Parkinson's Disease Detection Using Filter Feature Selection and a Genetic Algorithm with Ensemble Learning

Article Health Care Sciences & Services

Optimization-Based Ensemble Feature Selection Algorithm and Deep Learning Classifier for Parkinson's Disease

B. Sabeena et al.

Summary: Parkinson's Disease is a severe and incurable condition that requires early and accurate identification for better patient survival. This study utilizes optimization-based ensemble feature selections to analyze feature relevance and classify Parkinson's disease accurately. The proposed model combines data mining techniques and machine learning techniques to achieve optimal feature subsets for classification tasks.

JOURNAL OF HEALTHCARE ENGINEERING (2022)

Add to Collection

Article Mathematical & Computational Biology

Severity Prediction over Parkinson's Disease Prediction by Using the Deep Brooke Inception Net Classifier

R. Sarankumar et al.

Summary: This research proposes a strategy for predicting the severity of Parkinson's disease using the Parkinson's Telemonitoring Voice Data Set from UCI and deep neural networks. By preprocessing raw signal data, decomposing features, and utilizing a deep learning classifier, the proposed strategy outperforms conventional methods in accuracy for detecting the severity of the disease.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2022)

Add to Collection

Article Engineering, Multidisciplinary

A Novel Ensemble Stacking Learning Algorithm for Parkinson's Disease Prediction

T. Velmurugan et al.

Summary: This research introduces a novel ensemble learning algorithm to identify Parkinson's disease using voice estimations. The method demonstrates improved classification ability compared to other techniques, providing more reliable outcomes and higher accuracy for Parkinson's disease patients.

MATHEMATICAL PROBLEMS IN ENGINEERING (2022)

Add to Collection

Article Health Care Sciences & Services

An Efficient Rotation Forest-Based Ensemble Approach for Predicting Severity of Parkinson's Disease

Saeid Sheikhi et al.

Summary: This study proposes a machine learning approach to predict the severity of Parkinson's disease. By analyzing and classifying patients' voice data, the proposed method can detect the severity of the disease in the early stages.

JOURNAL OF HEALTHCARE ENGINEERING (2022)

Add to Collection

Article Engineering, Electrical & Electronic

A Comparative Study of Existing Machine Learning Approaches for Parkinson's Disease Detection

Gunjan Pahuja et al.

Summary: Parkinson's disease affects millions worldwide, with a higher prevalence in individuals over 50. Early detection remains a challenge despite technological advancements. This study compares classification algorithms for PD detection, finding that Artificial Neural Networks are the most effective classifier for accurate diagnosis.

IETE JOURNAL OF RESEARCH (2021)

Add to Collection

Article Biology

Robust identification of Parkinson's disease subtypes using radiomics and hybrid machine learning

Mohammad R. Salmanpour et al.

Summary: This study successfully identified robust Parkinson's disease subtypes through the application of multiple feature-reduction and cluster-analysis methods based on multidimensional data from longitudinal datasets. Utilizing radiomics information enabled consistent generation of clusters through ensemble analysis of trajectories, resulting in the identification of three distinct PD subtypes - mild, intermediate, and severe.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Classification of Parkinson disease using binary Rao optimization algorithms

Suvita Rani Sharma et al.

Summary: The binary versions of Rao algorithms are proposed for solving feature selection problems in Parkinson's disease datasets, optimizing the k parameter of the k-nearest neighbour classifier. The performance of these algorithms is evaluated through 30 independent runs with a 10-fold cross-validation procedure and compared with state of the art methods, with significance analysis conducted using the Friedman rank test.

EXPERT SYSTEMS (2021)

Add to Collection

Article Health Care Sciences & Services

Assessment of Acoustic Features and Machine Learning for Parkinson's Detection

Moumita Pramanik et al.

Summary: This study utilizes a machine learning approach to detect Parkinson's disease, achieving a detection accuracy of 78.97% and a precision of 0.926 using a collaborative feature bank and Naive Bayes detector. The simplicity of Naive Bayes makes the system robust and effective compared to other methods.

JOURNAL OF HEALTHCARE ENGINEERING (2021)

Add to Collection

Article Engineering, Biomedical

A new approach: information gain algorithm-based k-nearest neighbors hybrid diagnostic system for Parkinson's disease

Cuneyt Yucelbas

Summary: The IGKNN model developed in this study showed excellent performance in diagnosing early stages of PD based on speech signals, outperforming other approaches reported in the literature.

PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence