scholarly journals Weighted Hybrid Feature Reduction Embedded with Ensemble Learning for Speech Data of Parkinson’s Disease

Mathematics ◽  
2021 ◽  
Vol 9 (24) ◽  
pp. 3172
Author(s):  
Zeeshan Hameed ◽  
Waheed Ur Rehman ◽  
Wakeel Khan ◽  
Nasim Ullah ◽  
Fahad R. Albogamy
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Ensemble Learning ◽  
Neurodegenerative Disorder ◽  
Small Sample Size ◽  
Small Sample ◽  
Feature Reduction ◽  
Speech Data ◽  
Boosting Method ◽  
The Stability

Parkinson’s disease (PD) is a progressive and long-term neurodegenerative disorder of the central nervous system. It has been studied that 90% of the PD subjects have voice impairments which are some of the vital characteristics of PD patients and have been widely used for diagnostic purposes. However, the curse of dimensionality, high aliasing, redundancy, and small sample size in PD speech data bring great challenges to classify PD objects. Feature reduction can efficiently solve these issues. However, existing feature reduction algorithms ignore high aliasing, noise, and the stability of algorithms, and thus fail to give substantial classification accuracy. To mitigate these problems, this study proposes a weighted hybrid feature reduction embedded with ensemble learning technique which comprises (1) hybrid feature reduction technique that increases inter-class variance, reduces intra-class variance, preserves the neighborhood structure of data, and remove co-related features that causes high aliasing and noise in classification. (2) Weighted-boosting method to train the model precisely. (3) Furthermore, the stability of the algorithm is enhanced by introducing a bagging strategy. The experiments were performed on three different datasets including two widely used datasets and a dataset provided by Southwest Hospital (Army Military Medical University) Chongqing, China. The experimental results indicated that compared with existing feature reduction methods, the proposed algorithm always shows the highest accuracy, precision, recall, and G-mean for speech data of PD. Moreover, the proposed algorithm not only shows excellent performance for classification but also deals with imbalanced data precisely and achieved the highest AUC in most of the cases. In addition, compared with state-of-the-art algorithms, the proposed method shows improvement up to 4.53%. In the future, this algorithm can be used for early and differential diagnoses, which are rated as challenging tasks.

scholarly journals Hierarchical Boosting Dual-Stage Feature Reduction Ensemble Model for Parkinson’s Disease Speech Data

Diagnostics ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2312
Author(s):  
Mingyao Yang ◽  
Jie Ma ◽  
Pin Wang ◽  
Zhiyong Huang ◽  
Yongming Li ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Small Sample ◽  
Feature Reduction ◽  
Ensemble Model ◽  
High Quality ◽  
Speech Data ◽  
Dual Stage ◽  
Instance Space ◽  
Quality Features

As a neurodegenerative disease, Parkinson’s disease (PD) is hard to identify at the early stage, while using speech data to build a machine learning diagnosis model has proved effective in its early diagnosis. However, speech data show high degrees of redundancy, repetition, and unnecessary noise, which influence the accuracy of diagnosis results. Although feature reduction (FR) could alleviate this issue, the traditional FR is one-sided (traditional feature extraction could construct high-quality features without feature preference, while traditional feature selection could achieve feature preference but could not construct high-quality features). To address this issue, the Hierarchical Boosting Dual-Stage Feature Reduction Ensemble Model (HBD-SFREM) is proposed in this paper. The major contributions of HBD-SFREM are as follows: (1) The instance space of the deep hierarchy is built by an iterative deep extraction mechanism. (2) The manifold features extraction method embeds the nearest neighbor feature preference method to form the dual-stage feature reduction pair. (3) The dual-stage feature reduction pair is iteratively performed by the AdaBoost mechanism to obtain instances features with higher quality, thus achieving a substantial improvement in model recognition accuracy. (4) The deep hierarchy instance space is integrated into the original instance space to improve the generalization of the algorithm. Three PD speech datasets and a self-collected dataset are used to test HBD-SFREM in this paper. Compared with other FR algorithms and deep learning algorithms, the accuracy of HBD-SFREM in PD speech recognition is improved significantly and would not be affected by a small sample dataset. Thus, HBD-SFREM could give a reference for other related studies.

scholarly journals Role of MicroRNAs in Parkinson’s Disease

2019 ◽  
Vol 20 (22) ◽  
pp. 5649 ◽  
Author(s):  
Suh Yee Goh ◽  
Yin Xia Chao ◽  
Shaikali Thameem Dheen ◽  
Eng-King Tan ◽  
Samuel Sam-Wah Tay
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Small Sample Size ◽  
Small Sample ◽  
Biological Molecules ◽  
Incomplete Penetrance ◽  
Cellular Functions ◽  
Druggable Targets ◽  
The Brain

Parkinson’s disease (PD) is a disabling neurodegenerative disease that manifests with resting tremor, bradykinesia, rigidity and postural instability. Since the discovery of microRNAs (miRNAs) in 1993, miRNAs have been shown to be important biological molecules involved in diverse processes to maintain normal cellular functions. Over the past decade, many studies have reported dysregulation of miRNA expressions in PD. Here, we identified 15 miRNAs from 34 reported screening studies that demonstrated dysregulation in the brain and/or neuronal models, cerebrospinal fluid (CSF) and blood. Specific miRNAs-of-interest that have been implicated in PD pathogenesis include miR-30, miR-29, let-7, miR-485 and miR-26. However, there are several challenges and limitations in drawing definitive conclusions due to the small sample size in clinical studies, varied laboratory techniques and methodologies and their incomplete penetrance of the blood–brain barrier. Developing an optimal delivery system and unravelling druggable targets of miRNAs in both experimental and human models and clinical validation of the results may pave way for novel therapeutics in PD.

scholarly journals Gambling Habits of People With Parkinson’s Disease: An Exploratory Study

2017 ◽  
Author(s):  
Dominic Nadeau ◽  
Isabelle Giroux ◽  
Martine Simard ◽  
Christian Jacques ◽  
Nicolas Dupré
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Impulse Control ◽  
Small Sample Size ◽  
Structured Interview ◽  
Small Sample ◽  
Slot Machines ◽  
Gambling Problem ◽  
Maladie De Parkinson ◽  
Gambling Activities

The development of pathological gambling (PG) among people with Parkinson’s disease (PD) is increasingly reported. The intake of dopamine agonists is most often associated with the emergence of this addiction. Although it is known that gambling habits contribute to the onset of gambling problems in the general population, these habits have not yet been studied in individuals with PD. Thus, this study aimed to explore gambling habits in people with PD. Twenty-five individuals with PD and 8 caregivers participated. Thirteen gamblers took part in a semi-structured interview regarding their gambling habits and the presence of a gambling problem and other impulse-control disorders. The results show that gamblers mainly play lotteries and slot machines. Most gamble for pleasure, but some reported wanting to win money to finance a cure for their PD. None of the gamblers involved a caregiver in their gambling activities and no gambler currently presented a gambling problem. However, 2 at-risk gamblers reported having developed a gambling problem in the past. This study sheds light on factors that may contribute to the development of PG among patients with PD, namely, the emergence of new reasons for gambling after a PD diagnosis, erroneous beliefs about gambling, and discretion about gambling habits. Prevention strategies are discussed in view of these results. However, given the small sample size, further studies examining the gambling habits of people with PD are required.RésuméDe plus en plus, on observe le développement du jeu pathologique (JP) chez les personnes atteintes de la maladie de Parkinson (MP). La prise d’agonistes de la dopamine est le plus souvent associée à l’émergence de cette dépendance. Bien qu’il soit connu que les habitudes de jeu contribuent à l’apparition de problèmes de jeu dans la population en général, ces habitudes n’ont pas encore été étudiées chez les personnes atteintes de la maladie de Parkinson (MP). Dans cette optique, cette étude explore les habitudes de jeu chez les personnes atteintes de la MP. Vingt-cinq personnes atteintes de la maladie de Parkinson et huit soignants y ont participé. Treize joueurs ont participé à une entrevue semi-structurée concernant leurs habitudes de jeu et la présence d’un problème de jeu et d’autres troubles liés au contrôle des impulsions. Les résultats montrent que les joueurs jouent principalement aux loteries et aux machines à sous. La plupart jouent par plaisir, mais certains ont déclaré vouloir gagner de l’argent pour financer une thérapie contre la maladie. Aucun des joueurs n’avait avec lui un fournisseur de soins dans ses activités de jeu et aucun joueur ne présentait actuellement de problème de jeu. Cependant, deux joueurs à risque ont déclaré en avoir développé un par le passé. Cette étude met en lumière les facteurs qui peuvent contribuer au développement du jeu pathologique chez les personnes atteintes de Parkinson, à savoir l’émergence de nouvelles raisons pour le jeu après un diagnostic de MP, les croyances erronées sur le jeu et la discrétion sur les habitudes de jeu. Compte tenu de ces résultats, des stratégies de prévention sont analysées. Cependant, étant donné la petite taille de l’échantillon, d’autres études examinant les habitudes de jeu des personnes atteintes de cette maladie sont nécessaires.

scholarly journals Frequency of the LRRK2 G2019S mutation in late-onset sporadic patients with Parkinson’s disease

2014 ◽  
Vol 72 (5) ◽  
pp. 356-359 ◽  
Author(s):  
Hsin Fen Chien ◽  
Tamires Rocha Figueiredo ◽  
Marianna Almeida Hollaender ◽  
Fabiano Tofoli ◽  
Leonel Takao Takada ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Late Onset ◽  
Small Sample Size ◽  
Clinical Manifestations ◽  
Small Sample ◽  
Genetical Analysis ◽  
G2019s Mutation ◽  
Lrrk2 Gene ◽  
And Gender

Mutations in the LRRK2 gene, predominantly G2019S, have been reported in individuals with autosomal dominant inheritance and sporadic Parkinson’s disease (PD). The G2019S mutation has an age-dependent penetrance and evidence shows common ancestry. The clinical manifestations are indistinguishable from idiopathic PD. Its prevalence varies according to the population studied ranging from less than 0.1% in Asians to 41% in North African Arabs. This study aimed to identify G2019S mutation in Brazilian idiopathic PD patients.Method:We sampled 100 PD patients and 100 age- and gender-matched controls. Genetical analysis was accomplished by polymerase chain reaction (PCR).Results:No G2019S mutations were found in both patients with sporadic PD and controls.Conclusions:Our results may be explained by the relatively small sample size.

scholarly journals COVID-19 and Parkinson’s Disease: What We Know So Far?

2021 ◽  
pp. 1-10
Author(s):  
Carlo Alberto Artusi ◽  
Alberto Romagnolo ◽  
Claudia Ledda ◽  
Maurizio Zibetti ◽  
Mario Giorgio Rizzone ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Vitamin D ◽  
Parkinson's Disease ◽  
General Population ◽  
Protective Factors ◽  
Small Sample Size ◽  
Demographic Data ◽  
Case Fatality ◽  
Small Sample ◽  
Infection Prevalence

Background: Many studies on Parkinson’s disease (PD) patients affected by Coronavirus-disease-2019 (COVID-19) were recently published. However, the small sample size of infected patients enrolled in most studies did not allow to draw robust conclusions on the COVID-19 impact in PD. Objective: We aimed to assess whether the prevalence and outcome of COVID-19 in PD patients are different from those observed in the general population. Methods: We conducted a systematic review of studies reporting data on PD patients with a diagnosis of COVID-19 (PD-COVID+). We extracted prevalence, clinical-demographic data, outcome, and mortality. We also analyzed risk or protective factors based on comparisons between PD-COVID+ and control populations with PD without COVID-19 or without PD with COVID-19. Results: We included 16 studies reporting on a total of 11,325 PD patients, 1,061 with a confirmed diagnosis of COVID-19. The median infection prevalence ranged from 0.6% to 8.5%. PD-COVID+ patients had a median age of 74 and a disease duration of 9.4 years. Pooling all PD-COVID+ patients from included studies, 28.6% required hospitalization, 37.1% required levodopa dose increasing, and 18.9% died. The case fatality was higher in PD-COVID+ patients than the general population, with longer PD duration as a possible risk factor for worse outcome. Amantadine and vitamin D were proposed as potential protective factors. Conclusion: Available studies indicate a higher case fatality in PD patients affected by COVID-19 than the general population. Conversely, current literature does not definitively clarify whether PD patients are more susceptible to get infected. The potential protective role of vitamin D and amantadine is intriguing but deserves further investigation.

scholarly journals Diagnosis of Parkinson’s Disorder through Speech Data using Machine Learning Algorithms

2020 ◽  
Vol 9 (3) ◽  
pp. 69-72
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Health Care ◽  
Decision Making ◽  
Parkinson's Disease ◽  
Neurodegenerative Disorder ◽  
Machine Learning Algorithms ◽  
Speech Data ◽  
Computer Aided ◽  
Comprehensive Comparison

Parkinson's disease is a neurodegenerative disorder that affects millions of people around the globe. Detecting Parkinson's disease at an earlier stage could help to better diagnose the disease. Machine learning provides potentially large opportunities for computer-aided identification and diagnosis that could minimize unavoidable health care errors and inherent clinical uncertainty, provide guidance, and improve decision-making. In this paper, we explore the feature extraction and prediction algorithms used to predict Parkinson's disease and provide a comprehensive comparison of these algorithms

scholarly journals Measuring implicit sequence learning and dual task ability in mild to moderate Parkinson´s disease: A feasibility study

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0251849
Author(s):  
Malin Freidle ◽  
Hanna Johansson ◽  
Alexander V. Lebedev ◽  
Urban Ekman ◽  
Martin Lövdén ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Reaction Time ◽  
Dual Task ◽  
Sequence Learning ◽  
Small Sample Size ◽  
Small Sample ◽  
Difficulty Level ◽  
Implicit Sequence Learning ◽  
Healthy Individuals

We investigated the feasibility aspects of two choice reaction time tasks designed to assess implicit sequence learning and dual task ability in individuals with mild to moderate Parkinson’s disease in comparison to healthy individuals. Twelve individuals with mild to moderate Parkinson’s disease and 12 healthy individuals, all ≥ 60 years of age, were included. A serial reaction time task was used as a measure of implicit sequence learning and a similar task but with the addition of a simple counting task, was used as a measure of dual task ability. We have present thorough descriptive statistics of the data but we have refrained from any inferential statistics due to the small sample size. All participants understood the task instructions and the difficulty level of both tasks was deemed acceptable. There were indications of task fatigue that demand careful choices for how best to analyse the data from such tasks in future trials. Ceiling effects were present in several accuracy outcomes, but not in the reaction time outcomes. Overall, we found both tasks to be feasible to use in samples of individuals with mild to moderate Parkinson’s disease and healthy older individuals.

scholarly journals Gambling Habits of People With Parkinson’s Disease: An Exploratory Study

2017 ◽  
Author(s):  
Dominic Nadeau ◽  
Isabelle Giroux ◽  
Martine Simard ◽  
Christian Jacques ◽  
Nicolas Dupré
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Impulse Control ◽  
Small Sample Size ◽  
Structured Interview ◽  
Small Sample ◽  
Slot Machines ◽  
Gambling Problem ◽  
Maladie De Parkinson ◽  
Gambling Activities

The development of pathological gambling (PG) among people with Parkinson’s disease (PD) is increasingly reported. The intake of dopamine agonists is most often associated with the emergence of this addiction. Although it is known that gambling habits contribute to the onset of gambling problems in the general population, these habits have not yet been studied in individuals with PD. Thus, this study aimed to explore gambling habits in people with PD. Twenty-five individuals with PD and 8 caregivers participated. Thirteen gamblers took part in a semi-structured interview regarding their gambling habits and the presence of a gambling problem and other impulse-control disorders. The results show that gamblers mainly play lotteries and slot machines. Most gamble for pleasure, but some reported wanting to win money to finance a cure for their PD. None of the gamblers involved a caregiver in their gambling activities and no gambler currently presented a gambling problem. However, 2 at-risk gamblers reported having developed a gambling problem in the past. This study sheds light on factors that may contribute to the development of PG among patients with PD, namely, the emergence of new reasons for gambling after a PD diagnosis, erroneous beliefs about gambling, and discretion about gambling habits. Prevention strategies are discussed in view of these results. However, given the small sample size, further studies examining the gambling habits of people with PD are required.RésuméDe plus en plus, on observe le développement du jeu pathologique (JP) chez les personnes atteintes de la maladie de Parkinson (MP). La prise d’agonistes de la dopamine est le plus souvent associée à l’émergence de cette dépendance. Bien qu’il soit connu que les habitudes de jeu contribuent à l’apparition de problèmes de jeu dans la population en général, ces habitudes n’ont pas encore été étudiées chez les personnes atteintes de la maladie de Parkinson (MP). Dans cette optique, cette étude explore les habitudes de jeu chez les personnes atteintes de la MP. Vingt-cinq personnes atteintes de la maladie de Parkinson et huit soignants y ont participé. Treize joueurs ont participé à une entrevue semi-structurée concernant leurs habitudes de jeu et la présence d’un problème de jeu et d’autres troubles liés au contrôle des impulsions. Les résultats montrent que les joueurs jouent principalement aux loteries et aux machines à sous. La plupart jouent par plaisir, mais certains ont déclaré vouloir gagner de l’argent pour financer une thérapie contre la maladie. Aucun des joueurs n’avait avec lui un fournisseur de soins dans ses activités de jeu et aucun joueur ne présentait actuellement de problème de jeu. Cependant, deux joueurs à risque ont déclaré en avoir développé un par le passé. Cette étude met en lumière les facteurs qui peuvent contribuer au développement du jeu pathologique chez les personnes atteintes de Parkinson, à savoir l’émergence de nouvelles raisons pour le jeu après un diagnostic de MP, les croyances erronées sur le jeu et la discrétion sur les habitudes de jeu. Compte tenu de ces résultats, des stratégies de prévention sont analysées. Cependant, étant donné la petite taille de l’échantillon, d’autres études examinant les habitudes de jeu des personnes atteintes de cette maladie sont nécessaires.

scholarly journals Spatiotemporal Gait Patterns During Overt and Covert Evaluation in Patients With Parkinson’s Disease and Healthy Subjects: Is There a Hawthorne Effect?

2015 ◽  
Vol 31 (3) ◽  
pp. 189-194 ◽  
Author(s):  
Verónica Robles-García ◽  
Yoanna Corral-Bergantiños ◽  
Nelson Espinosa ◽  
María Amalia Jácome ◽  
Carlos García-Sancho ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Healthy Subjects ◽  
Small Sample Size ◽  
Step Length ◽  
Gait Pattern ◽  
Small Sample ◽  
Time Variability ◽  
Expectancy Effects ◽  
Experimental Conditions

Parkinson’s disease (PD) and aging lead to gait impairments. Some of the disturbances of gait are focused on step length, cadence, and temporal variability of gait cycle. Under experimental conditions gait can be overtly evaluated, but patients with PD are prone to expectancy effects; thus it seems relevant to determine if such evaluation truly reflects the spontaneous gait pattern in such patients, and also in healthy subjects. Thirty subjects (15 subjects with PD and 15 healthy control subjects) were asked to walk using their natural, preferred gait pattern. In half of the trials subjects were made aware that they were being evaluated (overt evaluation), while in the rest of the trials the evaluation was performed covertly (covert evaluation). During covert evaluation the gait pattern was modified in all groups. Gait speed was significantly increased (P = .022); step cadence and average step length were also significantly modified, the average step length increased (P = .002) and the cadence was reduced (P ≤ .001). Stride cycle time variability was unchanged significantly (P = .084). These changes were not significantly different compared between elderly and young healthy controls either. Due to the small sample size, a note of caution is in order; however, the significant results suggest that covert evaluation of gait might be considered to complement experimental evaluations of gait.

A-75 Effects of Rivastigmine on Neurocognitive Deficits in Patients with Parkinson’s Disease

2021 ◽  
Vol 36 (6) ◽  
pp. 1117-1117
Author(s):  
Carrie Roper ◽  
Rainer Coelln ◽  
Lisa Shulman ◽  
Kristen Mordecai
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cognitive Impairment ◽  
Executive Functioning ◽  
Cognitive Deficits ◽  
Small Sample Size ◽  
Randomized Study ◽  
Small Sample ◽  
Neurocognitive Deficits ◽  
Open Label

Abstract Objective Cognitive impairments are commonly seen in Parkinson’s disease (PD). However, identification and tracking of cognitive deficits are not always part of treatment plans. Cholinergic treatment with rivastigmine has demonstrated beneficial effects on cognition and gait stability in PD-dementia, but less evidence exists in PD-mild cognitive impairment. We investigated the cognitive effects of rivastigmine treatment in a 3-month open-label pilot study. Method 31 participants with PD and mild–moderate cognitive impairment (24 male; mean age = 71.7; mean years-of-education = 17.2; mean Montreal Cognitive Assessment (MoCA) score = 21.7) completed pre-testing in a single-site, non-randomized study at the University of Maryland Parkinson’s Disease and Movement Disorders Center. A subset of 12 patients returned for follow-up after 12 weeks of rivastigmine treatment. A physical examination, the MoCA, and a computerized cognitive measure (NeuroTrax) were completed at each session. It was hypothesized that rivastigmine would benefit cognition, particularly executive functioning. Results Rivastigmine benefited global cognitive functioning as measured by both the MoCA (t(10) = −2.5, p < 0.05; M(Time 1) = 22.6(2.2), M(Time 2) = 24.9(3.9)) and NeuroTrax (t(11) = −3.0, p < 0.05; M(Time 1) = 88.7(13.6), M(Time 2) = 95.5(11.6)), though no domain-specific changes were evident. Relationships among the two measures were also examined. Moderate correlations were found between MoCA total scores and NeuroTrax measures including Global Cognitive Scale (r = 0.40, p < 0.05), Visuospatial Functioning (r = 0.39, p < 0.05), Executive Functioning (r = 0.50, p < 0.005), and Motor Response (speed/planning; r = 0.51, p < 0.005). Conclusions Although small sample size and practice effects must be considered, results suggest potential global cognitive benefit of rivastigmine for patients with PD experiencing mild–moderate cognitive deficits. Treatment planning for all PD patients should include periodic cognitive screenings and consideration of treatment options.

Sign in / Sign up

Export Citation Format

Share Document