Accuracy of clinical diagnosis of Parkinson disease: A systematic review and meta-analysis

Accuracy of 18F-FDG PET Imaging in Differentiating Parkinson's Disease from Atypical Parkinsonian Syndromes: A Systematic Review and Meta-Analysis

RATIONALE AND OBJECTIVE

To quantitatively assess the accuracy of 18F-FDG PET in differentiating Parkinson's Disease (PD) from Atypical Parkinsonian Syndromes (APSs).

METHODS

PubMed, Embase, and Web of Science databases were searched to identify studies published from the inception of the databases up to June 2024 that used 18F-FDG PET imaging for the differential diagnosis of PD and APSs. The risk of bias in the included studies was assessed using the QUADAS-2 or QUADAS-AI tool. Bivariate random-effects models were used to calculate the pooled sensitivity, specificity, and the area under the curves (AUC) of summary receiver operating characteristic (SROC).

RESULTS

24 studies met the inclusion criteria, involving a total of 1508 PD patients and 1370 APSs patients. 12 studies relied on visual interpretation by radiologists, of which the pooled sensitivity, specificity, and SROC-AUC for direct visual interpretation in diagnosing PD were 96% (95%CI: 91%, 98%), 90% (95%CI: 83%, 95%), and 0.98 (95%CI: 0.96, 0.99), respectively; the pooled sensitivity, specificity, and SROC-AUC for visual interpretation supported by univariate algorithms in diagnosing PD were 93% (95%CI: 90%, 95%), 90% (95%CI: 85%, 94%), and 0.96 (95%CI: 0.94, 0.97), respectively. 12 studies relied on artificial intelligence (AI) to analyze 18F-FDG PET imaging data. The pooled sensitivity, specificity, and SROC-AUC of machine learning (ML) for diagnosing PD were 87% (95%CI: 82%, 91%), 91% (95%CI: 86%, 94%), and 0.95 (95%CI: 0.93, 0.96), respectively. The pooled sensitivity, specificity, and SROC-AUC of deep learning (DL) for diagnosing PD were 97% (95%CI: 95%, 98%), 95% (95%CI: 89%, 98%), and 0.98 (95%CI: 0.96, 0.99), respectively.

CONCLUSION

18F-FDG PET has a high accuracy in differentiating PD from APS, among which AI-assisted automatic classification performs well, with a diagnostic accuracy comparable to that of radiologists, and is expected to become an important auxiliary means of clinical diagnosis in the future.

Upper extremity functions, spinal posture, and axial rigidity in patients with parkinson's disease

OBJECTIVE

Upper extremity dysfunction is frequently seen in Parkinson's disease (PD). Existing research has shown that bradykinesia, which is main symptom of PD, is primarily responsible but the combined effects of spinal posture and axial rigidity on upper extremity functions were not investigated yet. The aim of this study was to investigate upper extremity functions in patients with PD and to evaluate relationship of these with spinal posture and axial rigidity.

METHODS

This prospective controlled study included 40 patients with PD and 40 healthy controls. Upper extremity function was measured with the 9-Hole Peg Test. Spinal posture and axial rigidity were measured with a Spinal Mouse.

RESULTS

Compared with the control group, a decrease in upper extremity functions (p < 0.001), decreased lumbar lordosis (p = 0.003), and posterior sacral tilt (p = 0.021) were determined in patients' group. Thoracic and lumbar mobility in the sagittal (all p < 0.001) and frontal planes (p = 0.004, p < 0.001) was found to be reduced in the patient group. A correlation was determined between upper extremity functions and lumbar mobility in the sagittal (p = 0.022, r= -0.362) and frontal planes (p = 0.045, r= -0.319) and lumbar lordosis (p = 0.048, r = 0.302).

CONCLUSIONS

The results of this study demonstrated that altered spinal posture and increased axial rigidity were related with decreased upper extremity functions in patients with PD. There is a need for further studies to investigate effect of trunk-based therapies on upper extremity function in patients with PD.

A minimally invasive biomarker for sensitive and accurate diagnosis of Parkinson's disease

Seeding activities of disease-associated α-synuclein aggregates (αSynD), a hallmark of Parkinson's disease (PD), are detectable by seed amplification assay (αSyn-SAA) and being developed as a diagnostic biomarker for PD. Sensitive and accurate αSyn-SAA for blood or saliva would greatly facilitate PD diagnosis. This prospective diagnostic study conducted αSyn-SAA analyses on serum and saliva samples collected from patients clinically diagnosed with PD or healthy controls (HC). 124 subjects (82 PD, 42 HC) donated blood and had extensive clinical assessments, of whom 74 subjects (48 PD, 26 HC) also donated saliva at the same visits. An additional 57 subjects (35 PD, 22 HC) donated saliva and had more limited clinical assessments. The mean ages were 69.21, 66.55, 69.58, and 64.71 years for PD serum donors, HC serum donors, PD saliva donors, and HC saliva donors, respectively. αSynD seeding activities in either sample type alone or both sample types together were evaluated for PD diagnosis. Serum αSyn-SAA data from 124 subjects showed 80.49% sensitivity, 90.48% specificity, and 0.9006 accuracy (AUC of ROC); saliva αSyn-SAA data from 131 subjects attained 74.70% sensitivity, 97.92% specificity, and 0.8966 accuracy. Remarkably, the combined serum and saliva αSyn-SAA from 74 subjects with both sample types achieved better diagnostic performance: 95.83% sensitivity, 96.15% specificity, and 0.98 accuracy. In addition, serum αSynD seeding activities correlated inversely with Montreal Cognitive Assessment in males and positively with Hamilton Depression Rating Scale in females and in the < 70 age group, whereas saliva αSynD seeding activities correlated inversely with age at diagnosis in males and in the < 70 age group. Our data indicate that serum and saliva αSyn-SAA together can achieve high diagnostic accuracy for PD comparable to that of CSF αSyn-SAA, suggesting their potential utility for highly sensitive, accurate, and minimally invasive diagnosis of PD in routine clinical practice and clinical studies.

Electrochemical biosensors in early detection of Parkinson disease

Parkinson's disease (PD) is a progressive neurodegenerative disorder affecting the motor system, with symptoms including tremors, rigidity, bradykinesia, and postural instability. Affecting over six million people globally, PD's pathophysiology is marked by the loss of dopaminergic neurons in the substantia nigra. Early diagnosis is crucial for effective management, yet current methods are limited by low sensitivity, high cost, and the need for advanced equipment. Electrochemical biosensors have emerged as promising tools for early PD diagnosis, converting biological reactions into measurable electrical signals for evaluating PD biomarkers. Advances in nanotechnology and material science have led to innovative sensing platforms with enhanced sensitivity and selectivity. Key biomarkers such as alpha-synuclein (α-syn), dopamine (DA), and microRNAs (miRNAs) have been targeted using these biosensors. For instance, gold nanoparticle-modified graphene immunosensors have shown ultra-sensitive detection of α-syn, while graphene-based biosensors have demonstrated high sensitivity for DA detection. Additionally, nanobiosensors for miR-195 and electrochemical aptasensors have shown potential for early PD diagnosis. The integration of nanomaterials like gold nanoparticles, quantum dots, and carbon nanotubes has further advanced the field, enhancing electrochemical activity and sensitivity. These developments offer a reliable, rapid, and cost-effective approach for early PD diagnosis, paving the way for better management and treatment. Continued research is essential for the commercialization and clinical integration of these biosensors, ultimately improving patient outcomes.

Gait analysis in the early stage of Parkinson's disease with a machine learning approach

Background

Gait disorder is a prominent motor symptom in Parkinson's disease (PD), objective and quantitative assessment of gait is essential for diagnosing and treating PD, particularly in its early stage.

Methods

This study utilized a non-contact gait assessment system to investigate gait characteristics between individuals with PD and healthy controls, with a focus on early-stage PD. Additionally, we trained two machine learning models to differentiate early-stage PD patients from controls and to predict MDS-UPDRS III score.

Results

Early-stage PD patients demonstrated reduced stride length, decreased gait speed, slower stride and swing speeds, extended turning time, and reduced cadence compared to controls. Our model, after an integrated analysis of gait parameters, accurately identified early-stage PD patients. Moreover, the model indicated that gait parameters could predict the MDS-UPDRS III score using a machine learning regression approach.

Conclusion

The non-contact gait assessment system facilitates the objective and quantitative evaluation of gait disorder in PD patients, effectively distinguishing those in the early stage from healthy individuals. The system holds significant potential for the early detection of PD. It also harnesses gait parameters for a reasoned prediction of the MDS-UPDRS III score, thereby quantifying disease severity. Overall, gait assessment is a valuable method for the early identification and ongoing monitoring of PD.

From small to tall: breed-varied household pet dogs can be trained to detect Parkinson's Disease

Parkinson's Disease (PD) is a clinically diagnosed disease that carries a reported misdiagnosis rate of 10-20%. Recent scientific discoveries have provided evidence of volatile organic compounds in sebum that are unique to patients with PD. The primary objective of this study was to determine if companion dogs could be trained to distinguish between sebum samples provided by PD-positive patients and PD-negative human controls. This was a randomized, handler-blind, controlled study. Twenty-three canines of varying breeds, ages, and environmental backgrounds were included. The study period encompassed 200 total working days from 2021 to 2022. Factors investigated included donor gender and levodopa drug affectivity, as well as canine breed, age, and duration of training time. The findings in this study were compiled from data collected during the final two years of a seven-year research program. For this two-year reporting period, when averaged as a group, the 23 dogs were 89% sensitive and 87% specific to olfactory distinction between PD-positive and PD-negative human donor samples. Ten of the twenty-three dogs averaged 90% or higher in both sensitivity and specificity. In 161 separate trials, a dog was presented with both novel PD-positive and PD-negative samples. For these novel exposures, the dogs collectively averaged 86% sensitivity and 89% specificity. PD medication was also investigated and was found to have no discernible impact on canine sensitivity or specificity results. Study findings support the application of companion dogs, trained with force-free, reward-based methodologies, for the detection of PD-positive and PD-negative samples under controlled conditions.

Machine learning and wearable sensors for automated Parkinson's disease diagnosis aid: a systematic review

BACKGROUND

The diagnosis of Parkinson's disease is currently based on clinical evaluation. Despite clinical hallmarks, unfortunately, the error rate is still significant. Low in-vivo diagnostic accuracy of clinical evaluation mainly relies on the lack of quantitative biomarkers for an objective motor performance assessment. Non-invasive technologies, such as wearable sensors, coupled with machine learning algorithms, assess quantitatively and objectively the motor performances, with possible benefits either for in-clinic and at-home settings. We conducted a systematic review of the literature on machine learning algorithms embedded in smart devices in Parkinson's disease diagnosis.

METHODS

Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we searched PubMed for articles published between December, 2007 and July, 2023, using a search string combining "Parkinson's disease" AND ("healthy" or "control") AND "diagnosis", within the Groups and Outcome domains. Additional search terms included "Algorithm", "Technology" and "Performance".

RESULTS

From 89 identified studies, 47 met the inclusion criteria based on the search string and four additional studies were included based on the Authors' expertise. Gait emerged as the most common parameter analysed by machine learning models, with Support Vector Machines as the prevalent algorithm. The results suggest promising accuracy with complex algorithms like Random Forest, Support Vector Machines, and K-Nearest Neighbours.

DISCUSSION

Despite the promise shown by machine learning algorithms, real-world applications may still face limitations. This review suggests that integrating machine learning with wearable sensors has the potential to improve Parkinson's disease diagnosis. These tools could provide clinicians with objective data, potentially aiding in earlier detection.

Convolutional neural network based detection of early stage Parkinson's disease using the six minute walk test

The heterogeneity of Parkinson's disease (PD) presents considerable challenges for accurate diagnosis, particularly during early-stage disease, when the symptoms may be extremely subtle. This study aimed to assess the accuracy of a convolutional neural network (CNN) technique based on the 6-min walk test (6MWT) measured using wearable sensors to distinguish patients with early-stage PD (n = 78) from healthy controls (n = 50). The participants wore six sensors, and performed the 6MWT. The time-series data were converted into new images. The results revealed that the gyroscopic vertical component of the lumbar spine displayed the highest classification accuracy of 83.5%, followed by those of the thoracic spine (83.1%) and right thigh (79.5%) segment. These findings suggest that the 6MWT and CNN models may facilitate earlier diagnosis and monitoring of PD symptoms, enabling clinicians to provide timely treatment during the critical transition from normal to pathologic gait patterns.

Beyond the usual suspects: multi-factorial computational models in the search for neurodegenerative disease mechanisms

From Alzheimer's disease to amyotrophic lateral sclerosis, the molecular cascades underlying neurodegenerative disorders remain poorly understood. The clinical view of neurodegeneration is confounded by symptomatic heterogeneity and mixed pathology in almost every patient. While the underlying physiological alterations originate, proliferate, and propagate potentially decades before symptomatic onset, the complexity and inaccessibility of the living brain limit direct observation over a patient's lifespan. Consequently, there is a critical need for robust computational methods to support the search for causal mechanisms of neurodegeneration by distinguishing pathogenic processes from consequential alterations, and inter-individual variability from intra-individual progression. Recently, promising advances have been made by data-driven spatiotemporal modeling of the brain, based on in vivo neuroimaging and biospecimen markers. These methods include disease progression models comparing the temporal evolution of various biomarkers, causal models linking interacting biological processes, network propagation models reproducing the spatial spreading of pathology, and biophysical models spanning cellular- to network-scale phenomena. In this review, we discuss various computational approaches for integrating cross-sectional, longitudinal, and multi-modal data, primarily from large observational neuroimaging studies, to understand (i) the temporal ordering of physiological alterations, i(i) their spatial relationships to the brain's molecular and cellular architecture, (iii) mechanistic interactions between biological processes, and (iv) the macroscopic effects of microscopic factors. We consider the extents to which computational models can evaluate mechanistic hypotheses, explore applications such as improving treatment selection, and discuss how model-informed insights can lay the groundwork for a pathobiological redefinition of neurodegenerative disorders.

Diagnostic value of six plasma biomarkers in progressive supranuclear palsy, multiple system atrophy, and Parkinson's disease

OBJECTIVES

This study aimed to evaluate the diagnostic ability of six plasma biomarkers in progressive supranuclear palsy (PSP), multiple system atrophy (MSA), and different subtypes of Parkinson's disease (PD).

METHODS

Neurofilament light chain (NfL), phosphorylated tau-181, glial fibrillary acidic protein (GFAP), amyloid-β 42 (Aβ42), and amyloid-β 40 (Aβ40) levels were measured using the single-molecule array (Simoa) technique in a cohort of patients with PSP, MSA, different subtypes of PD, and healthy controls (HCs).

RESULTS

Plasma NfL and GFAP levels were beneficial in discriminating between the disease groups and HCs. Plasma NfL, Aβ42, and Aβ40 could distinguish atypical Parkinsonian syndrome (APS) from PD and its subtypes. GFAP could discriminate APS from tremor dominant PD but could not discriminate APS from postural instability and gait disorder dominant PD. The efficacy of differentiation improved when a combination of multiple plasma biomarkers was applied.

CONCLUSIONS

In this study, the plasma biomarkers NfL, GFAP, Aβ42, and Aβ40 exhibited high discriminatory diagnostic value in PD and APS, and could be used as clinically potential diagnostic biomarkers. Plasma biomarker combinations could improve the differential diagnostic efficacy in the comparisons of PD and APS.

AI-Powered Telemedicine for Automatic Scoring of Neuromuscular Examinations

Telemedicine is now being used more frequently to evaluate patients with myasthenia gravis (MG). Assessing this condition involves clinical outcome measures, such as the standardized MG-ADL scale or the more complex MG-CE score obtained during clinical exams. However, human subjectivity limits the reliability of these examinations. We propose a set of AI-powered digital tools to improve scoring efficiency and quality using computer vision, deep learning, and natural language processing. This paper focuses on automating a standard telemedicine video by segmenting it into clips corresponding to the MG-CE assessment. This AI-powered solution offers a quantitative assessment of neurological deficits, improving upon subjective evaluations prone to examiner variability. It has the potential to enhance efficiency, patient participation in MG clinical trials, and broader applicability to various neurological diseases.

Simple biomarkers to distinguish Parkinson's disease from its mimics in clinical practice: a comprehensive review and future directions

In the last few years, a plethora of biomarkers have been proposed for the differentiation of Parkinson's disease (PD) from its mimics. Most of them consist of complex measures, often based on expensive technology, not easily employed outside research centers. MRI measures have been widely used to differentiate between PD and other parkinsonism. However, these measurements were often performed manually on small brain areas in small patient cohorts with intra- and inter-rater variability. The aim of the current review is to provide a comprehensive and updated overview of the literature on biomarkers commonly used to differentiate PD from its mimics (including parkinsonism and tremor syndromes), focusing on parameters derived by simple qualitative or quantitative measurements that can be used in routine practice. Several electrophysiological, sonographic and MRI biomarkers have shown promising results, including the blink-reflex recovery cycle, tremor analysis, sonographic or MRI assessment of substantia nigra, and several qualitative MRI signs or simple linear measures to be directly performed on MR images. The most significant issue is that most studies have been conducted on small patient cohorts from a single center, with limited reproducibility of the findings. Future studies should be carried out on larger international cohorts of patients to ensure generalizability. Moreover, research on simple biomarkers should seek measurements to differentiate patients with different diseases but similar clinical phenotypes, distinguish subtypes of the same disease, assess disease progression, and correlate biomarkers with pathological data. An even more important goal would be to predict the disease in the preclinical phase.

PD-ARnet: a deep learning approach for Parkinson's disease diagnosis from resting-state fMRI

Objective. The clinical diagnosis of Parkinson's disease (PD) relying on medical history, clinical symptoms, and signs is subjective and lacks sensitivity. Resting-state fMRI (rs-fMRI) has been demonstrated to be an effective biomarker for diagnosing PD.Approach.This study proposes a deep learning approach for the automatic diagnosis of PD using rs-fMRI, named PD-ARnet. Specifically, PD-ARnet utilizes Amplitude of Low Frequency Fluctuations and Regional Homogeneity extracted from rs-fMRI as inputs. The inputs are then processed through a developed dual-branch 3D feature extractor to perform advanced feature extraction. During this process, a Correlation-Driven weighting module is applied to capture complementary information from both features. Subsequently, the Attention-Enhanced fusion module is developed to effectively merge two types of features, and the fused features are input into a fully connected layer for automatic diagnosis classification.Main results.Using 145 samples from the PPMI dataset to evaluate the detection performance of PD-ARnet, the results indicated an average classification accuracy of 91.6% (95% confidence interval [CI]: 90.9%, 92.4%), precision of 94.7% (95% CI: 94.2%, 95.1%), recall of 86.2% (95% CI: 84.9%, 87.4%), F1 score of 90.2% (95% CI: 89.3%, 91.1%), and AUC of 92.8% (95% CI: 91.1%, 95.0%).Significance.The proposed method has the potential to become a clinical auxiliary diagnostic tool for PD, reducing subjectivity in the diagnostic process, and enhancing diagnostic efficiency and consistency.

Enhancing early Parkinson's disease detection through multimodal deep learning and explainable AI: insights from the PPMI database

Parkinson's is the second most common neurodegenerative disease, affecting nearly 8.5M people and steadily increasing. In this research, Multimodal Deep Learning is investigated for the Prodromal stage detection of Parkinson's Disease (PD), combining different 3D architectures with the novel Excitation Network (EN) and supported by Explainable Artificial Intelligence (XAI) techniques. Utilizing data from the Parkinson's Progression Markers Initiative, this study introduces a joint co-learning approach for multimodal fusion, enabling end-to-end training of deep neural networks and facilitating the learning of complementary information from both imaging and clinical modalities. DenseNet with EN outperformed other models, showing a substantial increase in accuracy when supplemented with clinical data. XAI methods, such as Integrated Gradients for ResNet and DenseNet, and Attention Heatmaps for Vision Transformer (ViT), revealed that DenseNet focused on brain regions believed to be critical to prodromal pathophysiology, including the right temporal and left pre-frontal areas. Similarly, ViT highlighted the lateral ventricles associated with cognitive decline, indicating their potential in the Prodromal stage. These findings underscore the potential of these regions as early-stage PD biomarkers and showcase the proposed framework's efficacy in predicting subtypes of PD and aiding in early diagnosis, paving the way for innovative diagnostic tools and precision medicine.

Multi-modality radiomics of conventional T1 weighted and diffusion tensor imaging for differentiating Parkinson's disease motor subtypes in early-stages

This study aimed to develop and validate a multi-modality radiomics approach using T1-weighted and diffusion tensor imaging (DTI) to differentiate Parkinson's disease (PD) motor subtypes, specifically tremor-dominant (TD) and postural instability gait difficulty (PIGD), in early disease stages. We analyzed T1-weighted and DTI scans from 140 early-stage PD patients (70 TD, 70 PIGD) and 70 healthy controls from the Parkinson's Progression Markers Initiative database. Radiomics features were extracted from 16 brain regions of interest. After harmonization and feature selection, four machine learning classifiers were trained and evaluated for both three-class (HC vs TD vs PIGD) and binary (TD vs PIGD) classification tasks. The light gradient boosting machine (LGBM) classifier demonstrated the best overall performance. For the three-class classification, LGBM achieved an accuracy of 85% and an area under the receiver operating characteristic curve (AUC) of 0.94 using combined T1 and DTI features. In the binary classification task, LGBM reached an accuracy of 95% and AUC of 0.95. Key discriminative features were identified in the Thalamus, Amygdala, Hippocampus, and Substantia Nigra for the three-group classification, and in the Pallidum, Amygdala, Hippocampus, and Accumbens for binary classification. The combined T1 + DTI approach consistently outperformed single-modality classifications, with DTI alone showing particularly low performance (AUC 0.55-0.62) in binary classification. The high accuracy and AUC values suggest that this approach could significantly improve early diagnosis and subtyping of PD. These findings have important implications for clinical management, potentially enabling more personalized treatment strategies based on early, accurate subtype identification.

Metabolomics Unveils Disrupted Pathways in Parkinson's Disease: Toward Biomarker-Based Diagnosis

Parkinson's disease (PD) is a neurodegenerative disorder characterized by diverse symptoms, where accurate diagnosis remains challenging. Traditional clinical observation methods often result in misdiagnosis, highlighting the need for biomarker-based diagnostic approaches. This study utilizes ultraperformance liquid chromatography coupled to an electrospray ionization source and quadrupole time-of-flight untargeted metabolomics combined with biochemometrics to identify novel serum biomarkers for PD. Analyzing a Brazilian cohort of serum samples from 39 PD patients and 15 healthy controls, we identified 15 metabolites significantly associated with PD, with 11 reported as potential biomarkers for the first time. Key disrupted metabolic pathways include caffeine metabolism, arachidonic acid metabolism, and primary bile acid biosynthesis. Our machine learning model demonstrated high accuracy, with the Rotation Forest boosting model achieving 94.1% accuracy in distinguishing PD patients from controls. It is based on three new PD biomarkers (downregulated: 1-lyso-2-arachidonoyl-phosphatidate and hypoxanthine and upregulated: ferulic acid) and surpasses the general 80% diagnostic accuracy obtained from initial clinical evaluations conducted by specialists. Besides, this machine learning model based on a decision tree allowed for visual and easy interpretability of affected metabolites in PD patients. These findings could improve the detection and monitoring of PD, paving the way for more precise diagnostics and therapeutic interventions. Our research emphasizes the critical role of metabolomics and machine learning in advancing our understanding of the chemical profile of neurodegenerative diseases.

Utilizing deep learning models in an intelligent spiral drawing classification system for Parkinson's disease classification

Introduction

Parkinson's disease (PD) is a neurodegenerative illness that impairs normal human movement. The primary cause of PD is the deficiency of dopamine in the human brain. PD also leads to several other challenges, including insomnia, eating disturbances, excessive sleepiness, fluctuations in blood pressure, sexual dysfunction, and other issues.

Methods

The suggested system is an extremely promising technological strategy that may help medical professionals provide accurate and unbiased disease diagnoses. This is accomplished by utilizing significant and unique traits taken from spiral drawings connected to Parkinson's disease. While PD cannot be cured, early administration of drugs may significantly improve the condition of a patient with PD. An expeditious and accurate clinical classification of PD ensures that efficacious therapeutic interventions can commence promptly, potentially impeding the advancement of the disease and enhancing the quality of life for both patients and their caregivers. Transfer learning models have been applied to diagnose PD by analyzing important and distinctive characteristics extracted from hand-drawn spirals. The studies were carried out in conjunction with a comparison analysis employing 102 spiral drawings. This work enhances current research by analyzing the effectiveness of transfer learning models, including VGG19, InceptionV3, ResNet50v2, and DenseNet169, for identifying PD using hand-drawn spirals.

Results

Transfer machine learning models demonstrate highly encouraging outcomes in providing a precise and reliable classification of PD. Actual results demonstrate that the InceptionV3 model achieved a high accuracy of 89% when learning from spiral drawing images and had a superior receiver operating characteristic (ROC) curve value of 95%.

Discussion

The comparison results suggest that PD identification using these models is currently at the forefront of PD research. The dataset will be enlarged, transfer learning strategies will be investigated, and the system's integration into a comprehensive Parkinson's monitoring and evaluation platform will be looked into as future research areas. The results of this study could lead to a better quality of life for Parkinson's sufferers, individualized treatment, and an early classification.

Cerebral Glucose Metabolism Is a Valuable Predictor of Survival in Patients with Lewy Body Diseases

OBJECTIVE

Patients with Lewy body diseases have an increased risk of dementia, which is a significant predictor for survival. Posterior cortical hypometabolism on [18F]fluorodeoxyglucose positron emission tomography (PET) precedes the development of dementia by years. We therefore examined the prognostic value of cerebral glucose metabolism for survival.

METHODS

We enrolled patients diagnosed with Parkinson's disease (PD), Parkinson's disease with dementia, or dementia with Lewy bodies who underwent [18F]fluorodeoxyglucose PET. Regional cerebral metabolism of each patient was analyzed by determining the expression of the PD-related cognitive pattern (Z-score) and by visual PET rating. We analyzed the predictive value of PET for overall survival using Cox regression analyses (age- and sex-corrected) and calculated prognostic indices for the best model.

RESULTS

Glucose metabolism was a significant predictor of survival in 259 included patients (n = 118 events; hazard ratio: 1.4 [1.2-1.6] per Z-score; hazard ratio: 1.8 [1.5-2.2] per visual PET rating score; both p < 0.0001). Risk stratification with visual PET rating scores yielded a median survival of 4.8, 6.8, and 12.9 years for patients with severe, moderate, and mild posterior cortical hypometabolism (median survival not reached for normal cortical metabolism). Stratification into 5 groups based on the prognostic index revealed 10-year survival rates of 94.1%, 78.3%, 34.7%, 0.0%, and 0.0%.

INTERPRETATION

Regional cerebral glucose metabolism is a significant predictor of survival in Lewy body diseases and may allow an earlier survival prediction than the clinical milestone "dementia." Thus, [18F]fluorodeoxyglucose PET may improve the basis for therapy decisions, especially for invasive therapeutic procedures like deep brain stimulation in Parkinson's disease. ANN NEUROL 2024;96:539-550.

Simplification of Mobility Tests and Data Processing to Increase Applicability of Wearable Sensors as Diagnostic Tools for Parkinson's Disease

Quantitative mobility analysis using wearable sensors, while promising as a diagnostic tool for Parkinson's disease (PD), is not commonly applied in clinical settings. Major obstacles include uncertainty regarding the best protocol for instrumented mobility testing and subsequent data processing, as well as the added workload and complexity of this multi-step process. To simplify sensor-based mobility testing in diagnosing PD, we analyzed data from 262 PD participants and 50 controls performing several motor tasks wearing a sensor on their lower back containing a triaxial accelerometer and a triaxial gyroscope. Using ensembles of heterogeneous machine learning models incorporating a range of classifiers trained on a set of sensor features, we show that our models effectively differentiate between participants with PD and controls, both for mixed-stage PD (92.6% accuracy) and a group selected for mild PD only (89.4% accuracy). Omitting algorithmic segmentation of complex mobility tasks decreased the diagnostic accuracy of our models, as did the inclusion of kinesiological features. Feature importance analysis revealed that Timed Up and Go (TUG) tasks to contribute the highest-yield predictive features, with only minor decreases in accuracy for models based on cognitive TUG as a single mobility task. Our machine learning approach facilitates major simplification of instrumented mobility testing without compromising predictive performance.

Multimodal Retinal Imaging Classification for Parkinson's Disease Using a Convolutional Neural Network

Purpose

Changes in retinal structure and microvasculature are connected to parallel changes in the brain. Two recent studies described machine learning algorithms trained on retinal images and quantitative data that identified Alzheimer's dementia and mild cognitive impairment with high accuracy. Prior studies also demonstrated retinal differences in individuals with PD. Herein, we developed a convolutional neural network (CNN) to classify multimodal retinal imaging from either a Parkinson's disease (PD) or control group.

Methods

We trained a CNN to receive retinal image inputs of optical coherence tomography (OCT) ganglion cell-inner plexiform layer (GC-IPL) thickness color maps, OCT angiography 6 × 6-mm en face macular images of the superficial capillary plexus, and ultra-widefield (UWF) fundus color and autofluorescence photographs to classify the retinal imaging as PD or control. The model consists of a shared pretrained VGG19 feature extractor and image-specific feature transformations which converge to a single output. Model results were assessed using receiver operating characteristic (ROC) curves and bootstrapped 95% confidence intervals for area under the ROC curve (AUC) values.

Results

In total, 371 eyes of 249 control subjects and 75 eyes of 52 PD subjects were used for training, validation, and testing. Our best CNN variant achieved an AUC of 0.918. UWF color photographs were the most effective imaging input, and GC-IPL thickness maps were the least contributory.

Conclusions

Using retinal images, our pilot CNN was able to identify individuals with PD and serves as a proof of concept to spur the collection of larger imaging datasets needed for clinical-grade algorithms.

Translational Relevance

Developing machine learning models for automated detection of Parkinson's disease from retinal imaging could lead to earlier and more widespread diagnoses.

Sjögren's syndrome and Parkinson's disease: a bidirectional Mendelian randomization study

Background

Previous epidemiological studies have reported an association between Sjögren's syndrome (SS) and Parkinson's disease (PD); however, the causality and direction of this relationship remain unclear. In this study, we aimed to investigate the causal relationship between genetically determined SS and the risk of PD using bidirectional Mendelian randomization (MR).

Methods

Summary statistics for Sjögren's syndrome used as exposure were obtained from the FinnGen database, comprising 1,290 cases and 213,145 controls. The outcome dataset for PD was derived from the United Kingdom Biobank database, including 6,998 cases and 415,466 controls. Various MR methods, such as inverse variance weighted (IVW), Mendelian randomization Egger regression (MR-Egger), weighted median (WM), simple mode, weighted mode, MR-pleiotropy residual sum and outlier (MR-PRESSO), and robust adjusted profile score (RAPS), were employed to investigate the causal effects of SS on PD. Instrumental variable strength evaluation and sensitivity analyses were conducted to ensure the reliability of the results. In addition, reverse MR analysis was performed to examine the causal effects of PD on SS.

Results

The WM, IVW, RAPS and MR-PRESSO methods demonstrated a significant association between genetically predicted SS and reduced risk of PD (odds ratio ORWM = 0.9988, ORIVW = 0.9987, ORRAPS = 0.9987, ORMR-PRESSO = 0.9987, respectively, P < 0.05). None of the MR analyses showed evidence of horizontal pleiotropy (P > 0.05) based on the MR-Egger and MR-PRESSO tests, and there was no statistical heterogeneity in the test results of the MR-Egger and IVW methods. The leave-one-out sensitivity analysis confirmed the robustness of the causal relationship between SS and PD. Furthermore, reverse MR analysis did not support any causal effects of PD on SS.

Conclusion

Our MR study supports a potential causal association between SS and a reduced risk of PD. Further extensive clinical investigations and comprehensive fundamental research are warranted to elucidate the underlying mechanisms linking SS and PD.

Exercise for People with Parkinson's Disease: Updates and Future Considerations

Parkinson's disease (PD) is now the world's fastest-growing neurological disorder with rapidly rising prevalence and increasing demand for effective health services. Recent research has focused on the importance of early diagnosis and proactive management of physical function. Accumulating evidence indicates that reduced physical activity levels and mild pre-clinical disability are present in many people prior to a clinical diagnosis, perhaps developing over years. Early referral to a physiotherapist at the time of diagnosis is now recommended in global guidelines. Multiple forms of exercise have been found to have benefits in early and mid-stage disease across a range of motor and non-motor symptoms. Evidence from longitudinal studies confirms that disability is delayed when regular exercise is sustained over long periods. Exercise is now recognized as an essential component of treatment, in combination with medical therapies. Contemporary physiotherapy interventions now combine health behavior change techniques with physical exercise to promote the development of long-term exercise adherence. Advances in technology and digital health have progressed quickly and now offer opportunities for remote assessment and monitoring, remote exercise supervision, and support adherence through feedback and motivational strategies. Recent biomedical discoveries forecast improved earlier and more accurate diagnosis of PD, allowing opportunities for earlier interventions. Current research in progress will provide important insights into the dose and intensity of aerobic exercise in PD. Physiotherapists have important roles in advocacy and education in conjunction with care delivery to support access to evidence-based care for all people with PD.

A minimally Invasive Biomarker for Sensitive and Accurate Diagnosis of Parkinson's Disease

Importance

Parkinson's disease (PD), the second most common neurodegenerative disease, is pathologically characterized by intraneuronal deposition of misfolded alpha-synuclein aggregates (αSyn D ). αSyn D seeding activities in CSF and skin samples have shown great promise in PD diagnosis, but they require invasive procedures. Sensitive and accurate αSyn D seed amplification assay (αSyn-SAA) for more accessible and minimally invasive samples (such as blood and saliva) are urgently needed for PD pathological diagnosis in routine clinical practice.

Objective

To develop a sensitive and accurate αSyn-SAA biomarker using blood and saliva samples for sensitive, accurate and minimally invasive PD diagnosis.

Design Setting and Participants

This prospective diagnostic study evaluates serum and saliva samples collected from patients clinically diagnosed with PD or healthy controls (HC) without PD at an academic Parkinson's and Movement Disorders Center from February 2020 to March 2024. Patients diagnosed with non-PD parkinsonism were excluded from this analysis. A total of 124 serum samples (82 PD and 42 HC) and 131 saliva samples (83 PD and 48 HC) were collected and examined by αSyn-SAA. Out of the 124 serum donors, a subset of 74 subjects (48 PD and 26 HC) also donated saliva samples during the same visits. PD patients with serum samples had a mean age of 69.21 years (range 44-88); HC subjects with serum samples had a mean age of 66.55 years (range 44-81); PD patients with saliva samples had a mean age of 69.58 years (range 49-87); HC subjects with saliva samples had a mean age of 64.71 years (range 30-81).

Main Outcomes and Measures

Serum and/or saliva αSyn D seeding activities from PD and HC subjects were measured by αSyn-SAA using the Real-Time Quaking-Induced Conversion (RT-QuIC) platform. These PD patients had extensive clinical assessments including MDS-UPDRS. For a subset of PD and HC subjects whose serum and saliva samples were both collected during the same visits, the αSyn D seeding activities in both samples from the same subjects were examined, and the diagnostic accuracies for PD based on the seeding activities in either sample alone or both samples together were compared.

Results

RT-QuIC analysis of αSyn D seeding activities in the 124 serum samples revealed a sensitivity of 80.49%, a specificity of 90.48%, and an accuracy of 0.9006 (AUC of ROC, 95% CI, 0.8472-0.9539, p <0.0001) for PD diagnosis. RT-QuIC analysis of αSyn D seeding activity in 131 saliva samples revealed a sensitivity of 74.70%, a specificity of 97.92%, and an accuracy of 0.8966 (AUC of ROC, 95% CI, 0.8454-0.9478, p <0.0001). When aSyn D seeding activities in the paired serum-saliva samples from the subset of 48 PD and 26 HC subjects were considered together, sensitivity was 95.83%, specificity was 96.15%, and the accuracy was 0.98 (AUC of ROC, 95% CI, 0.96-1.00, p <0.001), which are significantly better than when αSyn D seeding activities in either serum or saliva were used alone. For the paired serum-saliva samples, when specificity was set at 100% by elevating the αSyn-SAA cutoff values, a sensitivity of 91.7% and an accuracy of 0.9457 were still attained. Detailed correlation analysis revealed that αSyn D seeding activities in the serum of PD patients were correlated inversely with Montreal Cognitive Assessment (MoCA) score ( p =0.04), positively with Hamilton Depression Rating Scale (HAM-D) ( p =0.03), and weakly positively with PDQ-39 cognitive impairment score ( p =0.07). Subgroup analysis revealed that the inverse correlation with MoCA was only seen in males ( p =0.013) and weakly in the ≥70 age group ( p =0.07), and that the positive correlation with HAM-D was only seen in females ( p =0.04) and in the <70 age group ( p =0.01). In contrast, αSyn D seeding activities in the saliva of PD patients were inversely correlated with age at diagnosis ( p =0.02) and the REM sleep behavior disorder (RBD) status ( p =0.04), but subgroup analysis showed that the inverse correlation with age at diagnosis was only seen in males ( p =0.04) and in the <70 age group ( p =0.01).

Conclusion and Relevance

Our data show that concurrent RT-QuIC assay of αSyn D seeding activities in both serum and saliva can achieve high diagnostic accuracies comparable to that of CSF αSyn-SAA, suggesting that αSyn D seeding activities in serum and saliva together can potentially be used as a valuable biomarker for highly sensitive, accurate, and minimally invasive diagnosis of PD in routine clinical practice. αSyn D seeding activities in serum and saliva of PD patients correlate differentially with some clinical characteristics and in an age and sex-dependent manner.

KEY POINTS

Question: Are αSyn D seeding activities in serum and saliva together a more sensitive and accurate diagnostic PD biomarker than αSyn D seeding activities in either sample type alone? Are αSyn D seeding activities in either serum or saliva correlated with any clinical characteristics? Findings: Examinations of αSyn D seeding activities in 124 serum samples and 131 saliva samples from PD and heathy control subjects show that αSyn D seeding activities in both serum and saliva samples together can provide significantly more sensitive and accurate diagnosis of PD than either sample type alone. αSyn D seeding activities in serum or saliva exhibit varied inverse or positive correlations with some clinical features in an age and sex-dependent manner. Meaning: αSyn D seeding activities in serum and saliva together can potentially be used as a valuable pathological biomarker for highly sensitive, accurate, and minimally invasive PD diagnosis in routine clinical practice and clinical studies, and αSyn D seeding activities in serum or saliva correlate with some clinical characteristics in an age and sex-dependent manner, suggesting some possible clinical utility of quantitative serum/saliva αSyn-SAA data.

A Comprehensive Approach to Parkinson's Disease: Addressing Its Molecular, Clinical, and Therapeutic Aspects

Parkinson's disease (PD) is a gradually worsening neurodegenerative disorder affecting the nervous system, marked by a slow progression and varied symptoms. It is the second most common neurodegenerative disease, affecting over six million people in the world. Its multifactorial etiology includes environmental, genomic, and epigenetic factors. Clinical symptoms consist of non-motor and motor symptoms, with motor symptoms being the classic presentation. Therapeutic approaches encompass pharmacological, non-pharmacological, and surgical interventions. Traditional pharmacological treatment consists of administering drugs (MAOIs, DA, and levodopa), while emerging evidence explores the potential of antidiabetic agents for neuroprotection and gene therapy for attenuating parkinsonian symptoms. Non-pharmacological treatments, such as exercise, a calcium-rich diet, and adequate vitamin D supplementation, aim to slow disease progression and prevent complications. For those patients who have medically induced side effects and/or refractory symptoms, surgery is a therapeutic option. Deep brain stimulation is the primary surgical option, associated with motor symptom improvement. Levodopa/carbidopa intestinal gel infusion through percutaneous endoscopic gastrojejunostomy and a portable infusion pump succeeded in reducing "off" time, where non-motor and motor symptoms occur, and increasing "on" time. This article aims to address the general aspects of PD and to provide a comparative comprehensive review of the conventional and the latest therapeutic advancements and emerging treatments for PD. Nevertheless, further studies are required to optimize treatment and provide suitable alternatives.

Preliminary study of substantia nigra analysis by tensorial feature extraction

PURPOSE

Parkinson disease (PD) is a common progressive neurodegenerative disorder in our ageing society. Early-stage PD biomarkers are desired for timely clinical intervention and understanding of pathophysiology. Since one of the characteristics of PD is the progressive loss of dopaminergic neurons in the substantia nigra pars compacta, we propose a feature extraction method for analysing the differences in the substantia nigra between PD and non-PD patients.

METHOD

We propose a feature-extraction method for volumetric images based on a rank-1 tensor decomposition. Furthermore, we apply a feature selection method that excludes common features between PD and non-PD. We collect neuromelanin images of 263 patients: 124 PD and 139 non-PD patients and divide them into training and testing datasets for experiments. We then experimentally evaluate the classification accuracy of the substantia nigra between PD and non-PD patients using the proposed feature extraction method and linear discriminant analysis.

RESULTS

The proposed method achieves a sensitivity of 0.72 and a specificity of 0.64 for our testing dataset of 66 non-PD and 42 PD patients. Furthermore, we visualise the important patterns in the substantia nigra by a linear combination of rank-1 tensors with selected features. The visualised patterns include the ventrolateral tier, where the severe loss of neurons can be observed in PD.

CONCLUSIONS

We develop a new feature-extraction method for the analysis of the substantia nigra towards PD diagnosis. In the experiments, even though the classification accuracy with the proposed feature extraction method and linear discriminant analysis is lower than that of expert physicians, the results suggest the potential of tensorial feature extraction.

Statin use and the risk of Parkinson's disease in persons with diabetes: A nested case-control study

AIMS

Persons with diabetes may have an elevated risk of Parkinson's disease (PD). Statin use could also modify the progression of PD. The aim was to study whether there is an association between statin exposure and risk of PD in persons with diabetes.

METHODS

A nationwide, nested case-control study restricted to people with diabetes was performed as part of nationwide register-based Finnish study on PD (FINPARK). Study included 2017 PD cases and their 7934 matched controls without PD. Persons with PD were diagnosed between 1999 and 2015, and statin use (1995-2015) was determined from Prescription Register. In the main analysis, exposure at least 3 years before outcome was considered. Cumulative exposure was categorized into tertiles, and associations were analysed with conditional logistic regression (adjusted with comorbidities and number of antidiabetic drugs).

RESULTS

Prevalence of statin use was similar in PD cases and controls, with 54.2% of cases and 54.4% controls exposed before the lag time (adjusted odds ratio [aOR] = 1.03; 95% confidence interval [CI]: 0.92-1.15). Those in the highest cumulative statin exposure tertile had higher risk of PD than statin nonusers (aOR = 1.22; 95% CI: 1.04-1.43), or those in the lowest cumulative statin exposure tertile (aOR = 1.29; 95% CI: 1.07-1.57).

CONCLUSION

Our nationwide study that controlled for diabetes duration and used 3-year lag between exposure and outcome to account for reverse causality does not provide support for the hypothesis that statin use decreases the risk of PD.

Complemental Value of Microstructural and Macrostructural MRI in the Discrimination of Neurodegenerative Parkinson Syndromes

PURPOSE

Various MRI-based techniques were tested for the differentiation of neurodegenerative Parkinson syndromes (NPS); the value of these techniques in direct comparison and combination is uncertain. We thus compared the diagnostic performance of macrostructural, single compartmental, and multicompartmental MRI in the differentiation of NPS.

METHODS

We retrospectively included patients with NPS, including 136 Parkinson's disease (PD), 41 multiple system atrophy (MSA) and 32 progressive supranuclear palsy (PSP) and 27 healthy controls (HC). Macrostructural tissue probability values (TPV) were obtained by CAT12. The microstructure was assessed using a mesoscopic approach by diffusion tensor imaging (DTI), neurite orientation dispersion and density imaging (NODDI), and diffusion microstructure imaging (DMI). After an atlas-based read-out, a linear support vector machine (SVM) was trained on a training set (n = 196) and validated in an independent test cohort (n = 40). The diagnostic performance of the SVM was compared for different inputs individually and in combination.

RESULTS

Regarding the inputs separately, we observed the best diagnostic performance for DMI. Overall, the combination of DMI and TPV performed best and correctly classified 88% of the patients. The corresponding area under the receiver operating characteristic curve was 0.87 for HC, 0.97 for PD, 1.0 for MSA, and 0.99 for PSP.

CONCLUSION

We were able to demonstrate that (1) MRI parameters that approximate the microstructure provided substantial added value over conventional macrostructural imaging, (2) multicompartmental biophysically motivated models performed better than the single compartmental DTI and (3) combining macrostructural and microstructural information classified NPS and HC with satisfactory performance, thus suggesting a complementary value of both approaches.

Long-Term Follow-Up of the LEAP Study: Early Versus Delayed Levodopa in Early Parkinson's Disease

BACKGROUND AND OBJECTIVE

The Levodopa in EArly Parkinson's disease study showed no effect of earlier versus later levodopa initiation on Parkinson's disease (PD) progression over 80 weeks. We now report the effects over 5 years.

METHODS

The Levodopa in EArly Parkinson's disease study randomly assigned patients to levodopa/carbidopa 300/75 mg daily for 80 weeks (early start) or to placebo for 40 weeks followed by levodopa/carbidopa 300/75 mg daily for 40 weeks (delayed start). Follow-up visits were performed 3 and 5 years after baseline. We assessed the between-group differences in terms of square root transformed total Unified Parkinson's Disease Rating Scale score at 3 and 5 years with linear regression. We compared the prevalence of dyskinesia, prevalence of wearing off, and the levodopa equivalent daily dose.

RESULTS

A total of 321 patients completed the 5-year visit. The adjusted square root transformed total Unified Parkinson's Disease Rating Scale did not differ between treatment groups at 3 (estimated difference, 0.17; standard error, 0.13; P = 0.18) and 5 years (estimated difference, 0.24; standard error, 0.13; P = 0.07). At 5 years, 46 of 160 patients in the early-start group and 62 of 161 patients in the delayed-start group experienced dyskinesia (P = 0.06). The prevalence of wearing off and the levodopa equivalent daily dose were not significantly different between groups.

CONCLUSIONS

We did not find a difference in disease progression or in prevalence of motor complications between patients with early PD starting treatment with a low dose of levodopa 40 weeks earlier versus 40 weeks later over the subsequent 5 years. © 2024 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Metacognitive accuracy differences in Parkinson's disease and REM sleep behavioral disorder relative to healthy controls

Background

Metacognition is the ability to monitor and self-assess cognitive performance. It can be impaired in neurodegenerative diseases, with implications for daily function, and the ability of patients to reliably report their symptoms to health professionals. However, metacognition has not been systematically assessed in early-mid stage Parkinson's disease (PD) and REM sleep behavioral disorder (RBD), a prodrome of PD.

Objectives

This study aimed to evaluate metacognitive accuracy and self-confidence in PD and RBD patients across various cognitive tasks.

Methods

We conducted detailed computerized cognitive assessments with 19 cognitive tasks within an established PD and RBD cohort. Participants self-rated their performance post-task. Metacognitive accuracy was calculated by comparing these ratings against objective performance and further analyzed against clinical and mental health factors.

Results

PD and RBD patients' metacognitive accuracy aligned with control subjects. However, they exhibited lower confidence across cognitive domains, reflecting their reduced cognitive performance. A notable inverse correlation was observed between their confidence and MDS-UPDRS I and II scales and HADS anxiety and depression scores.

Conclusion

Our findings indicate that patients with early to mid-stage PD and RBD are generally aware of their cognitive status, differing from other neurological disorders. The inverse relationship between patient confidence and symptoms of depression, anxiety, and daily life challenges underscores the impact of emotional and functional difficulties on their self-perception of cognitive abilities. This insight could be significant for understanding how these conditions affect mental health, aiding clinicians in developing more effective patient care strategies.

Multimodal imaging and electrophysiological study in the differential diagnosis of rest tremor

Introduction

Distinguishing tremor-dominant Parkinson's disease (tPD) from essential tremor with rest tremor (rET) can be challenging and often requires dopamine imaging. This study aimed to differentiate between these two diseases through a machine learning (ML) approach based on rest tremor (RT) electrophysiological features and structural MRI data.

Methods

We enrolled 72 patients including 40 tPD patients and 32 rET patients, and 45 control subjects (HC). RT electrophysiological features (frequency, amplitude, and phase) were calculated using surface electromyography (sEMG). Several MRI morphometric variables (cortical thickness, surface area, cortical/subcortical volumes, roughness, and mean curvature) were extracted using Freesurfer. ML models based on a tree-based classification algorithm termed XGBoost using MRI and/or electrophysiological data were tested in distinguishing tPD from rET patients.

Results

Both structural MRI and sEMG data showed acceptable performance in distinguishing the two patient groups. Models based on electrophysiological data performed slightly better than those based on MRI data only (mean AUC: 0.92 and 0.87, respectively; p = 0.0071). The top-performing model used a combination of sEMG features (amplitude and phase) and MRI data (cortical volumes, surface area, and mean curvature), reaching AUC: 0.97 ± 0.03 and outperforming models using separately either MRI (p = 0.0001) or EMG data (p = 0.0231). In the best model, the most important feature was the RT phase.

Conclusion

Machine learning models combining electrophysiological and MRI data showed great potential in distinguishing between tPD and rET patients and may serve as biomarkers to support clinicians in the differential diagnosis of rest tremor syndromes in the absence of expensive and invasive diagnostic procedures such as dopamine imaging.

Integrated Bioinformatics Analysis for Revealing CBL is a Potential Diagnosing Biomarker and Related Immune Infiltration in Parkinson's Disease

Purpose

There is growing evidence that the immune system plays an important role in the progression of Parkinson's disease, the second most common neurodegenerative disorder. This study aims to address the comprehensive understanding of the immunopathogenesis of Parkinson's disease and explore new inflammatory biomarkers.

Patients and Methods

In this study, Immune-related differential expressed genes (DEIRGs) were obtained from GEO database and Immport database. The hub gene was screened in DEIRGs using LASSO regression and random forest algorithm, and the mRNA expression of the identified hub gene was validated using clinical blood samples.

Results

We obtained a total of 157 DEIRGs that played an important role in the immune response. The results of immune cell infiltration analysis showed that the degree of memory B cells infiltration was higher in PD patients, while the degree of Monocytes, resting mast cells and M0 macrophages infiltration was lower (p<0.05). A total of 8 hub genes were screened by machine learning methods, and RT-PCR results showed that the expression level of CBL gene in PD was significantly increased (p<0.05).

Conclusion

Our findings suggest that CBL is a new potential diagnostic biomarker for PD and that abnormal immune cell infiltration may influence PD development.

Single-molecule characterization of salivary protein aggregates from Parkinson's disease patients: a pilot study

Saliva is a convenient and accessible biofluid that has potential as a future diagnostic tool for Parkinson's disease. Candidate diagnostic tests for Parkinson's disease to date have predominantly focused on measurements of α-synuclein in CSF, but there is a need for accurate tests utilizing more easily accessible sample types. Prior studies utilizing saliva have used bulk measurements of salivary α-synuclein to provide diagnostic insight. Aggregate structure may influence the contribution of α-synuclein to disease pathology. Single-molecule approaches can characterize the structure of individual aggregates present in the biofluid and may, therefore, provide greater insight than bulk measurements. We have employed an antibody-based single-molecule pulldown assay to quantify salivary α-synuclein and amyloid-β peptide aggregate numbers and subsequently super-resolved captured aggregates using direct Stochastic Optical Reconstruction Microscopy to describe their morphological features. We show that the salivary α-synuclein aggregate/amyloid-β aggregate ratio is increased almost 2-fold in patients with Parkinson's disease (n = 20) compared with controls (n = 20, P < 0.05). Morphological information also provides insight, with saliva from patients with Parkinson's disease containing a greater proportion of larger and more fibrillar amyloid-β aggregates than control saliva (P < 0.05). Furthermore, the combination of count and morphology data provides greater diagnostic value than either measure alone, distinguishing between patients with Parkinson's disease (n = 17) and controls (n = 18) with a high degree of accuracy (area under the curve = 0.87, P < 0.001) and a larger dynamic range. We, therefore, demonstrate for the first time the application of highly sensitive single-molecule imaging techniques to saliva. In addition, we show that aggregates present within saliva retain relevant structural information, further expanding the potential utility of saliva-based diagnostic methods.

Machine Learning Models for Parkinson Disease: Systematic Review

Background

With the increasing availability of data, computing resources, and easier-to-use software libraries, machine learning (ML) is increasingly used in disease detection and prediction, including for Parkinson disease (PD). Despite the large number of studies published every year, very few ML systems have been adopted for real-world use. In particular, a lack of external validity may result in poor performance of these systems in clinical practice. Additional methodological issues in ML design and reporting can also hinder clinical adoption, even for applications that would benefit from such data-driven systems.

Objective

To sample the current ML practices in PD applications, we conducted a systematic review of studies published in 2020 and 2021 that used ML models to diagnose PD or track PD progression.

Methods

We conducted a systematic literature review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines in PubMed between January 2020 and April 2021, using the following exact string: "Parkinson's" AND ("ML" OR "prediction" OR "classification" OR "detection" or "artificial intelligence" OR "AI"). The search resulted in 1085 publications. After a search query and review, we found 113 publications that used ML for the classification or regression-based prediction of PD or PD-related symptoms.

Results

Only 65.5% (74/113) of studies used a holdout test set to avoid potentially inflated accuracies, and approximately half (25/46, 54%) of the studies without a holdout test set did not state this as a potential concern. Surprisingly, 38.9% (44/113) of studies did not report on how or if models were tuned, and an additional 27.4% (31/113) used ad hoc model tuning, which is generally frowned upon in ML model optimization. Only 15% (17/113) of studies performed direct comparisons of results with other models, severely limiting the interpretation of results.

Conclusions

This review highlights the notable limitations of current ML systems and techniques that may contribute to a gap between reported performance in research and the real-life applicability of ML models aiming to detect and predict diseases such as PD.

Machine learning for the detection and diagnosis of cognitive impairment in Parkinson's Disease: A systematic review

BACKGROUND

Parkinson's Disease is the second most common neurological disease in over 60s. Cognitive impairment is a major clinical symptom, with risk of severe dysfunction up to 20 years post-diagnosis. Processes for detection and diagnosis of cognitive impairments are not sufficient to predict decline at an early stage for significant impact. Ageing populations, neurologist shortages and subjective interpretations reduce the effectiveness of decisions and diagnoses. Researchers are now utilising machine learning for detection and diagnosis of cognitive impairment based on symptom presentation and clinical investigation. This work aims to provide an overview of published studies applying machine learning to detecting and diagnosing cognitive impairment, evaluate the feasibility of implemented methods, their impacts, and provide suitable recommendations for methods, modalities and outcomes.

METHODS

To provide an overview of the machine learning techniques, data sources and modalities used for detection and diagnosis of cognitive impairment in Parkinson's Disease, we conducted a review of studies published on the PubMed, IEEE Xplore, Scopus and ScienceDirect databases. 70 studies were included in this review, with the most relevant information extracted from each. From each study, strategy, modalities, sources, methods and outcomes were extracted.

RESULTS

Literatures demonstrate that machine learning techniques have potential to provide considerable insight into investigation of cognitive impairment in Parkinson's Disease. Our review demonstrates the versatility of machine learning in analysing a wide range of different modalities for the detection and diagnosis of cognitive impairment in Parkinson's Disease, including imaging, EEG, speech and more, yielding notable diagnostic accuracy.

CONCLUSIONS

Machine learning based interventions have the potential to glean meaningful insight from data, and may offer non-invasive means of enhancing cognitive impairment assessment, providing clear and formidable potential for implementation of machine learning into clinical practice.

The rise of Parkinson's disease is a global challenge, but efforts to tackle this must begin at a national level: a protocol for national digital screening and "eat, move, sleep" lifestyle interventions to prevent or slow the rise of non-communicable diseases in Thailand

The rising prevalence of Parkinson's disease (PD) globally presents a significant public health challenge for national healthcare systems, particularly in low-to-middle income countries, such as Thailand, which may have insufficient resources to meet these escalating healthcare needs. There are also many undiagnosed cases of early-stage PD, a period when therapeutic interventions would have the most value and least cost. The traditional "passive" approach, whereby clinicians wait for patients with symptomatic PD to seek treatment, is inadequate. Proactive, early identification of PD will allow timely therapeutic interventions, and digital health technologies can be scaled up in the identification and early diagnosis of cases. The Parkinson's disease risk survey (TCTR20231025005) aims to evaluate a digital population screening platform to identify undiagnosed PD cases in the Thai population. Recognizing the long prodromal phase of PD, the target demographic for screening is people aged ≥ 40 years, approximately 20 years before the usual emergence of motor symptoms. Thailand has a highly rated healthcare system with an established universal healthcare program for citizens, making it ideal for deploying a national screening program using digital technology. Designed by a multidisciplinary group of PD experts, the digital platform comprises a 20-item questionnaire about PD symptoms along with objective tests of eight digital markers: voice vowel, voice sentences, resting and postural tremor, alternate finger tapping, a "pinch-to-size" test, gait and balance, with performance recorded using a mobile application and smartphone's sensors. Machine learning tools use the collected data to identify subjects at risk of developing, or with early signs of, PD. This article describes the selection and validation of questionnaire items and digital markers, with results showing the chosen parameters and data analysis methods to be robust, reliable, and reproducible. This digital platform could serve as a model for similar screening strategies for other non-communicable diseases in Thailand.

Systematic genome-wide Mendelian randomization reveals the causal links between miRNAs and Parkinson's disease

Background

MicroRNAs (miRNAs) have pivotal roles in gene regulation. Circulating miRNAs have been developed as novel candidate non-invasive biomarkers for diagnosis, prognosis, and treatment response for diseases. However, miRNAs that have causal effects on Parkinson's Disease (PD) remain largely unknown. To investigate the causal relationships between miRNAs and PD, here we conduct a Mendelian randomization (MR) study.

Methods

This study utilized the summary-level data of respective genome-wide association studies (GWAS) for 2083 miRNAs and seven PD-related outcomes to comprehensively reveal the causal associations between the circulating miRNAs and PD. Two-sample MR design was deployed and the causal effects were estimated with inverse variance weighted, MR-Egger, and weighted median. Comprehensively sensitive analyses were followed, including Cochran's Q test, MR-Egger intercept test, MR-PRESSO, and leave-one-out analysis, to validate the robustness of our results. Finally, we investigated the potential role of the MR significant miRNAs by predicting their target genes and functional enrichment analysis.

Results

Inverse variance weighted estimates suggested that two miRNAs, miR-205-5p (β = -0.46, 95%CI: -0.690 to -0.229, p = 9.3 × 10-5) and miR-6800-5p (β = -0.389, 95%CI: -0.575 to -0.202, p = 4.32 × 10-5), significantly decreased the rate of cognitive decline among PD patients. In addition, eight miRNAs were nominally associated with more than three PD-related outcomes each. No significant heterogeneity of instrumental variables or horizontal pleiotropy was found. Gene Ontology (GO) analysis showed that the targets of these causal miRNAs were significantly enriched in cell cycle, apoptotic, and aging pathways.

Conclusion

This MR study identified two miRNAs whose genetically regulated expression might have a causal role in the development of PD dementia. Our findings provided potential miRNA biomarkers to make better and early diagnoses and risk assessments of PD.

Pose-based tremor type and level analysis for Parkinson's disease from video

PURPOSE

Current methods for diagnosis of PD rely on clinical examination. The accuracy of diagnosis ranges between 73 and 84%, and is influenced by the experience of the clinical assessor. Hence, an automatic, effective and interpretable supporting system for PD symptom identification would support clinicians in making more robust PD diagnostic decisions.

METHODS

We propose to analyze Parkinson's tremor (PT) to support the analysis of PD, since PT is one of the most typical symptoms of PD with broad generalizability. To realize the idea, we present SPA-PTA, a deep learning-based PT classification and severity estimation system that takes consumer-grade videos of front-facing humans as input. The core of the system is a novel attention module with a lightweight pyramidal channel-squeezing-fusion architecture that effectively extracts relevant PT information and filters noise. It enhances modeling performance while improving system interpretability.

RESULTS

We validate our system via individual-based leave-one-out cross-validation on two tasks: the PT classification task and the tremor severity rating estimation task. Our system presents a 91.3% accuracy and 80.0% F1-score in classifying PT with non-PT class, while providing a 76.4% accuracy and 76.7% F1-score in more complex multiclass tremor rating classification task.

CONCLUSION

Our system offers a cost-effective PT classification and tremor severity estimation results as warning signs of PD for undiagnosed patients with PT symptoms. In addition, it provides a potential solution for supporting PD diagnosis in regions with limited clinical resources.

How close are we to a breakthrough? The hunt for blood biomarkers in Parkinson's disease diagnosis

Parkinson's disease (PD), being the second largest neurodegenerative disease, poses challenges in early detection, resulting in a lack of timely treatment options to effectively manage the disease. By the time clinical diagnosis becomes possible, more than 60% of dopamine neurons in the substantia nigra (SN) of patients have already degenerated. Therefore, early diagnosis or identification of warning signs is crucial for the prompt and timely beginning of the treatment. However, conducting invasive or complex diagnostic procedures on asymptomatic patients can be challenging, making routine blood tests a more feasible approach in such cases. Numerous studies have been conducted over an extended period to search for effective diagnostic biomarkers in blood samples. However, thus far, no highly effective biomarkers have been confirmed. Besides classical proteins like α-synuclein (α-syn), phosphorylated α-syn and oligomeric α-syn, other molecules involved in disease progression should also be given equal attention. In this review, we will not only discuss proposed biomarkers that are currently under investigation but also delve into the mechanisms underlying the disease, focusing on processes such as α-syn misfolding, intercellular transmission and the crossing of the blood-brain barrier (BBB). Our aim is to provide an updated overview of molecules based on these processes that may potentially serve as blood biomarkers.

The comorbidity profiles and medication issues of patients with multiple system atrophy: a systematic cross-sectional analysis

BACKGROUND

Multiple system atrophy (MSA) is a complex and fatal neurodegenerative movement disorder. Understanding the comorbidities and drug therapy is crucial for MSA patients' safety and management.

OBJECTIVES

To investigate the pattern of comorbidities and aspects of drug therapy in MSA patients.

METHODS

Cross-sectional data of MSA patients according to Gilman et al. (2008) diagnostic criteria and control patients without neurodegenerative diseases (non-ND) were collected from German, multicenter cohorts. The prevalence of comorbidities according to WHO ICD-10 classification and drugs administered according to WHO ATC system were analyzed. Potential drug-drug interactions were identified using AiDKlinik®.

RESULTS

The analysis included 254 MSA and 363 age- and sex-matched non-ND control patients. MSA patients exhibited a significantly higher burden of comorbidities, in particular diseases of the genitourinary system. Also, more medications were prescribed MSA patients, resulting in a higher prevalence of polypharmacy. Importantly, the risk of potential drug-drug interactions, including severe interactions and contraindicated combinations, was elevated in MSA patients. When comparing MSA-P and MSA-C subtypes, MSA-P patients suffered more frequently from diseases of the genitourinary system and diseases of the musculoskeletal system and connective tissue.

CONCLUSIONS

MSA patients face a substantial burden of comorbidities, notably in the genitourinary system. This, coupled with increased polypharmacy and potential drug interactions, highlights the complexity of managing MSA patients. Clinicians should carefully consider these factors when devising treatment strategies for MSA patients.

Wearable sensor devices can automatically identify the ON-OFF status of patients with Parkinson's disease through an interpretable machine learning model

Introduction

Accurately and objectively quantifying the clinical features of Parkinson's disease (PD) is crucial for assisting in diagnosis and guiding the formulation of treatment plans. Therefore, based on the data on multi-site motor features, this study aimed to develop an interpretable machine learning (ML) model for classifying the "OFF" and "ON" status of patients with PD, as well as to explore the motor features that are most associated with changes in clinical symptoms.

Methods

We employed a support vector machine with a recursive feature elimination (SVM-RFE) algorithm to select promising motion features. Subsequently, 12 ML models were constructed based on these features, and we identified the model with the best classification performance. Then, we used the SHapley Additive exPlanations (SHAP) and the Local Interpretable Model agnostic Explanations (LIME) methods to explain the model and rank the importance of those motor features.

Results

A total of 96 patients were finally included in this study. The naive Bayes (NB) model had the highest classification performance (AUC = 0.956; sensitivity = 0.8947, 95% CI 0.6686-0.9870; accuracy = 0.8421, 95% CI 0.6875-0.9398). Based on the NB model, we analyzed the importance of eight motor features toward the classification results using the SHAP algorithm. The Gait: range of motion (RoM) Shank left (L) (degrees) [Mean] might be the most important motor feature for all classification horizons.

Conclusion

The symptoms of PD could be objectively quantified. By utilizing suitable motor features to construct ML models, it became possible to intelligently identify whether patients with PD were in the "ON" or "OFF" status. The variations in these motor features were significantly correlated with improvement rates in patients' quality of life. In the future, they might act as objective digital biomarkers to elucidate the changes in symptoms observed in patients with PD and might be used to assist in the diagnosis and treatment of patients with PD.

The connection of motor improvement after deep brain stimulation in Parkinson's disease and microstructural integrity of the substantia nigra and subthalamic nucleus

BACKGROUND

Nigrostriatal microstructural integrity has been suggested as a biomarker for levodopa response in Parkinson's disease (PD), which is a strong predictor for motor response to deep brain stimulation (DBS) of the subthalamic nucleus (STN). This study aimed to explore the impact of microstructural integrity of the substantia nigra (SN), STN, and putamen on motor response to STN-DBS using diffusion microstructure imaging.

METHODS

Data was collected from 23 PD patients (mean age 63 ± 7, 6 females) who underwent STN-DBS, had preoperative 3 T diffusion magnetic resonance imaging including multishell diffusion-weighted MRI with b-values of 1000 and 2000 s/mm2 and records of motor improvement available.

RESULTS

The association between a poorer DBS-response and increased free interstitial fluid showed notable effect sizes (rho > |0.4|) in SN and STN, but not in putamen. However, this did not reach significance after Bonferroni correction and controlling for sex and age.

CONCLUSION

Microstructural integrity of SN and STN are potential biomarkers for the prediction of therapy efficacy following STN-DBS, but further studies are required to confirm these associations.

Analysis of biomarkers in speculative CNS-enriched extracellular vesicles for parkinsonian disorders: a comprehensive systematic review and diagnostic meta-analysis

BACKGROUND AND OBJECTIVE

Parkinsonian disorders, including Parkinson's disease (PD), multiple system atrophy (MSA), dementia with Lewy bodies (DLB), progressive supranuclear palsy (PSP), and corticobasal syndrome (CBS), exhibit overlapping early-stage symptoms, complicating definitive diagnosis despite heterogeneous cellular and regional pathophysiology. Additionally, the progression and the eventual conversion of prodromal conditions such as REM behavior disorder (RBD) to PD, MSA, or DLB remain challenging to predict. Extracellular vesicles (EVs) are small, membrane-enclosed structures released by cells, playing a vital role in communicating cell-state-specific messages. Due to their ability to cross the blood-brain barrier into the peripheral circulation, measuring biomarkers in blood-isolated speculative CNS enriched EVs has become a popular diagnostic approach. However, replication and independent validation remain challenging in this field. Here, we aimed to evaluate the diagnostic accuracy of speculative CNS-enriched EVs for parkinsonian disorders.

METHODS

We conducted a PRISMA-guided systematic review and meta-analysis, covering 18 studies with a total of 1695 patients with PD, 253 with MSA, 21 with DLB, 172 with PSP, 152 with CBS, 189 with RBD, and 1288 HCs, employing either hierarchical bivariate models or univariate models based on study size.

RESULTS

Diagnostic accuracy was moderate for differentiating patients with PD from HCs, but revealed high heterogeneity and significant publication bias, suggesting an inflation of the perceived diagnostic effectiveness. The bias observed indicates that studies with non-significant or lower effect sizes were less likely to be published. Although results for differentiating patients with PD from those with MSA or PSP and CBS appeared promising, their validity is limited due to the small number of involved studies coming from the same research group. Despite initial reports, our analyses suggest that using speculative CNS-enriched EV biomarkers may not reliably differentiate patients with MSA from HCs or patients with RBD from HCs, due to their lesser accuracy and substantial variability among the studies, further complicated by substantial publication bias.

CONCLUSION

Our findings underscore the moderate, yet unreliable diagnostic accuracy of biomarkers in speculative CNS-enriched EVs in differentiating parkinsonian disorders, highlighting the presence of substantial heterogeneity and significant publication bias. These observations reinforce the need for larger, more standardized, and unbiased studies to validate the utility of these biomarkers but also call for the development of better biomarkers for parkinsonian disorders.

Structural neuroimaging markers of normal pressure hydrocephalus versus Alzheimer's dementia and Parkinson's disease, and hydrocephalus versus atrophy in chronic TBI-a narrative review

Introduction

Normal Pressure Hydrocephalus (NPH) is a prominent type of reversible dementia that may be treated with shunt surgery, and it is crucial to differentiate it from irreversible degeneration caused by its symptomatic mimics like Alzheimer's Dementia (AD) and Parkinson's Disease (PD). Similarly, it is important to distinguish between (normal pressure) hydrocephalus and irreversible atrophy/degeneration which are among the chronic effects of Traumatic Brain Injury (cTBI), as the former may be reversed through shunt placement. The purpose of this review is to elucidate the structural imaging markers which may be foundational to the development of accurate, noninvasive, and accessible solutions to this problem.

Methods

By searching the PubMed database for keywords related to NPH, AD, PD, and cTBI, we reviewed studies that examined the (1) distinct neuroanatomical markers of degeneration in NPH versus AD and PD, and atrophy versus hydrocephalus in cTBI and (2) computational methods for their (semi-) automatic assessment on Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) scans.

Results

Structural markers of NPH and those that can distinguish it from AD have been well studied, but only a few studies have explored its structural distinction between PD. The structural implications of cTBI over time have been studied. But neuroanatomical markers that can predict shunt response in patients with either symptomatic idiopathic NPH or post-traumatic hydrocephalus have not been reliably established. MRI-based markers dominate this field of investigation as compared to CT, which is also reflected in the disproportionate number of MRI-based computational methods for their automatic assessment.

Conclusion

Along with an up-to-date literature review on the structural neurodegeneration due to NPH versus AD/PD, and hydrocephalus versus atrophy in cTBI, this article sheds light on the potential of structural imaging markers as (differential) diagnostic aids for the timely recognition of patients with reversible (normal pressure) hydrocephalus, and opportunities to develop computational tools for their objective assessment.

Association of peripheral immune activation with amyotrophic lateral sclerosis and Parkinson's disease: A systematic review and meta-analysis

BACKGROUND

Recent studies have revealed the link between immune activation and neurodegenerative diseases.

METHODS

By employing meta-analysis, we estimated the standardized mean difference (SMD) and their corresponding 95% confidence intervals (CIs) between the groups.

RESULTS

According to the pre-set criteria, a total of 21 published articles including 2377 ALS patients and 1244 HCs, as well as 60 articles including 5111 PD patients and 4237 HCs, were identified. This study provided evidence of peripheral immune activation in the pathogenesis of ALS and PD.

CONCLUSION

Our results suggested monitoring changes in peripheral blood immune cell populations, particularly lymphocyte subsets, will benefit understanding the developments and exploring reliable and specific biomarkers of these two diseases.

Connecting the Dots: Exploring the Relationship between Optical Coherence Tomography and 99mTc-TRODAT-1 SPECT Parameters in Parkinson's Disease

Background and Objective

While optical coherence tomography (OCT) is explored as a potential biomarker in Parkinson's disease (PD), technetium-99m-labeled tropane derivative (99mTc-TRODAT-1) single-photon emission computed tomography (SPECT) imaging has a proven role in diagnosing PD. Our objective was to compare the OCT parameters in PD patients and healthy controls (HCs) and correlate them with 99mTc-TRODAT-1 parameters in PD patients.

Materials and Methods

This cross-sectional study included 30 PD patients and 30 age- and gender-matched HCs. Demographic data, PD details including Movement Disorders Society Unified Parkinson's Disease Rating Scale-III (MDS-UPDRS-III) and Hoehn-Yahr (HY) staging, and OCT parameters including macular and peripapillary retinal nerve fiber layer (RNFL) thickness in bilateral eyes were recorded. PD patients underwent 99mTc-TRODAT-1 SPECT imaging. The terms "ipsilateral" and "contralateral" were used with reference to more severely affected body side in PD patients and compared with corresponding sides in HCs.

Results

PD patients showed significant ipsilateral superior parafoveal quadrant (mean ± standard deviation [SD] = 311.10 ± 15.90 vs. 297.57 ± 26.55, P = 0.02) and contralateral average perifoveal (mean ± SD = 278.75 ± 18.97 vs. 269.08 ± 16.91, P = 0.04) thinning compared to HCs. Peripapillary RNFL parameters were comparable between PD patients and HCs. MDS-UPDRS-III score and HY stage were inversely correlated to both ipsilateral (Spearman rho = -0.52, P = 0.003; Spearman rho = -0.47, P = 0.008) and contralateral (Spearman rho = -0.53, P = 0.002; Spearman rho = -0.58, P < 0.001) macular volumes, respectively. PD duration was inversely correlated with ipsilateral temporal parafoveal thickness (ρ = -0.41, P = 0.02). No correlation was observed between OCT and 99mTc-TRODAT-1 SPECT parameters in PD patients.

Conclusion

Compared to HCs, a significant thinning was observed in the ipsilateral superior parafoveal quadrant and the contralateral average perifoveal region in PD patients. Macular volume and ipsilateral temporal parafoveal thickness were inversely correlated with disease severity and duration, respectively. OCT and 99mTc-TRODAT-1 SPECT parameters failed to correlate in PD patients.

Subspace corrected relevance learning with application in neuroimaging

In machine learning, data often comes from different sources, but combining them can introduce extraneous variation that affects both generalization and interpretability. For example, we investigate the classification of neurodegenerative diseases using FDG-PET data collected from multiple neuroimaging centers. However, data collected at different centers introduces unwanted variation due to differences in scanners, scanning protocols, and processing methods. To address this issue, we propose a two-step approach to limit the influence of center-dependent variation on the classification of healthy controls and early vs. late-stage Parkinson's disease patients. First, we train a Generalized Matrix Learning Vector Quantization (GMLVQ) model on healthy control data to identify a "relevance space" that distinguishes between centers. Second, we use this space to construct a correction matrix that restricts a second GMLVQ system's training on the diagnostic problem. We evaluate the effectiveness of this approach on the real-world multi-center datasets and simulated artificial dataset. Our results demonstrate that the approach produces machine learning systems with reduced bias - being more specific due to eliminating information related to center differences during the training process - and more informative relevance profiles that can be interpreted by medical experts. This method can be adapted to similar problems outside the neuroimaging domain, as long as an appropriate "relevance space" can be identified to construct the correction matrix.

Artificial intelligence-based video monitoring of movement disorders in the elderly: a review on current and future landscapes

ABSTRACT

Due to global ageing, the burden of chronic movement and neurological disorders (Parkinson's disease and essential tremor) is rapidly increasing. Current diagnosis and monitoring of these disorders rely largely on face-to-face assessments utilising clinical rating scales, which are semi-subjective and time-consuming. To address these challenges, the utilisation of artificial intelligence (AI) has emerged. This review explores the advantages and challenges associated with using AI-driven video monitoring to care for elderly patients with movement disorders. The AI-based video monitoring systems offer improved efficiency and objectivity in remote patient monitoring, enabling real-time analysis of data, more uniform outcomes and augmented support for clinical trials. However, challenges, such as video quality, privacy compliance and noisy training labels, during development need to be addressed. Ultimately, the advancement of video monitoring for movement disorders is expected to evolve towards discreet, home-based evaluations during routine daily activities. This progression must incorporate data security, ethical considerations and adherence to regulatory standards.

A fast and non-invasive artificial intelligence olfactory-like system that aids diagnosis of Parkinson's disease

BACKGROUND AND PURPOSE

Several previous studies have shown that skin sebum analysis can be used to diagnose Parkinson's disease (PD). The aim of this study was to develop a portable artificial intelligence olfactory-like (AIO) system based on gas chromatographic analysis of the volatile organic compounds (VOCs) in patient sebum and explore its application value in the diagnosis of PD.

METHODS

The skin VOCs from 121 PD patients and 129 healthy controls were analyzed using the AIO system and three classic machine learning models were established, including the gradient boosting decision tree (GBDT), random forest and extreme gradient boosting, to assist the diagnosis of PD and predict its severity.

RESULTS

A 20-s time series of AIO system data were collected from each participant. The VOC peaks at a large number of time points roughly concentrated around 5-12 s were significantly higher in PD subjects. The gradient boosting decision tree model showed the best ability to differentiate PD from healthy controls, yielding a sensitivity of 83.33% and a specificity of 84.00%. However, the system failed to predict PD progression scored by Hoehn-Yahr stage.

CONCLUSIONS

This study provides a fast, low-cost and non-invasive method to distinguish PD patients from healthy controls. Furthermore, our study also indicates abnormal sebaceous gland secretion in PD patients, providing new evidence for exploring the pathogenesis of PD.

The association between plasma GPNMB and Parkinson's disease and multiple system atrophy

AIMS

Parkinson's disease (PD), as the second most common neurodegenerative disorder, often presents diagnostic challenges in differentiation from other forms of Parkinsonism. Recent studies have reported an association between plasma glycoprotein nonmetastatic melanoma protein B (pGPNMB) and PD.

METHODS

A retrospective study was conducted, comprising 401 PD patients, 111 multiple system atrophy (MSA) patients, 13 progressive supranuclear palsy (PSP) patients and 461 healthy controls from the Chinese Han population, with an assessment of pGPNMB levels.

RESULTS

The study revealed that pGPNMB concentrations were significantly lower in PD and MSA patients compared to controls (area under the receiver operating characteristics curve (AUC) 0.62 and 0.74, respectively, P < 0.0001 for both), but no difference was found in PSP patients compared to controls (P > 0.05). Interestingly, the level of pGPNMB was significantly higher in PD patients than in MSA patients (AUC = 0.63, P < 0.0001). Furthermore, the study explored the association between pGPNMB levels and disease severity in PD and MSA patients, revealing a positive correlation in PD patients but not in MSA patients with both disease severity and cognitive impairment.

CONCLUSION

This study successfully replicated prior findings, demonstrating an association between pGPNMB levels and disease severity, and also identified a correlation with cognitive impairment in PD patients of the Chinese Han population. Additionally, this study is the first to identify a significant difference in pGPNMB levels between MSA, PD, and normal controls. The data provide new evidence supporting the potential role of pGPNMB in the diagnosis and differential diagnosis of Parkinsonism.