Multi-Modal Deep Learning Diagnosis of Parkinson’s Disease—A Systematic Review

Abstract

Parkinson's Disease (PD) is among the most frequent neurological disorders. Approaches that employ artificial intelligence and notably deep learning, have been extensively embraced with promising outcomes. This study dispenses an exhaustive review between 2016 and January 2023 on deep learning techniques used in the prognosis and evolution of symptoms and characteristics of the disease based on gait, upper limb movement, speech and facial expression-related information as well as the fusion of more than one of the aforementioned modalities. The search resulted in the selection of 87 original research publications, of which we have summarized the relevant information regarding the utilized learning and development process, demographic information, primary outcomes, and sensory equipment related information. Various deep learning algorithms and frameworks have attained state-of-theart performance in many PD-related tasks by outperforming conventional machine learning approaches, according to the research reviewed. In the meanwhile, we identify significant drawbacks in the existing research, including a lack of data availability and interpretability of models. The fast advancements in deep learning and the rise in accessible data provide the opportunity to address these difficulties in the near future and for the broad application of this technology in clinical settings.

Detecting Minor Symptoms of Parkinson’s Disease in the Wild Using Bi-LSTM with Attention Mechanism

“…Recently, convolutional neural networks (CNNs) have demonstrated remarkable capabilities in medical image analysis, disease detection, diagnosis, and prognosis [ 21 , 37 ]. These networks have the potential to significantly impact healthcare by contributing to early disease detection, treatment planning, and improved clinical outcomes.…”

“…LSTM excels in capturing dependencies and patterns over long sequences, making it particularly well suited for time series and sequential data analysis. In healthcare, LSTM-based models have been successfully applied on various occasions, such as disease prediction, patient monitoring, and medical signal analysis [ 21 , 44 ]. These models leverage the memory capabilities of LSTM to capture temporal dynamics and contextual information, enabling accurate predictions and insights from healthcare data.…”

“…In recent years, there has been growing interest in utilizing artificial intelligence (AI) techniques to develop noninvasive and accessible methods for early PD detection [ 21 ]. The advent of wearable devices, such as accelerometers embedded in smartphones or smartwatches, has provided a wealth of data which can be leveraged to extract meaningful information about an individual’s movement patterns and identify potential biomarkers for PD [ 22 , 23 ].…”

A Novel Artificial-Intelligence-Based Approach for Classification of Parkinson’s Disease Using Complex and Large Vocal Features

“…The approach improves prediction accuracy and time complexity for large datasets compared to other machine learning techniques. Skaramagkas et al [ 29 ] (2023) have submitted a report that offers a thorough analysis of the deep learning methods applied to PD research between 2016 and January 2023. The paper highlights the potential results of deep learning algorithms in predicting and monitoring PD symptoms based on speech, facial expression, upper limb movement, gait, and these factors combined, but it also draws attention to drawbacks such as data accessibility and model interpretability.…”

Using Lower Limb Wearable Sensors to Identify Gait Modalities: A Machine-Learning-Based Approach

“…Previous studies have explored attaching wearable sensors at the chest [17,18], wrist [12], hip [19,20], waist [21][22][23], thigh [4,24], shank [4] and foot [5,15,25]. The lower back is a frequently chosen attachment sites for collecting acceleration signals [1,[26][27][28]. Attachment sites at the bottom of the back can produce success rates higher than 87% when classifying Parkinson's disease [1], 94% when predicting age differences between participants [27] and 97% when predicting participants running speeds [26].…”