On the Use of t-Distributed Stochastic Neighbor Embedding for Data Visualization and Classification of Individuals with Parkinson's Disease.
ABSTRACT: Parkinson's disease (PD) is a neurodegenerative disorder that remains incurable. The available treatments for the disorder include pharmacologic therapies and deep brain stimulation (DBS). These approaches may cause distinct side effects and motor responses. This work presents the application of t-distributed stochastic neighbor embedding (t-SNE), which is a machine learning algorithm for nonlinear dimensionality reduction and data visualization, for the problem of discriminating neurologically healthy individuals from those suffering from PD (treated with levodopa and DBS). Furthermore, the assessment of classification methods is presented. Inertial and electromyographic data were collected while the subjects executed a sequence of four motor tasks. The results were focused on the comparison of the classification performance of a support vector machine (SVM) while discriminating two-dimensional feature sets estimated from Principal Component Analysis (PCA), Sammon's mapping, and t-SNE. The results showed visual and statistical differences for all three investigated groups. Classification accuracy for PCA, Sammon's mapping, and t-SNE was, respectively, 73.5%, 78.6%, and 96.9% for the training set and 67.8%, 74.1%, and 76.6% for the test set. The possibility of discriminating healthy individuals from those with PD treated with levodopa and DBS highlights the fact that each treatment method produces distinct motor behavior. The scatter plots resulting from t-SNE could be used in the clinical practice as an objective tool for measuring the discrepancy between normal and abnormal motor behaviors, being thus useful for the adjustment of treatments and the follow-up of the disorder.
Project description:Levodopa and, later, deep brain stimulation (DBS) have become the mainstays of therapy for motor symptoms associated with Parkinson's disease (PD). Although these therapeutic options lead to similar clinical outcomes, the neural mechanisms underlying their efficacy are different. Therefore, investigating the differential effects of DBS and levodopa on functional brain architecture and associated motor improvement is of paramount interest. Namely, we expected changes in functional brain connectivity patterns when comparing levodopa treatment with DBS. Clinical assessment and functional magnetic resonance imaging (fMRI) was performed before and after implanting electrodes for DBS in the subthalamic nucleus (STN) in 13 PD patients suffering from severe levodopa-induced motor fluctuations and peak-of-dose dyskinesia. All measurements were acquired in a within subject-design with and without levodopa treatment, and with and without DBS. Brain connectivity changes were computed using eigenvector centrality (EC) that offers a data-driven and parameter-free approach-similarly to Google's PageRank algorithm-revealing brain regions that have an increased connectivity to other regions that are highly connected, too. Both levodopa and DBS led to comparable improvement of motor symptoms as measured with the Unified Parkinson's Disease Rating Scale motor score (UPDRS-III). However, this similar therapeutic effect was underpinned by different connectivity modulations within the motor system. In particular, EC revealed a major increase of interconnectedness in the left and right motor cortex when comparing DBS to levodopa. This was accompanied by an increase of connectivity of these motor hubs with the thalamus and cerebellum. We observed, for the first time, significant functional connectivity changes when comparing the effects of STN DBS and oral levodopa administration, revealing different treatment-specific mechanisms linked to clinical benefit in PD. Specifically, in contrast to levodopa treatment, STN DBS was associated with increased connectivity within the cortico-thalamo-cerebellar network. Moreover, given the favorable effects of STN DBS on motor complications, the changes in the patients' clinical profile might also contribute to connectivity changes associated with STN-DBS. Understanding the observed connectivity changes may be essential for enhancing the effectiveness of DBS treatment, and for better defining the pathophysiology of the disrupted motor network in PD.
Project description:PURPOSE:To study the effect of STN-DBS on balance performance of Parkinson's disease. METHOD:16 idiopathic PD patients treated with bilateral STN-DBS (DBS Group) and 20 PD patients treated with Levodopa (Medicine group) were included in the study. Clinical material including Levodopa Equivalent Daily Dose (LEDD, mg/day), life quality (PDQ-39) were collected. For DBS group and Medicine group, The motor disability (Movement Disorder Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale ?, MDS-UPDRSIII) and balance performance (MDS-UPDRS 3.12, Berg Balance Scale BBS) and the Limits of Stability (LoS) (target acquisition percentage, trunk swing angle standard deviation, time) in state of Med-Off/Med-On at preoperation, postoperation, 6 months postoperation and 12 months postoperation were evaluated. Repeated ANOVA was used to analyze the effect of STN-DBS on balance performance. RESULT:The Clinical material (age, gender, duration, LEDD preoperation, PDQ39), motor disability (Med-on/Med-Off), balance performance (Med-on/Med-Off) and LoS preoperation had no differences in DBS-group and Medical-group (P>0.05). During the follow up, LEDD, PDQ39, Motor disability (MDS-UPDRSIII), balance performance (MDS-UPDRS 3.12, BBS) in Medicine-group had no significant changes in both Med-Off and Med-On. For DBS-group, immediately improvement of motor disability (MDS-UPDRSIII), LoS (target acquisition percentage, trunk swing angle standard deviation, time) and LEDD were observed postoperation (P<0.05); PDQ39, balance performance (MDS-UPDRS 3.12, BBS) began to improve at 6 months and 12 months postoperation. Repeated ANOVA showed that DBS could significantly improve the motor disability, balance performance and LoS in PD. CONCLUSION:STN-DBS could improve the balance performance of PD patients in H&Y3.
Project description:Introduction: Parkinson's disease (PD) is a progressive movement disorder characterized by heterogenous motor dysfunction with fluctuations in severity. Objective, short-timescale characterization of this dysfunction is necessary as therapies become increasingly adaptive. Objectives: This study aims to characterize a novel, naturalistic, and goal-directed tablet-based task and complementary analysis protocol designed to characterize the motor features of PD. Methods: A total of 26 patients with PD and without deep brain stimulation (DBS), 20 control subjects, and eight patients with PD and with DBS completed the task. Eight metrics, each designed to capture an aspect of motor dysfunction in PD, were calculated from 1-second, non-overlapping epochs of the raw positional and pressure data captured during task completion. These metrics were used to generate a classifier using a support vector machine (SVM) model to produce a unifying, scalar "motor error score" (MES). The data generated from these patients with PD were compared to same-day standard clinical assessments. Additionally, these data were compared to analogous data generated from a separate group of 12 patients with essential tremor (ET) to assess the task's specificity for different movement disorders. Finally, an SVM model was generated for each of the eight patients with PD and with DBS to differentiate between their motor dysfunction in the "DBS On" and "DBS Off" stimulation states. Results: The eight metrics calculated from the raw positional and force data captured during task completion were non-redundant. MES generated by the SVM analysis protocol showed a strong correlation with MDS-UPDRS-III scores assigned by movement disorder specialists. Analysis of the relative contributions of each of the eight metrics showed a significant difference between the motor dysfunction of PD and ET. Much of this difference was attributable to the homogenous, tremor-dominant phenotype of ET motor dysfunction. Finally, in individual patients with PD with DBS, task performance and subsequent SVM classification effectively differentiated between the "DBS On" and "DBS Off" stimulation states. Conclusion: This tablet-based task and analysis protocol correlated strongly with expert clinical assessments of PD motor dysfunction. Additionally, the task showed specificity for PD when compared to ET, another common movement disorder. This specificity was driven by the relative heterogeneity of motor dysfunction of PD compared to ET. Finally, the task was able to distinguish between the "DBS On" and "DBS Off" states within single patients with PD. This task provides temporally-precise and specific information about motor dysfunction in at least two movement disorders that could feasibly correlate to neural activity.
Project description:Purpose. To investigate the impact of deep brain stimulation of the subthalamic nucleus (STN DBS) and levodopa intake on vowel articulation in dysarthric speakers with Parkinson's disease (PD). Methods. Vowel articulation was assessed in seven Quebec French speakers diagnosed with idiopathic PD who underwent STN DBS. Assessments were conducted on- and off-medication, first prior to surgery and then 1 year later. All recordings were made on-stimulation. Vowel articulation was measured using acoustic vowel space and formant centralization ratio. Results. Compared to the period before surgery, vowel articulation was reduced after surgery when patients were off-medication, while it was better on-medication. The impact of levodopa intake on vowel articulation changed with STN DBS: before surgery, levodopa impaired articulation, while it no longer had a negative effect after surgery. Conclusions. These results indicate that while STN DBS could lead to a direct deterioration in articulation, it may indirectly improve it by reducing the levodopa dose required to manage motor symptoms. These findings suggest that, with respect to speech production, STN DBS and levodopa intake cannot be investigated separately because the two are intrinsically linked. Along with motor symptoms, speech production should be considered when optimizing therapeutic management of patients with PD.
Project description:Levodopa medication is the most efficient treatment for motor symptoms of Parkinson's disease (PD). Levodopa significantly alleviates rigidity, rest tremor, and bradykinesia in PD. The severity of motor symptoms can be graded with UPDRS-III scale. Levodopa challenge test is routinely used to assess patients' eligibility to deep-brain stimulation (DBS) in PD. Feasible and objective measurements to assess motor symptoms of PD during levodopa challenge test would be helpful in unifying the treatment. Twelve patients with advanced PD who were candidates for DBS treatment were recruited to the study. Measurements were done in four phases before and after levodopa challenge test. Rest tremor and rigidity were evaluated using UPDRS-III score. Electromyographic (EMG) signals from biceps brachii and kinematic signals from forearm were recorded with wireless measurement setup. The patients performed two different tasks: arm isometric tension and arm passive flexion-extension. The electromyographic and the kinematic signals were analyzed with parametric, principal component, and spectrum-based approaches. The principal component approach for isometric tension EMG signals showed significant decline in characteristics related to PD during levodopa challenge test. The spectral approach on passive flexion-extension EMG signals showed a significant decrease on involuntary muscle activity during the levodopa challenge test. Both effects were stronger during the levodopa challenge test compared to that of patients' personal medication. There were no significant changes in the parametric approach for EMG and kinematic signals during the measurement. The results show that a wireless and wearable measurement and analysis can be used to study the effect of levodopa medication in advanced Parkinson's disease.
Project description:Deep brain stimulation (DBS) of the subthalamic region is an established therapy for advanced Parkinson's disease (PD). However, patients often require time-intensive post-operative management to balance their coupled stimulation and medication treatments. Given the large and complex parameter space associated with this task, we propose that clinical decision support systems (CDSS) based on machine learning algorithms could assist in treatment optimization.Develop a proof-of-concept implementation of a CDSS that incorporates patient-specific details on both stimulation and medication.Clinical data from 10 patients, and 89 post-DBS surgery visits, were used to create a prototype CDSS. The system was designed to provide three key functions: (1) information retrieval; (2) visualization of treatment, and; (3) recommendation on expected effective stimulation and drug dosages, based on three machine learning methods that included support vector machines, Naïve Bayes, and random forest.Measures of medication dosages, time factors, and symptom-specific pre-operative response to levodopa were significantly correlated with post-operative outcomes (P < 0.05) and their effect on outcomes was of similar magnitude to that of DBS. Using those results, the combined machine learning algorithms were able to accurately predict 86% (12/14) of the motor improvement scores at one year after surgery.Using patient-specific details, an appropriately parameterized CDSS could help select theoretically optimal DBS parameter settings and medication dosages that have potential to improve the clinical management of PD patients.
Project description:Difficulty with step initiation, called "start hesitation," is related to gait bradykinesia and is an early hallmark of gait freezing in Parkinson disease (PD). Authors of this study investigated the effects of deep brain stimulation (DBS) and levodopa on step initiation before and 6 months after DBS surgery in 29 patients with PD who were randomized to either the bilateral subthalamic nucleus (STN) or globus pallidus internus (GPi) as the DBS site.The authors measured the amplitude and duration of anticipatory postural adjustments (APAs), the feed-forward postural preparation that precedes the onset of voluntary step initiation, based on center-of-pressure displacements on a force plate. They also measured the length and velocity of the first step using a motion analysis system to study kinematics. Some of the patients (22) were from a large, multicenter, double-blind clinical trial, and all patients in the study (29, PD-DBS group) were randomized to DBS in either the bilateral STN (15 patients) or bilateral GPi (14 patients). Differences in step initiation were investigated in 2 conditions before surgery (off/on levodopa) and in 4 conditions after surgery (off/on levodopa combined with off/on DBS). Twenty-eight elderly healthy control volunteers (CTRL group) were also tested, and 9 control volunteers with PD who met the criteria for DBS (PD-C group) were tested at baseline and 6 months later.Patients in the PD-DBS group had smaller amplitudes and longer durations of APAs compared with those in the 28 healthy control volunteers in all conditions. Before surgery, APAs improved with levodopa. After surgery, the APAs were significantly worse than in the best-treatment state before surgery (DOPA condition), and responsiveness to levodopa decreased. No differences in APAs were detected between the STN and GPi groups. A comparison with PD control volunteers who did not undergo DBS surgery confirmed that a deterioration in step preparation was not related to disease progression. Step length and velocity were smaller in the PD-DBS group than in controls in all conditions. Before surgery, levodopa improved the length and velocity of the first step. Both step length and velocity were unchanged in the best-treatment state before surgery (DOPA condition) as compared with after surgery (DBS+DOPA), with only step velocity in the STN group getting worse after surgery.Six months of DBS in the STN or GPi impaired anticipatory postural preparation for step initiation, the opposite effect as with levodopa. Deep brain stimulation disrupted postural preparation more than step execution, suggesting independent motor pathways for preparation and execution of gait. Although turning the stimulators on after surgery combined with levodopa benefited the postural preparation to step, a comparison of pre- and postsurgery conditions suggests that either the surgery itself or 6 months of continuous stimulation may lead to an alteration of circuits or plastic changes that impair step initiation.
Project description:BACKGROUND:Gocovri® (amantadine) extended release capsules are approved for the treatment of dyskinesia in patients with Parkinson's disease (PD) receiving levodopa-based therapy. OBJECTIVE:To evaluate the long-term safety, tolerability, and efficacy of Gocovri in patients with PD experiencing levodopa-induced dyskinesia. METHODS:In this 2-year open-label trial, patients completing double-blind Gocovri clinical trials or excluded from prior trials because of deep-brain stimulation (DBS) received Gocovri 274?mg once daily at bedtime. The primary objective was to evaluate long-term safety and tolerability. In addition, dyskinesia and OFF time were assessed using Part IV (Motor Complications) scores on the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS). RESULTS:Among 223 enrolled patients (mean PD duration, 11.7 years; mean levodopa use, 9.3 years), 75.8% completed 1 year of treatment and 57.8% completed the trial, with a median treatment duration of 1.9 years. Common adverse events were fall (32.7%), hallucination (24.2%), peripheral edema (16.1%), constipation (13.5%), and urinary tract infection (10.3%); 31 patients (13.9%) discontinued because of adverse events considered related to study drug. At baseline, MDS-UPDRS Part IV scores were lower for patients continuing Gocovri (mean, 6.5 points) than for previous placebo (9.4) or DBS groups (10.5) but were similar for all groups by week 8 (6.3, 6.2, 6.4, respectively), and remained low for the duration of the trial (at week 100: 6.9, 7.3, 7.0, respectively). CONCLUSIONS:In patients with PD, Gocovri showed long-term safety and tolerability consistent with double-blind trial findings, and durable reduction in motor complications (dyskinesia and OFF time).
Project description:Benign tremulous parkinsonism (BTP) is characterized by prominent resting tremor combined with action and postural components, and with only subtle rigidity and bradykinesia. This tremor is frequently disabling and poorly responsive to therapy with levodopa. Thus, BTP could be considered either as a distinct clinical disorder or a variant of PD. We present a case of a 57-year-old man who had a 3-year history of severe and functionally disabling resting tremor with action and postural features bilaterally but with left dominant hand predominance. There was only very mild rigidity and bradykinesia and no postural instability. His tremor was refractory to dopaminergic therapy, including carbidopa/levodopa. The dopamine transporter (DAT) imaging showed reduced tracer uptake in the putamen bilaterally, more so on the right side. He was treated with deep brain stimulation (DBS) targeting the right ventral intermediate nucleus of the thalamus. His tremor resolved immediately after procedure. The DAT imaging abnormalities indicate the presynaptic dopamine deficiency. In some autopsied BTP cases classic alpha-synuclein pathology of PD was observed. Thus, despite the lack of levodopa responsiveness BTP likely represents a variant of PD and not a distinct neurodegenerative disorder. DBS should be considered for patients with BTP PD variant despite their poor responsiveness to levodopa treatment.
Project description:<h4>Objective</h4>To evaluate the effectiveness of levodopa-carbidopa intestinal gel (LCIG) as an add-on rescue therapy following deep brain stimulation (DBS) for treatment of motor fluctuations.<h4>Background</h4>Both DBS and LCIG are FDA-approved therapies for treatment of motor fluctuations in advanced PD. Few studies have examined dual therapy for refractory motor fluctuations and it is unknown what the effect on quality of life will be in advanced PD.<h4>Methods</h4>We conducted a retrospective study using a large database of all medical and surgical PD cases at the University of Florida. Six patients were identified with DBS who subsequently received rescue LCIG therapy. The clinical histories, indications for intervention and outcomes were reviewed.<h4>Results</h4>All patients were managed initially with DBS (bilateral STN DBS (n = 3), bilateral GPi DBS (n = 1), unilateral GPI DBS (n = 2)). Patients with well-placed (n = 3) and suboptimally placed DBS leads (n = 3) had significant reduction in their motor fluctuations with improvement in the off-medication time after rescue LCIG therapy. Improvement in quality of life scores (PDQ-39) was appreciated in four DBS patients following the addition of LCIG therapy.<h4>Conclusions</h4>LCIG is a promising add-on rescue therapy for select patients with existing DBS devices. The LCIG may possibly reduce motor fluctuations and improve quality of life in advanced PD irrespective of the DBS target or the accuracy of lead placement. Dual therapy may also be ideal for patients who are considered high risk for additional DBS surgeries.