scholarly journals Lipidomics Prediction of Parkinson’s Disease Severity: A Machine-Learning Analysis

2021 ◽  
pp. 1-15
Author(s):  
Hila Avisar ◽  
Cristina Guardia-Laguarta ◽  
Estela Area-Gomez ◽  
Matthew Surface ◽  
Amanda K. Chan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Severity ◽  
Rating Scale ◽  
Age At Onset ◽  
Machine Learning Algorithms ◽  
Lipid Classes ◽  
Lipid Species ◽  
Severity Prediction

Background: The role of the lipidome as a biomarker for Parkinson’s disease (PD) is a relatively new field that currently only focuses on PD diagnosis. Objective: To identify a relevant lipidome signature for PD severity markers. Methods: Disease severity of 149 PD patients was assessed by the Unified Parkinson’s Disease Rating Scale (UPDRS) and the Montreal Cognitive Assessment (MoCA). The lipid composition of whole blood samples was analyzed, consisting of 517 lipid species from 37 classes; these included all major classes of glycerophospholipids, sphingolipids, glycerolipids, and sterols. To handle the high number of lipids, the selection of lipid species and classes was consolidated via analysis of interrelations between lipidomics and disease severity prediction using the random forest machine-learning algorithm aided by conventional statistical methods. Results: Specific lipid classes dihydrosphingomyelin (dhSM), plasmalogen phosphatidylethanolamine (PEp), glucosylceramide (GlcCer), dihydro globotriaosylceramide (dhGB3), and to a lesser degree dihydro GM3 ganglioside (dhGM3), as well as species dhSM(20:0), PEp(38:6), PEp(42:7), GlcCer(16:0), GlcCer(24:1), dhGM3(22:0), dhGM3(16:0), and dhGB3(16:0) contribute to PD severity prediction of UPDRS III score. These, together with age, age at onset, and disease duration, also contribute to prediction of UPDRS total score. We demonstrate that certain lipid classes and species interrelate differently with the degree of severity of motor symptoms between men and women, and that predicting intermediate disease stages is more accurate than predicting less or more severe stages. Conclusion: Using machine-learning algorithms and methodologies, we identified lipid signatures that enable prediction of motor severity in PD. Future studies should focus on identifying the biological mechanisms linking GlcCer, dhGB3, dhSM, and PEp with PD severity.

scholarly journals Predicting Longitudinal Disease Severity for Individuals with Parkinson’s Disease using Functional MRI and Machine Learning Prognostic Models

2020 ◽  
Author(s):  
Kevin P. Nguyen ◽  
Vyom Raval ◽  
Alex Treacher ◽  
Cooper Mellema ◽  
Frank Yu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Severity ◽  
Clinical Decision Making ◽  
Rating Scale ◽  
Neurodegenerative Disorder ◽  
Clinical Severity ◽  
Predictive Values ◽  
Updrs Score

AbstractParkinson’s disease is the second most common neurodegenerative disorder and is characterized by the loss of ability to control voluntary movements. Predictive biomarkers of progression in Parkinson’s Disease are urgently needed to expedite the development of neuroprotective treatments and facilitate discussions about disease prognosis between clinicians and patients. Resting-state functional magnetic resonance imaging (rs-fMRI) shows promise in predicting progression, with derived measures, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), having been previously been associated with current disease severity. In this work, ReHo and fALFF features from 82 Parkinson’s Disease subjects are used to train machine learning predictors of baseline clinical severity and progression at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Depression Rating Scale (MDS-UPDRS) score. This is the first time that rs-fMRI and machine learning have been combined to predict future disease progression. The machine learning models explain up to 30.4% (R2 = 0.304) of the variance in baseline MDS-UPDRS scores, 55.8% (R2 = 0.558) of the variance in year 1 scores, and 47.1% (R2 = 0.471) of the variance in year 2 scores with high statistical significance (p < 0.0001). For distinguishing high- and low-progression individuals (MDS-UPDRS score above or below the median), the models achieve positive predictive values of up to 71% and negative predictive values of up to 84%. The models learn patterns of ReHo and fALFF measures that predict better and worse prognoses. Higher ReHo and fALFF in regions of the default motor network predicted lower current severity and lower future progression. The rs-fMRI features in the temporal lobe, limbic system, and motor cortex were also identified as predictors. These results present a potential neuroimaging biomarker that accurately predicts progression, which may be useful as a clinical decision-making tool and in future trials of neuroprotective treatments.

Stereopsis Deficits in Parkinson’s Disease and Their Clinical Implications

2020 ◽  
Author(s):  
Fang Ba ◽  
Tina T. Sang ◽  
Jaleh Fatehi ◽  
Wenjing He ◽  
Emanuel Mostofi ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Severity ◽  
Rating Scale ◽  
Disease Status ◽  
Cognitive Status ◽  
Control Group ◽  
Motor Disorder ◽  
Healthy Control ◽  
Stereo Acuity

Abstract Background: Parkinson's disease (PD) is not exclusively a motor disorder. Among non-motor features, PD patients possess sensory visual dysfunctions. Stereopsis deficit can significantly impact patients' motor performance. However, it is not routinely tested, and its significance is under-investigated. Studying stereopsis using reliable 3D stimuli may help determine its implications in disease status in PD.The objective of the study is to investigate stereopsis abnormalities in PD with reliable and more physiological tools, and their correlation with indicators of PD severity. Methods: Twenty-four healthy control and 20 PD participants were first evaluated for visual acuity, visual field, contrast acuity, and stereoperception with 2D and Titmus stereotests, followed by the assessment with the 3D active shutter system. The correlation between stereopsis and disease severity, Unified Parkinson’s disease rating scale motor scores (UPDRS-III), levodopa equivalent daily dose (LEDD), course of disease and cognitive status were evaluated using univariate regression models. Results: Screening visual tests did not reveal any differences between PD and control group. With the 3D active shutter system, PD patients demonstrated significantly worse stereopsis (i.e p=0.002, 26 seconds of arc). There was a trend that UPDRS-III and LEDD negatively correlate with the stereo acuity, suggesting poorer stereoperception is related to disease severity. Preserved cognitive function correlated with more intact stereo acuity. Conclusion: With more reliable and physiological tools, PD patients exhibit poorer stereopsis. These deficits reflected PD motor and cognitive status. How stereopsis relates to gait, fall risks and navigation warrants more investigations in the future.

Tremor Identification Using Machine Learning in Parkinson's Disease

2019 ◽  
pp. 128-151
Author(s):  
Angana Saikia ◽  
Vinayak Majhi ◽  
Masaraf Hussain ◽  
Sudip Paul ◽  
Amitava Datta
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Support Vector Machine ◽  
Parkinson's Disease ◽  
Discriminant Analysis ◽  
Learning Algorithms ◽  
The Body ◽  
Machine Learning Algorithms ◽  
Support Vector

Tremor is an involuntary quivering movement or shake. Characteristically occurring at rest, the classic slow, rhythmic tremor of Parkinson's disease (PD) typically starts in one hand, foot, or leg and can eventually affect both sides of the body. The resting tremor of PD can also occur in the jaw, chin, mouth, or tongue. Loss of dopamine leads to the symptoms of Parkinson's disease and may include a tremor. For some people, a tremor might be the first symptom of PD. Various studies have proposed measurable technologies and the analysis of the characteristics of Parkinsonian tremors using different techniques. Various machine-learning algorithms such as a support vector machine (SVM) with three kernels, a discriminant analysis, a random forest, and a kNN algorithm are also used to classify and identify various kinds of tremors. This chapter focuses on an in-depth review on identification and classification of various Parkinsonian tremors using machine learning algorithms.

scholarly journals Zonisamide Administration Improves Fatty Acid β-Oxidation in Parkinson’s Disease

Cells ◽  
2018 ◽  
Vol 8 (1) ◽  
pp. 14 ◽  
Author(s):  
Shin-Ichi Ueno ◽  
Shinji Saiki ◽  
Motoki Fujimaki ◽  
Haruka Takeshige-Amano ◽  
Taku Hatano ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Severity ◽  
Rating Scale ◽  
Statistical Significance ◽  
Experimental Studies ◽  
Time Of Flight ◽  
Metabolome Analysis ◽  
Flight Mass Spectrometry

Although many experimental studies have shown the favorable effects of zonisamide on mitochondria using models of Parkinson’s disease (PD), the influence of zonisamide on metabolism in PD patients remains unclear. To assess metabolic status under zonisamide treatment in PD, we performed a pilot study using a comprehensive metabolome analysis. Plasma samples were collected for at least one year from 30 patients with PD: 10 without zonisamide medication and 20 with zonisamide medication. We performed comprehensive metabolome analyses of plasma with capillary electrophoresis time-of-flight mass spectrometry and liquid chromatography time-of-flight mass spectrometry. We also measured disease severity using Hoehn and Yahr (H&Y) staging and the Unified Parkinson’s Disease Rating Scale (UPDRS) motor section, and analyzed blood chemistry. In PD with zonisamide treatment, 15 long-chain acylcarnitines (LCACs) tended to be increased, of which four (AC(12:0), AC(12:1)-1, AC(16:1), and AC(16:2)) showed statistical significance. Of these, two LCACs (AC(16:1) and AC(16:2)) were also identified by partial least squares analysis. There was no association of any LCAC with age, disease severity, levodopa daily dose, or levodopa equivalent dose. Because an upregulation of LCACs implies improvement of mitochondrial β-oxidation, zonisamide might be beneficial for mitochondrial β-oxidation, which is suppressed in PD.

scholarly journals Can Gut Microbiota Be a Good Predictor for Parkinson’s Disease? A Machine Learning Approach

2020 ◽  
Vol 10 (4) ◽  
pp. 242 ◽  
Author(s):  
Daniele Pietrucci ◽  
Adelaide Teofani ◽  
Valeria Unida ◽  
Rocco Cerroni ◽  
Silvia Biocca ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Random Forest ◽  
Gut Microbiota ◽  
Biological Data ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Published Data ◽  
Promising Tool

The involvement of the gut microbiota in Parkinson’s disease (PD), investigated in several studies, identified some common alterations of the microbial community, such as a decrease in Lachnospiraceae and an increase in Verrucomicrobiaceae families in PD patients. However, the results of other bacterial families are often contradictory. Machine learning is a promising tool for building predictive models for the classification of biological data, such as those produced in metagenomic studies. We tested three different machine learning algorithms (random forest, neural networks and support vector machines), analyzing 846 metagenomic samples (472 from PD patients and 374 from healthy controls), including our published data and those downloaded from public databases. Prediction performance was evaluated by the area under curve, accuracy, precision, recall and F-score metrics. The random forest algorithm provided the best results. Bacterial families were sorted according to their importance in the classification, and a subset of 22 families has been identified for the prediction of patient status. Although the results are promising, it is necessary to train the algorithm with a larger number of samples in order to increase the accuracy of the procedure.

scholarly journals The Influence of Playing a Non-Reward Game on Motor Ability and Executive Function in Parkinson’s Disease

2012 ◽  
Vol 25 (2) ◽  
pp. 119-125 ◽  
Author(s):  
Alisson Menezes Araújo Lima ◽  
Fabiana de Campos Cordeiro Hirata ◽  
Gabriela Sales de Bruin ◽  
Rosa Maria Salani Mota ◽  
Veralice Meireles Sales de Bruin
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Executive Function ◽  
Depressive Symptoms ◽  
Rating Scale ◽  
Age At Onset ◽  
Stroop Test ◽  
Finger Tapping ◽  
Walk Test ◽  
Motor Ability

The aim of this study is to evaluate the acute effect of playing games on executive function and motor ability in Parkinson's disease (PD). Consecutive cases with PD were studied with the Unified Parkinson Disease Rating Scale (UPDRS), Mini-Mental State examination (MMSE), Beck Depression Inventory (BDI), Stroop test, finger tapping and 14-meter walk test. After randomization, patients performed a game of dominoes and were tested before and after experiment being further categorized as control, winners or non-winners. Forty patients, 27 male (67.5%), aged 48 to 84 years (63.2 ± 8.5), Hoehn & Yahr I to III were included. Twenty-eight (70%) presented depressive symptoms (BDI > 10). Groups (Control N = 13; Winners = 14 and Non-winners = 13) were not different regarding age, disease duration, age at onset, BMI, MMSE scores, depressive symptoms, levodopa dose, and previous practice of games. Winners presented significantly better results on executive function (Stroop test,p= 0.002) and on motor activity (Finger tapping,p= 0.01). Non-winners showed a trend of better performance in the 14-meter-walk test. This study shows that the practice of a non-reward game acutely improved memory and motor skills in PD. Our results suggest a role for the reward system in the modulation of the dopaminergic function of the basal ganglia in these patients.

scholarly journals Machine Learning Prediction of Parkinson's Disease Onset and Subtype Using Germline Variants

2021 ◽  
Author(s):  
Saya R Dennis ◽  
Tanya Simuni ◽  
Yuan Luo
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Neurodegenerative Disorder ◽  
Disease Onset ◽  
The United States ◽  
Machine Learning Algorithms ◽  
Progression Rate ◽  
High Importance ◽  
Germline Variants

Parkinson's Disease is the second most common neurodegenerative disorder in the United States, and is characterized by a largely irreversible worsening of motor and non-motor symptoms as the disease progresses. A prominent characteristic of the disease is its high heterogeneity in manifestation as well as the progression rate. For sporadic Parkinson's Disease, which comprises ~90% of all diagnoses, the relationship between the patient genome and disease onset or progression subtype remains largely elusive. Machine learning algorithms are increasingly adopted to study the genomics of diseases due to their ability to capture patterns within the vast feature space of the human genome that might be contributing to the phenotype of interest. In our study, we develop two machine learning models that predict the onset as well as the progression subtype of Parkinson's Disease based on subjects' germline mutations. Our best models achieved an ROC of 0.77 and 0.61 for disease onset and subtype prediction, respectively. To the best of our knowledge, our models present state-of-the-art prediction performances of PD onset and subtype solely based on the subjects' germline variants. The genes with high importance in our best-performing models were enriched for several canonical pathways related to signaling, immune system, and protein modifications, all of which have been previously associated with PD symptoms or pathogenesis. These high-importance gene sets provide us with promising candidate genes for future biomedical and clinical research.

scholarly journals The Association of Olfactory Dysfunction With Depression, Cognition, and Disease Severity in Parkinson's Disease

2021 ◽  
Vol 12 ◽  
Author(s):  
Ting-Chun Fang ◽  
Ming-Hong Chang ◽  
Chun-Pai Yang ◽  
Yi-Huei Chen ◽  
Ching-Heng Lin
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cognitive Impairment ◽  
Disease Severity ◽  
Rating Scale ◽  
Statistical Significance ◽  
Olfactory Dysfunction ◽  
University Of Pennsylvania ◽  
Disease Rating ◽  
The University

Background: Non-motor subtypes of Parkinson's disease (PD) include the limbic, cognitive, and brainstem phenotype, which may have different pathological pathways with olfaction. In this work, we aim to clarify the association between olfactory dysfunction, depression, cognition, and disease severity in PD.Methods: A total of 105 PD subjects were included and divided into anosmia and non-anosmic groups, using the University of Pennsylvania Smell Identification Test (UPSIT). All patients were evaluated with the movement disorder society unified Parkinson's disease rating scale (MDS-UPDRS), the Beck depression inventory (BDI)-II, and the Montreal cognitive assessment (MoCA).Results: The BDI-II and UPSIT scores had a trend of reverse correlation without statistical significance (β-coefficient −0.12, p = 0.232). However, the odds ratio (OR) in anosmia was 2.74 (95% CI 1.01–7.46) for depression and 2.58 (95% CI 1.06–6.29) for cognitive impairment. For the MDS-UPDRS total and Part 3 score, the anosmia had a β-coefficient of 12.26 (95% CI 5.69–18.82) and 8.07 (95% CI 3.46–12.67), respectively. Neither depression nor cognitive impairment is associated with motor symptoms.Conclusion: More severe olfactory dysfunction in PD is associated with cognitive impairment and greater disease severity. Depression in PD may involve complex pathways, causing relatively weak association with olfactory dysfunction.

Tremor Identification Using Machine Learning in Parkinson's Disease

2021 ◽  
pp. 341-365
Author(s):  
Angana Saikia ◽  
Vinayak Majhi ◽  
Masaraf Hussain ◽  
Sudip Paul ◽  
Amitava Datta
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Support Vector Machine ◽  
Parkinson's Disease ◽  
Discriminant Analysis ◽  
Learning Algorithms ◽  
The Body ◽  
Machine Learning Algorithms ◽  
Support Vector

Tremor is an involuntary quivering movement or shake. Characteristically occurring at rest, the classic slow, rhythmic tremor of Parkinson's disease (PD) typically starts in one hand, foot, or leg and can eventually affect both sides of the body. The resting tremor of PD can also occur in the jaw, chin, mouth, or tongue. Loss of dopamine leads to the symptoms of Parkinson's disease and may include a tremor. For some people, a tremor might be the first symptom of PD. Various studies have proposed measurable technologies and the analysis of the characteristics of Parkinsonian tremors using different techniques. Various machine-learning algorithms such as a support vector machine (SVM) with three kernels, a discriminant analysis, a random forest, and a kNN algorithm are also used to classify and identify various kinds of tremors. This chapter focuses on an in-depth review on identification and classification of various Parkinsonian tremors using machine learning algorithms.

Sign in / Sign up

Export Citation Format

Share Document