An Application of the Filter Feature Selection Method in a Machine Learning Model for the Prognostic of Parkinson's Disease (original) (raw)
Related papers
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi
Dopamine levels fall due to brain nerve cell destruction, producing Parkinson's symptoms. Humans with this illness experience central nervous system damage, which lowers the quality of life. This disease is not deadly, but when people's quality of life decreases, they cannot perform daily activities as people do. Even in one case, this disease can cause death indirectly. Contrast support vector machines (SVM) and naive Bayesian approaches with and without fast correlation-based filter (FCBF) feature selection, this study attempts to determine the optimum model to detect Parkinson's disease categorization. In this study, datasets from the UCI Machine Learning Repository are used. The results showed that SVM with FCBF achieved the highest accuracy among all the models tested. SVM with FCBF provides an accuracy of 86.1538%, sensitivity of 93.8775%, and specificity of 62.5000%. Both methods, SVM and Naive Bayes, have improved in performance due to FCBF, with SVM showing a mo...
USING FEATURE SELECTION AND FEATURE EXTRACTION TO FIND BIOMARKERS IN PARKINSON'S DISEASE
We employed machine learning to identify plausible molecular biomark-ers for Parkinson's disease (PD) using an approach previously employed in cancer biomarker discovery. The top five biomarker gene candidates were SLC39A5, RAB42, BTNL9, INPP5A and a hypothetical gene. We compared a traditional gene/feature selection method with the recursive feature elimination using the support vector machines algorithm (RFE-SVM) and found that RFE-SVM out-performs the traditional ranking method in both classification of PD and accuracy, using the NIPS 2003 Feature Selection Challenge criterion. We used the Naive Bayes as the baseline classifier as well as SVMs. These results indicate that it may be possible to computationally identify novel biomarkers for PD using our approach.
Comparative Analysis to identify the best Classifier for Parkinson Prediction
IEEE, 2021
Parkinson disease has become one of the most common diseases among people over the age of 65. Neurodegenerative disease affects movement, speech and other cognitive abilities. Among patients, the symptoms vary at a different rate, for which diagnosis of the disease sometimes takes years by when treatment is no longer an option. However, using machine learning algorithms to classify the symptoms among patients, it is possible for early detection of the disease. İn this paper, the performance of machine learning algorithms are measures that can detect Parkinson disease. Three different datasets are used for the study. Each dataset goes through various feature selection techniques. Machine learning classifiers such as KNN, LDA, NB, LR, SVM, DT, RT, RF and ANN are implemented on the datasets and their performance is measured. It is observed that SVM has a high accuracy rate of prediction over all the feature selection techniques in all the datasets.
The Impact of Feature Selection Techniques on the Performance of Predicting Parkinson’s Disease
2018
Parkinson’s Disease (PD) is one of the leading causes of death around the world. However, there is no cure for this disease yet; only treatments after early diagnosis may help to relieve the symptoms. This study aims to analyze the impact of feature selection techniques on the performance of diagnosing PD by incorporating different data mining techniques. To accomplish this task, identifying the best feature selection approach was the primary focus. In this paper, the authors had applied five feature selection techniques namely: Gain Ratio, Kruskal-Wallis Test, Random Forest Variable Importance, RELIEF and Symmetrical Uncertainty along with four classification algorithms (K-Nearest Neighbor, Logistic Regression, Random forest, and Support Vector machine) on the PD dataset collected from the UCI Machine Learning repository. The result of this study was obtained by taking the four different subsets (Top 5, 10, 15, and 20 features) from each feature selection approach and applying the ...
Prediction of Cognitive Degeneration in Parkinson’s Disease Patients Using a Machine Learning Method
Brain Sciences
This study developed a predictive model for cognitive degeneration in patients with Parkinson’s disease (PD) using a machine learning method. The clinical data, plasma biomarkers, and neuropsychological test results of patients with PD were collected and utilized as model predictors. Machine learning methods comprising support vector machines (SVMs) and principal component analysis (PCA) were applied to obtain a cognitive classification model. Using 32 comprehensive predictive parameters, the PCA-SVM classifier reached 92.3% accuracy and 0.929 area under the receiver operating characteristic curve (AUC). Furthermore, the accuracy could be increased to 100% and the AUC to 1.0 in a PCA-SVM model using only 13 carefully chosen features.
We employed machine learning to identify plausible molecular biomarkers for Parkinson's disease (PD) using an approach previously employed in cancer biomarker discovery. The top five biomarker gene candidates were SLC39A5, RAB42, BTNL9, INPP5A and a hypothetical gene. We compared a traditional gene/feature selection method with the recursive feature elimination using the support vector machines algorithm (RFE-SVM) and found that RFE-SVM out-performs the traditional ranking method in both classification of PD and accuracy, using the NIPS 2003 Feature Selection Challenge criterion. We used the Naive Bayes as the baseline classifier as well as SVMs. These results indicate that it may be possible to computationally identify novel biomarkers for PD using our approach.
Feature Selection Based Machine Learning to Improve Prediction of Parkinson Disease
Brain Informatics
Parkinson's disease (PD) is a kind of neurodegenerative disorder characterized by the loss of dopamine-producing cells in the brain. The disruption of brain cells that create dopamine, a chemical that allows brain cells to connect with one another, causes Parkinson's disease. Control, adaptability, and rapidity of movement are all controlled by dopamine-producing cells in the brain. Researchers have been investigating for techniques to identify non-motor symptoms that show early in the disease as soon as possible, slowing the disease's progression. A machine learning-based detection of Parkinson's disease is proposed in this research. Feature selection and classification techniques are used in the proposed detection technique. Boruta, Recursive Feature Elimination (RFE) and Random Forest (RF) Classifier have been used for the feature selection process. Four classification algorithms are considered to detect Parkinson disease which are gradient boosting, extreme gradient boosting, bagging and Extra Tree Classifier. Bagging with recursive feature elimination was found to outperform the other methods. The lowest number of voice characteristics for the diagnosis in Parkinson attained 82.35% accuracy.
Analysing the Performance of Support Vector Machine Algorithm in Predicting Parkinson’s Disease
IJIRIS:: AM Publications, 2023
Parkinson’s disease (PD) is a neurodegenerative measure disease where the symptoms steadily develop start with an insignificant a slight shaking movement in one hand and a feeling of stiffness in the body and it became worse over time. Dopamine is most notably involved in helping us feel preference as part of the brain's reward system. It acts as a message between the parts of the brain and nervous system that support control and co-ordinate body movements. As dopamine generally neurons in the parts begin to experience difficulty in speaking, writing, walking or completing another simple task. Virtually, 90% pretentious people with Parkinson have tongue disorders. It affects over 6 million people worldwide. At present there is no conclusive result for this disease by non-specialist clinicians, particularly in the early stage of the disease where identification of the symptoms is very difficult in its earlier stages. The future predictive analytics outline is a combination of K-means clustering and Decision Tree which is used to improvement visions from patients. By using machine learning methods, the problem can be explained with negligible error rate. The investigated approach serves as a guide in determining the diagnosis and in planning the appropriate by a loss of nerve cells in the part of the brain.
PERFORMANCE OF CLASSIFICATION TECHNIQUES ON PARKINSON'S DISEASE
International Journal of Advances in Science Engineering and Technology, 2017
Nowadays, many methods and algorithms have been developed that may influence the decision-making process and are used to extract meaningful information. One of the well know methods or approaches in information extraction is data mining. Data mining tries to establish the best model to support decision system, to extract information and to categorize, to summarize and etc. according to given data set. The Parkinson's disease-related data obtained from UCI Machine Learning Database is used to try several data mining techniques and methods to see the successes of techniques regarding to diagnosis accuracy ratio to support the expert. So far, Parkinson's disease can actually be diagnosed after medical examinations. However, diagnosis with computer has been the subject of many researches due to demand to help physician. In this study, a research is conducted using 16 different data mining techniques and methods to support the doctors in the decision-making process. The results of the applied methods for the study regarding to diagnosis accuracy ratesare as follows; IB1 (96.4103%), RotationForest (92.3077%) RandomForest (91.7949%), MultilayerPerceptron (90.7692%),
Prediction of Parkinson's Disease using Hybrid Feature Selection based Techniques
IEEE, 2021
Parkinson's disease (PD) is one of the significant severe problems globally in recent times. It is a neurological disorder that progresses over time and the most severe problems after Alzheimer's disease. Our article proposes a Hybrid Feature Selection system for the initial detection of PD from speech recordings. This method picks the best set of instances that can lessen instance vector dimensions from 22 to 5. We have proposed a machine learning-based model using five different classifiers named Random Forest, Logistic Regression, XGBoost, AdaBoost, and Gradient Tree Boosting. Gradient Tree Boosting presents the best appearance with a spectacular accuracy of 98.31% and the area under the ROC curve 98.66%, among all classifiers used to predict PD. We showed that the stated design has greater accuracy than the current methods available in the literature, and the number of instances is less than others.