (ON: 7.8 ± 2.2 vs. 4.7 ± 3.1 hours, p<0.001; OFF: 5.5 ± 4.5 vs. 2.2 ± 2.2 hours, p<0.001), with the DAT-ready group spending less time in ON and more time in OFF. However, time in motor states alone was insufficient to clearly identify eligible patients. Incorporating symptom severity and disease symptom density improved alignment between algorithmic assessments and clinical decision-making. Beyond replicating clinical decisions, continuous monitoring uncovered missed and borderline cases where symptom fluctuations may lead to an underestimation of DAT eligibility in clinical evaluations.

Conclusion: Wearable sensors and AI-driven symptom monitoring provide continuous, objective insights into motor fluctuations in PD. This approach potentially enhances patient stratification, allowing for earlier and more precise identification of those needing advanced therapies.

References: 1. Fujikawa J, Morigaki R, Yamamoto N, et al. Therapeutic Devices for Motor Symptoms in Parkinson’s Disease: Current Progress and a Systematic Review of Recent Randomized Controlled Trials. Front Aging Neurosci. 2022;14:807909. doi:10.3389/fnagi.2022.807909
2. Antonini, A., Stoessl, A. J., Kleinman, L. S., Skalicky, A. M., Marshall, T. S., Sail, K. R., … Odin, P. L. A. (2018). Developing consensus among movement disorder specialists on clinical indicators for identification and management of advanced Parkinson’s disease: a multi-country Delphi-panel approach. Current Medical Research and Opinion, 34(12), 2063–2073. https://doi.org/10.1080/03007995.2018.1502165
3. Papapetropoulos S (Spyros). Patient Diaries As a Clinical Endpoint in Parkinson’s Disease Clinical Trials. CNS Neuroscience & Therapeutics. 2012;18(5):380-387. doi:10.1111/j.1755-5949.2011.00253.x
4. Ancona S, Faraci FD, Khatab E, et al. Wearables in the home-based assessment of abnormal movements in Parkinson’s disease: a systematic review of the literature. J Neurol. 2022;269(1):100-110. doi:10.1007/s00415-020-10350-3
5. Goschenhofer J, Pfister FMJ, Yuksel KA, Bischl B, Fietzek U, Thomas J. Wearable-Based Parkinson’s Disease Severity Monitoring Using Deep Learning. In: Brefeld U, Fromont E, Hotho A, Knobbe A, Maathuis M, Robardet C, eds. Machine Learning and Knowledge Discovery in Databases. Vol 11908. Lecture Notes in Computer Science. Springer International Publishing; 2020:400-415. doi:10.1007/978-3-030-46133-1_24
6. Pfister FMJ, Um TT, Pichler DC, et al. High-Resolution Motor State Detection in Parkinson’s Disease Using Convolutional Neural Networks. Sci Rep. 2020;10(1):5860. doi:10.1038/s41598-020-61789-3

« Back to 2025 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/ai-driven-wearable-sensor-monitoring-for-improved-assessment-of-advanced-treatment-readiness-in-parkinsons-disease-a-pilot-study/