Parkinson’s Disease Classification and Clinical Score Regression via United Embedding and Sparse Learning From Longitudinal Data

Abstract

Parkinson's disease (PD) is known as an irreversible neurodegenerative disease that mainly affects the patient's motor system. Early classification and regression of PD are essential to slow down this degenerative process from its onset. In this paper, a novel adaptive unsupervised feature selection approach is proposed by exploiting manifold learning from longitudinal multimodal data. Classification and clinical score prediction are performed jointly to facilitate early PD diagnosis. Specifically, the proposed approach performs united embedding and sparse regression, which can determine the similarity matrices and discriminative features adaptively. Meanwhile, we constrain the similarity matrix among subjects and exploit norm to conduct sparse adaptive control for obtaining the intrinsic information of the multimodal data structure. An effective iterative optimization algorithm is proposed to solve this problem. We perform abundant experiments on the Parkinson's Progression Markers Initiative (PPMI) dataset to verify the validity of the

Review Of Models & Techniques For Identification Of Human Health Diseases

“…In terms of complexity, CT [6], SVM [15], SSDP [24], and LR [27] are able to achieve better performance, while in terms of delay, UESR [5], JHCP MMP [13], SVM [15], and SVM [47] are able to showcase faster performance, thus can be used for high-speed clinical deployments. While, MI GAN [8], JHCP MMP [13], PCA NET [17], PD Res Net [21], SALL [25], CWT [33], 3D CNN [34], PGO [38], GERF [39], RL [42], DNN EWBO [44], EC [46], and THS GAN [50] showcase high scalability, thus can be used for identification of large number of diseases in clinical scenarios.…”

“…Their strategy outperforms state-of-the-art approaches for both picture imputation and the diagnosis of brain disorders when applied to the ADNI-1/2 datasets. According to [5], Parkinson's disease (PD) is an irreversible neurological condition that affects the motor system. Early identification and therapy may dramatically decrease the course of Parkinson's disease.…”

“…The most accurate imaging methods are magnetic resonance imaging (MRI), position emission tomography (PET), and computer tomography (CT), but since they are also costly, they are seldom utilized as preventative screenings. They are used instead after the illness has reached a more severe stage [5,6]. It would be advantageous to create and adopt less expensive substitutes as a direct consequence of this.…”

Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson’s disease

“…Since Parkinson's disease is a progressive disorder, it is necessary to model multi-modal data over time in order to identify biomarkers for PD progression. Some efforts have been made to tackle this difficult problem in recent years [98][99][100][101][102] . Due to the complexity of longitudinal multi-modal (imaging and clinical) data, methods such as embedding learning and sparse regression have been proposed, which have obtained promising results 102 .…”

“…Some efforts have been made to tackle this difficult problem in recent years [98][99][100][101][102] . Due to the complexity of longitudinal multi-modal (imaging and clinical) data, methods such as embedding learning and sparse regression have been proposed, which have obtained promising results 102 . Further research is needed to improve modeling these longitudinal multimodal data so that reliable biomarkers can be identified to enhance the diagnosis and management of PD.…”