Faculty Bibliography

Recent advances in wearable sensor technology and machine learning (ML) have allowed for the seamless and objective study of human motion in clinical applications, including Parkinson's disease, and stroke. Using ML to identify salient patterns in sensor data has the potential for widespread application in neurological disorders, so understanding how to develop this approach for one's area of inquiry is vital. We previously proposed an approach that combined wearable inertial measurement units (IMUs) and ML to classify motions made by stroke patients. However, our approach had computational and practical limitations. We address these limitations here in the form of a primer, presenting how to optimize a sensor-ML approach for clinical implementation. First, we demonstrate how to identify the ML algorithm that maximizes classification performance and pragmatic implementation. Second, we demonstrate how to identify the motion capture approach that maximizes classification performance but reduces cost. We used previously collected motion data from chronic stroke patients wearing off-the-shelf IMUs during a rehabilitation-like activity. To identify the optimal ML algorithm, we compared the classification performance, computational complexity, and tuning requirements of four off-the-shelf algorithms. To identify the optimal motion capture approach, we compared the classification performance of various sensor configurations (number and location on the body) and sensor type (IMUs vs. accelerometers). Of the algorithms tested, linear discriminant analysis had the highest classification performance, low computational complexity, and modest tuning requirements. Of the sensor configurations tested, seven sensors on the paretic arm and trunk led to the highest classification performance, and IMUs outperformed accelerometers. Overall, we present a refined sensor-ML approach that maximizes both classification performance and pragmatic implementation. In addition, with this primer, we showcase important considerations for appraising off-the-shelf algorithms and sensors for quantitative motion assessment.

Parkinson Disease (PD) is a complex neurodegenerative disorder characterized by large genetic heterogeneity and missing heritability. Since the genetic background of PD can partly vary among ethnicities and neurological scales have been scarcely investigated in a PD setting, we performed an exploratory Whole Exome Sequencing (WES) analysis of 123 PD patients from mainland Italy, investigating scales assessing motor (UPDRS), cognitive (MoCA), and other non-motor symptoms (NMS). We performed variant prioritization, followed by targeted association testing of prioritized variants in 446 PD cases and 211 controls. Then we ran Exome-Wide Association Scans (EWAS) within sequenced PD cases (N = 113), testing both motor and non-motor PD endophenotypes, as well as their associations with Polygenic Risk Scores (PRS) influencing brain subcortical volumes. We identified a variant associated with PD, rs201330591 in GTF2H2 (5q13; alternative T allele: OR [CI] = 8.16[1.08; 61.52], FDR = 0.048), which was not replicated in an independent cohort of European ancestry (1,148 PD cases, 503 controls). In the EWAS, polygenic analyses revealed statistically significant multivariable associations of amygdala- [β(SE) = -0.039(0.013); FDR = 0.039] and caudate-PRS [0.043(0.013); 0.028] with motor symptoms. All subcortical PRSs in a multivariable model notably increased the variance explained in motor (adjusted-R² = 38.6%), cognitive (32.2%) and other non-motor symptoms (28.9%), compared to baseline models (~20%). Although, the small sample size warrants further replications, these findings suggest shared genetic architecture between PD symptoms and subcortical structures, and provide interesting clues on PD genetic and neuroimaging features.

Background/UNASSIGNED:We as spine surgeons increasingly need to carefully screen our own patients for major medical/cardiac comorbidities to determine if they are candidates for spine surgery. Our medical/cardiac colleagues rarely understand how long anti-platelet aggregates and non-steroidal anti-inflammatories (NSAIDs) have to be stopped prior to spine operaeitons, and when it is safe for them to be reinstated. Case Study/UNASSIGNED:A patient over 65 years of age, presented with 6 months of increased bilateral lower extremity sciatica, and 2-block neurogenic claudication. The MR scan showed moderate to severe lumbar stenosis L2-S1 with grade I L4-L5 spondylolisthesis, and multiple bilateral synovial cysts. Nevertheless, his neurological examination was normal. Further, he had > 5 stents placed within the last five years, and had undergone cardiac surgery two years ago requiring placement of a bovine aortic valve, and resection of a left ventricular wall aneurysm. He was also still on full dose Aspirin (325 mg/day), and Clopidogrel (75 mg po bid). Notably, 3 prior spinal surgeons (neurosurgery/orthopedics) had recommended multilevel lumbar laminectomy with instrumented fusions (e.g. including multilevel transforaminal lumbar interbody fusions (TLIF)). Conclusions/UNASSIGNED:Despite multilevel L2-S1 stenosis, Grade I L4-L5 spondylolisthesis, and multilevel bilateral synovial cysts, the patient's normal neurological examination and multiple cardiac comorbidities (i.e. requiring continued full-dose ASA/Clopidogrel) precluded, in my opinion, offering surgical intervention. Rather, I referred the patient to neurology for conservative management. What would you have done?

During movement, modulation of beta power occurs over the sensorimotor areas, with a decrease just before its start (event-related desynchronization, ERD) and a rebound after its end (event-related synchronization, ERS). We have recently found that the depth of ERD-to-ERS modulation increases during practice in a reaching task and the following day decreases to baseline levels. Importantly, the magnitude of the beta modulation increase during practice is highly correlated with the retention of motor skill tested the following day. Together with other evidence, this suggests that the increase of practice-related modulation depth may be the expression of sensorimotor cortex's plasticity. Here, we determine whether the practice-related increase of beta modulation depth is equally present in a group of younger and a group of older subjects during the performance of a 30-minute block of reaching movements. We focused our analyses on two regions of interest (ROIs): the left sensorimotor and the frontal region. Performance indices were significantly different in the two groups, with the movements of older subjects being slower and less accurate. Importantly, both groups presented a similar increase of the practice-related beta modulation depth in both ROIs in the course of the task. Peak latency analysis revealed a progressive delay of the ERS peak that correlated with the total movement time. Altogether, these findings support the notion that the depth of beta modulation in a reaching movement task does not depend on age and confirm previous findings that only ERS peak latency but not ERS magnitude is related to performance indices.

Over the last decades, psychophysical and electrophysiological studies in patients and animal models of Parkinson's disease (PD), have consistently revealed a number of visual abnormalities. In particular, specific alterations of contrast sensitivity curves, electroretinogram (ERG), and visual-evoked potentials (VEP), have been attributed to dopaminergic retinal depletion. However, fundamental mechanisms of cortical visual processing, such as normalization or "gain control" computations, have not yet been examined in PD patients. Here, we measured electrophysiological indices of gain control in both space (surround suppression) and time (sensory adaptation) in PD patients based on steady-state VEP (ssVEP). Compared with controls, patients exhibited a significantly higher initial ssVEP amplitude that quickly decayed over time, and greater relative suppression of ssVEP amplitude as a function of surrounding stimulus contrast. Meanwhile, EEG frequency spectra were broadly elevated in patients relative to controls. Thus, contrary to what might be expected given the reduced contrast sensitivity often reported in PD, visual neural responses are not weaker; rather, they are initially larger but undergo an exaggerated degree of spatial and temporal gain control and are embedded within a greater background noise level. These differences may reflect cortical mechanisms that compensate for dysfunctional center-surround interactions at the retinal level.