Prediction of Parkinson’s disease tremor onset using radial basis function neural networks

The possibility of using a radial basis function neural network (RBFNN) to accurately recognise and predict the onset of Parkinson’s disease tremors in human subjects is discussed in this paper. The data for training the RBFNN are obtained by means of deep brain electrodes implanted in a Parkinson disease patient’s brain. The effectiveness of a RBFNN is initially demonstrated by a real case study.

Prediction of Parkinson’s Disease tremor onset using a radial basis function neural network based on particle swarm optimization

Deep Brain Stimulation (DBS) has been successfully used throughout the world for the treatment of Parkinson's disease symptoms. To control abnormal spontaneous electrical activity in target brain areas DBS utilizes a continuous stimulation signal. This continuous power draw means that its implanted battery power source needs to be replaced every 18–24 months. To prolong the life span of the battery, a technique to accurately recognize and predict the onset of the Parkinson's disease tremors in human subjects and thus implement an on-demand stimulator is discussed here. The approach is to use a radial basis function neural network (RBFNN) based on particle swarm optimization (PSO) and principal component analysis (PCA) with Local Field Potential (LFP) data recorded via the stimulation electrodes to predict activity related to tremor onset. To test this approach, LFPs from the subthalamic nucleus (STN) obtained through deep brain electrodes implanted in a Parkinson patient are used to train the network. To validate the network's performance, electromyographic (EMG) signals from the patient's forearm are recorded in parallel with the LFPs to accurately determine occurrences of tremor, and these are compared to the performance of the network. It has been found that detection accuracies of up to 89% are possible. Performance comparisons have also been made between a conventional RBFNN and an RBFNN based on PSO which show a marginal decrease in performance but with notable reduction in computational overhead.

Parkinson’s Disease tremor classification – a comparison between Support Vector Machines and neural networks

Deep Brain Stimulation has been used in the study of and for treating Parkinson’s Disease (PD) tremor symptoms since the 1980s. In the research reported here we have carried out a comparative analysis to classify tremor onset based on intraoperative microelectrode recordings of a PD patient’s brain Local Field Potential (LFP) signals. In particular, we compared the performance of a Support Vector Machine (SVM) with two well known artificial neural network classifiers, namely a Multiple Layer Perceptron (MLP) and a Radial Basis Function Network (RBN). The results show that in this study, using specifically PD data, the SVM provided an overall better classification rate achieving an accuracy of 81% recognition.

Pathogenic Parkinson’s disease mutations across the functional domains of LRRK2 alter the autophagic/lysosomal response to starvation

LRRK2 is one of the most important genetic contributors to Parkinson’s disease (PD). Point mutations in this gene cause an autosomal dominant form of PD, but to date no cellular phenotype has been consis- tently linked with mutations in each of the functional domains (ROC, COR and Kinase) of the protein product of this gene. In this study, primary fibroblasts from individuals carrying pathogenic mutations in the three central domains of LRRK2 were assessed for alterations in the autophagy/lysosomal pathway using a combination of biochemical and cellular approaches. Mutations in all three domains resulted in alterations in markers for autophagy/lysosomal function compared to wild type cells. These data high- light the autophagy and lysosomal pathways as read outs for pathogenic LRRK2 function and as a marker for disease, and provide insight into the mechanisms linking LRRK2 function and mutations.

A fuzzy logic controller for intestinal levodopa infusion in Parkinson’s disease

The aim of this work is to evaluate the fuzzy system for different types of patients for levodopa infusion in Parkinson Disease based on simulation experiments using the pharmacokinetic-pharmacodynamic model. Fuzzy system is to control patient’s condition by adjusting the value of flow rate, and it must be effective on three types of patients, there are three different types of patients, including sensitive, typical and tolerant patient; the sensitive patients are very sensitive to drug dosage, but the tolerant patients are resistant to drug dose, so it is important for controller to deal with dose increment and decrement to adapt different types of patients, such as sensitive and tolerant patients. Using the fuzzy system, three different types of patients can get useful control for simulating medication treatment, and controller will get good effect for patients, when the initial flow rate of infusion is in the small range of the approximate optimal value for the current patient’ type.

Classification of Parkinson’s Disease using MultiPass Lvq,Logistic Model Tree,K-Star for Audio Data set : Classification of Parkinson Disease using Audio Dataset

Parkinson's disease (PD) is a degenerative illness whose cardinal symptoms include rigidity, tremor, and slowness of movement. In addition to its widely recognized effects PD can have a profound effect on speech and voice.The speech symptoms most commonly demonstrated by patients with PD are reduced vocal loudness, monopitch, disruptions of voice quality, and abnormally fast rate of speech. This cluster of speech symptoms is often termed Hypokinetic Dysarthria.The disease can be difficult to diagnose accurately, especially in its early stages, due to this reason, automatic techniques based on Artificial Intelligence should increase the diagnosing accuracy and to help the doctors make better decisions. The aim of the thesis work is to predict the PD based on the audio files collected from various patients.Audio files are preprocessed in order to attain the features.The preprocessed data contains 23 attributes and 195 instances. On an average there are six voice recordings per person, By using data compression technique such as Discrete Cosine Transform (DCT) number of instances can be minimized, after data compression, attribute selection is done using several WEKA build in methods such as ChiSquared, GainRatio, Infogain after identifying the important attributes, we evaluate attributes one by one by using stepwise regression.Based on the selected attributes we process in WEKA by using cost sensitive classifier with various algorithms like MultiPass LVQ, Logistic Model Tree(LMT), K-Star.The classified results shows on an average 80%.By using this features 95% approximate classification of PD is acheived.This shows that using the audio dataset, PD could be predicted with a higher level of accuracy.

Gross Motor Deficits in Children Prenatally Exposed to Alcohol: A Meta-analysis

BACKGROUND AND OBJECTIVES: Gross motor (GM) deficits are often reported in children with prenatal alcohol exposure (PAE), but their prevalence and the domains affected are not clear. The objective of this review was to characterize GM impairment in children with a diagnosis of fetal alcohol spectrum disorder (FASD) or moderate to heavy maternal alcohol intake.METHODS: A systematic review with meta-analysis was conducted. Medline, Embase, Allied and Complementary Medicine Database, Cumulative Index to Nursing and Allied Health Literature, PsycINFO, PEDro, and Google Scholar databases were searched. Published observational studies including children aged 0 to <= 18 years with (1) an FASD diagnosis or moderate to heavy PAE, or a mother with confirmed alcohol dependency or binge drinking during pregnancy, and (2) GM outcomes obtained by using a standardized assessment tool. Data were extracted regarding participants, exposure, diagnosis, and outcomes by using a standardized protocol. Methodological quality was evaluated by using Strengthening the Reporting of Observational Studies in Epidemiology guidelines.RESULTS: The search recovered 2881 articles of which 14 met the systematic review inclusion criteria. The subjects' mean age ranged from 3 days to 13 years. Study limitations included failure to report cutoffs for impairment, nonstandardized reporting of PAE, and small sample sizes. The meta-analysis pooled results (n = 10) revealed a significant association between a diagnosis of FASD or moderate to heavy PAE and GM impairment (odds ratio: 2.9; 95% confidence interval: 2.1-4.0). GM deficits were found in balance, coordination, and ball skills. There was insufficient data to determine prevalence.CONCLUSIONS: The significant results suggest evaluation of GM proficiency should be a standard component of multidisciplinary FASD diagnostic services.

Classification of handwriting patterns in patients with Parkinson´s disease, using a biometric sensor

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Enhancing rehabilitation of motor deficits with peripheral nerve stimulation

A number of different neurorehabilitation strategies include manipulation of the somatosensory system, e.g. in the form of training by passive movement. Recently, peripheral electrical nerve stimulation has been proposed as a simple, painless method of enhancing rehabilitation of motor deficits. Several physiological studies both in animals and in humans indicate that a prolonged period of patterned peripheral electrical stimulation induces short-term plasticity at multiple levels of the motor system. Small-scale studies in humans indicate that these plastic changes are linked with improvement in motor function, particularly in patients with chronic motor deficits after stroke. Somatosensory-mediated disinhibition of motor pathways is a possible underlying mechanism and might explain why peripheral electrical stimulation is more effective when combined with active training. Further large-scale studies are needed to identify the optimal stimulation protocol and the patient groups that stand to benefit the most from this technique.

Co-morbidity burden in Parkinson’s disease : Comparison with controls and its influence on prognosis

Open Access funded by Parkinson's UK Financial support: This study was funded by Parkinson’s UK, the Scottish Chief Scientist Office, NHS Grampian endowments, the BMA Doris Hillier award, RS Macdonald Trust, the BUPA Foundation, and SPRING. The funders had no involvement in the study. We acknowledge funding for the PINE study from Parkinson’s UK (G-0502, G-0914 G-1302), the Scottish Chief Scientist Office (CAF/12/05), the BMA Doris Hillier award, RS Macdonald Trust, the BUPA Foundation, NHS Grampian endowments and SPRING. We thank the patients and controls for their participation and the research staff who collected data and supported the study database.

Potential Benefit of Singing for People with Parkinson’s Disease : A Systematic Review

Acknowledgements including sources of support This study was not supported by any particular grant or funding source. The senior author MSB, an epidemiologist with research experience in PD, wishes to thank clinician authors JB, RAA and SMB for their invaluable contributions. JB is a retired health professional with long-standing experience in community health. RAA and SMB are qualified and practising speech and language therapists and RAA specialises in adult neurological disorders. Additionally, we thank Dr Katherine Deane of the University of East Anglia for expert input regarding the Threats to Validity quality tool, on which she was the lead developer.

Axon pathology in Parkinson’s disease and Lewy body dementia hippocampus contains α-, β-, and γ-synuclein

Pathogenic α-synuclein (αS) gene mutations occur in rare familial Parkinson’s disease (PD) kindreds, and wild-type αS is a major component of Lewy bodies (LBs) in sporadic PD, dementia with LBs (DLB), and the LB variant of Alzheimer’s disease, but β-synuclein (βS) and γ-synuclein (γS) have not yet been implicated in neurological disorders. Here we show that in PD and DLB, but not normal brains, antibodies to αS and βS reveal novel presynaptic axon terminal pathology in the hippocampal dentate, hilar, and CA2/3 regions, whereas antibodies to γS detect previously unrecognized axonal spheroid-like lesions in the hippocampal dentate molecular layer. The aggregation of other synaptic proteins and synaptic vesicle-like structures in the αS- and βS-labeled hilar dystrophic neurites suggests that synaptic dysfunction may result from these lesions. Our findings broaden the concept of neurodegenerative “synucleinopathies” by implicating βS and γS, in addition to αS, in the onset/progression of PD and DLB.