Small sample learning classifies Parkinson's disease patients based on their walking behavior.

Around the globe, thousands of people worldwide are suffering by Parkinson’s Disease (PD), a central nervous system degenerative condition. Early detection and diagnosis of PD is crucial for successful treatment and management of the disease. In past few years, Machine learning (ML) algorithms has shown great potential in predicting PD based on various physiological and neurological markers. In this disease prediction system, a system is proposed using ML-based approach to predict the presence of PD in patients. The system employs various machine learning models, including Gradient Boosted Tree, random forest, and logistic regression, to identify key markers and patterns associated with the disease. Overall, this disease prediction system provides a valuable tool for early detection and diagnosis of PD, which can lead to better management and treatment of the disease. The proposed approach can also be extended to other neurological disorders, providing a general framework for disease prediction and diagnosis.

Parkinson's disease (PD) is a neurodegenerative disorder characterized by a range of motor and non-motor symptoms. One of the notable non-motor symptoms of PD is the presence of vocal disorders, attributed to the underlying pathophysiological changes in the neural control of the laryngeal and vocal tract musculature. From this perspective, the integration of machine learning (ML) techniques in the analysis of speech signals has significantly contributed to the detection and diagnosis of PD. Particularly, MEL Frequency Cepstral Coefficients (MFCCs) and Gammatone Frequency Cepstral Coefficients (GTCCs) are both feature extraction techniques commonly used in the field of speech and audio signal processing that could exhibit great potential for vocal disorder identification. This study presents a novel approach to the early detection of PD through ML applied to speech analysis, leveraging both MFCCs and GTCCs. The recordings contained in the Mobile Device Voice Recordings at King's College London (MDVR-KCL) dataset were used. These recordings were collected from healthy individuals and PD patients while they read a passage and during a spontaneous conversation on the phone. Particularly, the speech data regarding the spontaneous dialogue task were processed through speaker diarization, a technique that partitions an audio stream into homogeneous segments according to speaker identity. The ML applied to MFCCS and GTCCs allowed us to classify PD patients with a test accuracy of 92.3%. This research further demonstrates the potential to employ mobile phones as a non-invasive, cost-effective tool for the early detection of PD, significantly improving patient prognosis and quality of life.

Parkinson's disease (PD) is a chronic neurological progressive disorder caused by lack of the chemical dopamine in the brain. Up to today, there is still no cure or prevention for PD, and usually the disease worsens gradually over time. However, this disease can be controlled with some treatment, especially in the early stage. Hence, this study proposes a method in early detection and diagnosis of PD by using the Multilayer Feedforward Neural Network (MLFNN) with Back-propagation (BP) algorithm. This MLFNN with BP algorithm is simulated using MATLAB software. The dataset information used in this study was taken from the Oxford Parkinson's Disease Detection Dataset. The output of the network is classified into healthy or PD by using K-Means Clustering algorithm. The performance of this classifier was evaluated based on the three parameters; sensitivity, specificity and accuracy. The result shows that network can be used in diagnosis and detection of PD due to the good performance, which is 83.3% for sensitivity, 63.6% for specificity, and 80% for accuracy.

Enhancing Parkinson’s disease identification using ensemble classifier and data augmentation techniques in machine learning

New era of artificial intelligence and machine learning-based detection, diagnosis, and therapeutics in Parkinson's disease.

BackgroundEarly diagnosis is crucial for ensuring that patients with Parkinson disease (PD) receive timely treatment, which can improve their quality of life and prolong lifespan. Wearable sensors have emerged as promising tools for early PD diagnosis, offering noninvasive, continuous symptom monitoring.ObjectiveThis review aimed to evaluate how wearable sensors have been applied in early diagnosis of PD over the past decade, focusing on sensor types, methods, findings, and limitations.MethodsThe systematic review was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were sourced from PubMed, IEEE Xplore, Scopus, and Web of Science and screened based on predefined criteria. The inclusion criteria were as follows: (1) the study was observational or experimental, (2) wearable sensors were applied for the early diagnosis of PD, (3) participants were diagnosed with early-stage or prodromal PD, (4) the study included at least 10 participants with PD, and (5) the article was published between 2013 and 2023. Studies were excluded if they focused solely on treatment, rehabilitation, symptom monitoring, or nonwearable devices; lacked diagnostic clarity; were not published in English; or were not primary research articles. All the selected studies were assessed for quality using the Quality Assessment of Diagnostic Accuracy Studies-2, the quality assessment tool recommended by the Cochrane Collaboration.ResultsOverall, 1888 records were retrieved from the selected databases, with 1044 records remaining after duplicate removal. Following the screening of titles and abstracts, 949 ineligible records were excluded, leaving 95 articles for eligibility. Eventually, of the 1044 studies, 12 (1.12%) met the inclusion criteria, validating the feasibility of wearable sensors in the early diagnosis of PD. Most (10/12, 83%) were cross-sectional studies, with 1 longitudinal and 1 mixed-design study. Of the 12 studies, 4 (33%) focused on identification diagnosis, 2 (17%) addressed the staged diagnosis of PD, and 1 (8%) focused on the identification of specific symptoms. Of the 12 studies, 5 (42%) assessed the overall feasibility and performance of wearable sensors in early PD detection without targeting specific classification purposes. The main wearable sensors used were inertial measurement units (8/12, 67%) and accelerometers (4/12, 33%), which primarily captured motion-related data. While initial findings suggest that wearable sensors are feasible for early PD diagnosis, the evidence is still limited by small sample sizes and short study durations.ConclusionsWearable sensors show promise in supporting the early diagnosis of PD, particularly for motor symptoms monitoring. However, several limitations remain in validating and applying wearable sensors in clinical contexts, including cross-sectional designs and limited diagnostic standardization. More diverse studies are needed to further validate these findings and address existing shortcomings to better advance the use of wearable sensors in the early diagnosis of PD.Trial RegistrationPROSPERO CRD42024544198; https://www.crd.york.ac.uk/PROSPERO/view/CRD42024544198

Parkinson's disease (PD) is a prevalent, disabling neurodegenerative disorder. Early diagnosis and treatment of PD remains challenging due to the absence of definitive diagnostic tests and the non-specificity of its clinical manifestations. Initial consultations for PD symptoms often involve specialists who are not specifically trained in PD. Consequently, it is imperative to assess the general knowledge regarding PD among these specialists to develop optimal educational strategies and enhance early recognition and diagnosis of PD. We developed a questionnaire covering motor symptoms, non-motor symptoms, prodromal symptoms, risk factors and antiparkinsonian medications based on published guidelines, and conducted the web-based survey via Wenjuan xing (https://www.wjx.cn/) among physicians not specializing in PD in Guangdong Province, China. A total of 312 respondents, working in 28 diverse departments across 64 hospitals of three different categories, were eligible for data analysis. Notably, 95.2% of the respondents were aware of rest tremor as a motor symptom, yet only 76.9% recognized bradykinesia as a motor symptom. Regarding non-motor symptoms, erectile dysfunction, urinary dysfunction, restless legs, olfactory loss, orthostatic hypotension, rapid eye movement behavior disorder (RBD), lower back pain and diaphoresis, were recognized by less than 50% of the respondents. Additionally, with the exception of subthreshold parkinsonism or abnormal quantitative motor testing, prodromal symptoms such as excessive daytime somnolence, depression (± anxiety), olfactory loss, urinary dysfunction, RBD, and constipation were recognized by 36.5-48.7% of the respondents. First-degree relatives with PD received recognition from 86.5% of the respondents, whereas the remaining risk factors were recognized by 50-60% of the participants. Concerning protective factors for PD, recognition was limited to no more than 23%. Levodopa and dopamine releasers were the most widely recognized antiparkinsonian medications, while the recognition of other medications was below 70%. Variables such as medical degrees, professional titles, hospital categories, and education subjects contributed to statistical differences in PD knowledge. Among non-PD specialists in south China, current knowledge regarding PD, including non-motor symptoms, prodromal symptoms, risk and protective factors, and antiparkinsonian medications, is relatively inadequate. This necessitates targeted education and training to improve their understanding and recognition of PD.

Parkinson's disease (PD) is a neurodegenerative disorder that affects movement and cognitive function. Early diagnosis of PD is crucial for effective treatment and management of the disease. Magnetic resonance imaging (MRI) is a non-invasive diagnostic tool that can provide detailed images of the brain. In this study, we propose a method for PD detection using MRI images based on image processing techniques. Our approach involves several stages, including preprocessing, feature extraction, and classification. Preprocessing involves normalization, segmentation, and registration of the MRI images to remove noise and align the images for feature extraction. Feature extraction involves the use of handcrafted features such as intensity histograms, texture features, and morphological features to describe the MRI images. Classification involves the use of machine learning algorithms such as convolutional neural networks (CNNs) to predict whether an individual has PD based on the extracted features. We evaluate our method on a publicly available dataset of MRI images from PD patients and healthy controls. Our results show that our method achieves high accuracy, sensitivity, and specificity for PD detection compared to existing methods. Our approach has the potential to improve early diagnosis and management of PD through non-invasive and accurate MRI-based diagnosis

The purpose of this review is to outline the impact of the COVID-19 pandemic on movement disorder holistic care, particularly in the care of people with Parkinson disease (PWP). As the pandemic unfolds, a flurry of literature was published regarding the impact of COVID-19 on people with Parkinson disease including the direct impact of infection, availability of ambulatory care, loss of community-based team care, and acceptability of telemedicine. COVID-19 has impacted the care of PWP in numerous ways. Recognizing infection in PWP poses challenges. Specific long-term complications, including emerging reports of long COVID syndrome is a growing concern. Caregivers and PWP have also been impacted by COVID-19 social isolation restrictions, with radical changes to the structure of social networks and support systems globally. In a matter of weeks, the global community saw an incredible uptake in telemedicine, which brought benefits and pitfalls. As PWP adapted to virtual platforms and the changing architecture of care delivery, the pandemic amplified many preexisting inequities amongst populations and countries, exposing a new 'digital divide'.

Validation of an in vivo electrochemical immunosensing platform for simultaneous detection of multiple cytokines in Parkinson’s disease mice model

2021 Workshop: Neurodegenerative Diseases in the Gut-Brain Axis—Parkinson's Disease

Parkinson’s disease (PD) is a complex neurodegenerative disease. At present, the early diagnosis of PD is still extremely challenging, and there is still a lack of consensus on the brain characterization of PD, and a more efficient and robust PD detection method is urgently needed. In order to further explore the features of PD based on brain activity and achieve effective detection of PD patients (including OFF and ON medications), in this study, a multi-pattern analysis based on brain activation and brain functional connectivity was performed on the brain functional activity of PD patients, and a novel PD detection model based on multi-scale convolutional neural network (MCNN) was proposed. Based on the analysis of power spectral density (PSD) and phase-locked value (PLV) features of multiple frequency bands of two independent resting-state electroencephalography (EEG) datasets, we found that there were significant differences in PSD and PLV between HCs and PD patients (including OFF and ON medications), especially in the β and γ bands, which were very effective for PD detection. Moreover, the combined use of brain activation represented by PSD and functional connectivity patterns represented by PLV can effectively improve the performance of PD detection. Furthermore, our proposed MCNN model shows great potential for automatic PD detection, with cross-validation accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve all above 99%. Our study may help to further understand the characteristics of PD and provide new ideas for future PD diagnosis based on spontaneous EEG activity.

Parkinson's disease (PD) is a prevalent neurodegenerative disorder that significantly benefits from early diagnosis for effective disease management and intervention. Despite advancements in medical technology, there remains a critical gap in the early and non-invasive detection of PD. Current diagnostic methods are often invasive, expensive, or late in identifying the disease, leading to missed opportunities for early intervention. The goal of this study is to explore the efficiency and accuracy of combining fNIRS technology with machine learning algorithms in diagnosing early-stage PD patients and to evaluate the feasibility of this approach in clinical practice. Using an ETG-4000 type near-infrared brain function imaging instrument, data was collected from 120 PD patients and 60 healthy controls. This cross-sectional study employed a multi-channel mode to monitor cerebral blood oxygen changes. The collected data were processed using a general linear model and β values were extracted. Subsequently, four types of machine learning models were developed for analysis: Support vector machine (SVM), K-nearest neighbors (K-NN), random forest (RF), and logistic regression (LR). Additionally, SHapley Additive exPlanations (SHAP) technology was applied to enhance model interpretability. The SVM model demonstrated higher accuracy in differentiating between PD patients and control group (accuracy of 85%, f1 score of 0.85, and an area under the ROC curve of 0.95). SHAP analysis identified the four most contributory channels (CH) as CH01, CH04, CH05, and CH08. The model based on the SVM algorithm exhibited good diagnostic performance in the early detection of PD patients. Future early diagnosis of PD should focus on the Frontopolar Cortex (FPC) region.

Parkinson's Disease (PD) is a chronic and progressive neurological disorder characterized by a range of motor and non-motor symptoms due to the degeneration of dopaminergic neurons in the brain. Diagnosing PD is a complex process that relies on clinical assessments, as there are no definitive biomarkers. However, the advent of machine learning (ML) and deep learning (DL) techniques has shown promising advancements in the early detection and diagnosis of PD. This chapter reviews recent studies that apply various ML and DL models to PD detection, discussing the methodologies, datasets, and results. Researchers have leveraged these models to improve diagnostic accuracy, prognosticate disease progression, and predict patient health outcomes under medication. This synthesis of literature provides valuable insights into the state-of-the-art ML applications in PD and explores their significance in the medical field for enhancing patient care.

Parkinson&#x2019;s disease (PD) is one of the chronic neurological diseases whose progression is slow and symptoms have similarities with other diseases. Early detection and diagnosis of PD is crucial to prescribe proper treatment for patient&#x2019;s productive and healthy lives. The disease&#x2019;s symptoms are characterized by tremors, muscle rigidity, slowness in movements, balancing along with other psychiatric symptoms. The dynamics of handwritten records served as one of the dominant mechanisms which support PD detection and assessment. Several machine learning methods have been investigated for the early detection of this disease. But most of these handcrafted feature extraction techniques predominantly suffer from low performance accuracy issues. This cannot be tolerable for dealing with detection of such a chronic ailment. To this end, an efficient deep learning model is proposed which can assist to have early detection of Parkinson&#x2019;s disease. The significant contribution of the proposed model is to select the most optimum features which have the effect of getting the high-performance accuracies. The feature optimization is done through genetic algorithm wherein <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula>-Nearest Neighbour technique. The proposed novel model results into detection accuracy higher than 95&#x0025;, precision of 98&#x0025;, area under curve of 0.90 with a loss of 0.12 only. The performance of proposed model is compared with some state-of-the-art machine learning and deep learning-based PD detection approaches to demonstrate the better detection ability of our model.