scholarly journals A-14 Propensity Scores in Neuropsychological Research: Four Aspects of Digital Clock Drawing Distinguish Individuals with Non-Dementia Idiopathic Parkinson’s Disease from Matched Controls

2020 ◽  
Vol 35 (6) ◽  
pp. 787-787
Author(s):  
B Frank ◽  
C Dion ◽  
L Hizel ◽  
S Crowley ◽  
C Price
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Bayes Factor ◽  
Propensity Scores ◽  
Nearest Neighbor ◽  
Causal Effect ◽  
Randomized Experiments ◽  
Digital Clock ◽  
Clock Drawing ◽  
Parsimonious Model

Abstract Objective In situations in which randomized experiments are impossible or unethical, propensity score matching offers a method to reduce bias on causal effect estimates (Thoemmes & Kim, 2011). In this study, we examined differences on the digital clock drawing test (dCDT; Souillard-Mandar et al., 2016) between individuals with idiopathic non-dementia Parkinson’s disease (PD) and matched controls. Method This study involved a retrospective analysis of two federally funded investigations (NSF-13-543; R01-NS082386). The sample included 261 participants (110 PD, 151 non-PD). Participants were matched according to demographic covariates, as well as measures of mood, comorbidity, and premorbid functioning. The PD group and matched controls were compared using logistic regression in a Bayesian framework, with projection predictive variable selection implemented to obtain a parsimonious model (Piironen, Paasiniemi, & Vehtari, 2018). All effects were standardized. Results Of 261 participants, 212 were matched using nearest neighbor matching (Figure 1). The final, parsimonious model included four variables from the dCDT: total strokes (command condition), total time (command condition), and area (command and copy conditions). While all effects were retained, positive to strong evidence was found for dCDT total time (βMedian = 0.91, βSD = 0.25, 95% CI [0.44, 1.42], Bayes factor [BF] = 97.80) and dCDT area (copy condition; βMedian = −0.52, βSD = 0.19, 95% CI [−0.90, −0.17], BF = 4.78). Conclusions Propensity scores can be employed in causal comparative studies to match control participants and reduce bias from nuisance covariates. Four aspects of dCDT performance were optimal in distinguishing individuals with PD from matched controls.

scholarly journals A Deep Learning Approach for Classification and Diagnosis of Parkinson’s Disease

2021 ◽  
Author(s):  
Monika Jyotiyana ◽  
Nishtha Kesswani ◽  
Munish Kumar
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Nearest Neighbor ◽  
Health Sector ◽  
Classification Model ◽  
Support Vector ◽  
Learning Approaches ◽  
K Nearest Neighbor ◽  
Linear Discriminant

Abstract Deep learning techniques are playing an important role in the classification and prediction of diseases. Undoubtedly deep learning has a promising future in the health sector, especially in medical imaging. The popularity of deep learning approaches is because of their ability to handle a large amount of data related to the patients with accuracy, reliability in a short span of time. However, the practitioners may take time in analyzing and generating reports. In this paper, we have proposed a Deep Neural Network-based classification model for Parkinson’s disease. Our proposed method is one such good example giving faster and more accurate results for the classification of Parkinson’s disease patients with excellent accuracy of 94.87%. Based on the attributes of the dataset of the patient, the model can be used for the identification of Parkinsonism's. We have also compared the results with other existing approaches like Linear Discriminant Analysis, Support Vector Machine, K-Nearest Neighbor, Decision Tree, Classification and Regression Trees, Random Forest, Linear Regression, Logistic Regression, Multi-Layer Perceptron, and Naive Bayes.

scholarly journals Application of Fuzzy K-Nearest Neighbor (FKNN) to Detect the Parkinson’s Disease

2019 ◽  
Vol 1 (1) ◽  
Author(s):  
L.N. Desinaini ◽  
Azizatul Mualimah ◽  
Dian C. R. Novitasari ◽  
Moh. Hafiyusholeh
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Principal Component Analysis ◽  
Parkinson's Disease ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Component Analysis ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Positive Data

AbstractParkinson’s disease is a neurological disorder in which there is a gradual loss of brain cells that make and store dopamine. Researchers estimate that four to six million people worldwide, are living with Parkinson’s. The average age of patients is 60 years old, but some are diagnosed at age 40 or even younger and the worst thing is some patients are late to find out that they have Parkinson's disease. In this paper, we present a diagnosis system based on Fuzzy K-Nearest Neighbor (FKNN) to detect Parkinson’s disease. We use Parkinson’s disease dataset taken from UCI Machine Learning Repository. The first step is normalize the Parkinson’s disease dataset and analyze using Principal Component Analysis (PCA). The result shows that there are four new factors that influence Parkinson’s disease with total variance is 85.719%. In classification step, we use several percentage of training data to classify (detect) the Parkinson's disease i.e. 50%, 60%, 70%, 75%, 80% and 90%. We also use k = 3, 5, 7, and 9. The classification result shows that the highest accuracy obtained for the percentage of training data is 90% and k = 5, where 19 are correctly classified i.e. 14 positive data and 5 negative data, while 1 positive data is classified incorrectly.Keywords: Parkinson's disease; Fuzzy K-Nearest Neighbor; Principal Component Analysis. AbstrakPenyakit Parkinson merupakan kelainan sel saraf pada otak yang menyebabkan hilangnya dopamin pada otak. Para peneliti mengestimasi bahwa, empat sampai enam juta orang di dunia, menderita Parkinson. Penyakit ini rata-rata diderita oleh pasien berusia 60 tahun, namun beberapa orang terdeteksi saat berusia 40 tahun atau lebih muda dan hal terburuk adalah seseorang terlambat untuk mendeteksinya. Di dalam artikel ini, kami menyajikan sistem diagnosa penyakit Parkinson menggunakan metode Fuzzy K-Nearest Neighbor (FKNN). Kami menggunakan Data uji yang diperoleh dari UCI Machine Learning Repository yang telah banyak diterapkan pada masalah klasifikasi. Tahapan pertama yang kami lakukan adalah menormalisasi data kemudian menganalisisnya menggunakan Analisis Komponen Utama (Principal Component Analysis). Hasil Analisis Komponen Utama menunjukkan bahwa terdapat empat factor baru yang mempengaruhi penyakit Parkinson dengan variansi total 87,719%. Pada tahap klasifikasi, kami menggunakan beberapa prosentase data latih untuk mendeteksi penyakit yaitu 50%, 60%, 70%, 75%, 80% and 90%. Selain itu, kami menggunakan beberapa nilai k yaitu 3, 5, 7, and 9. Hasil menunjukkan bahwa klasifikasi dengan akurasi tertinggi diperoleh untuk 90% data latih dengan k = 5, dimana 19 diklasifikasikan secara tepat yaitu 14 data positif dan 5 data negatif, sedangkan satu data positif tidak diklasifikasikan dengan tepat.Keywords: penyakit Parkinson; Fuzzy K-Nearest Neighbor; Analisis Komponen Utama.

scholarly journals Tendency towards being a “Morning person” increases risk of Parkinson’s disease: evidence from Mendelian randomisation

2018 ◽  
Author(s):  
AJ Noyce ◽  
DA Kia ◽  
K Heilbron ◽  
JEC Jepson ◽  
G Hemani ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Circadian Rhythm ◽  
Causal Relationship ◽  
Odds Ratio ◽  
Causal Effect ◽  
Coffee Consumption ◽  
Sensitivity Analyses ◽  
Mendelian Randomisation ◽  
Effect Estimate

AbstractBackgroundCircadian rhythm may play a role in neurodegenerative diseases such as Parkinson’s disease (PD). Chronotype is the behavioural manifestation of circadian rhythm and Mendelian randomisation (MR) involves the use of genetic variants to explore causal effects of exposures on outcomes. This study aimed to explore a causal relationship between chronotype and coffee consumption on risk of PD.MethodsTwo-sample MR was undertaken using publicly available GWAS data. Associations between genetic instrumental variables (IV) and “morning person” (one extreme of chronotype) were obtained from the personal genetics company 23andMe, Inc., and UK Biobank, and consisted of the per-allele odds ratio of being a “morning person” for 15 independent variants. The per-allele difference in log-odds of PD for each variant was estimated from a recent meta-analysis. The inverse variance weight method was used to estimate an odds ratio (OR) for the effect of being a “morning person” on PD. Additional MR methods were used to check for bias in the IVW estimate, arising through violation of MR assumptions. The results were compared to analyses employing a genetic instrument of coffee consumption, because coffee consumption has been previously inversely linked to PD.FindingsBeing a “morning person” was causally linked with risk of PD (OR 1⋅27; 95% confidence interval 1⋅06-1⋅51; p=0⋅012). Sensitivity analyses did not suggest that invalid instruments were biasing the effect estimate and there was no evidence for a reverse causal relationship between liability for PD and chronotype. There was no robust evidence for a causal effect of high coffee consumption using IV analysis, but the effect was imprecisely estimated (OR 1⋅12; 95% CI 0⋅89-1⋅42; p=0⋅22).InterpretationWe observed causal evidence to support the notion that being a “morning person”, a phenotype driven by the circadian clock, is associated with a higher risk of PD. Further work on the mechanisms is warranted and may lead to novel therapeutic targets.FundingNo specific funding source.

scholarly journals Finding drug targeting mechanisms with genetic evidence for Parkinson’s disease

2020 ◽  
Author(s):  
Catherine S. Storm ◽  
Demis A. Kia ◽  
Mona Almramhi ◽  
Sara Bandres-Ciga ◽  
Chris Finan ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Drug Targeting ◽  
Drug Targets ◽  
Molecular Mechanisms ◽  
Disease Risk ◽  
Target Identification ◽  
Causal Effect ◽  
Age At Onset ◽  
Genetic Evidence

SummaryParkinson’s disease (PD) is a neurodegenerative movement disorder that currently has no disease-modifying treatment, partly owing to inefficiencies in drug target identification and validation using human evidence. Here, we use Mendelian randomization to investigate more than 3000 genes that encode druggable proteins, seeking to predict their efficacy as drug targets for PD. We use expression and protein quantitative trait loci for druggable genes to mimic exposure to medications, and we examine the causal effect on PD risk (in two large case-control cohorts), PD age at onset and progression. We propose 23 potential drug targeting mechanisms for PD, of which four are repurposing opportunities of already-licensed or clinical-phase drugs. We identify two drugs which may increase PD risk. Importantly, there is remarkably little overlap between our MR-supported drug targeting mechanisms to prevent PD and those that reduce PD progression, suggesting that molecular mechanisms driving disease risk and progression differ. Drugs with genetic support are considerably more likely to be successful in clinical trials, and we provide compelling genetic evidence and an analysis pipeline that can be used to prioritise drug development efforts for PD.

Sign in / Sign up

Export Citation Format

Share Document