Peterson, Daniel

Parkinson’s disease (PD) significantly affects patients’ quality of life through debilitating motor symptoms, such as Freezing of Gait (FoG). Continuous, in-home monitoring of FoG is essential for timely clinical intervention but remains challenging due to high power consumption, annotation cost, and the controlled environments required by current wearables. We introduce LIFT-PD (the source code is available at: https://github.com/shovito66/LIFT-PD ), a novel self-supervised learning (SSL) framework for real-time, patient-independent FoG detection that uniquely utilizes a single waist-worn accelerometer—an approach traditionally considered less optimal due to weaker gait signatures. LIFT-PD leverages SSL on unlabeled data collected from uncontrolled, real-world settings and employs a novel Differential Hopping Windowing Technique (DHWT) to address gait variability and dataset imbalance. Additionally, an opportunistic inference module selectively activates the deep learning model only during patient movement, significantly reducing power consumption and enabling continuous monitoring ( \(>\) 48 hours). Experimental results show that LIFT-PD achieves a 7.25% increase in precision and 4.4% improvement in accuracy compared to supervised and semi-supervised baseline models while requiring approximately 40% fewer labeled training samples. Evaluations across diverse patient characteristics-including severity, medication state, age, and gender-confirm the model’s robustness and clinical applicability, positioning LIFT-PD as a practical, energy-efficient, and scalable solution for continuous real-world FoG monitoring in PD.

Parkinson’s disease (PD) is the second-most common neurodegenerative disease. With more than 20,000 new diagnosed cases each year, PD affects millions of individuals worldwide and is most prevalent in the elderly population. The current clinical methods for the diagnosis and severity assessment of PD rely on the visual and physical examination of subjects and identifying key disease motor signs and symptoms such as bradykinesia, rigidity, tremor, and postural instability. In the present study, we developed a method for the diagnosis and severity assessment of PD using Gramian Angular Fields (GAFs) in combination with deep Convolutional Neural Networks (CNNs). Our model was applied to PD gait signals captured using pressure sensors embedded into insoles. Our results indicated an accuracy of 98.6%, a true positive rate (TPR) of 99.2%, and a true negative rate (TNR) of 98.5%, showcasing superior classification performance for PD diagnosis compared to the methods used in recent studies in the literature. The estimation of disease severity scores using gait signals showed a high accuracy for the Hoehn and Yahr score as well as the Timed Up and Go (TUG) test score (R2 > 0.8), while we achieved a lower prediction performance for the Unified Parkinson’s Disease Rating Scale (UPDRS) and its motor component (UPDRSM) scores (R2 < 0.2). These results were achieved using gait signals recorded in time windows as small as 10 s, which may pave the way for shorter, more accessible assessment tools for diagnosis and severity assessment of PD.

Introduction. Reactive movements in response to a loss of balance are altered in people with Parkinson’s disease (PD) and are critical for fall prevention. Further, falls are more common while attention is divided. Although divided attention has been shown to impact postural responses in healthy older adults, the impact of dividing attention on reactive balance, and the natural prioritization across postural and cognitive tasks in people with PD is largely unknown. Objectives. To characterize (1) the impact of a secondary cognitive task on reactive postural control and (2) the prioritization across stepping and cognitive tasks in people with PD. Methods. Sixteen people with PD and 14 age-matched controls underwent step-inducing, support-surface perturbations from stance, with and without an auditory Stroop secondary cognitive task. Cognitive, neuromuscular, and protective stepping performance were calculated for single and dual task scenarios. Results. In PD and control participants, cognitive reaction times ( P = .001) and muscle onset latency ( P = .007), but not protective step outcomes ( P > .12 for all) were worse during dual tasking compared with single-task scenarios. Both PD and control groups prioritized the protective stepping task over the cognitive task. Overall, people with PD exhibited worse first-step margin of stability (a measure of protective step performance) than controls ( P = .044). Conclusion. This study provides preliminary evidence that people with PD, like age-matched controls, exhibit cognitive and neuromuscular, but not protective step, dual-task interference. The lack of dual-task interference on step performance indicates a postural prioritization for PD and healthy older adults during dual-task protective stepping.