Automatic Diagnosis of Parkinson's Disease Based on Deep Learning Models and Multimodal Data

Automatic Diagnosis of Parkinson's Disease Based on Deep Learning Models and Multimodal Data

DOI: 10.4018/979-8-3693-1281-0.ch009
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Parkinson's disease (PD) is a common age-related neurodegenerative disorder in the aging society. Early diagnosis of PD is particularly important for efficient intervention. Currently, the diagnosis of PD is mainly made by neurologists who assess the abnormalities of the patient's motor system and evaluate the severity according to established criteria, which is highly dependent on the neurologists' expertise and often unsatisfactory. Artificial intelligence provides new potential for automatic and reliable diagnosis of PD based on multimodal data analysis. Some deep learning models have been developed for automatic detection of PD based on diverse biomarkers such as brain imaging images, electroencephalograms, walking postures, speech, handwriting, etc., with promising accuracy. This chapter summarizes the state-of-the-art, technical advancements, unmet research gaps, and future directions of deep learning models for PD detection. It provides a reference for biomedical engineers, data scientists, and health professionals.
Chapter Preview
Top

Introduction

Unmet Clinical Need for the Diagnosis of Parkinson's Disease (PD)

Parkinson's disease (PD) is the second most common chronic progressive neurodegenerative condition worldwide. PD mainly occurs in individuals aged 50 years and above with motor symptoms include resting tremor, muscle tonus, and bradykinesia, and non-motor symptoms such as sleep dysfunction, dysgeusia, and cognitive deficits, etc. (Alzubaidi et al., 2021; D’Sa et al., 2023; Giannakopoulou et al., 2022). Males are more susceptible to the PD than females. The disease progresses gradually over time, negatively affecting the patient's daily life (Barua et al., 2021). The pathology of PD is not fully clear. Current clinical interventions include medication and surgery to alleviate symptoms, but a complete cure for PD has not yet been found (E et al., 2021; Guo et al., 2022; Suri et al., 2022). The high cost of treatment is a significant economic burden on patients, their families, and the society (H. W. Loh et al., 2021).

Age is the most significant and unalterable risk factor for PD, while genetic, environmental, and behavioral factors also play a role (Barua et al., 2021; Tolosa et al., 2021). As the global population ages, the prevalence of PD increased dramatically with disability-adjusted life years worldwide (Giannakopoulou et al., 2022), and early identification and diagnosis of patients in the disease's early stages is crucial to improve treatment efficiency and prognosis (Oliveira et al., 2023). Aging is associated with the decrease in dopamine secretion in neurons in the human brain. The pathological hallmark of PD consists of involute neuronal inclusions in the form of Lewy bodies and Lewy neurites with loss of neurons along the substantia nigra and other regions of the brain (Tolosa et al., 2021). However, the exact etiology of PD is still unclear. Although various pathophysiologic findings have aided in diagnosing PD, they do not enable clinicians to distinguish PD patients from healthy subjects.

At present, PD is diagnosed by reviewing the patient's medical history, symptoms, signs, and examination outcomes. The symptoms are evaluated through scales, e.g., the Movement Disorders Society Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) and the Hoehn and Yahr (H&Y) Staging Scale (Giannakopoulou et al., 2022). Radiological examinations, including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET) can highlight the pathological changes in brain regions, providing reference for the detection of PD. However, there is no standardized imaging protocol for the detection of PD. In addition, it is difficult to exclude the confounding effects of other age-associated neurological diseases. With the lack of understanding of the underlying pathophysiology and the subjective nature of the diagnostic process, early and accurate of PD is still an unmet challenge (Alzubaidi et al., 2021; H. W. Loh et al., 2021; Xu et al., 2023).

Key Terms in this Chapter

Substantia Nigra: Is a midbrain dopaminergic nucleus which has a critical role in modulating motor movement and reward functions as part of the basal ganglia circuitry.

Lewy Bodies: The defining pathological characteristic of Parkinson's disease and dementia with Lewy bodies, constitute the second most common nerve cell pathology, after the neurofibrillary lesions of Alzheimer's disease.

Disability-Adjusted Life Years: A measure for total health combining Years Lost due to Disability and the Years of Life Lost due to premature mortality.

MDS-UPDRS: The most widely used clinical Parkinson's Disease Rating Scale, which consists of four sections, including Non-motor Experience of Daily Life; II: Motor Experience of Daily Life; III: Motor Examination; IV: Motor Complications;

CNN: A deep learning approach that is widely used for solving complex problems, and overcomes the limitations of traditional machine learning approaches.

Robustness: The capacity of an analytical procedure to produce unbiased results when small changes in the experimental conditions are made voluntarily.

Complete Chapter List

Search this Book:
Reset