Association between neutrophil-to-lymphocyte ratio and motor subtypes in idiopathic Parkinson's disease: a prospective observational study.

BACKGROUND: Peripheral immunity and neuroinflammation interact with each other and they play important roles in the pathophysiology of idiopathic Parkinson's disease (IPD). There have been very few real-world reports on the relationship between peripheral immune inflammation and motor phenotypes of IPD. This study aimed to investigate the potential correlation between peripheral inflammatory indicators and motor subtypes in patients with IPD. METHODS: This observational, prospective case-control study examined patients with IPD and healthy controls (HC) matched for age and sex between September 2021 and July 2023 at the Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University. The levels of peripheral inflammatory indicators were collected from each patient with IPD and HCs. Differences in the levels of peripheral inflammatory indicators among groups were compared. Binary logistic regression analysis was used to explore the inflammatory mechanism underlying the motor subtype of IPD. RESULTS: A total number of 94 patients with IPD were recruited at the Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University between September 2021 and July 2023, including 49 males and 45 females, and 37 healthy volunteers matched for age and sex were also enrolled as the control group. Of the 94 patients with IPD, 42.6% performed as the TD motor subtype and 57.4% performed as the AR motor subtype. NLR and the plasma levels of IL-1ßand TNF-α in the IPD group were higher than those in the HC group (P < 0.05). The disease duration, Hoehn and Yahr (H-Y) stage, NLR, and the levels of IL-1ß in the AR group were higher than those in the TD group (P < 0.05). Additionally, IL-1ß plasma levels and NLR were positively correlated with disease duration, H-Y stage, movement disorder society-Unified Parkinson's Disease Rating Scale-III motor score, and AR subtype. The binary logistic regression model revealed that the plasma level of IL-1ß was mildly associated with the AR motor subtype and NLR was strongly associated with the AR motor subtype. The combination of NLR and IL-1ß showed better performance in identifying the AR motor subtype. CONCLUSION: NLR is strongly associated with the AR motor subtype in IPD, and peripheral immunity is probably involved in the pathogenesis of AR motor subtype in IPD.

CNN-Based Neurodegenerative Disease Classification Using QR-Represented Gait Data.

PURPOSE: The primary aim of this study is to develop an effective and reliable diagnostic system for neurodegenerative diseases by utilizing gait data transformed into QR codes and classified using convolutional neural networks (CNNs). The objective of this method is to enhance the precision of diagnosing neurodegenerative diseases, including amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD), through the introduction of a novel approach to analyze gait patterns. METHODS: The research evaluates the CNN-based classification approach using QR-represented gait data to address the diagnostic challenges associated with neurodegenerative diseases. The gait data of subjects were converted into QR codes, which were then classified using a CNN deep learning model. The dataset includes recordings from patients with Parkinson's disease (n = 15), Huntington's disease (n = 20), and amyotrophic lateral sclerosis (n = 13), and from 16 healthy controls. RESULTS: The accuracy rates obtained through 10-fold cross-validation were as follows: 94.86% for NDD versus control, 95.81% for PD versus control, 93.56% for HD versus control, 97.65% for ALS versus control, and 84.65% for PD versus HD versus ALS versus control. These results demonstrate the potential of the proposed system in distinguishing between different neurodegenerative diseases and control groups. CONCLUSION: The results indicate that the designed system may serve as a complementary tool for the diagnosis of neurodegenerative diseases, particularly in individuals who already present with varying degrees of motor impairment. Further validation and research are needed to establish its wider applicability.

Approaches to Early Parkinson's Disease Subtyping.

Parkinson's disease (PD) unfolds with pathological processes and neurodegeneration well before the emergence of noticeable motor symptoms, providing a window for early identification. The extended prodromal phase allows the use of risk stratification measures and prodromal markers to pinpoint individuals likely to develop PD. Importantly, a growing body of evidence emphasizes the heterogeneity within prodromal and clinically diagnosed PD. The disease likely comprises distinct subtypes exhibiting diverse clinical manifestations, pathophysiological mechanisms, and patterns of α-synuclein progression in the central and peripheral nervous systems. There is a pressing need to refine the definition and early identification of these prodromal subtypes. This requires a comprehensive strategy that integrates genetic, pathological, imaging, and multi-omics markers, alongside careful observation of subtle motor and non-motor symptoms. Such multi-dimensional classification of early PD subtypes will improve our understanding of underlying disease pathophysiology, improve predictions of clinical endpoints, progression trajectory and medication response, contribute to drug discovery and personalized medicine by identifying subtype-specific disease mechanisms, and facilitate drug trials by reducing confounding effects of heterogeneity. Here we explore different subtyping methodologies in prodromal and clinical PD, focusing on clinical, imaging, genetic and molecular subtyping approaches. We also emphasize the need for refined, theoretical a priori disease models. These will be prerequisite to understanding the biological underpinnings of biological subtypes, which have been defined by large scale data-driven approaches and multi-omics fingerprints.

Parkinson's disease is an incurable neurodegenerative disorder characterized by a 20-year prodromal phase before an individual is formally diagnosed. During this prodromal or early disease phase, non-motor symptoms gradually accumulate including a reduced ability to smell, sleep disturbance, constipation, depression, anxiety, and memory problems. Subtle motor symptoms including slowness of movement, stiffness, and tremor may be present, but not to the extent required for a clinical diagnosis. Each individual with prodromal Parkinson's disease is affected with a unique combination of these symptoms which progress at different rates. Subtyping attempts to understand this variability by defining groups of patients with sets of key features at a clinical, genetic, imaging, or molecular level. This article reviews subtyping approaches and how they might improve our understanding of how Parkinson's disease evolves.

Late feature fusion using neural network with voting classifier for Parkinson's disease detection.

Parkinson's disease (PD) is classified as a neurological, progressive illness brought on by cell death in the posterior midbrain. Early PD detection will assist doctors in reducing the disease's consequences. A collection of skilled models that may be applied to regression as well as classification is known as artificial intelligence (AI). PD can be detected using a variety of dataset formats, including text, speech, and picture datasets. For the purpose of classifying Parkinson's disease, this study suggests merging deep with machine learning recognition approaches. The three primary components of the suggested approach are designed to enhance the accuracy of Parkinson's disease early diagnosis. These sections cover the topics of categorising, combining, and separating. Convolutional Neural Networks (CNN) as well as attention procedures are used to create feature extractors. The related motion signals are fed to a combination of convolutional neural network and long-short-memory model for feature extraction. Besides, for the classification of patients from non-suffers of Parkinson's disease, Random Forest, Logistic Regression, Support Vector Machine, Extreme Boot Classifier, and voting classifier were used. Our result shows that for the PD handwriting and related motion datasets, using the proposed CNN with an attention and voting classifier yields 99.95% accuracy, 99.99% precision, 99.98% sensitivity, and 99.95% F1-score. Based on these results, it is warranted to conclude that the proposed methodology of feature extraction from photos of handwriting and relating motor symptoms, fusing of those features, and following it with a voting classifier yields excellent results for PD classification.

A novel voice classification based on Gower distance for Parkinson disease detection.

BACKGROUND: Traditional classifier for the classification of diseases, such as K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM), often struggle with high-dimensional medical datasets. OBJECTIVE: This study presents a novel classifier to overcome the limitations of traditional classifiers in Parkinson's disease (PD) detection based on Gower distance. METHODS: We present the Gower distance metric to handle diverse feature sets in voice recordings, which acts as a dissimilarity measure for all feature types, making the model adept at identifying subtle patterns indicative of PD. Additionally, the Cuckoo Search algorithm is employed for feature selection, reducing dimensionality by focusing on key features, thereby lessening the computational load associated with high-dimensional datasets. RESULTS: The proposed classifier based on Gower distance resulted in an accuracy rate of 98.3% with feature selection and achieved an accuracy of 94.92% without the feature selection method. It outperforms traditional classifiers and recent studies in PD detection from voice recordings. CONCLUSIONS: This accuracy shows the capability of the approach in the correct classification of instances and points out the potential of the approach as a reliable diagnostic tool for the medical practitioner. The findings state that the proposed approach holds promise for improving the diagnosis and monitoring of PD, both within medical institutions and at homes for the elderly.

Simultaneous time-frequency analysis of gait signals of both legs in classifying neurodegenerative diseases.

BACKGROUND: Neurodegenerative diseases (NDDs) pose significant challenges due to their debilitating nature and limited therapeutic options. Accurate and timely diagnosis is crucial for optimizing patient care and treatment strategies. Gait analysis, utilizing wearable sensors, has shown promise in assessing motor abnormalities associated with NDDs. RESEARCH QUESTION: Research Question 1 To what extent can analyzing the interaction of both limbs in the time-frequency domain serve as a suitable methodology for accurately classifying NDDs? Research Question 2 How effective is the utilization of color-coded images, in conjunction with deep transfer learning models, for the classification of NDDs? METHODS: GaitNDD database was used, comprising recordings from patients with Huntington's disease, amyotrophic lateral sclerosis, Parkinson's disease, and healthy controls. The gait signals underwent signal preparation, wavelet coherence analysis, and principal component analysis for feature enhancement. Deep transfer learning models (AlexNet, GoogLeNet, SqueezeNet) were employed for classification. Performance metrics, including accuracy, sensitivity, specificity, precision, and F1 score, were evaluated using 5-fold cross-validation. RESULTS: The classification performance of the models varied depending on the time window used. For 5-second gait signal segments, AlexNet achieved an accuracy of 95.91 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.49 % and 92.73 %, respectively. For 10-second segments, AlexNet outperformed other models with an accuracy of 99.20 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.75 % and 95.00 %, respectively. Statistical tests confirmed the significance of the extracted features, indicating their discriminative power for classification. SIGNIFICANCE: The proposed method demonstrated superior performance compared to previous studies, offering a non-invasive and cost-effective approach for the automated diagnosis of NDDs. By analyzing the interaction between both legs during walking using wavelet coherence, and utilizing deep transfer learning models, accurate classification of NDDs was achieved.

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.

Exploring Spectrogram-Based Audio Classification for Parkinson's Disease: A Study on Speech Classification and Qualitative Reliability Verification.

Patients suffering from Parkinson's disease suffer from voice impairment. In this study, we introduce models to classify normal and Parkinson's patients using their speech. We used an AST (audio spectrogram transformer), a transformer-based speech classification model that has recently outperformed CNN-based models in many fields, and a CNN-based PSLA (pretraining, sampling, labeling, and aggregation), a high-performance model in the existing speech classification field, for the study. This study compares and analyzes the models from both quantitative and qualitative perspectives. First, qualitatively, PSLA outperformed AST by more than 4% in accuracy, and the AUC was also higher, with 94.16% for AST and 97.43% for PSLA. Furthermore, we qualitatively evaluated the ability of the models to capture the acoustic features of Parkinson's through various CAM (class activation map)-based XAI (eXplainable AI) models such as GradCAM and EigenCAM. Based on PSLA, we found that the model focuses well on the muffled frequency band of Parkinson's speech, and the heatmap analysis of false positives and false negatives shows that the speech features are also visually represented when the model actually makes incorrect predictions. The contribution of this paper is that we not only found a suitable model for diagnosing Parkinson's through speech using two different types of models but also validated the predictions of the model in practice.

Parkinson's image detection and classification based on deep learning.

OBJECTIVE: There are two major issues in the MRI image diagnosis task for Parkinson's disease. Firstly, there are slight differences in MRI images between healthy individuals and Parkinson's patients, and the medical field has not yet established precise lesion localization standards, which poses a huge challenge for the effective prediction of Parkinson's disease through MRI images. Secondly, the early diagnosis of Parkinson's disease traditionally relies on the subjective judgment of doctors, which leads to insufficient accuracy and consistency. This article proposes an improved YOLOv5 detection algorithm based on deep learning for predicting and classifying Parkinson's images. METHODS: This article improves the YOLOv5s network as the basic framework. Firstly, the CA attention mechanism was introduced to enable the model to dynamically adjust attention based on local features of the image, significantly enhancing the sensitivity of the model to PD related small pathological features; Secondly, replace the dynamic full dimensional convolution module to optimize the multi-level extraction of image features; Finally, the coupling head strategy is adopted to improve the execution efficiency of classification and localization tasks separately. RESULTS: We validated the effectiveness of the proposed method using a dataset of 582 MRI images from 108 patients. The results show that the proposed method achieves 0.961, 0.974, and 0.986 in Precision, Recall, and mAP, respectively, and the experimental results are superior to other algorithms. CONSLUSION: The improved model has achieved high accuracy and detection accuracy, and can accurately detect and recognize complex Parkinson's MRI images. SIGNIFICANCE: This algorithm has shown good performance in the early diagnosis of Parkinson's disease and can provide clinical assistance for doctors in early diagnosis. It compensates for the limitations of traditional methods.

Reinforcement Learning-Based Adaptive Classification for Medication State Monitoring in Parkinson's Disease.

Parkinson's Disease (PD) patients frequently transition between the 'ON' state, where medication is effective, and the 'OFF' state, affecting their quality of life. Monitoring these transitions is vital for personalized therapy. We introduced a framework based on Reinforcement Learning (RL) to detect transitions between medication states by learning from continuous movement data. Unlike traditional approaches that typically identify each state based on static data patterns, our approach focuses on understanding the dynamic patterns of change throughout the transitions, providing a more generalizable medication state monitoring method. We integrated a deep Long Short-Term Memory (LSTM) neural network and three one-class unsupervised classifiers to implement an RL-based adaptive classifier. We tested on two PD datasets: Dataset PD1 with 12 subjects (14-minute average recording) and Dataset PD2 with seven subjects (120-minute average recording). Data from wrist and ankle wearables captured transitions during 2 to 4-hour daily activities. The algorithm demonstrated its effectiveness in detecting medication states, achieving an average weighted F1-score of 82.94% when trained and tested on Dataset PD1. It performed well when trained on Dataset PD1 and tested on Dataset PD2, with a weighted F1-score of 76.67%. It surpassed other models, was resilient to severe PD symptoms, and performed well with imbalanced data. Notably, prior work has not addressed the generalizability from one dataset to another, essential for real-world applications with varied sensors. Our innovative framework revolutionizes PD monitoring, setting the stage for advanced therapeutic methods and greatly enhancing the life quality of PD patients.

Replication and reliability of Parkinson's disease clinical subtypes.

BACKGROUND: We recently identified three distinct Parkinson's disease subtypes: "motor only" (predominant motor deficits with intact cognition and psychiatric function); "psychiatric & motor" (prominent psychiatric symptoms and moderate motor deficits); "cognitive & motor" (cognitive and motor deficits). OBJECTIVE: We used an independent cohort to replicate and assess reliability of these Parkinson's disease subtypes. METHODS: We tested our original subtype classification with an independent cohort (N = 100) of Parkinson's disease participants without dementia and the same comprehensive evaluations assessing motor, cognitive, and psychiatric function. Next, we combined the original (N = 162) and replication (N = 100) datasets to test the classification model with the full combined dataset (N = 262). We also generated 10 random split-half samples of the combined dataset to establish the reliability of the subtype classifications. Latent class analyses were applied to the replication, combined, and split-half samples to determine subtype classification. RESULTS: First, LCA supported the three-class solution - Motor Only, Psychiatric & Motor, and Cognitive & Motor- in the replication sample. Next, using the larger, combined sample, LCA again supported the three subtype groups, with the emergence of a potential fourth group defined by more severe motor deficits. Finally, split-half analyses showed that the three-class model also had the best fit in 13/20 (65%) split-half samples; two-class and four-class solutions provided the best model fit in five (25%) and two (10%) split-half replications, respectively. CONCLUSIONS: These results support the reproducibility and reliability of the Parkinson's disease behavioral subtypes of motor only, psychiatric & motor, and cognitive & motor groups.

Essential tremor-Parkinson's disease syndrome: clinical characteristics and subtypes using cluster analysis.

BACKGROUND: Essential tremor (ET) and Parkinson's disease (PD) are common movement disorders. ET-PD syndrome is characterized by the occurrence of PD in patients with a previous history of ET, which may be an independent phenotype distinct from PD. This study aims to identify clinical characteristics and subtypes in ET-PD. METHODS: A total of 93 newly diagnosed ET-PD patients and 93 newly diagnosed PD patients matched for age, sex, education, and disease duration of PD were selected using propensity score matching analysis. The K-means cluster analysis was performed for 11 variables derived from the ET-PD group, and cluster profiles were established through statistical analysis of demographic and clinical variables. RESULTS: The ET-PD group consisted of a high number of patients with a family history of ET exhibiting evident tremor with milder hypokinesia and postural instability symptoms, as compared to the PD group. Through the cluster analysis, two clusters of ET-PD patients were identified. The ET-PD cluster 1 ( n  = 34) had a shorter ET duration before PD onset, lower number of patients with a family history of ET, higher unified PD rating scale instability scores, higher non-motor symptoms scores (non-motor symptoms scale D1 scores, Hamilton depression scale scores, Hamilton anxiety scale scores, and PD sleep scale-2 scores), and higher Chinese version of the PD questionnaire-39 scores relative to the ET-PD cluster 2 ( n  = 59). CONCLUSION: ET-PD patients had significantly different characteristics for motor symptoms as compared to PD patients, and may be distinctly divided into two clinical subtypes, namely, the ET-PD complex type and the ET-PD simple type.

New therapeutic approaches to Parkinson's disease targeting GBA, LRRK2 and Parkin.

Parkinson's disease (PD) is defined as a complex disorder with multifactorial pathogenesis, yet a more accurate definition could be that PD is not a single entity, but rather a mixture of different diseases with similar phenotypes. Attempts to classify subtypes of PD have been made based on clinical phenotypes or biomarkers. However, the most practical approach, at least for a portion of the patients, could be to classify patients based on genes involved in PD. GBA and LRRK2 mutations are the most common genetic causes or risk factors of PD, and PRKN is the most common cause of autosomal recessive form of PD. Patients carrying variants in GBA, LRRK2 or PRKN differ in some of their clinical characteristics, pathology and biochemical parameters. Thus, these three PD-associated genes are of special interest for drug development. Existing therapeutic approaches in PD are strictly symptomatic, as numerous clinical trials aimed at modifying PD progression or providing neuroprotection have failed over the last few decades. The lack of precision medicine approach in most of these trials could be one of the reasons why they were not successful. In the current review we discuss novel therapeutic approaches targeting GBA, LRRK2 and PRKN and discuss different aspects related to these genes and clinical trials.

Identifying Parkinson's disease subtypes with motor and non-motor symptoms via model-based multi-partition clustering.

Identification of Parkinson's disease subtypes may help understand underlying disease mechanisms and provide personalized management. Although clustering methods have been previously used for subtyping, they have reported generic subtypes of limited relevance in real life practice because patients do not always fit into a single category. The aim of this study was to identify new subtypes assuming that patients could be grouped differently according to certain sets of related symptoms. To this purpose, a novel model-based multi-partition clustering method was applied on data from an international, multi-center, cross-sectional study of 402 Parkinson's disease patients. Both motor and non-motor symptoms were considered. As a result, eight sets of related symptoms were identified. Each of them provided a different way to group patients: impulse control issues, overall non-motor symptoms, presence of dyskinesias and pyschosis, fatigue, axial symptoms and motor fluctuations, autonomic dysfunction, depression, and excessive sweating. Each of these groups could be seen as a subtype of the disease. Significant differences between subtypes (P< 0.01) were found in sex, age, age of onset, disease duration, Hoehn & Yahr stage, and treatment. Independent confirmation of these results could have implications for the clinical management of Parkinson's disease patients.

Determinants of quality of life in Parkinson's disease: a perspective of novel clinical subtypes.

OBJECTIVE: New subtyping classification systems of Parkinson's disease (PD) have been proposed for phenotyping patients into three different subtypes: mild motor-predominant (PD-MMP), intermediate (PD-IM) and diffuse malignant (PD-DM). The quality of life (QoL) underlying the novel PD clinical subtypes is unknown. This study aimed explore the feasibility of the classification in Chinese PD patients and to investigate the potential heterogeneous determinants of QoL among the three subtypes. METHODS: 298 PD patients were enrolled, including 129 PD-MMP patients, 121 PD-IM patients and 48 PD-DM patients. All patients completed the QoL assessment, clinical evaluations and neuropsychological tests. Univariate linear analysis and multiple stepwise regression analysis were performed to identify determinants of QoL. RESULTS: Compared to PD-MMP patients, PD-IM and PD-DM patients had more impaired QoL. The Geriatric Depression Rating Scale (GDS) score, Non-Motor Symptoms Questionnaire (NMSQ) score, Unified Parkinson's Disease Rating Scale part III (UPDRS-III) score and Epworth Sleepiness Score (ESS) were independent contributors to QoL in PD-MMP patients. The GDS score, ESS and sniffin' sticks screening 12 test score were independent contributors to QoL in PD-IM patients. The GDS score and Mini Mental State Examination score were independent contributors to QoL in PD-DM patients. INTERPRETATION: The new novel subtyping classification is feasible for Chinese PD patients. Although depression was the most crucial determinant for QoL in PD-MMP, PD-IM and PD-DM patients, the other contributors of QoL in the three subtypes were heterogeneous. These findings may prompt clinicians to target specific factors for improving QoL depending on PD subtypes.

Does Subthalamic Deep Brain Stimulation Impact Asymmetry and Dyscoordination of Gait in Parkinson's Disease?

Background. Subthalamic deep brain stimulation (STN-DBS) is an effective treatment for selected Parkinson's disease (PD) patients. Gait characteristics are often altered after surgery, but quantitative therapeutic effects are poorly described. Objective. The goal of this study was to systematically investigate modifications in asymmetry and dyscoordination of gait 6 months postoperatively in patients with PD and compare the outcomes with preoperative baseline and to asymptomatic controls without PD. Methods. A convenience sample of thirty-two patients with PD (19 with postural instability and gait disorder (PIGD) type and 13 with tremor dominant disease) and 51 asymptomatic controls participated. Parkinson patients were tested prior to the surgery in both OFF and ON medication states, and 6-months postoperatively in the ON stimulation condition. Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) I to IV and medication were compared to preoperative conditions. Asymmetry ratios, phase coordination index, and walking speed were assessed. Results. MDS-UPDRS I to IV at 6 months improved significantly, and levodopa equivalent daily dosages significantly decreased. STN-DBS increased step time asymmetry (hedges' g effect sizes [95% confidence interval] between pre- and post-surgery: .27 [-.13, .73]) and phase coordination index (.29 [-.08, .67]). These effects were higher in the PIGD subgroup than the tremor dominant (step time asymmetry: .38 [-.06, .90] vs .09 [-.83, 1.0] and phase coordination index: .39 [-.04, .84] vs .13 [-.76, .96]). Conclusions. This study provides objective evidence of how STN-DBS increases asymmetry and dyscoordination of gait in patients with PD and suggests motor subtypes-associated differences in the treatment response.

Use of machine learning method on automatic classification of motor subtype of Parkinson's disease based on multilevel indices of rs-fMRI.

OBJECTIVE: This study aimed to develop an automatic classifier to distinguish different motor subtypes of Parkinson's disease (PD) based on multilevel indices of resting-state functional magnetic resonance imaging (rs-fMRI). METHODS: Ninety-six PD patients, which included thirty-nine postural instability and gait difficulty (PIGD) subtype and fifty-seven tremor-dominant (TD) subtype, were enrolled and allocated to training and validation datasets with a ratio of 7:3. A total of five types of index, consisting of mean regional homogeneity (mReHo), mean amplitude of low-frequency fluctuation (mALFF), degree of centrality (DC), voxel-mirrored homotopic connectivity (VMHC), and functional connectivity (FC), were extracted. The features were then selected using a two-sample t-test, the least absolute shrinkage and selection operator (LASSO), and Spearman's rank correlation coefficient. Finally, support vector machine (SVM) models based on the separate index and multilevel indices were built, and the performance of models was assessed via the area under the receiver operating characteristic curve (AUC). Feature importance was evaluated using Shapley additive explanation (SHAP) values. RESULTS: The optimal SVM model was obtained based on multilevel rs-fMRI indices, with an AUC of 0.934 in the training dataset and an AUC of 0.917 in the validation dataset. The AUCs of the models based on the separate index were ranged from 0.783 to 0.858 for the training dataset and from 0.713 to 0.792 for the validation dataset. SHAP analysis revealed that functional activity and connectivity in frontal lobe and cerebellum were important features for differentiating PD subtypes. CONCLUSIONS: Our findings demonstrated multilevel rs-fMRI indices could provide more comprehensive information on brain functionalteration. Furthermore, the machine learning method based on multilevel rs-fMRI indices might be served as an alternative approach for automatically classifying clinical subtypes in PD at the individual level.

Predicting and Characterizing Neurodegenerative Subtypes with Multimodal Neurocognitive Signatures of Social and Cognitive Processes.

BACKGROUND: Social cognition is critically compromised across neurodegenerative diseases, including the behavioral variant frontotemporal dementia (bvFTD), Alzheimer's disease (AD), and Parkinson's disease (PD). However, no previous study has used social cognition and other cognitive tasks to predict diagnoses of these conditions, let alone reporting the brain correlates of prediction outcomes. OBJECTIVE: We performed a diagnostic classification analysis using social cognition, cognitive screening (CS), and executive function (EF) measures, and explored which anatomical and functional networks were associated with main predictors. METHODS: Multiple group discriminant function analyses (MDAs) and ROC analyses of social cognition (facial emotional recognition, theory of mind), CS, and EF were implemented in 223 participants (bvFTD, AD, PD, controls). Gray matter volume and functional connectivity correlates of top discriminant scores were investigated. RESULTS: Although all patient groups revealed deficits in social cognition, CS, and EF, our classification approach provided robust discriminatory characterizations. Regarding controls, probabilistic social cognition outcomes provided the best characterization for bvFTD (together with CS) and PD, but not AD (for which CS alone was the best predictor). Within patient groups, the best MDA probabilities scores yielded high classification rates for bvFTD versus PD (98.3%, social cognition), AD versus PD (98.6%, social cognition + CS), and bvFTD versus AD (71.7%, social cognition + CS). Top MDA scores were associated with specific patterns of atrophy and functional networks across neurodegenerative conditions. CONCLUSION: Standardized validated measures of social cognition, in combination with CS, can provide a dimensional classification with specific pathophysiological markers of neurodegeneration diagnoses.

Distinct progression patterns across Parkinson disease clinical subtypes.

OBJECTIVE: To examine specific symptom progression patterns and possible disease staging in Parkinson disease clinical subtypes. METHODS: We recently identified Parkinson disease clinical subtypes based on comprehensive behavioral evaluations, "Motor Only," "Psychiatric & Motor," and "Cognitive & Motor," which differed in dementia and mortality rates. Parkinson disease participants ("Motor Only": n = 61, "Psychiatric & Motor": n = 17, "Cognitive & Motor": n = 70) and controls (n = 55) completed longitudinal, comprehensive motor, cognitive, and psychiatric evaluations (average follow-up = 4.6 years). Hierarchical linear modeling examined group differences in symptom progression. A three-way interaction among time, group, and symptom duration (or baseline age, separately) was incorporated to examine disease stages. RESULTS: All three subtypes increased in motor dysfunction compared to controls. The "Motor Only" subtype did not show significant cognitive or psychiatric changes compared to the other two subtypes. The "Cognitive & Motor" subtype's cognitive dysfunction at baseline further declined compared to the other two subtypes, while also increasing in psychiatric symptoms. The "Psychiatric & Motor" subtype's elevated psychiatric symptoms at baseline remained steady or improved over time, with mild, steady decline in cognition. The pattern of behavioral changes and analyses for disease staging yielded no evidence for sequential disease stages. INTERPRETATION: Parkinson disease clinical subtypes progress in clear, temporally distinct patterns from one another, particularly in cognitive and psychiatric features. This highlights the importance of comprehensive clinical examinations as the order of symptom presentation impacts clinical prognosis.

Premotor antidepressants use differs according to Parkinson's disease subtype: A cohort study.

BACKGROUND: Depression is more frequently associated with akinetic-rigid/postural instability gait difficulty subtypes of Parkinson's disease than with tremor-dominant subtype. OBJECTIVES: The aim of the study is to investigate the frequency of exposure to antidepressant drugs, as proxy of depression, before motor onset according to Parkinson's disease subtypes. METHOD: Based on a historical cohort design, the exposure to antidepressant drugs before Parkinson's disease motor onset was obtained from the drug prescription database and assessed in the resident population of the Local Healthcare Trust of Bologna (443,117 subjects older than 35 years). Diagnosis of Parkinson's disease and subtype (tremor dominant, non-tremor dominant) at onset were recorded by neurologists and obtained from the "ParkLink Bologna" record linkage system. Exposure to antidepressants was compared both to the general population and between the two subtypes. RESULTS: From 2006 to 2018, 198 patients had a tremor dominant subtype at onset whereas 450 did not. Comparison with the general population for antidepressant exposure showed an adjusted hazard ratio of 0.86 (95% CI 0.44-1.70) for the tremor dominant subtype and 1.66 (1.16-2.39) for the non-tremor dominant subtype. Comparison of non-tremor dominant with tremor dominant subtypes showed an adjusted odds ratio of 1.86 (1.05-3.95) for antidepressant exposure. CONCLUSIONS: In our study, non-tremor dominant Parkinson's disease at onset was significantly associated with exposure to antidepressants in comparison to the general population and in comparison with the tremor dominant subtype. These results support the hypothesis of different biological substrates for different Parkinson's disease subtypes even before motor onset.