Efficient detection of Parkinson's disease using deep learning techniques over medical data

Sahu, Lipsita; Sharma, Rohit; Sahu, Ipsita; Das, Manoja Kumar; Sahu, Binod Kumar; Kumar, Raghvendra

doi:10.1111/exsy.12787

Cited by 48 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The calculated outcome shows that the suggested algorithm is superior with 93.46% accuracy. [11] Vyas, T et al, "Parkinson's illness diagnosis using deep learning". We have used MRI (magnetic resonance imaging) brain images for this reason.…”

Section: Literature Reviewmentioning

confidence: 99%

Parkinson Disease Prediction Using Deep Learning Algorithm

Suchitra

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

Parkinson's is a neurological disorder that worsens over time. People have trouble communicating, writing, walking, or doing other basic activities once dopamine-producing neurons in specific regions of the brain are damaged or die. Over time, these symptoms worsen the seriousness of the patients' situation. Using Parkinson's Visual Large Dataset from UCI patient populations, which would be dependent on healthy as well as unhealthy of spiral and wave data, we present a technique in this study for determining the prevalence of Parkinson's disease. We have designed a neural network to detect the disorder and predict the severity of the condition. Here, we identify Parkinson's disease using two deep learning models: the convolution neural network and the Alex net. Additionally, this project seeks to investigate how to recognize the Parkinson patient using image data such as healthy and unhealthy spiral and wave data since various databases may record various aspects of this disease. Here, we employ a five-step process that includes data gathering, preprocessing, model application, classification, and estimation based on user-selected input data. Results of the experiments demonstrated the system's improved efficiency. Finally, we compare the classification report and model accuracy score to demonstrate which algorithm is optimal for the system's prediction.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Parkinson Disease Prediction Using Deep Learning Algorithm

Suchitra

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

show abstract

“…Although DL is proved to be very effective, the use of low-interpretability models may however evoke the resistance of clinicians asking for high-level evidence in clinical practice, in turn resulting in the overfitting phenomenon as well as a lack of generalization. ML and DL models for the assessment of PD were compared mainly for binary classification tasks (healthy vs. PD), involving acoustic features as an input to ML pipelines: apart from a few exceptions [ 38 , 39 ], the majority of studies reported better performance from of DL models [ 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 ]. Similar results are also reported in works employing deep features extracted from spectrograms [ 46 , 47 , 48 , 49 , 50 , 51 ].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Costantini

Cesarini

Leo

et al. 2023

Sensors

View full text Add to dashboard Cite

Parkinson’s Disease (PD) is one of the most common non-curable neurodegenerative diseases. Diagnosis is achieved clinically on the basis of different symptoms with considerable delays from the onset of neurodegenerative processes in the central nervous system. In this study, we investigated early and full-blown PD patients based on the analysis of their voice characteristics with the aid of the most commonly employed machine learning (ML) techniques. A custom dataset was made with hi-fi quality recordings of vocal tasks gathered from Italian healthy control subjects and PD patients, divided into early diagnosed, off-medication patients on the one hand, and mid-advanced patients treated with L-Dopa on the other. Following the current state-of-the-art, several ML pipelines were compared usingdifferent feature selection and classification algorithms, and deep learning was also explored with a custom CNN architecture. Results show how feature-based ML and deep learning achieve comparable results in terms of classification, with KNN, SVM and naïve Bayes classifiers performing similarly, with a slight edge for KNN. Much more evident is the predominance of CFS as the best feature selector. The selected features act as relevant vocal biomarkers capable of differentiating healthy subjects, early untreated PD patients and mid-advanced L-Dopa treated patients.

show abstract

“…When brain networks are incorrectly connected to coordinate activities, certain disorders in the human body arise [1,2]. Some of the most common neurodevelopmental disorders are autism spectrum disorder (ASD) [3], schizophrenia [4], attention defcit hyperactivity disorder (ADHD) [5], epilepsy [6], Parkinson's disease [7], obsessive-compulsive disorder [8], and bipolar disorder (BD) [9].…”

Section: Introductionmentioning

confidence: 99%

Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting State Functional MRI Images

Koc,

Kalkan,

Bilgen

2023

Autism Research and Treatment

View full text Add to dashboard Cite

This study aims to increase the accuracy of autism spectrum disorder (ASD) diagnosis based on cognitive and behavioral phenotypes through multiple neuroimaging modalities. We apply machine learning (ML) algorithms to classify ASD patients and healthy control (HC) participants using structural magnetic resonance imaging (s-MRI) together with resting state functional MRI (rs-f-MRI and f-MRI) data from the large multisite data repository ABIDE (autism brain imaging data exchange) and identify important brain connectivity features. The 2D f-MRI images were converted into 3D s-MRI images, and datasets were preprocessed using the Montreal Neurological Institute (MNI) atlas. The data were then denoised to remove any confounding factors. We show, by using three fusion strategies such as early fusion, late fusion, and cross fusion, that, in this implementation, hybrid convolutional recurrent neural networks achieve better performance in comparison to either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). The proposed model classifies subjects as autistic or not according to how functional and anatomical connectivity metrics provide an overall diagnosis based on the autism diagnostic observation schedule (ADOS) standard. Our hybrid network achieved an accuracy of 96% by fusing s-MRI and f-MRI together, which outperforms the methods used in previous studies.

show abstract

Efficient detection of Parkinson's disease using deep learning techniques over medical data

Cited by 48 publications

References 34 publications

Parkinson Disease Prediction Using Deep Learning Algorithm

Parkinson Disease Prediction Using Deep Learning Algorithm

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting State Functional MRI Images

Contact Info

Product

Resources

About