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

Unraveling Parkinson's disease motor subtypes: A deep learning approach based on spatiotemporal dynamics of EEG microstates

BACKGROUND

Despite prior studies on early-stage Parkinson's disease (PD) brain connectivity and temporal patterns, differences between tremor-dominant (TD) and postural instability/gait difficulty (PIGD) motor subtypes remain poorly understood. Our study aims to understand the contribution of altered brain network dynamics to heterogeneous motor phenotypes in PD for improving personalized treatment.

METHODS

Electroencephalography (EEG) microstate dynamics were firstly used to capture spatiotemporal brain network changes. A deep learning model was developed to classify PD motor subtypes where spatial variability and electrode location data were incorporated into the analysis.

RESULTS

Compared to healthy individuals, both PD-TD and PD-PIGD patients showed increased local segregation of brain regions. The PD-PIGD subtype had more severe and extensive disorganization in microstate A dynamics, suggesting greater disruption in auditory and motor-related networks. Incorporating spatial information significantly improved the accuracy of subtype classification, with an AUC of 0.972, indicating that EEG microstate dynamic spatial patterns reflect distinct PD motor pathologies. The increased spatial variability in the PD-PIGD group was more closely associated with motor impairments.

CONCLUSIONS

This study presents a novel framework for differentiating PD motor subtypes and emphasizes dynamic brain network features as potential markers for understanding motor symptom variability in PD, which may contribute to the development of personalized treatment strategies.

TRIAL REGISTRATION

ChiCTR2300067657.

Differentiating patterns of neuro-circuitry abnormalities in tremor dominant parkinson's disease and multiple system atrophy: a resting-state fMRI study

This study aimed to elucidate distinctive patterns of brain functional activity in tremor-dominant Multiple System Atrophy (MSA) and Parkinson's Disease (PD) patients and develop a diagnostic model distinguishing between the two conditions based on these changes. Resting-state fMRI data from 45 MSA patients, 55 PD patients, and 48 healthy controls were analyzed using Percent Amplitude of Fluctuation (PerAF), Functional (FC) and Effective Connectivity (EC) analyses. The Support Vector Machine (SVM) was used to create the diagnostic model from the identified functional alterations. Partial correlation analyses explored the relationship between functional abnormalities and tremors. Both MSA and PD patients with tremors exhibited similar activity changes in bilateral Orbital part of the superior frontal gyrus (ORBsup), Cerebellum VIII (CRBL8), left Cerebellum IV-V (CRBL45.L), right rectus (REC), and FC based on the seeds of PUT.L, CRBL8.R, and REC.R. These changes were more pronounced in MSA patients. However, MSA patients exhibited heightened putamen activity and enhanced EC from caudate (CAU) to putamen, whereas these activity and connectivity were decreased in PD patients. The SVM model achieved strong performance, with the putamen exerting the most significant influence on classification. In summary, dysfunction within the cerebello-cortical and basal ganglia network circuits is implicated in the tremors of both MSA and PD patients. The alteration in cerebellar-cortical regions were similar, with MSA displaying more pronounced changes, contrasting changes were observed in the basal ganglia region. The putamen may serve as crucial neurobiological indicators for the precise differentiation of MSA and PD patients.

Predicting Parkinson's disease trajectory using clinical and functional MRI features: A reproduction and replication study

Parkinson's disease (PD) is a common neurodegenerative disorder with a poorly understood physiopathology and no established biomarkers for the diagnosis of early stages and for prediction of disease progression. Several neuroimaging biomarkers have been studied recently, but these are susceptible to several sources of variability related for instance to cohort selection or image analysis. In this context, an evaluation of the robustness of such biomarkers to variations in the data processing workflow is essential. This study is part of a larger project investigating the replicability of potential neuroimaging biomarkers of PD. Here, we attempt to fully reproduce (reimplementing the experiments with the same methods, including data collection from the same database) and replicate (different data and/or method) the models described in (Nguyen et al., 2021) to predict individual's PD current state and progression using demographic, clinical and neuroimaging features (fALFF and ReHo extracted from resting-state fMRI). We use the Parkinson's Progression Markers Initiative dataset (PPMI, ppmi-info.org), as in (Nguyen et al., 2021) and aim to reproduce the original cohort, imaging features and machine learning models as closely as possible using the information available in the paper and the code. We also investigated methodological variations in cohort selection, feature extraction pipelines and sets of input features. Different criteria were used to evaluate the reproduction attempt and compare the results with the original ones. Notably, we obtained significantly better than chance performance using the analysis pipeline closest to that in the original study (R2 > 0), which is consistent with its findings. In addition, we performed a partial reproduction using derived data provided by the authors of the original study, and we obtained results that were close to the original ones. The challenges encountered while attempting to reproduce (fully and partially) and replicating the original work are likely explained by the complexity of neuroimaging studies, in particular in clinical settings. We provide recommendations to further facilitate the reproducibility of such studies in the future.

Houston, We Have AI Problem! Quality Issues with Neuroimaging-Based Artificial Intelligence in Parkinson's Disease: A Systematic Review

In recent years, many neuroimaging studies have applied artificial intelligence (AI) to facilitate existing challenges in Parkinson's disease (PD) diagnosis, prognosis, and intervention. The aim of this systematic review was to provide an overview of neuroimaging-based AI studies and to assess their methodological quality. A PubMed search yielded 810 studies, of which 244 that investigated the utility of neuroimaging-based AI for PD diagnosis, prognosis, or intervention were included. We systematically categorized studies by outcomes and rated them with respect to five minimal quality criteria (MQC) pertaining to data splitting, data leakage, model complexity, performance reporting, and indication of biological plausibility. We found that the majority of studies aimed to distinguish PD patients from healthy controls (54%) or atypical parkinsonian syndromes (25%), whereas prognostic or interventional studies were sparse. Only 20% of evaluated studies passed all five MQC, with data leakage, non-minimal model complexity, and reporting of biological plausibility as the primary factors for quality loss. Data leakage was associated with a significant inflation of accuracies. Very few studies employed external test sets (8%), where accuracy was significantly lower, and 19% of studies did not account for data imbalance. Adherence to MQC was low across all observed years and journal impact factors. This review outlines that AI has been applied to a wide variety of research questions pertaining to PD; however, the number of studies failing to pass the MQC is alarming. Therefore, we provide recommendations to enhance the interpretability, generalizability, and clinical utility of future AI applications using neuroimaging in PD. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Machine Learning Approaches to Identify Affected Brain Regions in Movement Disorders Using MRI Data: A Systematic Review and Diagnostic Meta-analysis

BACKGROUND

Movement disorders such as Parkinson's disease are associated with structural and functional changes in specific brain regions. Advanced magnetic resonance imaging (MRI) techniques combined with machine learning (ML) are promising tools for identifying imaging biomarkers and patterns associated with these disorders.

PURPOSE/HYPOTHESIS

We aimed to systematically identify the brain regions most commonly affected in movement disorders using ML approaches applied to structural and functional MRI data. We searched the PubMed and Scopus databases using relevant keywords up to June 2023 for studies that used ML approaches to detect brain regions associated with movement disorders using MRI data.

STUDY TYPE

A systematic review and diagnostic meta-analysis.

POPULATION/SUBJECTS

Sixty-seven studies with 6,285 patients were included.

FIELD STRENGTH/SEQUENCE

Studies utilizing 1.5T or 3T MR scanners and the acquisition of diffusion tensor imaging (DTI), structural MRI (sMRI), functional MRI (fMRI), or a combination of these were included.

ASSESSMENT

The authors independently assessed the study quality using the CLAIM and QUADAS-2 criteria and extracted data on diagnostic accuracy measures.

STATISTICAL TESTS

Sensitivity, specificity, accuracy, and area under the curve were pooled using random-effects models. Q statistics and the I2 index were used to evaluate heterogeneity, and Begg's funnel plot was used to identify publication bias.

RESULTS

sMRI showed the highest sensitivity (93%) and mixed modalities had the highest specificity (90%) for detecting regional abnormalities. sMRI had a 94% sensitivity for identifying subcortical changes. The support vector machine (93%) and logistic regression (91%) models exhibited high diagnostic accuracies.

DATA CONCLUSION

The combination of advanced MR neuroimaging techniques and ML is a promising approach for identifying brain biomarkers and affected regions in movement disorders with subcortical structures frequently implicated. Structural MRI, in particular, showed strong performance.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

Identifying genetic targets in clinical subtypes of Parkinson's disease for optimizing pharmacological treatment strategies

The heterogeneity of Parkinson's disease (PD) has been recognized in clinical, with patients categorized into distinct subsets based on motor phenotype, such as tremor-dominant PD (TD), postural instability and gait difficulty-dominant PD (PIGD) and mixed PD (Mix). Despite this categorization, the underlying mechanisms of this heterogeneity remain poorly understood, and there is no personalized effective treatment for each PD subtype. To address this, a rat model for PD subtypes was established by unilateral stereotaxic injection of 6-OHDA, followed by cluster analysis of behavioral data. The serum neurofilament light chain (NfL) and uric acid (UA) levels as well as alterations in brain autonomic activity in rats were consistent with clinical patients, and metabolomics results showed that more than 70% of the metabolites in the serum of different subtypes of PD rats and clinical patients appeared to be consistently altered. Further transcriptomic analysis by RNA-seq has elucidated that the development of PD subtypes is associated with altered gene expression in neurotransmitter, neuronal damage in the central or peripheral nervous system, and lipid metabolism. In addition, based on the subtype-specific differentially expressed genes, 25 potential drug candidates were identified. Notably, the Alox15 inhibitor baicalein showed a greater efficacy on Mix rats, highlighting the possibility of selecting targeted treatments for well-defined individuals.

Abnormal Interhemispheric Functional Connectivity in Acute Pericoronitis: A Resting-State MRI Study

OBJECTIVE

Acute pericoronitis (AP) is a prevalent cause of odontogenic toothache which can significantly impact brain function. Previous research has predominantly concentrated on localized brain activity. However, the synergistic changes between brain hemispheres induced by toothache and resulting abnormal functional connectivity across the brain have not been comprehensively studied.

METHODS

A total of 34 patients with AP and 34 healthy individuals, matched for age, sex, and education were recruited for this study. All participants underwent resting-state functional magnetic resonance imaging (rs-MRI) scans. The voxel mirror homotopic connectivity (VMHC) method was used to identify intergroup differences. Brain regions exhibiting statistically significant differences were selected as regions of interest for further functional connectivity analysis. The partial correlation method was utilized to assess the correlation between abnormal VMHC values in different regions and clinical parameters, with age and sex included as covariates.

RESULTS

Patients with AP exhibited reduced VMHC values in the thalamus and elevated VMHC values in the inferior frontal gyrus compared with healthy controls. Subsequent functional connectivity analyses revealed extensive changes in functional networks, predominantly affecting the default, frontoparietal, cerebellar, and pain networks.

CONCLUSION

Changes in functional patterns across these brain networks offer novel insights into the neurophysiological mechanisms underlying pain information processing.

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.

Combined brain topological metrics with machine learning to distinguish essential tremor and tremor-dominant Parkinson's disease

BACKGROUND

Essential tremor (ET) and Parkinson's disease (PD) are the two most prevalent movement disorders, sharing several overlapping tremor clinical features. Although growing evidence pointed out that changes in similar brain network nodes are associated with these two diseases, the brain network topological properties are still not very clear.

OBJECTIVE

The combination of graph theory analysis with machine learning (ML) algorithms provides a promising way to reveal the topological pathogenesis in ET and tremor-dominant PD (tPD).

METHODS

Topological metrics were extracted from Resting-state functional images of 86 ET patients, 86 tPD patients, and 86 age- and sex-matched healthy controls (HCs). Three steps were conducted to feature dimensionality reduction and four frequently used classifiers were adopted to discriminate ET, tPD, and HCs.

RESULTS

A support vector machine classifier achieved the best classification performance of four classifiers for discriminating ET, tPD, and HCs with 89.0% mean accuracy (mACC) and was used for binary classification. Particularly, the binary classification performances among ET vs. tPD, ET vs. HCs, and tPD vs. HCs were with 94.2% mACC, 86.0% mACC, and 86.3% mACC, respectively. The most power discriminative features were mainly located in the default, frontal-parietal, cingulo-opercular, sensorimotor, and cerebellum networks. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with clinical characteristics.

CONCLUSIONS

These results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET, tPD, and HCs but also help to reveal the potential brain topological network pathogenesis in ET and tPD.

An rs-fMRI based neuroimaging marker for adult absence epilepsy

OBJECTIVE

Approximately 20-30 % of epilepsy patients exhibit negative findings on routine magnetic resonance imaging, and this condition is known as nonlesional epilepsy. Absence epilepsy (AE) is a prevalent form of nonlesional epilepsy. This study aimed to investigate the clinical diagnostic utility of regional homogeneity (ReHo) assessed through the support vector machine (SVM) approach for identifying AE.

METHODS

This research involved 102 healthy individuals and 93 AE patients. Resting-state functional magnetic resonance imaging was employed for data acquisition in all participants. ReHo analysis, coupled with SVM methodology, was utilized for data processing.

RESULTS

Compared to healthy control individuals, AE patients demonstrated significantly elevated ReHo values in the bilateral putamen, accompanied by decreased ReHo in the bilateral thalamus. SVM was used to differentiate patients with AE from healthy control individuals based on rs-fMRI data. A composite assessment of altered ReHo in the left putamen and left thalamus yielded the highest accuracy at 81.64 %, with a sensitivity of 95.41 % and a specificity of 69.23 %.

SIGNIFICANCE

According to the results, altered ReHo values in the bilateral putamen and thalamus could serve as neuroimaging markers for AE, offering objective guidance for its diagnosis.

Multimodal data fusion reveals functional and neurochemical correlates of Parkinson's disease

BACKGROUND

Neurotransmitter deficits and spatial associations among neurotransmitter distribution, brain activity, and clinical features in Parkinson's disease (PD) remain unclear. Better understanding of neurotransmitter impairments in PD may provide potential therapeutic targets. Therefore, we aimed to investigate the spatial relationship between PD-related patterns and neurotransmitter deficits.

METHODS

We included 59 patients with PD and 41 age- and sex-matched healthy controls (HCs). The voxel-wise mean amplitude of the low-frequency fluctuation (mALFF) was calculated and compared between the two groups. The JuSpace toolbox was used to test whether spatial patterns of mALFF alterations in patients with PD were associated with specific neurotransmitter receptor/transporter densities.

RESULTS

Compared to HCs, patients with PD showed reduced mALFF in the sensorimotor- and visual-related regions. In addition, mALFF alteration patterns were significantly associated with the spatial distribution of the serotonergic, dopaminergic, noradrenergic, glutamatergic, cannabinoid, and acetylcholinergic neurotransmitter systems (p < 0.05, false discovery rate-corrected).

CONCLUSIONS

Our results revealed abnormal brain activity patterns and specific neurotransmitter deficits in patients with PD, which may provide new insights into the mechanisms and potential targets for pharmacotherapy.

Quantifying cerebral blood flow changes using arterial spin labeling: A comparative study of idiopathic rapid eye movement sleep behavior disorder and Parkinson's disease

INTRODUCTION

Idiopathic rapid eye movement sleep behavior disorder (iRBD) and Parkinson's disease (PD) have been found to have changes in cerebral perfusion and overlap of some of the lesioned brain areas. However, a consensus regarding the specific location and diagnostic significance of these cerebral blood perfusion alternations remains elusive in both iRBD and PD. The present study evaluated the patterns of cerebral blood flow changes in iRBD and PD.

MATERIAL AND METHODS

A total of 59 right-handed subjects were enrolled, including 15 patients with iRBD, 20 patients with PD, and 24 healthy controls (HC). They were randomly divided into groups at a ratio of 4 to 1 for training and testing. A PASL sequence was employed to obtain quantitative cerebral blood flow (CBF) maps. The CBF values were calculated from these acquired maps. In addition, AutoGluon was employed to construct a classifier for CBF features selection and classification. An independent t-test was performed for CBF variations, with age and sex as nuisance variables. The performance of the feature was evaluated using receiver operating characteristic (ROC) curves. A significance level of P < 0.05 was considered significant. CBF in several brain regions, including the left median cingulate and paracingulate gyri and the right middle occipital gyrus (MOG), showed significant differences between PD and HC, demonstrating good classification performance. The combined model that integrates all features achieved even higher performance with an AUC of 0.9380. Additionally, CBF values in multiple brain regions, including the right MOG and the left angular gyrus, displayed significant differences between PD and iRBD. Particularly, CBF values in the left angular gyrus exhibited good performance in classifying PD and iRBD. The combined model achieved improved performance, with an AUC of 0.8533. No significant differences were found in brain regions when comparing CBF values between iRBD and HC subjects.

CONCLUSIONS

ASL-based quantitative CBF change features can offer reliable biomarkers to assist in the diagnosis of PD. Regarding the characteristic of CBF in the right MOG, it is anticipated to serve as an imaging biomarker for predicting the progression of iRBD to PD.

Structural and Functional Alterations of Motor-Thalamus in Different Motor Subtype of Parkinson's Disease: An Individual Study

RATIONALE AND OBJECTIVES

This study aimed to investigate the structural and functional alterations occurring within bilateral premotor thalamus (mPMtha) in motor subtypes of Parkinson's disease (PD).

MATERIALS AND METHODS

Sixty-one individuals with instability and gait difficulty (PIGD) subtype, 60 individuals with tremor-dominant (TD) subtype and 66 healthy controls (HCs) participated in the study. All participants underwent resting-state functional magnetic resonance imaging (rs-fMRI) and 3D T1-weighted (3DT1) scans. Functional connectivity (FC) analysis and Voxel-based morphometry (VBM) analysis were performed to evaluate the function and volume of mPMtha. Additionally, correlations between motor performance and FC values, volumes were examined separately. Support vector machine (SVM) model based on FC values and thalamic volumes was conducted to assist in the clinical diagnosis of PD motor subtype.

RESULTS

Compared to HCs and PIGD, TD subtype showed increased FC between the bilateral mPMtha and left middle occipital gyrus, left inferior parietal lobule (IPL). While PIGD subtype demonstrated decreased FC between right mPMtha and precentral gyrus (PreCG), supramarginal, IPL and superior parietal lobule. FC of bilateral mPMtha with the identified regions were significantly correlated with motor performance scores in PD patients. The SVM classification based on FC values demonstrated a high level of efficiency (AUC=0.874). The volumes of the bilateral mPMtha were indifferent among three groups.

CONCLUSION

We noted distinct FC alterations of mPMtha in TD and PIGD subtypes, and these changes were correlated with motor performance. Furthermore, the machine learning based on statistically significant FC might be served as an alternative approach for automatically classifying PD motor subtypes individually.

Electroencephalography oscillations can predict the cortical response following theta burst stimulation

BACKGROUND

Continuous theta burst stimulation and intermittent theta burst stimulation are clinically popular models of repetitive transcranial magnetic stimulation. However, they are limited by high variability between individuals in cortical excitability changes following stimulation. Although electroencephalography oscillations have been reported to modulate the cortical response to transcranial magnetic stimulation, their association remains unclear. This study aims to explore whether machine learning models based on EEG oscillation features can predict the cortical response to transcranial magnetic stimulation.

METHOD

Twenty-three young, healthy adults attended two randomly assigned sessions for continuous and intermittent theta burst stimulation. In each session, ten minutes of resting-state electroencephalography were recorded before delivering brain stimulation. Participants were classified as responders or non-responders based on changes in resting motor thresholds. Support vector machines and multi-layer perceptrons were used to establish predictive models of individual responses to transcranial magnetic stimulation.

RESULT

Among the evaluated algorithms, support vector machines achieved the best performance in discriminating responders from non-responders for intermittent theta burst stimulation (accuracy: 91.30%) and continuous theta burst stimulation (accuracy: 95.66%). The global clustering coefficient and global characteristic path length in the beta band had the greatest impact on model output.

CONCLUSION

These findings suggest that EEG features can serve as markers of cortical response to transcranial magnetic stimulation. They offer insights into the association between neural oscillations and variability in individuals' responses to transcranial magnetic stimulation, aiding in the optimization of individualized protocols.

Deep learning-based multimodality classification of chronic mild traumatic brain injury using resting-state functional MRI and PET imaging

Mild traumatic brain injury (mTBI) is a public health concern. The present study aimed to develop an automatic classifier to distinguish between patients with chronic mTBI (n = 83) and healthy controls (HCs) (n = 40). Resting-state functional MRI (rs-fMRI) and positron emission tomography (PET) imaging were acquired from the subjects. We proposed a novel deep-learning-based framework, including an autoencoder (AE), to extract high-level latent and rectified linear unit (ReLU) and sigmoid activation functions. Single and multimodality algorithms integrating multiple rs-fMRI metrics and PET data were developed. We hypothesized that combining different imaging modalities provides complementary information and improves classification performance. Additionally, a novel data interpretation approach was utilized to identify top-performing features learned by the AEs. Our method delivered a classification accuracy within the range of 79-91.67% for single neuroimaging modalities. However, the performance of classification improved to 95.83%, thereby employing the multimodality model. The models have identified several brain regions located in the default mode network, sensorimotor network, visual cortex, cerebellum, and limbic system as the most discriminative features. We suggest that this approach could be extended to the objective biomarkers predicting mTBI in clinical settings.

Identifying metabolic dysfunction-associated steatotic liver disease in patients with hypertension and pre-hypertension: An interpretable machine learning approach

Objective

Metabolic dysfunction-associated steatotic liver disease (MASLD) is one of the most prevalent liver diseases and is associated with pre-hypertension and hypertension. Our research aims to develop interpretable machine learning (ML) models to accurately identify MASLD in hypertensive and pre-hypertensive populations.

Methods

The dataset for 4722 hypertensive and pre-hypertensive patients is from subjects in the NAGALA study. Six ML models, including the decision tree, K-nearest neighbor, gradient boosting, naive Bayes, support vector machine, and random forest (RF) models, were used in this study. The optimal model was constructed according to the performances of models evaluated by K-fold cross-validation (k = 5), the area under the receiver operating characteristic curve (AUC), average precision (AP), accuracy, sensitivity, specificity, and F1. Shapley additive explanation (SHAP) values were employed for both global and local interpretation of the model results.

Results

The prevalence of MASLD in hypertensive and pre-hypertensive patients was 44.3% (362 cases) and 28.3% (1107 cases), respectively. The RF model outperformed the other five models with an AUC of 0.889, AP of 0.800, accuracy of 0.819, sensitivity of 0.816, specificity of 0.821, and F1 of 0.729. According to the SHAP analysis, the top five important features were alanine aminotransferase, body mass index, waist circumference, high-density lipoprotein cholesterol, and total cholesterol. Further analysis of the feature selection in the RF model revealed that incorporating all features leads to optimal model performance.

Conclusions

ML algorithms, especially RF algorithm, improve the accuracy of MASLD identification, and the global and local interpretation of the RF model results enables us to intuitively understand how various features affect the chances of MASLD in patients with hypertension and pre-hypertension.

Distinct changes in global brain synchronization in different motor subtypes of Parkinson's disease

This study investigated alterations in degree centrality (DC) in different motor subtypes of Parkinson's disease (PD) and analyzed its clinical significance during disease occurrence. A total of 146 subjects were recruited in the study, including 90 patients with PD [51 and 39 with tremor dominant (TD) and akinetic-rigid dominant (ARD) disease, respectively] and 56 healthy controls (HCs). The resting-state functional magnetic resonance imaging data of all the subjects were obtained by 3.0 T magnetic resonance scans. The DC values, an indicator of whole brain synchronization, were calculated and compared among the TD, ARD, and HC groups. Disparities in DC values among the three groups were evaluated by analysis of variance and post hoc two-sample t-tests. Correlation between brain regions with DC differences and clinical variables were performed using partial correlation analysis after controlling for age, gender, and disease duration. Compared to the HCs, both TD and ARD groups demonstrated increased DC values bilaterally in the cerebellum; DC values were decreased in the left putamen and paracentral lobule in the TD group and in the left anterior cingulate gyrus and right supplementary motor area in the ARD group. Compared to the ARD group, the TD group showed decreased DC values in bilateral cerebellar hemispheres and increased DC values in the left anterior cingulate gyrus and right supplementary motor area. The DC of the whole brain showed inconsistencies and shared neural bases among patients with the two subtypes of PD. The differences between brain regions with abnormal DC values may be closely related to different clinical presentations of the two motor subtypes. Our findings provide new insights into the clinical heterogeneity of PD with respect to different motor subtypes.

Classifying Tremor Dominant and Postural Instability and Gait Difficulty Subtypes of Parkinson's Disease from Full-Body Kinematics

Characterizing motor subtypes of Parkinson's disease (PD) is an important aspect of clinical care that is useful for prognosis and medical management. Although all PD cases involve the loss of dopaminergic neurons in the brain, individual cases may present with different combinations of motor signs, which may indicate differences in underlying pathology and potential response to treatment. However, the conventional method for distinguishing PD motor subtypes involves resource-intensive physical examination by a movement disorders specialist. Moreover, the standardized rating scales for PD rely on subjective observation, which requires specialized training and unavoidable inter-rater variability. In this work, we propose a system that uses machine learning models to automatically and objectively identify some PD motor subtypes, specifically Tremor-Dominant (TD) and Postural Instability and Gait Difficulty (PIGD), from 3D kinematic data recorded during walking tasks for patients with PD (MDS-UPDRS-III Score, 34.7 ± 10.5, average disease duration 7.5 ± 4.5 years). This study demonstrates a machine learning model utilizing kinematic data that identifies PD motor subtypes with a 79.6% F1 score (N = 55 patients with parkinsonism). This significantly outperformed a comparison model using classification based on gait features (19.8% F1 score). Variants of our model trained to individual patients achieved a 95.4% F1 score. This analysis revealed that both temporal, spectral, and statistical features from lower body movements are helpful in distinguishing motor subtypes. Automatically assessing PD motor subtypes simply from walking may reduce the time and resources required from specialists, thereby improving patient care for PD treatments. Furthermore, this system can provide objective assessments to track the changes in PD motor subtypes over time to implement and modify appropriate treatment plans for individual patients as needed.

Topological analysis of functional connectivity in Parkinson's disease

Parkinson's disease (PD) is a clinically heterogeneous disorder, which mainly affects patients' motor and non-motor function. Functional connectivity was preliminary explored and studied through resting state functional magnetic resonance imaging (rsfMRI). Through the topological analysis of 54 PD scans and 31 age-matched normal controls (NC) in the Neurocon dataset, leveraging on rsfMRI data, the brain functional connection and the Vietoris-Rips (VR) complex were constructed. The barcodes of the complex were calculated to reflect the changes of functional connectivity neural circuits (FCNC) in brain network. The 0-dimensional Betti number β0 means the number of connected branches in VR complex. The average number of connected branches in PD group was greater than that in NC group when the threshold δ ≤ 0.7. Two-sample Mann-Whitney U test and false discovery rate (FDR) correction were used for statistical analysis to investigate the FCNC changes between PD and NC groups. In PD group, under threshold of 0.7, the number of FCNC involved was significantly differences and these brain regions include the Cuneus_R, Lingual_R, Fusiform_R and Heschl_R. There are also significant differences in brain regions in the Frontal_Inf_Orb_R and Pallidum_R, when the threshold increased to 0.8 and 0.9 (p < 0.05). In addition, when the length of FCNC was medium, there was a significant statistical difference between the PD group and the NC group in the Neurocon dataset and the Parkinson's Progression Markers Initiative (PPMI) dataset. Topological analysis based on rsfMRI data may provide comprehensive information about the changes of FCNC and may provide an alternative for clinical differential diagnosis.

Brain disease research based on functional magnetic resonance imaging data and machine learning: a review

Brain diseases, including neurodegenerative diseases and neuropsychiatric diseases, have long plagued the lives of the affected populations and caused a huge burden on public health. Functional magnetic resonance imaging (fMRI) is an excellent neuroimaging technology for measuring brain activity, which provides new insight for clinicians to help diagnose brain diseases. In recent years, machine learning methods have displayed superior performance in diagnosing brain diseases compared to conventional methods, attracting great attention from researchers. This paper reviews the representative research of machine learning methods in brain disease diagnosis based on fMRI data in the recent three years, focusing on the most frequent four active brain disease studies, including Alzheimer's disease/mild cognitive impairment, autism spectrum disorders, schizophrenia, and Parkinson's disease. We summarize these 55 articles from multiple perspectives, including the effect of the size of subjects, extracted features, feature selection methods, classification models, validation methods, and corresponding accuracies. Finally, we analyze these articles and introduce future research directions to provide neuroimaging scientists and researchers in the interdisciplinary fields of computing and medicine with new ideas for AI-aided brain disease diagnosis.

Abnormal functional connectivity density involvement in freezing of gait and its application for subtyping Parkinson's disease

The pathophysiological mechanisms at work in Parkinson's disease (PD) patients with freezing of gait (FOG) remain poorly understood. Functional connectivity density (FCD) could provide an unbiased way to analyse connectivity across the brain. In this study, a total of 23 PD patients with FOG (PD FOG + patients), 26 PD patients without FOG (PD FOG- patients), and 22 healthy controls (HCs) were recruited, and their resting-state functional magnetic resonance imaging (rs-fMRI) images were collected. FCD mapping was first performed to identify differences between groups. Pearson correlation analysis was used to explore relationships between FCD values and the severity of FOG. Then, a machine learning model was employed to classify each pair of groups. PD FOG + patients showed significantly increased short-range FCD in the precuneus, cingulate gyrus, and fusiform gyrus and decreased long-range FCD in the frontal gyrus, temporal gyrus, and cingulate gyrus. Short-range FCD values in the middle temporal gyrus and inferior temporal gyrus were positively correlated with FOG questionnaire (FOGQ) scores, and long-range FCD values in the middle frontal gyrus were negatively correlated with FOGQ scores. Using FCD in abnormal regions as input, a support vector machine (SVM) classifier can achieve classification with good performance. The mean accuracy values were 0.895 (PD FOG + vs. HC), 0.966 (PD FOG- vs. HC), and 0.897 (PD FOG + vs. PD FOG-). This study demonstrates that PD FOG + patients showed altered short- and long-range FCD in several brain regions involved in action planning and control, motion processing, emotion, cognition, and object recognition.

Amplitude of low-frequency fluctuation-based regional radiomics similarity network: Biomarker for Parkinson's disease

Parkinson's disease (PD) is a highly heterogeneous disorder that is difficult to diagnose. Therefore, reliable biomarkers are needed. We implemented a method constructing a regional radiomics similarity network (R2SN) based on the amplitude of low-frequency fluctuation (ALFF). We classified patients with PD and healthy individuals by using a machine learning approach in accordance with the R2SN connectome. The ALFF-based R2SN exhibited great reproducibility with different brain atlases and datasets. Great classification performances were achieved both in primary (AUC = 0.85 ± 0.02 and accuracy = 0.81 ± 0.03) and independent external validation (AUC = 0.77 and accuracy = 0.70) datasets. The discriminative R2SN edges correlated with the clinical evaluations of patients with PD. The nodes of discriminative R2SN edges were primarily located in the default mode, sensorimotor, executive control, visual and frontoparietal network, cerebellum and striatum. These findings demonstrate that ALFF-based R2SN is a robust potential neuroimaging biomarker for PD and could provide new insights into connectome reorganization in PD.

Predicting responses to cognitive behavioral therapy in obsessive-compulsive disorder based on multilevel indices of rs-fMRI

OBJECTIVE

This study aimed to identify neuroimaging predictors to predict the response of cognitive behavioral therapy (CBT) in patients with obsessive-compulsive disorder (OCD) based on indices of resting-state functional magnetic resonance imaging (rs-fMRI).

METHODS

Fifty patients with OCD were enrolled and allocated to either high or low responder groups after CBT using a 50 % response rate as the delineator. The pre-treatment amplitude of low-frequency fluctuation (ALFF), fractional ALFF (fALFF), regional homogeneity (ReHo), and degree centrality (DC) in each cerebrum region, defined by automated anatomical labeling atlas, were extracted. Least absolute shrinkage and selection operator and logistic regression were used to select features and establish models.

RESULTS

The combination of multilevel rs-fMRI indices achieved the best performance, with a cross-validation area under the receiver operating characteristic curve (AUC) of 0.900. In this combined model, an increase of interquartile range (IQR) in fALFF of right inferior orbital frontal gyrus (IOFG), and ReHo of left hippocampus and superior occipital gyrus (SOG) corresponded to a 26.52 %, 38.67 % and 24.38 % increase in the possibility to be high responders of CBT, respectively. ALFF of left thalamus and ReHo of left putamen were negatively associated with the response to CBT, with a 14.30 % and 19.91 % decrease per IQR increase of the index value.

CONCLUSION

The combination of ALFF, fALFF and ReHo achieved a better predictive performance than separate index. Pre-treatment ALFF of the left thalamus, fALFF of the right IOFG, ReHo of the left hippocampus, SOG and putamen can be used as predictors of CBT response.

Identification of chronic mild traumatic brain injury using resting state functional MRI and machine learning techniques

Mild traumatic brain injury (mTBI) is a major public health concern that can result in a broad spectrum of short-term and long-term symptoms. Recently, machine learning (ML) algorithms have been used in neuroscience research for diagnostics and prognostic assessment of brain disorders. The present study aimed to develop an automatic classifier to distinguish patients suffering from chronic mTBI from healthy controls (HCs) utilizing multilevel metrics of resting-state functional magnetic resonance imaging (rs-fMRI). Sixty mTBI patients and forty HCs were enrolled and allocated to training and testing datasets with a ratio of 80:20. Several rs-fMRI metrics including fractional amplitude of low-frequency fluctuation (fALFF), regional homogeneity (ReHo), degree centrality (DC), voxel-mirrored homotopic connectivity (VMHC), functional connectivity strength (FCS), and seed-based FC were generated from two main analytical categories: local measures and network measures. Statistical two-sample t-test was employed comparing between mTBI and HCs groups. Then, for each rs-fMRI metric the features were selected extracting the mean values from the clusters showing significant differences. Finally, the support vector machine (SVM) models based on separate and multilevel metrics were built and the performance of the classifiers were assessed using five-fold cross-validation and via the area under the receiver operating characteristic curve (AUC). Feature importance was estimated using Shapley additive explanation (SHAP) values. Among local measures, the range of AUC was 86.67-100% and the optimal SVM model was obtained based on combined multilevel rs-fMRI metrics and DC as a separate model with AUC of 100%. Among network measures, the range of AUC was 80.42-93.33% and the optimal SVM model was obtained based on the combined multilevel seed-based FC metrics. The SHAP analysis revealed the DC value in the left postcentral and seed-based FC value between the motor ventral network and right superior temporal as the most important local and network features with the greatest contribution to the classification models. Our findings demonstrated that different rs-fMRI metrics can provide complementary information for classifying patients suffering from chronic mTBI. Moreover, we showed that ML approach is a promising tool for detecting patients with mTBI and might serve as potential imaging biomarker to identify patients at individual level.

Clinical trial registration

[clinicaltrials.gov], identifier [NCT03241732].

Classification of Parkinson's disease motor phenotype: a machine learning approach

To assess the cortical activity in people with Parkinson's disease (PwP) with different motor phenotype (tremor-dominant-TD and postural instability and gait difficulty-PIGD) and to compare with controls. Twenty-four PwP (during OFF and ON medication) and twelve age-/sex-/handedness-matched healthy controls underwent electrophysiological assessment of spectral ratio analysis through electroencephalography (EEG) at resting state and during the hand movement. We performed a machine learning method with 35 attributes extracted from EEG. To verify the efficiency of the proposed phenotype-based EEG classification the random forest and random tree were tested (performed 30 times, using a tenfolds cross validation in Weka environment). The analyses based on phenotypes indicated a slowing down of cortical activity during OFF medication state in PwP. PD with TD phenotype presented this characteristic at resting and the individuals with PIGD presented during the hand movement. During the ON state, there is no difference between phenotypes at resting nor during the hand movement. PD phenotypes may influence spectral activity measured by EEG. Random forest machine learning provides a slightly more accurate, sensible and specific approach to distinguish different PD phenotypes. The phenotype of PD might be a clinical characteristic that could influence cortical activity.

Treadmill training in Parkinson's disease is underpinned by the interregional connectivity in cortical-subcortical network

Treadmill training (TT) has been extensively used as an intervention to improve gait and mobility in patients with Parkinson's disease (PD). Regional and global effects on brain activity could be induced through TT. Training effects can lead to a beneficial shift of interregional connectivity towards a physiological range. The current work investigates the effects of TT on brain activity and connectivity during walking and at rest by using both functional near-infrared spectroscopy and functional magnetic resonance imaging. Nineteen PD patients (74.0 ± 6.59 years, 13 males, disease duration 10.45 ± 6.83 years) before and after 6 weeks of TT, along with 19 age-matched healthy controls were assessed. Interregional effective connectivity (EC) between cortical and subcortical regions were assessed and its interrelation to prefrontal cortex (PFC) activity. Support vector regression (SVR) on the resting-state ECs was used to predict prefrontal connectivity. In response to TT, EC analysis indicated modifications in the patients with PD towards the level of healthy controls during walking and at rest. SVR revealed cerebellum related connectivity patterns that were associated with the training effect on PFC. These findings suggest that the potential therapeutic effect of training on brain activity may be facilitated via changes in compensatory modulation of the cerebellar interregional connectivity.

Machine Learning for Detecting Parkinson's Disease by Resting-State Functional Magnetic Resonance Imaging: A Multicenter Radiomics Analysis

Parkinson's disease (PD) is one of the most common progressive degenerative diseases, and its diagnosis is challenging on clinical grounds. Clinically, effective and quantifiable biomarkers to detect PD are urgently needed. In our study, we analyzed data from two centers, the primary set was used to train the model, and the independent external validation set was used to validate our model. We applied amplitude of low-frequency fluctuation (ALFF)-based radiomics method to extract radiomics features (including first- and high-order features). Subsequently, t-test and least absolute shrinkage and selection operator (LASSO) were harnessed for feature selection and data dimensionality reduction, and grid search method and nested 10-fold cross-validation were applied to determine the optimal hyper-parameter λ of LASSO and evaluate the performance of the model, in which a support vector machine was used to construct the classification model to classify patients with PD and healthy controls (HCs). We found that our model achieved good performance [accuracy = 81.45% and area under the curve (AUC) = 0.850] in the primary set and good generalization in the external validation set (accuracy = 67.44% and AUC = 0.667). Most of the discriminative features were high-order radiomics features, and the identified brain regions were mainly located in the sensorimotor network and lateral parietal cortex. Our study indicated that our proposed method can effectively classify patients with PD and HCs, ALFF-based radiomics features that might be potential biomarkers of PD, and provided further support for the pathological mechanism of PD, that is, PD may be related to abnormal brain activity in the sensorimotor network and lateral parietal cortex.