Effects of Parkinsonism on motor control

Assessing the reproducibility of machine-learning-based biomarker discovery in Parkinson's disease

Feature selection and machine learning algorithms can be used to analyze Single Nucleotide Polymorphisms (SNPs) data and identify potential disease biomarkers. Reproducibility of identified biomarkers is critical for them to be useful for clinical research; however, genotyping platforms and selection criteria for individuals to be genotyped affect the reproducibility of identified biomarkers. To assess biomarkers reproducibility, we collected five SNPs datasets from the database of Genotypes and Phenotypes (dbGaP) and explored several data integration strategies. While combining datasets can lead to a reduction in classification accuracy, it has the potential to improve the reproducibility of potential biomarkers. We evaluated the agreement among different strategies in terms of the SNPs that were identified as potential Parkinson's disease (PD) biomarkers. Our findings indicate that, on average, 93% of the SNPs identified in a single dataset fail to be identified in other datasets. However, through dataset integration, this lack of replication is reduced to 62%. We discovered fifty SNPs that were identified at least twice, which could potentially serve as novel PD biomarkers. These SNPs are indirectly linked to PD in the literature but have not been directly associated with PD before. These findings open up new potential avenues of investigation.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Long-term treatment with transcranial pulsed electromagnetic fields improves movement speed and elevates cerebrospinal erythropoietin in Parkinson's disease

Background

Parkinson’s disease is characterized by motor dysfunctions including bradykinesia. In a recent study, eight weeks of daily transcranial stimulation with bipolar pulsed electromagnetic fields improved functional rate of force development and decreased inter-hand tremor coherence in patients with mild Parkinson’s disease.

Objective

To investigate the effect of long-term treatment with transcranial bipolar pulsed electromagnetic fields on motor performance in terms of movement speed and on neurotrophic and angiogenic factors.

Methods

Patients diagnosed with idiopathic Parkinson’s disease had either daily 30-min treatment with bipolar (±50 V) transcranial pulsed electromagnetic stimulation (squared pulses, 3ms duration) for three eight-week periods separated by one-week pauses (T-PEMF group) (n = 16) or were included in a PD-control group (n = 8). Movement speed was assessed in a six-cycle sit-to-stand task performed on a force plate. Cerebrospinal fluid and venous blood were collected and analyzed for erythropoietin and vascular endothelial growth factor.

Results

Major significant improvement of movement speed compared to the natural development of the disease was found (p = 0.001). Thus, task completion time decreased gradually during the treatment period from 10.10s to 8.23s (p<0.001). The untreated PD-control group did not change (p = 0.458). The treated group did not differ statistically from that of a healthy age matched reference group at completion of treatment. Erythropoietin concentration in the cerebrospinal fluid also increased significantly in the treated group (p = 0.012).

Conclusion

Long-term treatment with transcranial bipolar pulsed electromagnetic fields increased movement speed markedly and elevated erythropoietin levels. We hypothesize that treatment with transcranial bipolar pulsed electromagnetic fields improved functional performance by increasing dopamine levels in the brain, possibly through erythropoietin induced neural repair and/or protection of dopaminergic neurons.

Parkinson’s Disease Detection from Drawing Movements Using Convolutional Neural Networks

Nowadays, an important research effort in healthcare biometrics is finding accurate biomarkers that allow developing medical-decision support tools. These tools help to detect and supervise illnesses like Parkinson’s disease (PD). This paper contributes to this effort by analyzing a convolutional neural network (CNN) for PD detection from drawing movements. This CNN includes two parts: feature extraction (convolutional layers) and classification (fully connected layers). The inputs to the CNN are the module of the Fast Fourier’s transform in the range of frequencies between 0 Hz and 25 Hz. We analyzed the discrimination capability of different directions during drawing movements obtaining the best results for X and Y directions. This analysis was performed using a public dataset: Parkinson Disease Spiral Drawings Using Digitized Graphics Tablet dataset. The best results obtained in this work showed an accuracy of 96.5%, a F1-score of 97.7%, and an area under the curve of 99.2%.

Movement Speed-Accuracy Trade-Off in Parkinson's Disease

Patients with Parkinson's disease (PD) often have difficulties generating rhythmic movements, and also difficulties on movement adjustments to accuracy constraints. In the reciprocal aiming task, maintaining a high accuracy comes with the cost of diminished movement speed, whereas increasing movement speed disrupts end-point accuracy, a phenomenon well known as the speed-accuracy trade-off. The aim of this study was to examine how PD impacts speed-accuracy trade-off during rhythmic aiming movements by studying the structural kinematic movement organization and to determine the influence of dopamine replacement therapy on continuous movement speed and accuracy. Eighteen patients with advanced idiopathic Parkinson's disease performed a reciprocal aiming task, where the difficulty of the task was manipulated through target width. All patients were tested in two different sessions: ON-medication and OFF-medication state. A control group composed of healthy age-matched participants was also included in the study. The following variables were used for the analyses: Movement time, Error rate, effective target width, and Performance Index. Percentage of acceleration time and percentage of non-linearity were completed with kinematics patterns description using Rayleigh-Duffing model. Both groups traded off speed against accuracy as the constraints pertaining to the latter increased. The trade-off was more pronounced with the PD patients. Dopamine therapy allowed the PD patients to move faster, but at the cost of movement accuracy. Surprisingly, the structural kinematic organization did not differ across group nor across medication condition. These results suggest that PD patients, when involved in a reciprocal aiming task, are able to produce rhythmic movements. PD patients' overall slowing down seems to reflect a global adaptation to the disease in the absence of a structurally altered kinematic organization.

Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson's disease

OBJECTIVE

We present the PaHaW Parkinson's disease handwriting database, consisting of handwriting samples from Parkinson's disease (PD) patients and healthy controls. Our goal is to show that kinematic features and pressure features in handwriting can be used for the differential diagnosis of PD.

METHODS AND MATERIAL

The database contains records from 37 PD patients and 38 healthy controls performing eight different handwriting tasks. The tasks include drawing an Archimedean spiral, repetitively writing orthographically simple syllables and words, and writing of a sentence. In addition to the conventional kinematic features related to the dynamics of handwriting, we investigated new pressure features based on the pressure exerted on the writing surface. To discriminate between PD patients and healthy subjects, three different classifiers were compared: K-nearest neighbors (K-NN), ensemble AdaBoost classifier, and support vector machines (SVM).

RESULTS

For predicting PD based on kinematic and pressure features of handwriting, the best performing model was SVM with classification accuracy of Pacc=81.3% (sensitivity Psen=87.4% and specificity of Pspe=80.9%). When evaluated separately, pressure features proved to be relevant for PD diagnosis, yielding Pacc=82.5% compared to Pacc=75.4% using kinematic features.

CONCLUSION

Experimental results showed that an analysis of kinematic and pressure features during handwriting can help assess subtle characteristics of handwriting and discriminate between PD patients and healthy controls.

Grip force modulation characteristics as a marker for clinical disease progression in individuals with Parkinson disease: case-control study

BACKGROUND

Upper extremity deficits are prevalent in individuals with Parkinson disease (PD). In the early stages of PD, such deficits can be subtle and challenging to document on clinical examination.

OBJECTIVE

The purpose of this study was to use a novel force sensor system to characterize grip force modulation, including force, temporal, and movement quality parameters, during a fine motor control task in individuals with early stage PD.

DESIGN

A case-control study was conducted.

METHODS

Fourteen individuals with early stage PD were compared with a control group of 14 healthy older adults. The relationship of force modulation parameters with motor symptom severity and disease chronicity also was assessed in people with PD. Force was measured during both precision and power grasp tasks using an instrumented twist-cap device capable of rotating in either direction.

RESULTS

Compared with the control group, the PD group demonstrated more movement arrests during both precision and power grasp and longer total movement times during the power grasp. These deficits persisted when a concurrent cognitive task was added, with some evidence of force control deficits in the PD group, including lower rates of force production during the precision grasp task and higher peak forces during the power grasp task. For precision grasp, a higher number of movement arrests in single- and dual-task conditions as well as longer total movement times in the dual-task condition were associated with more severe motor symptoms.

LIMITATIONS

The sample was small and consisted of individuals in the early stages of PD with mild motor deficits. The group with PD was predominantly male, whereas the control group was predominantly female.

CONCLUSION

The results suggest that assessing grip force modulation deficits during fine motor tasks is possible with instrumented devices, and such sensitive measures may be important for detecting and tracking change early in the progression of PD.

Effects of Parkinson's disease on optimization and structure of variance in multi-finger tasks

We explored the role of the basal ganglia in two components of multi-finger synergies by testing a group of patients with early-stage Parkinson's disease and a group of healthy controls. Synergies were defined as co-varied adjustments of commands to individual fingers that reduced variance of the total force and moment of force. The framework of the uncontrolled manifold hypothesis was used to quantify such co-variation patterns, while average performance across repetitive trials (sharing patterns) was analyzed using the analytical inverse optimization (ANIO) approach. The subjects performed four-finger pressing tasks that involved the accurate production of combinations of the total force and total moment of force and also repetitive trials at two selected combinations of the total force and moment. The ANIO approach revealed significantly larger deviations of the experimental data planes from an optimal plane for the patients compared to the control subjects. The synergy indices computed for total force stabilization were significantly higher in the control subjects compared to the patients; this was not true for synergy indices computed for moment of force stabilization. The differences in the synergy indices were due to the larger amount of variance that affected total force in the patients, while the amount of variance that did not affect total force was comparable between the groups. We conclude that the basal ganglia play an important role in both components of synergies reflecting optimization of the sharing patterns and stability of performance with respect to functionally important variables.

Use of sensitive devices to assess the effect of medication on attentional demands of precision and power grips in individuals with Parkinson disease

Deficits in fine motor control are a common early symptom in people with Parkinson disease (PD) and may serve as an ideal marker for the response to therapeutic interventions and progression of the disease. The long-term goal of this research is to develop sensitive clinical markers that can be used to accurately assess disease progression and the response to therapeutic interventions. The purpose of this preliminary study was to examine the effects of medication on the attentional demands of precision (Pre) and power (Pow) grips in individuals with PD. In order to assess force control during precision and power grip, we used an instrumented twist-cap device. Performance on the motor task was quantified using peak force levels (PF) and the time to reach peak force (TTP). To assess attentional demands of the motor task, participants performed an auditory analog of the Stroop test while performing the motor task. Dual-task cost (DTC) for all outcome variables was calculated. Dual-task cost for response latency (RL DTC) for both grips were greater (P < 0.005) when participants were on medications('ONMeds'). Mean [95%CI]: Pre = 25.7[14.7-36.7], Pow = 37.08[26.5-47.7]) compared with off medications('OFFMeds') (Pre = 12.6[1.5-23.6], Pow = 10.98[0.4-21.6]), suggesting that force control during both grip tasks may remain attentionally demanding even on medications.

Speech motor program maintenance, but not switching, is enhanced by left-hemispheric deep brain stimulation in Parkinson's disease

Speech reaction time (SRT) was measured in a response priming protocol in 12 participants with Parkinson's disease (PD) and hypokinetic dysarthria "on" and "off" left-hemispheric deep brain stimulation (DBS). Speech preparation was measured during speech motor programming in two randomly ordered speech conditions: speech maintenance and switching. Double blind testing was completed in participants with DBS of globus pallidus pars interna (GPi) (n = 5) or subthalamic nucleus (STN) (n = 7). SRT was significantly faster in the maintenance vs switch task, regardless of DBS state. SRT was faster in the speech maintenance task "on" stimulation, while there was no difference in speech switching "on" and "off" DBS. These data suggest that left-hemispheric DBS may have differential effects on aspects of speech preparation in PD. It is hypothesized that speech maintenance improvements may result from DBS-induced cortical enhancements, while the lack of difference in switching may be related to inhibition deficits mediated by the right-hemisphere. Alternatively, DBS may have little influence on the higher level motor processes (i.e., motor planning) which it is believed the switch task engaged to a greater extent than the maintenance task.

What do the basal ganglia do? A modeling perspective

Basal ganglia (BG) constitute a network of seven deep brain nuclei involved in a variety of crucial brain functions including: action selection, action gating, reward based learning, motor preparation, timing, etc. In spite of the immense amount of data available today, researchers continue to wonder how a single deep brain circuit performs such a bewildering range of functions. Computational models of BG have focused on individual functions and fail to give an integrative picture of BG function. A major breakthrough in our understanding of BG function is perhaps the insight that activities of mesencephalic dopaminergic cells represent some form of 'reward' to the organism. This insight enabled application of tools from 'reinforcement learning,' a branch of machine learning, in the study of BG function. Nevertheless, in spite of these bright spots, we are far from the goal of arriving at a comprehensive understanding of these 'mysterious nuclei.' A comprehensive knowledge of BG function has the potential to radically alter treatment and management of a variety of BG-related neurological disorders (Parkinson's disease, Huntington's chorea, etc.) and neuropsychiatric disorders (schizophrenia, obsessive compulsive disorder, etc.) also. In this article, we review the existing modeling literature on BG and hypothesize an integrative picture of the function of these nuclei.

Assessment of fine motor control in individuals with Parkinson's disease using force tracking with a secondary cognitive task

BACKGROUND AND PURPOSE

Motor symptoms of Parkinson's disease (PD) are typically assessed using clinical scales such as the Unified Parkinson's Disease Rating Scale, but clinical scales are insensitive to subtle changes early in the disease process. The goal of this project was to use current sensing technology to develop a quantitative assessment tool to document fine motor deficits in PD based on the ability to control grip force output. The assessment was designed to challenge deficits commonly encountered as a result of PD, including dual-task performance of a motor task and a cognitive task simultaneously.

METHODS

Two force sensors were used to measure the isometric pinch grip force between the thumb and index finger in 30 individuals with PD and 30 control participants of similar age without disability. Participants performed a target force tracking task with each of two different target waveforms (sinusoidal or pseudorandom) under each of three different cognitive load conditions (none, subtract 1, and subtract 3). Dependent variables calculated from the force sensor data included root mean square error, tremor integral, and lag.

RESULTS

In general, individuals with PD showed significantly less accuracy in generating the target forces as shown by larger root mean square error compared with controls (P < 0.001). They also showed greater amounts of tremor and lag compared with controls (P = 0.001 and <0.001, respectively). Deficits were more pronounced during the cognitive multitasking component of the test.

DISCUSSION AND CONCLUSIONS

These results will serve as a preliminary work for the development of a clinical biomarker for PD that may help to identify subtle deficits in fine motor control early in the disease process and facilitate tracking of disease progression with time.

Understanding Parkinsonian Handwriting Through a Computational Model of Basal Ganglia

Handwriting in Parkinson's disease (PD) is typically characterized by micrographia, jagged line contour, and unusual fluctuations in pen tip velocity. Although PD handwriting features have been used for diagnostics, they are not based on a signaling model of basal ganglia (BG). In this letter, we present a computational model of handwriting generation that highlights the role of BG. When PD conditions like reduced dopamine and altered dynamics of the subthalamic nucleus and globus pallidus externa subsystems are simulated, the handwriting produced by the model manifested characteristic PD handwriting distortions like micrographia and velocity fluctuations. Our approach to PD modeling is in tune with the perspective that PD is a dynamic disease.

Brain dopamine and kinematics of graphomotor functions

Three experiments were performed in an attempt to achieve a better understanding of the effect of dopamine on handwriting. In the first experiment, kinematic aspects of handwriting movements were compared between healthy participants and patients with Parkinson's disease (PD) on their usual dopaminergic treatment and following withdrawal of dopaminergic medication. In the second experiment, the writing performance of healthy participants with a hyperechogenicity of the substantia nigra as detected by transcranial sonography (TCS) was compared with the performance of healthy participants with low echogenicity of the substantia nigra. The third experiment examined the effect of central dopamine reduction on kinematic aspects of handwriting movements in healthy adults using acute phenylalanine and tyrosine depletion (APTD). A digitising tablet was used for the assessment of handwriting movements. Participants were asked to perform a simple writing task. Movement time, distance, velocity, acceleration and measures of fluency of handwriting movements were measured. The kinematic analysis of handwriting movements revealed that alterations of central dopaminergic neurotransmission adversely affect movement execution during handwriting. In comparison to the automatic processing of handwriting movements displayed by control participants, participants with an altered dopaminergic neurotransmission shifted from an automatic to a controlled processing of movement execution. Central dopamine appears to be of particular importance with regard to the automatic execution of well-learned movements.

Kinematic analysis of dopaminergic effects on skilled handwriting movements in Parkinson’s disease

Patients with Parkinson's disease (PD) exhibit impairments in the execution of highly practiced and skilled motor actions such as handwriting. The analysis of kinematic aspects of handwriting movements has demonstrated that size, speed, acceleration and stroke duration are affected in PD. Although beneficial effects of dopaminergic therapy in regard to execution of movements have been reported, the effects of pharmacological therapy on these measures have not been examined in detail. The present study has compared kinematic aspects of handwriting movements of 27 healthy subjects and 27 patients with PD both on their usual dopaminergic treatment and following withdrawal of dopaminergic medication. Healthy subjects were matched with PD patients according to age, sex, handedness and education level. A digitising tablet was used for the assessment of handwriting movements. Subjects were asked to perform a simple writing task. Movement time, distance, velocity, acceleration and measures of fluency of handwriting movements were measured. Compared with healthy subjects, the kinematics of handwriting movements in PD patients were markedly disturbed following withdrawal of dopaminergic medication. Although dopaminergic treatment in PD patients resulted in marked improvements in the kinematics of handwriting movements, PD patients did not reach an undisturbed level of performance. The results suggest that dopamine medication results in partial restoration of automatic movement execution.

Comparison of pallidal and subthalamic stimulation on force control in patient's with Parkinson's disease

The aim of this study was to determine the effects of unilateral deep brain stimulation (DBS) on the control and coordination of grasping forces produced by Parkinson's disease (PD) patients. Ten advanced PD patients with unilateral DBS in the globus pallidus (GPi) or the subthalamic nucleus (STN) (5 patients in each group) performed a functional bimanual dexterous manipulation task. Experiments were performed in the "Off" medication state with DBS "On" and "Off. " DBS resulted in (a) significant clinical improvements, (b) greater maximum grip force for both limbs, (c) reduced movement time, and (d) bilateral coupling of grasping forces. There were no significant differences between the GPi and STN groups for any clinical or kinematic measures. DBS of the GPi and STN leads to an improvement in the motor functioning of advanced PD patients. Improvement in force-timing specification during DBS might allow PD patients to employ a feedforward method of force control.