RESUMO
Quantification of motor symptom progression in Parkinson's disease (PD) patients is crucial for assessing disease progression and for optimizing therapeutic interventions, such as dopaminergic medications and deep brain stimulation. Cumulative and heuristic clinical experience has identified various clinical signs associated with PD severity, but these are neither objectively quantifiable nor robustly validated. Video-based objective symptom quantification enabled by machine learning (ML) introduces a potential solution. However, video-based diagnostic tools often have implementation challenges due to expensive and inaccessible technology, and typical "black-box" ML implementations are not tailored to be clinically interpretable. Here, we address these needs by releasing a comprehensive kinematic dataset and developing an interpretable video-based framework that predicts high versus low PD motor symptom severity according to MDS-UPDRS Part III metrics. This data driven approach validated and robustly quantified canonical movement features and identified new clinical insights, not previously appreciated as related to clinical severity, including pinkie finger movements and lower limb and axial features of gait. Our framework is enabled by retrospective, single-view, seconds-long videos recorded on consumer-grade devices such as smartphones, tablets, and digital cameras, thereby eliminating the requirement for specialized equipment. Following interpretable ML principles, our framework enforces robustness and interpretability by integrating (1) automatic, data-driven kinematic metric evaluation guided by pre-defined digital features of movement, (2) combination of bi-domain (body and hand) kinematic features, and (3) sparsity-inducing and stability-driven ML analysis with simple-to-interpret models. These elements ensure that the proposed framework quantifies clinically meaningful motor features useful for both ML predictions and clinical analysis.
RESUMO
Background: Neuropsychiatric symptoms are common and disabling in Parkinson's disease (PD), with troublesome anxiety occurring in one-third of patients. Management of anxiety in PD is challenging, hampered by insufficient insight into underlying mechanisms, lack of objective anxiety measurements, and largely ineffective treatments.In this study, we assessed the intracranial neurophysiological correlates of anxiety in PD patients treated with deep brain stimulation (DBS) in the laboratory and at home. We hypothesized that low-frequency (theta-alpha) activity would be associated with anxiety. Methods: We recorded local field potentials (LFP) from the subthalamic nucleus (STN) or the globus pallidus pars interna (GPi) DBS implants in three PD cohorts: 1) patients with recordings (STN) performed in hospital at rest via perioperatively externalized leads, without active stimulation, both ON or OFF dopaminergic medication; 2) patients with recordings (STN or GPi) performed at home while resting, via a chronically implanted commercially available sensing-enabled neurostimulator (Medtronic Percept™ device), ON dopaminergic medication, with stimulation both ON or OFF; 3) patients with recordings performed at home while engaging in a behavioral task via STN and GPi leads and electrocorticography paddles (ECoG) over premotor cortex connected to an investigational sensing-enabled neurostimulator, ON dopaminergic medication, with stimulation both ON or OFF.Trait anxiety was measured with validated clinical scales in all participants, and state anxiety was measured with momentary assessment scales at multiple time points in the two at-home cohorts. Power in theta (4-8 Hz) and alpha (8-12 Hz) ranges were extracted from the LFP recordings, and their relation with anxiety ratings was assessed using linear mixed-effects models. Results: In total, 33 PD patients (59 hemispheres) were included. Across three independent cohorts, with stimulation OFF, basal ganglia theta power was positively related to trait anxiety (all p<0.05). Also in a naturalistic setting, with individuals at home at rest with stimulation and medication ON, basal ganglia theta power was positively related to trait anxiety (p<0.05). This relationship held regardless of the hemisphere and DBS target. There was no correlation between trait anxiety and premotor cortical theta-alpha power. There was no within-patient association between basal ganglia theta-alpha power and state anxiety. Conclusion: We showed that basal ganglia theta activity indexes trait anxiety in PD. Our data suggest that theta could be a possible physiomarker of neuropsychiatric symptoms and specifically of anxiety in PD, potentially suitable for guiding advanced DBS treatment tailored to the individual patient's needs, including non-motor symptoms.