A Deep Learning Approach for Classification and Diagnosis of Parkinson’s Disease (original) (raw)
Related papers
Sensors
Parkinson’s disease (PD) is the second most common neurodegenerative disorder affecting over 6 million people globally. Although there are symptomatic treatments that can increase the survivability of the disease, there are no curative treatments. The prevalence of PD and disability-adjusted life years continue to increase steadily, leading to a growing burden on patients, their families, society and the economy. Dopaminergic medications can significantly slow down the progression of PD when applied during the early stages. However, these treatments often become less effective with the disease progression. Early diagnosis of PD is crucial for immediate interventions so that the patients can remain self-sufficient for the longest period of time possible. Unfortunately, diagnoses are often late, due to factors such as a global shortage of neurologists skilled in early PD diagnosis. Computer-aided diagnostic (CAD) tools, based on artificial intelligence methods, that can perform automa...
Unified deep learning approach for prediction of Parkinson's disease
IET Image Processing, 2020
The paper presents a novel approach, based on deep learning, for diagnosis of Parkinson's disease through medical imaging. The approach includes analysis and use of the knowledge extracted by Deep Convolutional and Recurrent Neural Networks (DNNs) when trained with medical images, such as Magnetic Resonance Images and DaTscans. Internal representations of the trained DNNs constitute the extracted knowledge which is used in a transfer learning and domain adaptation manner, so as to create a unified framework for prediction of Parkinson's across different medical environments. A large experimental study is presented illustrating the ability of the proposed approach to effectively predict Parkinson's, using different medical image sets from real environments.
A Unified Deep Learning Approach for Prediction of Parkinson's Disease
arXiv (Cornell University), 2019
The paper presents a novel approach, based on deep learning, for diagnosis of Parkinson's disease through medical imaging. The approach includes analysis and use of the knowledge extracted by Deep Convolutional and Recurrent Neural Networks (DNNs) when trained with medical images, such as Magnetic Resonance Images and DaTscans. Internal representations of the trained DNNs constitute the extracted knowledge which is used in a transfer learning and domain adaptation manner, so as to create a unified framework for prediction of Parkinson's across different medical environments. A large experimental study is presented illustrating the ability of the proposed approach to effectively predict Parkinson's, using different medical image sets from real environments.
Deep Learning Based Diagnosis of Parkinson's Disease Using CNN
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2020
Parkinson's disease is the degenerative disease caused by loss of dopamine producing neurons. PD is characterized by gradual degradation of motor function in the brain. In this, deep learning is used to diagnose the PD patients by means of Convolutional Neural Networks (CNN). The CNN architecture ALexNet is used to refine the diagnosis of Parkinson’s disease. The MR images are trained by the transfer learned network along with the KNN algorithm to give the accuracy measures.
European Journal of Information Technologies and Computer Science
Millions of people throughout the world suffer with Parkinson's disease (PD), severely reducing their quality of life. With the symptoms when we detect Parkinson disease automatically, it could provide insights to the disease's early stages of development, enhancing the patients' projected clinical results through correctly focused therapies. This potential has prompted numerous academics to explore ways for measuring and quantifying the existence of PD symptoms using commercially available sensors. In this paper, we offer an overview of some recent scientific articles on several machine learning techniques that assist physiologists in detecting PD early. In addition, a comparative study between traditional machine learning (TML) algorithms and deep learning (DL) architectures based on the scope of their appropriate usage for classifying PD effectively has been discussed. Based on the comparison on detecting the PD from previous works, this paper concludes that deep lear...
A deep learning approach for prediction of Parkinson’s disease progression
Biomedical Engineering Letters, 2020
This paper proposes a deep neural network (DNN) model using the reduced input feature space of Parkinson's telemonitoring dataset to predict Parkinson's disease (PD) progression. PD is a chronic and progressive nervous system disorder that affects body movement. PD is assessed by using the unified Parkinson's disease rating scale (UPDRS). In this paper, firstly, principal component analysis (PCA) is employed to the featured dataset to address the multicollinearity problems in the dataset and to reduce the dimension of input feature space. Then, the reduced input feature space is fed into the proposed DNN model with a tuned parameter norm penalty (L2) and analyses the prediction performance of it in PD progression by predicting Motor and Total-UPDRS score. The model's performance is evaluated by conducting several experiments and the result is compared with the result of previously developed methods on the same dataset. The model's prediction accuracy is measured by fitness parameters, mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R 2). The MAE, RMSE, and R 2 values are 0.926, 1.422, and 0.970 respectively for motor-UPDRS. These values are 1.334, 2.221, and 0.956 respectively for Total-UPDRS. Both the Motor and Total-UPDRS score is better predicted by the proposed method. This paper shows the usefulness and efficacy of the proposed method for predicting the UPDRS score in PD progression.
A novel automated Parkinson's disease identification approach using deep learning and EEG
PeerJ Computer Science, 2023
The neurological ailment known as Parkinson's disease (PD) affects people throughout the globe. The neurodegenerative PD-related disorder primarily affects people in middle to late life. Motor symptoms such as tremors, muscle rigidity, and sluggish, clumsy movement are common in patients with this disorder. Genetic and environmental variables play significant roles in the development of PD. Despite much investigation, the root cause of this neurodegenerative disease is still unidentified. Clinical diagnostics rely heavily on promptly detecting such irregularities to slow or stop the progression of illnesses successfully. Because of its direct correlation with brain activity, electroencephalography (EEG) is an essential PD diagnostic technique. Electroencephalography, or EEG, data are biomarkers of brain activity changes. However, these signals are nonlinear, non-stationary, and complicated, making analysis difficult. One must often resort to a lengthy human labor process to accomplish results using traditional machinelearning approaches. The breakdown, feature extraction, and classification processes are typical examples of these stages. To overcome these obstacles, we present a novel deep-learning model for the automated identification of Parkinson's disease (PD). The Gabor transform, a standard method in EEG signal processing, was used to turn the raw data from the EEG recordings into spectrograms. In this research, we propose densely linked bidirectional long short-term memory (DLBLSTM), which first represents each layer as the sum of its hidden state plus the hidden states of all layers above it, then recursively transmits that representation to all layers below it. This study's suggested deep learning model was trained using these spectrograms as input data. Using a robust sixfold cross-validation method, the proposed model showed excellent accuracy with a classification accuracy of 99.6%. The results indicate that the suggested algorithm can automatically identify PD.
Machine Learning Approaches for Detection and Diagnosis of Parkinson’s Disease - A Review
IEEE, 2021
Parkinson's disease (PD) is disabling disease that affects the quality of life. It belimps due to the death of cells that produce dopamine's in the substantia nigra part of the central nervous system (CNS) which affects the human body. People who have Parkinson's disease feel difficulty in doing activities like speaking, writing, and walking. In the recent past, speech, gait and EEG signals have been investigated for the detection of PD. However, speech analysis is the most considered technique to be used. Researches have shown that 90% of the people who suffer from Parkinson's disease have speech disorders. With the increase in the severity of the disease, the patient's voice gets more and more deteriorated. The non-invasive treatments for voice analysis are available that helps in ameliorating the life quality of a patient. Thus, for building the telemonitoring and telediagnosis models for prediction, the speech analysis has been tremendously increased. The proper interpretation of speech signals is one of the important classification problems for Parkinson's disease diagnosis. The main purpose of this paper is to contemplate the survey work of the machine learning techniques and deep learning procedures used for Parkinson's disease classification. Deep learning and machine learning techniques have been used as a part of the discovery for the efficient classification of PD. The various classification models like support vector machines, naive Bayes, deep neural networks, decision tree and random forest are effectively employed for classification purposes. The analysis of results of different research works showed that both machine learning and deep learning algorithms have shown promising future and therefore paving a better way for the detection of Parkinson's disease at its earlier stages. The classification accuracy achieved by the machine learning classifier. Among deep learning approaches, the deep neural network has achieved the best accuracy of 99.49%. The results obtained from different works suggest that artificial intelligence is becoming a powerful learning tool that has much to offer to data scientists as well as neurologists. In general the learning methods are adding value to decision-making problems especially in the field of medical diagnosis.
Analysis of Parkinson’s Disease Data
Procedia Computer Science, 2018
In this paper, we investigate the diagnostic data from patients suffering with Parkinson's disease (PD) and design classification/prediction model to simplify the diagnosis. The main aim of this research is to open possibilities to be able to apply deep learning algorithms to help better understand and diagnose the disease. To our knowledge, the capabilities of deep learning algorithms have not yet been completely utilized in the field of Parkinson's research and we believe that by having an in-depth understanding of data, we can create a platform to apply different algorithms to automate the Parkinson's Disease diagnosis to certain extent. We use Parkinson's Progression Markers Initiative (PPMI) dataset provided by Michael J. Fox Foundation to perform our analysis.
European Journal of Electrical Engineering and Computer Science, 2023
Parkinson's disease (PD) is a chronic neurological condition that is growing in prevalence and manifests both motor and non-motor symptoms. Most PD patients have trouble speaking, writing, and walking during the early stages of the disease. Analysis of speech problems has been effective in identifying Parkinson's disease. According to studies, 90% of Parkinson's disease patients experience speech problems. Even though there is no known cure for Parkinson's disease, using the right medication at an early stage can greatly reduce the symptoms. One of the key categorization issues for the diagnosis of Parkinson's disease is the correct interpretation of speech signals. The major goal of this project is to use deep learning and machine learning approaches to predict and categorize PD patients at an early stage. A trustworthy dataset from the UCI repository for Parkinson disease has been used to evaluate the method's performance. Several classification models are successfully used in this study for classification tasks, including Extreme Gradient Boosting (XGBoost)