Combined structural and functional patterns discriminating upper limb motor disability in multiple sclerosis using multivariate approaches

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

Altered neural intrinsic oscillations in patients with multiple sclerosis: effects of cortical thickness

Objective

To investigate the effects of cortical thickness on the identification accuracy of fractional amplitude of low-frequency fluctuation (fALFF) in patients with multiple sclerosis (MS).

Methods

Resting-state functional magnetic resonance imaging data were collected from 31 remitting MS, 20 acute MS, and 42 healthy controls (HCs). After preprocessing, we first calculated two-dimensional fALFF (2d-fALFF) maps using the DPABISurf toolkit, and 2d-fALFF per unit thickness was obtained by dividing 2d-fALFF by cortical thickness. Then, between-group comparison, clinical correlation, and classification analyses were performed in 2d-fALFF and 2d-fALFF per unit thickness maps. Finally, we also examined whether the effect of cortical thickness on 2d-fALFF maps was affected by the subfrequency band.

Results

In contrast with 2d-fALFF, more changed regions in 2d-fALFF per unit thickness maps were detected in MS patients, such as increased region of the right inferior frontal cortex and faded regions of the right paracentral lobule, middle cingulate cortex, and right medial temporal cortex. There was a significant positive correlation between the disease duration and the 2d-fALFF values in the left early visual cortex in remitting MS patients (r = 0.517, Bonferroni-corrected, p = 0.008 × 4 < 0.05). In contrast with 2d-fALFF, we detected a positive correlation between the 2d-fALFF per unit thickness of the right ventral stream visual cortex and the modified Fatigue Impact Scale (MFIS) scores (r = 0.555, Bonferroni-corrected, p = 0.017 × 4 > 0.05). For detecting MS patients, 2d-fALFF and 2d- fALFF per unit thickness both performed remarkably well in support vector machine (SVM) analysis, especially in the remitting phase (AUC = 86, 83%). Compared with 2d-fALFF, the SVM model of 2d-fALFF per unit thickness had significantly higher classification performance in distinguishing between remitting and acute MS. More changed regions and more clinically relevant 2d-fALFF per unit thickness maps in the subfrequency band were also detected in MS patients.

Conclusion

By dividing the functional value by the cortical thickness, the identification accuracy of fALFF in MS patients was detected to be potentially influenced by cortical thickness. Additionally, 2d-fALFF per unit thickness is a potential diagnostic marker that can be utilized to distinguish between acute and remitting MS patients. Notably, we observed similar variations in the subfrequency band.

Robust sex differences in functional brain connectivity are present in utero

Sex-based differences in brain structure and function are observable throughout development and are thought to contribute to differences in behavior, cognition, and the presentation of neurodevelopmental disorders. Using multiple support vector machine (SVM) models as a data-driven approach to assess sex differences, we sought to identify regions exhibiting sex-dependent differences in functional connectivity and determine whether they were robust and sufficiently reliable to classify sex even prior to birth. To accomplish this, we used a sample of 110 human fetal resting state fMRI scans from 95 fetuses, performed between 19 and 40 gestational weeks. Functional brain connectivity patterns classified fetal sex with 73% accuracy. Across SVM models, we identified features (functional connections) that reliably differentiated fetal sex. Highly consistent predictors included connections in the somatomotor and frontal areas alongside the hippocampus, cerebellum, and basal ganglia. Moreover, high consistency features also implicated a greater magnitude of cross-region connections in females, while male weighted features were predominately within anatomically bounded regions. Our findings indicate that these differences, which have been observed later in childhood, are present and reliably detectable even before birth. These results show that sex differences arise before birth in a manner that is consistent and reliable enough to be highly identifiable.

Multiple sclerosis diagnosis and phenotype identification by multivariate classification of in vivo frontal cortex metabolite profiles

Multiple sclerosis (MS) is a heterogeneous autoimmune disease for which diagnosis continues to rely on subjective clinical judgment over a battery of tests. Proton magnetic resonance spectroscopy (¹H MRS) enables the noninvasive in vivo detection of multiple small-molecule metabolites and is therefore in principle a promising means of gathering information sufficient for multiple sclerosis diagnosis and subtype classification. Here we show that supervised classification using ¹H-MRS-visible normal-appearing frontal cortex small-molecule metabolites alone can indeed differentiate individuals with progressive MS from control (held-out validation sensitivity 79% and specificity 68%), as well as between relapsing and progressive MS phenotypes (held-out validation sensitivity 84% and specificity 74%). Post hoc assessment demonstrated the disproportionate contributions of glutamate and glutamine to identifying MS status and phenotype, respectively. Our finding establishes ¹H MRS as a viable means of characterizing progressive multiple sclerosis disease status and paves the way for continued refinement of this method as an auxiliary or mainstay of multiple sclerosis diagnostics.

Task- and resting-state fMRI studies in multiple sclerosis: From regions to systems and time-varying analysis. Current status and future perspective

•

Functional MRI is able to detect adaptive and maladaptive abnormalities at different MS stages.

•

Increased fMRI activity is a feature of early MS, while progressive exhaustion of adaptive mechanisms is detected later on in the disease.

•

Collapse of long-range connections and impaired hub integration characterize MS network reorganization.

•

Time-varying connectivity analysis provides useful and complementary pieces of information to static functional connectivity.

•

New perspectives might be the use of multimodal MRI and artificial intelligence.

Multiple sclerosis (MS) is a neurological disorder affecting the central nervous system and features extensive functional brain changes that are poorly understood but relate strongly to clinical impairments. Functional magnetic resonance imaging (fMRI) is a non-invasive, powerful technique able to map activity of brain regions and to assess how such regions interact for an efficient brain network. FMRI has been widely applied to study functional brain changes in MS, allowing to investigate functional plasticity consequent to disease-related structural injury. The first studies in MS using active fMRI tasks mainly aimed to study such plastic changes by identifying abnormal activity in salient brain regions (or systems) involved by the task. In later studies the focus shifted towards resting state (RS) functional connectivity (FC) studies, which aimed to map large-scale functional networks of the brain and to establish how MS pathology impairs functional integration, eventually leading to the hypothesized network collapse as patients clinically progress. This review provides a summary of the main findings from studies using task-based and RS fMRI and illustrates how functional brain alterations relate to clinical disability and cognitive deficits in this condition. We also give an overview of longitudinal studies that used task-based and RS fMRI to monitor disease evolution and effects of motor and cognitive rehabilitation. In addition, we discuss the results of studies using newer technologies involving time-varying FC to investigate abnormal dynamism and flexibility of network configurations in MS. Finally, we show some preliminary results from two recent topics (i.e., multimodal MRI analysis and artificial intelligence) that are receiving increasing attention. Together, these functional studies could provide new (conceptual) insights into disease stage-specific mechanisms underlying progression in MS, with recommendations for future research.

Dynamic Functional Connectivity Better Predicts Disability Than Structural and Static Functional Connectivity in People With Multiple Sclerosis

Background: Advanced imaging techniques such as diffusion and functional MRI can be used to identify pathology-related changes to the brain's structural and functional connectivity (SC and FC) networks and mapping of these changes to disability and compensatory mechanisms in people with multiple sclerosis (pwMS). No study to date performed a comparison study to investigate which connectivity type (SC, static or dynamic FC) better distinguishes healthy controls (HC) from pwMS and/or classifies pwMS by disability status.

Aims: We aim to compare the performance of SC, static FC, and dynamic FC (dFC) in classifying (a) HC vs. pwMS and (b) pwMS who have no disability vs. with disability. The secondary objective of the study is to identify which brain regions' connectome measures contribute most to the classification tasks.

Materials and Methods: One hundred pwMS and 19 HC were included. Expanded Disability Status Scale (EDSS) was used to assess disability, where 67 pwMS who had EDSS<2 were considered as not having disability. Diffusion and resting-state functional MRI were used to compute the SC and FC matrices, respectively. Logistic regression with ridge regularization was performed, where the models included demographics/clinical information and either pairwise entries or regional summaries from one of the following matrices: SC, FC, and dFC. The performance of the models was assessed using the area under the receiver operating curve (AUC).

Results: In classifying HC vs. pwMS, the regional SC model significantly outperformed others with a median AUC of 0.89 (p <0.05). In classifying pwMS by disability status, the regional dFC and dFC metrics models significantly outperformed others with a median AUC of 0.65 and 0.61 (p < 0.05). Regional SC in the dorsal attention, subcortical and cerebellar networks were the most important variables in the HC vs. pwMS classification task. Increased regional dFC in dorsal attention and visual networks and decreased regional dFC in frontoparietal and cerebellar networks in certain dFC states was associated with being in the group of pwMS with evidence of disability.

Discussion: Damage to SCs is a hallmark of MS and, unsurprisingly, the most accurate connectomic measure in classifying patients and controls. On the other hand, dynamic FC metrics were most important for determining disability level in pwMS, and could represent functional compensation in response to white matter pathology in pwMS.

Structural disconnectivity from paramagnetic rim lesions is related to disability in multiple sclerosis

BACKGROUND

In people with multiple sclerosis (pwMS), lesions with a hyperintense rim (rim+) on Quantitative Susceptibility Mapping (QSM) have been shown to have greater myelin damage compared to rim- lesions, but their association with disability has not yet been investigated. Furthermore, how QSM rim+ and rim- lesions differentially impact disability through their disruptions to structural connectivity has not been explored. We test the hypothesis that structural disconnectivity due to rim+ lesions is more predictive of disability compared to structural disconnectivity due to rim- lesions.

METHODS

Ninety-six pwMS were included in our study. Individuals with Expanded Disability Status Scale (EDSS) <2 were considered to have lower disability (n = 59). For each gray matter region, a Change in Connectivity (ChaCo) score, that is, the percent of connecting streamlines also passing through a rim- or rim+ lesion, was computed. Adaptive Boosting was used to classify the pwMS into lower versus greater disability groups based on ChaCo scores from rim+ and rim- lesions. Classification performance was assessed using the area under ROC curve (AUC).

RESULTS

The model based on ChaCo from rim+ lesions outperformed the model based on ChaCo from rim- lesions (AUC = 0.67 vs 0.63, p-value < .05). The left thalamus and left cerebellum were the most important regions in classifying pwMS into disability categories.

CONCLUSION

rim+ lesions may be more influential on disability through their disruptions to the structural connectome than rim- lesions. This study provides a deeper understanding of how rim+ lesion location/size and resulting disruption to the structural connectome can contribute to MS-related disability.

Estimated connectivity networks outperform observed connectivity networks when classifying people with multiple sclerosis into disability groups

BACKGROUND

Multiple Sclerosis (MS), a neurodegenerative and neuroinflammatory disease, causing lesions that disrupt the brain's anatomical and physiological connectivity networks, resulting in cognitive, visual and/or motor disabilities. Advanced imaging techniques like diffusion and functional MRI allow measurement of the brain's structural connectivity (SC) and functional connectivity (FC) networks, and can enable a better understanding of how their disruptions cause disability in people with MS (pwMS). However, advanced MRI techniques are used mainly for research purposes as they are expensive, time-consuming and require high-level expertise to acquire and process. As an alternative, the Network Modification (NeMo) Tool can be used to estimate SC and FC using lesion masks derived from pwMS and a reference set of controls' connectivity networks.

OBJECTIVE

Here, we test the hypothesis that estimated SC and FC (eSC and eFC) from the NeMo Tool, based only on an individual's lesion masks, can be used to classify pwMS into disability categories just as well as SC and FC extracted from advanced MRI directly in pwMS. We also aim to find the connections most important for differentiating between no disability vs evidence of disability groups.

MATERIALS AND METHODS

One hundred pwMS (age:45.5 ± 11.4 years, 66% female, disease duration: 12.97 ± 8.07 years) were included in this study. Expanded Disability Status Scale (EDSS) was used to assess disability, 67 pwMS had no disability (EDSS < 2). Observed SC and FC were extracted from diffusion and functional MRI directly in pwMS, respectively. The NeMo Tool was used to estimate the remaining structural connectome (eSC), by removing streamlines in a reference set of tractograms that intersected the lesion mask. The NeMo Tool's eSC was used then as input to a deep neural network to estimate the corresponding FC (eFC). Logistic regression with ridge regularization was used to classify pwMS into disability categories (no disability vs evidence of disability), based on demographics/clinical information (sex, age, race, disease duration, clinical phenotype, and spinal lesion burden) and either pairwise entries or regional summaries from one of the following matrices: SC, FC, eSC, and eFC. The area under the ROC curve (AUC) was used to assess the classification performance. Both univariate statistics and parameter coefficients from the classification models were used to identify features important to differentiating between the groups.

RESULTS

The regional eSC and eFC models outperformed their observed FC and SC counterparts (p-value < 0.05), while the pairwise eSC and SC performed similarly (p = 0.10). Regional eSC and eFC models had higher AUC (0.66-0.68) than the pairwise models (0.60-0.65), with regional eFC having highest classification accuracy across all models. Ridge regression coefficients for the regional eFC and regional observed FC models were significantly correlated (Pearson's r = 0.52, p-value < 10e-7). Decreased estimated SC node strength in default mode and ventral attention networks and increased eFC node strength in visual networks was associated with evidence of disability.

DISCUSSION

Here, for the first time, we use clinically acquired lesion masks to estimate both structural and functional connectomes in patient populations to better understand brain lesion-dysfunction mapping in pwMS. Models based on the NeMo Tool's estimates of SC and FC better classified pwMS by disability level than SC and FC observed directly in the individual using advanced MRI. This work provides a viable alternative to performing high-cost, advanced MRI in patient populations, bringing the connectome one step closer to the clinic.

Current review and next steps for artificial intelligence in multiple sclerosis risk research

In the last few decades, the prevalence of multiple sclerosis (MS), a chronic inflammatory disease of the nervous system, has increased, particularly in Northern European countries, the United States, and United Kingdom. The promise of artificial intelligence (AI) and machine learning (ML) as tools to address problems in MS research has attracted increasing interest in these methods. Bayesian networks offer a clear advantage since they can integrate data and causal knowledge allowing for visualizing interactions between dependent variables and potential confounding factors. A review of AI/ML research methods applied to MS found 216 papers using terms "Multiple Sclerosis", "machine learning", "artificial intelligence", "Bayes", and "Bayesian", of which 90 were relevant and recently published. More than half of these involve the detection and segmentation of MS lesions for quantitative analysis; however clinical and lifestyle risk factor assessment and prediction have largely been ignored. Of those that address risk factors, most provide only association studies for some factors and often fail to include the potential impact of confounding factors and bias (especially where these have causal explanations) that could affect data interpretation, such as reporting quality and medical care access in various countries. To address these gaps in the literature, we propose a causal Bayesian network approach to assessing risk factors for MS, which can address deficiencies in current epidemiological methods of producing risk measurements and makes better use of observational data.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

Machine learning in secondary progressive multiple sclerosis: an improved predictive model for short-term disability progression

Background

Enhanced prediction of progression in secondary progressive multiple sclerosis (SPMS) could improve clinical trial design. Machine learning (ML) algorithms are methods for training predictive models with minimal human intervention.

Objective

To evaluate individual and ensemble model performance built using decision tree (DT)-based algorithms compared to logistic regression (LR) and support vector machines (SVMs) for predicting SPMS disability progression.

Methods

SPMS participants (n = 485) enrolled in a 2-year placebo-controlled (negative) trial assessing the efficacy of MBP8298 were classified as progressors if a 6-month sustained increase in Expanded Disability Status Scale (EDSS) (≥1.0 or ≥0.5 for a baseline of ≤5.5 or ≥6.0 respectively) was observed. Variables included EDSS, Multiple Sclerosis Functional Composite component scores, T2 lesion volume, brain parenchymal fraction, disease duration, age, and sex. Area under the receiver operating characteristic curve (AUC) was the primary outcome for model evaluation.

Results

Three DT-based models had greater AUCs (61.8%, 60.7%, and 60.2%) than independent and ensemble SVM (52.4% and 51.0%) and LR (49.5% and 51.1%).

Conclusion

SPMS disability progression was best predicted by non-parametric ML. If confirmed, ML could select those with highest progression risk for inclusion in SPMS trial cohorts and reduce the number of low-risk individuals exposed to experimental therapies.

Multivariate pattern classification of brain white matter connectivity predicts classic trigeminal neuralgia

Trigeminal neuralgia (TN) is a severe form of chronic facial neuropathic pain. Increasing interest in the neuroimaging of pain has highlighted changes in the root entry zone in TN, but also group-level central nervous system gray and white matter (WM) abnormalities. Group differences in neuroimaging data are frequently evaluated with univariate statistics; however, this approach is limited because it is based on single, or clusters of, voxels. By contrast, multivariate pattern analyses consider all the model's neuroanatomical features to capture a specific distributed spatial pattern. This approach has potential use as a prediction tool at the individual level. We hypothesized that a multivariate pattern classification method can distinguish specific patterns of abnormal WM connectivity of classic TN from healthy controls (HCs). Diffusion-weighted scans in 23 right-sided TN and matched controls were processed to extract whole-brain interregional streamlines. We used a linear support vector machine algorithm to differentiate interregional normalized streamline count between TN and HC. This algorithm successfully differentiated between TN and HC with an accuracy of 88%. The structural pattern emphasized WM connectivity of regions that subserve sensory, affective, and cognitive dimensions of pain, including the insula, precuneus, inferior and superior parietal lobules, and inferior and medial orbital frontal gyri. Normalized streamline counts were associated with longer pain duration and WM metric abnormality between the connections. This study demonstrates that machine-learning algorithms can detect characteristic patterns of structural alterations in TN and highlights the role of structural brain imaging for identification of neuroanatomical features associated with neuropathic pain disorders.

Upper Extremity Capability Tests in Multiple Sclerosis

Multiple sclerosis is a chronic demyelinating disease. Since attacks are accompanied by psychiatric and physical disabilities, additional symptoms such as withdrawal from the social environment and psychiatric disorders are also observed. It is very important to evaluate patients adequately and correctly, to determine the disability, and treat them with appropriate clinical approach. For this reason, Expanded Disability Status Scale score and upper extremity capacity measurement tests are used in many studies by investigators. These tests provide detailed examination on the patient's upper limbs, and indirectly provide information about their cognitive function. A multi-disciplinary approach for multiple sclerosis patients is the most crucial factor in clinical follow-up and treatment success.

Functional Connectivity in Multiple Sclerosis: Recent Findings and Future Directions

Multiple sclerosis is a debilitating disorder resulting from scattered lesions in the central nervous system. Because of the high variability of the lesion patterns between patients, it is difficult to relate existing biomarkers to symptoms and their progression. The scattered nature of lesions in multiple sclerosis offers itself to be studied through the lens of network analyses. Recent research into multiple sclerosis has taken such a network approach by making use of functional connectivity. In this review, we briefly introduce measures of functional connectivity and how to compute them. We then identify several common observations resulting from this approach: (a) high likelihood of altered connectivity in deep-gray matter regions, (b) decrease of brain modularity, (c) hemispheric asymmetries in connectivity alterations, and (d) correspondence of behavioral symptoms with task-related and task-unrelated networks. We propose incorporating such connectivity analyses into longitudinal studies in order to improve our understanding of the underlying mechanisms affected by multiple sclerosis, which can consequently offer a promising route to individualizing imaging-related biomarkers for multiple sclerosis.

Characterization of relapsing-remitting multiple sclerosis patients using support vector machine classifications of functional and diffusion MRI data

Multiple Sclerosis patients' clinical symptoms do not correlate strongly with structural assessment done with traditional magnetic resonance images. However, its diagnosis and evaluation of the disease's progression are based on a combination of this imaging analysis complemented with clinical examination. Therefore, other biomarkers are necessary to better understand the disease. In this paper, we capitalize on machine learning techniques to classify relapsing-remitting multiple sclerosis patients and healthy volunteers based on machine learning techniques, and to identify relevant brain areas and connectivity measures for characterizing patients. To this end, we acquired magnetic resonance imaging data from relapsing-remitting multiple sclerosis patients and healthy subjects. Fractional anisotropy maps, structural and functional connectivity were extracted from the scans. Each of them were used as separate input features to construct support vector machine classifiers. A fourth input feature was created by combining structural and functional connectivity. Patients were divided in two groups according to their degree of disability and, together with the control group, three group pairs were formed for comparison. Twelve separate classifiers were built from the combination of these four input features and three group pairs. The classifiers were able to distinguish between patients and healthy subjects, reaching accuracy levels as high as 89% ± 2%. In contrast, the performance was noticeably lower when comparing the two groups of patients with different levels of disability, reaching levels below 63% ± 5%. The brain regions that contributed the most to the classification were the right occipital, left frontal orbital, medial frontal cortices and lingual gyrus. The developed classifiers based on MRI data were able to distinguish multiple sclerosis patients and healthy subjects reliably. Moreover, the resulting classification models identified brain regions, and functional and structural connections relevant for better understanding of the disease.