Computer vision quantification of whole-body Parkinsonian bradykinesia using a large multi-site population.

Parkinson's disease (PD) is a common neurological disorder, with bradykinesia being one of its cardinal features. Objective quantification of bradykinesia using computer vision has the potential to standardise decision-making, for patient treatment and clinical trials, while facilitating remote assessment. We utilised a dataset of part-3 MDS-UPDRS motor assessments, collected at four independent clinical and one research sites on two continents, to build computer-vision-based models capable of inferring the correct severity rating robustly and consistently across all identifiable subgroups of patients. These results contrast with previous work limited by small sample sizes and small numbers of sites. Our bradykinesia estimation corresponded well with clinician ratings (interclass correlation 0.74). This agreement was consistent across four clinical sites. This result demonstrates how such technology can be successfully deployed into existing clinical workflows, with consumer-grade smartphone or tablet devices, adding minimal equipment cost and time.

Accuracy, precision, and safety of stereotactic, frame-based, intraoperative MRI-guided and MRI-verified deep brain stimulation in 650 consecutive procedures.

OBJECTIVE: Suboptimal lead placement is one of the most common indications for deep brain stimulation (DBS) revision procedures. Confirming lead placement in relation to the visible anatomical target with dedicated stereotactic imaging before terminating the procedure can mitigate this risk. In this study, the authors examined the accuracy, precision, and safety of intraoperative MRI (iMRI) to both guide and verify lead placement during frame-based stereotactic surgery. METHODS: A retrospective analysis of 650 consecutive DBS procedures for targeting accuracy, precision, and perioperative complications was performed. Frame-based lead placement took place in an operating room equipped with an MRI machine using stereotactic images to verify lead placement before removing the stereotactic frame. Immediate lead relocation was performed when necessary. Systematic analysis of the targeting error was calculated. RESULTS: Verification of 1201 DBS leads with stereotactic MRI was performed in 643 procedures and with stereotactic CT in 7. The mean ± SD of the final targeting error was 0.9 ± 0.3 mm (range 0.1-2.3 mm). Anatomically acceptable lead placement was achieved with a single brain pass for 97% (n = 1164) of leads; immediate intraoperative relocation was performed in 37 leads (3%) to obtain satisfactory anatomical placement. General anesthesia was used in 91% (n = 593) of the procedures. Hemorrhage was noted after 4 procedures (0.6%); 3 patients (0.4% of procedures) presented with transient neurological symptoms, and 1 experienced delayed cognitive decline. Two bleeds coincided with immediate relocation (2 of 37 leads, 5.4%), which contrasts with hemorrhage in 2 (0.2%) of 1164 leads implanted on the first pass (p = 0.0058). Three patients had transient seizures in the postoperative period. The seizures coincided with hemorrhage in 2 of these patients and with immediate lead relocation in the other. There were 21 infections (3.2% of procedures, 1.5% in 3 months) leading to hardware removal. Delayed (> 3 months) retargeting of 6 leads (0.5%) in 4 patients (0.6% of procedures) was performed because of suboptimal stimulation benefit. There were no MRI-related complications, no permanent motor deficits, and no deaths. CONCLUSIONS: To the authors' knowledge, this is the largest series reporting the use of iMRI to guide and verify lead location during DBS surgery. It demonstrates a high level of accuracy, precision, and safety. Significantly higher hemorrhage was encountered when multiple brain passes were required for lead implantation, although none led to permanent deficit. Meticulous audit and calibration can improve precision and maximize safety.

An Evaluation of KELVIN, an Artificial Intelligence Platform, as an Objective Assessment of the MDS UPDRS Part III.

BACKGROUND: Parkinson's disease severity is typically measured using the Movement Disorder Society Unified Parkinson's disease rating scale (MDS-UPDRS). While training for this scale exists, users may vary in how they score a patient with the consequence of intra-rater and inter-rater variability. OBJECTIVE: In this study we explored the consistency of an artificial intelligence platform compared with traditional clinical scoring in the assessment of motor severity in PD. METHODS: Twenty-two PD patients underwent simultaneous MDS-UPDRS scoring by two experienced MDS-UPDRS raters and the two sets of accompanying video footage were also scored by an artificial intelligence video analysis platform known as KELVIN. RESULTS: KELVIN was able to produce a summary score for 7 MDS-UPDRS part 3 items with good inter-rater reliability (Intraclass Correlation Coefficient (ICC) 0.80 in the OFF-medication state, ICC 0.73 in the ON-medication state). Clinician scores had exceptionally high levels of inter-rater reliability in both the OFF (0.99) and ON (0.94) medication conditions (possibly reflecting the highly experienced team). There was an ICC of 0.84 in the OFF-medication state and 0.31 in the ON-medication state between the mean Clinician and mean Kelvin scores for the equivalent 7 motor items, possibly due to dyskinesia impacting on the KELVIN scores. CONCLUSION: We conclude that KELVIN may prove useful in the capture and scoring of multiple items of MDS-UPDRS part 3 with levels of consistency not far short of that achieved by experienced MDS-UPDRS clinical raters, and is worthy of further investigation.

Novel Programming Features Help Alleviate Subthalamic Nucleus Stimulation-Induced Side Effects.

BACKGROUND: Subthalamic nucleus deep brain stimulation (STN-DBS) is a widely used treatment for Parkinson's disease (PD) patients with motor complications, but can result in adverse effects (AEs) in a significant proportion of treated patients. The use of novel programming features including short pulse width (PW) and directional steering in alleviating stimulation-induced AEs has not been explored. OBJECTIVE: To determine if programming with short PW, directional steering, or the combination of these novel techniques can improve stimulation-induced dysarthria, dyskinesia, and pyramidal AEs. METHODS: Thirty-two consecutive PD patients who experienced reversible AEs of STN-DBS had optimization of their settings using either short PW, directional steering, or the combination, while ensuring equivalent control of motor symptoms. Pairwise comparisons of pre- and post-optimization adverse effect ratings were made. Patients were left on the alternative setting with the greatest benefit and followed up at 6 months. Modeling of volume of tissue activated (VTA) and charge per pulse (Qp) calculations were used to explore potential underlying mechanisms of any differences found. RESULTS: There were significant improvements in stimulation-induced dysarthria, dyskinesia, and pyramidal side effects after optimization. At 6 months, mean AE ratings remained significantly improved compared to pre-optimization ratings. Different patterns of shift in VTA for each AE, and Qp could be used to explain improvements using novel techniques. CONCLUSIONS: Stimulation-induced dysarthria, dyskinesia, and pyramidal AEs induced by STN-DBS can be improved by using novel programming techniques. These represent additional tools to conventional methods that can be used to address these AEs. © 2020 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Short Versus Conventional Pulse-Width Deep Brain Stimulation in Parkinson's Disease: A Randomized Crossover Comparison.

BACKGROUND: Subthalamic nucleus deep brain stimulation (STN-DBS) is an effective therapy for selected Parkinson's disease patients with motor fluctuations, but can adversely affect speech and axial symptoms. The use of short pulse width (PW) has been shown to expand the therapeutic window acutely, but its utility in reducing side effects in chronic STN-DBS patients has not been evaluated. OBJECTIVE: To compare the effect of short PW settings using 30-µs with conventional 60-µs settings on stimulation-induced dysarthria in Parkinson's disease patients with previously implanted STN-DBS systems. METHODS: In this single-center, double-blind, randomized crossover trial, we assigned 16 Parkinson's disease patients who had been on STN-DBS for a mean of 6.5 years and exhibited moderate dysarthria to 30-µs or 60-µs settings for 4 weeks followed by the alternative PW setting for a further 4 weeks. The primary outcome was difference in dysarthric speech measured by the Sentence Intelligibility Test between study baseline and the 2 PW conditions. Secondary outcomes included motor, nonmotor, and quality of life measures. RESULTS: There was no difference in the Sentence Intelligibility Test scores between baseline and the 2 treatment conditions (P = 0.25). There were also no differences noted in motor, nonmotor, or quality of life scores. The 30-µs settings were well tolerated, and adverse event rates were similar to those at conventional PW settings. Post hoc analysis indicated that patients with dysarthria and a shorter duration of DBS may be improved by short PW stimulation. CONCLUSIONS: Short PW settings using 30 µs did not alter dysarthric speech in chronic STN-DBS patients. A future study should evaluate whether patients with shorter duration of DBS may be helped by short PW settings. © 2019 International Parkinson and Movement Disorder Society.

The Effect of Short Pulse Width Settings on the Therapeutic Window in Subthalamic Nucleus Deep Brain Stimulation for Parkinson's disease.

BACKGROUND: Subthalamic nucleus deep brain stimulation (STN-DBS) is an established treatment for selected Parkinson's disease (PD) patients, but therapy is often limited by side effects. Previous studies indicate an inverse relationship of the therapeutic window (TW) to pulse width (PW) settings down to 60µs, but there is limited data available on the effect of shorter PWs. OBJECTIVE: To define the TW of STN-DBS in PD at PW of 30µs (PW30) relative to standard PW settings at 60µs (PW60), and to compare speed of gait and speech intelligibility on the two PW conditions. METHODS: Monopolar review data of 15 consecutive PD patients who had screening of contacts performed at PW60 and PW30 was used to calculate the TW at each contact. We compared the TWs of the most efficacious contact per STN, and a secondary analysis was performed comparing all contacts. Speed of gait with a timed 10 metre walk test, speech intelligibility, and perceptual characteristics of speech were also compared at the efficacy thresholds for PW60 and PW30. RESULTS: The TW was significantly greater at PW30 [3.8±1.6mA] than at PW60 [1.7±1.1mA]. In the secondary analysis, 110 TWs could be calculated and these remained significantly higher at PW30. The timed 10 metre walk at PW30 was faster than at PW60, and perceptual rating scores of speech were significantly improved at PW30. CONCLUSIONS: STN-DBS in PD patients using a PW of 30µs significantly increases the TW compared to standard PW settings, and this effect is consistent across all contacts of an electrode. Speed of gait and perceptual speech scores are also improved at 30µs settings.