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

2021 ◽  
Vol 15 ◽  
Author(s):  
Ceren Tozlu ◽  
Keith Jamison ◽  
Susan A. Gauthier ◽  
Amy Kuceyeski
Keyword(s):  
Multiple Sclerosis ◽  
Functional Connectivity ◽  
Functional Mri ◽  
Imaging Techniques ◽  
Clinical Information ◽  
Brain Regions ◽  
Receiver Operating Curve ◽  
Compensatory Mechanisms ◽  
Disability Status ◽  
Secondary Objective

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.

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

2021 ◽  
Author(s):  
Ceren Tozlu ◽  
Keith Jamison ◽  
Zijin Gu ◽  
Susan Gauthier ◽  
Amy Kuceyeski
Keyword(s):  
Multiple Sclerosis ◽  
Functional Mri ◽  
Disease Duration ◽  
Imaging Techniques ◽  
Brain Lesion ◽  
Structural Connectivity ◽  
Clinical Information ◽  
P Value ◽  
Reference Set ◽  
Disability Categories

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:45.51 ± 1.4 years, 66% female, disease duration: 12.97 ± 8.07 years) were included in this study. Expanded DisabilityStatus 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 andSC 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 pair-wise 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 were 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.

HLA-DRB1*04:05 allele is associated with intracortical lesions on three-dimensional double inversion recovery images in Japanese patients with multiple sclerosis

2017 ◽  
Vol 24 (6) ◽  
pp. 710-720 ◽  
Author(s):  
Koji Shinoda ◽  
Takuya Matsushita ◽  
Yuri Nakamura ◽  
Katsuhisa Masaki ◽  
Ryo Yamasaki ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Three Dimensional ◽  
Multivariate Logistic Regression Analysis ◽  
Clinical Information ◽  
Japanese Patients ◽  
Inversion Recovery ◽  
Double Inversion Recovery ◽  
Inversion Recovery Imaging ◽  
Disability Status ◽  
Caucasian Patients

Background: Cortical lesions (CLs) frequently observed in Caucasian patients with multiple sclerosis (MS) contribute to disability. However, it remains unclear whether CLs are associated with clinical features and genetic risk factors, such as HLA-DRB1*15:01 and -DRB1*04:05 in Asian MS patients. Objective: To elucidate the frequency of CLs and their association with HLA-DRB1 and DPB1 alleles in Japanese MS patients. Methods: Three-dimensional double inversion recovery imaging and clinical information were retrospectively obtained from 92 Japanese MS patients. Results: CLs of any type, intracortical lesions (ICLs), and leukocortical lesions (LCLs) were detected in 39.1%, 26.1%, and 28.3% of patients, respectively. MS patients with ICLs had a significantly higher frequency of secondary progression and greater Expanded Disability Status Scale (EDSS) scores than those without ICLs. Similar trends were observed with CLs and LCLs. The number of all three lesion types positively correlated with EDSS scores. The frequency and number of ICLs were significantly higher in HLA-DRB1*15:01 carriers than in HLA-DRB1*15:01 non-carriers, but significantly lower in HLA-DRB1*04:05 carriers than in HLA-DRB1*04:05 non-carriers. Multivariate logistic regression analysis revealed a negative association of HLA-DRB1*04:05 with ICLs. Conclusion: ICLs are associated with greater disease severity in Japanese MS patients and are partly suppressed by the HLA-DRB1*04:05 allele.

scholarly journals Long-range connections are more severely damaged and relevant for cognition in multiple sclerosis

Brain ◽  
2019 ◽  
Vol 143 (1) ◽  
pp. 150-160 ◽  
Author(s):  
Kim A Meijer ◽  
Martijn D Steenwijk ◽  
Linda Douw ◽  
Menno M Schoonheim ◽  
Jeroen J G Geurts
Keyword(s):  
Multiple Sclerosis ◽  
Functional Connectivity ◽  
Fractional Anisotropy ◽  
Long Range ◽  
Short Range ◽  
Brain Regions ◽  
Healthy Controls ◽  
Network Efficiency ◽  
Structural Network ◽  
The Impact

Abstract An efficient network such as the human brain features a combination of global integration of information, driven by long-range connections, and local processing involving short-range connections. Whether these connections are equally damaged in multiple sclerosis is unknown, as is their relevance for cognitive impairment and brain function. Therefore, we cross-sectionally investigated the association between damage to short- and long-range connections with structural network efficiency, the functional connectome and cognition. From the Amsterdam multiple sclerosis cohort, 133 patients (age = 54.2 ± 9.6) with long-standing multiple sclerosis and 48 healthy controls (age = 50.8 ± 7.0) with neuropsychological testing and MRI were included. Structural connectivity was estimated from diffusion tensor images using probabilistic tractography (MRtrix 3.0) between pairs of brain regions. Structural connections were divided into short- (length &lt; quartile 1) and long-range (length &gt; quartile 3) connections, based on the mean distribution of tract lengths in healthy controls. To determine the severity of damage within these connections, (i) fractional anisotropy as a measure for integrity; (ii) total number of fibres; and (iii) percentage of tract affected by lesions were computed for each connecting tract and averaged for short- and long-range connections separately. To investigate the impact of damage in these connections for structural network efficiency, global efficiency was computed. Additionally, resting-state functional connectivity was computed between each pair of brain regions, after artefact removal with FMRIB’s ICA-based X-noiseifier. The functional connectivity similarity index was computed by correlating individual functional connectivity matrices with an average healthy control connectivity matrix. Our results showed that the structural network had a reduced efficiency and integrity in multiple sclerosis relative to healthy controls (both P &lt; 0.05). The long-range connections showed the largest reduction in fractional anisotropy (z = −1.03, P &lt; 0.001) and total number of fibres (z = −0.44, P &lt; 0.01), whereas in the short-range connections only fractional anisotropy was affected (z = −0.34, P = 0.03). Long-range connections also demonstrated a higher percentage of tract affected by lesions than short-range connections, independent of tract length (P &lt; 0.001). Damage to long-range connections was more strongly related to structural network efficiency and cognition (fractional anisotropy: r = 0.329 and r = 0.447. number of fibres r = 0.321 and r = 0.278. and percentage of lesions: r = −0.219; r = −0.426, respectively) than damage to short-range connections. Only damage to long-distance connections correlated with a more abnormal functional network (fractional anisotropy: r = 0.226). Our findings indicate that long-range connections are more severely affected by multiple sclerosis-specific damage than short-range connections. Moreover compared to short-range connections, damage to long-range connections better explains network efficiency and cognition.

scholarly journals Brain Resting State Functional Networks in Infants with Prenatal Opioid Exposure

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Nicole Steinhardt ◽  
Ramana Vishnubhotla ◽  
Yi Zhao ◽  
David M. Haas ◽  
Gregory M. Sokol ◽  
...  
Keyword(s):  
Functional Connectivity ◽  
Functional Mri ◽  
Gestational Age ◽  
Resting State ◽  
Brain Regions ◽  
Brain Network ◽  
Anterior Cingulate ◽  
Global Network ◽  
Neurodevelopmental Outcomes ◽  
Distinct Component

Purpose: Infants of mothers with opioid and substance use can present with postnatal withdrawal symptoms and are at risk of poor neurodevelopmental outcomes in later childhood. Identifying methods to evaluate the consequences of substance exposure on the developing brain can help initiate proactive therapies to improve outcomes for opioid-exposed neonates. Additionally, early brain imaging in infancy has the potential to identify early brain developmental alterations that could prognosticate neurodevelopmental outcomes in these children. In this study, we aim to identify differences in global brain network connectivity in infants with prenatal opioid exposure compared to healthy control infants, using resting-state functional MRI performed at less than 2 months completed gestational age.   Materials and Methods: In this prospective, IRB-approved study, we recruited 20 infants with prenatal opioid exposure and 20 healthy, opioid naïve infants. Anatomic imaging and resting-state functional MRI were performed at less than 48 weeks corrected gestational age, and rs-fMRI images were co-registered to the UNC neonate brain template and 90 anatomic atlas-labelled regions. Covariate Assisted Principal (CAP) regression was performed to identify brain network functional connectivity that was significantly different among infants with prenatal opioid exposure compared to healthy neonates.   Results: Of the 5 significantly different CAP components identified, the most distinct component (CAP5, p= 3.86 x 10-6) spanned several brain regions, including the right inferior temporal gyrus, bilateral Hesch’s gyrus, left thalamus, left supramarginal gyrus, left inferior parietal lobule, left superior parietal gyrus, right anterior cingulate gyrus, right gyrus rectus, left supplementary motor area, and left pars triangularis. Functional connectivity in this network was lower in the infants with prenatal opioid exposure compared to non-opioid exposed infants.   Conclusion: This study demonstrates global network alterations in infants with prenatal opioid exposure compared to non-opioid exposed infants. Future studies should be aimed at identifying clinical significance of this altered connectivity.

scholarly journals Structural and functional connectomes in people with multiple sclerosis

2020 ◽  
Author(s):  
Ceren Tozlu ◽  
Keith Jamison ◽  
Susan Gauthier ◽  
Amy Kuceyeski
Keyword(s):  
Multiple Sclerosis ◽  
Functional Mri ◽  
Imaging Modality ◽  
Structural Connectivity ◽  
Receiver Operating Curve ◽  
Ensemble Prediction ◽  
P Value ◽  
Lesion Volume ◽  
Healthy Controls ◽  
Functional Connectome

One of the challenges in multiple sclerosis is that lesion volume does not correlate with symptom severity. Advanced techniques such as diffusion and functional MRI allow imaging of the brain's connectivity networks, which may provide better insight as to brain-behavior relationships in impairment and compensation in multiple sclerosis. We aim to build machine learning models based on structural and functional connectomes to classify a) healthy controls versus people with multiple sclerosis and b) impaired versus not impaired people with multiple sclerosis. We also aim to identify the most important imaging modality for both classification tasks, and, finally, to investigate which brain regions' connectome measures contribute most to the classification. Fifteen healthy controls (age=43.6 ± 8.6, 53% female) and 76 people with multiple sclerosis (age: 45.2 ± 11.4 years, 65% female, disease duration: 12.2 ± 7.2 years) were included. Twenty-three people with multiple sclerosis were considered impaired, with an Expanded Disability Status Scale of 2 or higher. Subjects underwent MRI scans that included anatomical, diffusion and resting-state functional MRI. Random Forest models were constructed using structural and static/dynamic functional connectome measures independently; single modality models were then combined for an ensemble prediction. The accuracy of the models was assessed by the area under the receiver operating curve. Models that included structural connectomes significantly outperformed others when classifying healthy controls and people with multiple sclerosis, having a median accuracy of 0.86 (p-value<0.05, corrected). Models that included dynamic functional connectome metrics significantly outperformed others when distinguishing people with multiple sclerosis by impairment level, having a median accuracy of 0.63 (p-value<0.05, corrected). Structural connectivity between subcortical, somatomotor, and visual networks was most damaged by multiple sclerosis. For the classification of patients with multiple sclerosis into impairment severity groups, the most discriminatory metric was dwell time in a dynamic functional connectome state characterized by strong connectivity between and among somatomotor and visual networks. These results suggest that damage to the structural connectome, particularly in the subcortical, visual, and somatomotor networks, is a hallmark of multiple sclerosis, and, furthermore, that increased functional coordination between these same regions may be related to severity of motor disability in multiple sclerosis. The use of multi-modal connectome imaging has the potential to shed light on mechanisms of disease and compensation in multiple sclerosis, thus enabling more accurate prognoses and possibly the development of novel therapeutics.

scholarly journals The Economic Burden of Different Multiple Sclerosis Courses: Analysis from Italian Administrative and Clinical Databases

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Paolo Angelo Cortesi ◽  
Paolo Cozzolino ◽  
Ruggero Capra ◽  
Giancarlo Cesana ◽  
Lorenzo Giovanni Mantovani
Keyword(s):  
Multiple Sclerosis ◽  
Clinical Information ◽  
Clinical Databases ◽  
Disability Status ◽  
Relapsing Remitting ◽  
Illness Study ◽  
The Mean ◽  
The Cost ◽  
Mean Cost ◽  
Cost Of Illness Study

INTRODUCTION: Poor specific economic information are available for the different Multiple Sclerosis (MS) courses: relapsing remitting (RRMS), secondary progressive (SPMS) and primary progressive (PPMS). This study aims to fill this gap.METHODS: A cost of illness study was conducted. Clinical information of patients treated in a major MS Center located in Lombardy, in the period 2004-2010, were linked with administrative data of Lombardy Healthcare System. We assessed the mean cost per patient-year and its association with different MS characteristics.RESULTS: The study identified 869 patients (83.9% RRMS, 8.5% SPMS, 7.2% PPMS). RRMS reported the highest cost per patient-year with a mean of € 5,623 in Expanded Disability Status Scale (EDSS) 0-3, € 8,675 in EDSS 3.5-6.5, and € 7,451 in EDSS 7-9. The PPMS patients reported the lower annual mean cost per patient in all EDSS categories. The mul-tivariate analysis reported a significant association between cost per patient-year and EDSS categories, relapse and use of Disease Modifying Therapies but not to MS courses, age and sex.CONCLUSION: This study provides a complete picture of MS courses direct costs at the different disability levels. The results can help to better understand the burden of each MS courses and the cost-effectiveness of different interventions.

scholarly journals Increased functional sensorimotor network efficiency relates to disability in multiple sclerosis

2020 ◽  
pp. 135245852096629
Author(s):  
Myrte Strik ◽  
Declan T Chard ◽  
Iris Dekker ◽  
Kim A Meijer ◽  
Anand JC Eijlers ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Logistic Regression ◽  
Functional Connectivity ◽  
Structural Damage ◽  
Premotor Cortex ◽  
Functional Network ◽  
Grey Matter Volume ◽  
Network Efficiency ◽  
Brain Volumes ◽  
Disability Status

Background: Network abnormalities could help explain physical disability in multiple sclerosis (MS), which remains poorly understood. Objective: This study investigates functional network efficiency changes in the sensorimotor system. Methods: We included 222 MS patients, divided into low disability (LD, Expanded Disability Status Scale (EDSS) ⩽3.5, n = 185) and high disability (HD, EDSS ⩾6, n = 37), and 82 healthy controls (HC). Functional connectivity was assessed between 23 sensorimotor regions. Measures of efficiency were computed and compared between groups using general linear models corrected for age and sex. Binary logistic regression models related disability status to local functional network efficiency (LE), brain volumes and demographics. Functional connectivity patterns of regions important for disability were explored. Results: HD patients demonstrated significantly higher LE of the left primary somatosensory cortex (S1) and right pallidum compared to LD and HC, and left premotor cortex compared to HC only. The logistic regression model for disability ( R2 = 0.38) included age, deep grey matter volume and left S1 LE. S1 functional connectivity was increased with prefrontal and secondary sensory areas in HD patients, compared to LD and HC. Conclusion: Clinical disability in MS associates with functional sensorimotor increases in efficiency and connectivity, centred around S1, independent of structural damage.

scholarly journals Functional connectome differences in individuals with hallucinations across the psychosis continuum

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Maya J. L. Schutte ◽  
Marc M. Bohlken ◽  
Guusje Collin ◽  
Lucija Abramovic ◽  
Marco P. M. Boks ◽  
...  
Keyword(s):  
Functional Connectivity ◽  
Functional Mri ◽  
Resting State ◽  
Neural Mechanism ◽  
Brain Regions ◽  
Healthy Controls ◽  
Bipolar I Disorder ◽  
Functional Connectome ◽  
Psychosis Continuum ◽  
Mri Scans

AbstractHallucinations may arise from an imbalance between sensory and higher cognitive brain regions, reflected by alterations in functional connectivity. It is unknown whether hallucinations across the psychosis continuum exhibit similar alterations in functional connectivity, suggesting a common neural mechanism, or whether different mechanisms link to hallucinations across phenotypes. We acquired resting-state functional MRI scans of 483 participants, including 40 non-clinical individuals with hallucinations, 99 schizophrenia patients with hallucinations, 74 bipolar-I disorder patients with hallucinations, 42 bipolar-I disorder patients without hallucinations, and 228 healthy controls. The weighted connectivity matrices were compared using network-based statistics. Non-clinical individuals with hallucinations and schizophrenia patients with hallucinations exhibited increased connectivity, mainly among fronto-temporal and fronto-insula/cingulate areas compared to controls (P < 0.001 adjusted). Differential effects were observed for bipolar-I disorder patients with hallucinations versus controls, mainly characterized by decreased connectivity between fronto-temporal and fronto-striatal areas (P = 0.012 adjusted). No connectivity alterations were found between bipolar-I disorder patients without hallucinations and controls. Our results support the notion that hallucinations in non-clinical individuals and schizophrenia patients are related to altered interactions between sensory and higher-order cognitive brain regions. However, a different dysconnectivity pattern was observed for bipolar-I disorder patients with hallucinations, which implies a different neural mechanism across the psychosis continuum.

scholarly journals Migraine in Multiple Sclerosis Patients Affects Functional Connectivity of the Brain Circuitry Involved in Pain Processing

2021 ◽  
Vol 12 ◽  
Author(s):  
Emanuele Pravatà ◽  
Gianna C. Riccitelli ◽  
Carlo Sestieri ◽  
Rosaria Sacco ◽  
Alessandro Cianfoni ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Functional Connectivity ◽  
Pain Perception ◽  
Brain Regions ◽  
Daily Activities ◽  
Control Group ◽  
Resting State Functional Connectivity ◽  
Brain Circuitry ◽  
Multiple Sclerosis Patients ◽  
The Brain

Migraine is particularly common in patients with multiple sclerosis (MS) and has been linked to the dysfunction of the brain circuitry modulating the peripheral nociceptive stimuli. Using MRI, we explored whether changes in the resting state-functional connectivity (RS-FC) may characterize the occurrence of migraine in patients with MS. The RS-FC characteristics in concerned brain regions were explored in 20 MS patients with migraine (MS+M) during the interictal phase, and compared with 19 MS patients without migraine (MS-M), which served as a control group. Functional differences were correlated to the frequency and severity of previous migraine attacks, and with the resulting impact on daily activities. In MS+M, the loss of periaqueductal gray matter (PAG) positive connectivity with the default mode network and the left posterior cranial pons was associated with an increase of migraine attacks frequency. In contrast, the loss of PAG negative connectivity with sensorimotor and visual network was linked to migraine symptom severity and related daily activities impact. Finally, a PAG negative connection was established with the prefrontal executive control network. Migraine in MS+M patients and its impact on daily activities, underlies RS-FC rearrangements between brain regions involved in pain perception and modulation.

scholarly journals Prediction of disease progression and outcomes in multiple sclerosis with machine learning

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Mauro F. Pinto ◽  
Hugo Oliveira ◽  
Sónia Batista ◽  
Luís Cruz ◽  
Mafalda Pinto ◽  
...  
Keyword(s):  
Machine Learning ◽  
Multiple Sclerosis ◽  
Age At Onset ◽  
Clinical Information ◽  
Chronic Inflammatory Disease ◽  
Compensatory Mechanisms ◽  
Disease Evolution ◽  
Secondary Progressive ◽  
First Case ◽  
Multiple Sclerosis Patients

AbstractMultiple Sclerosis is a chronic inflammatory disease, affecting the Central Nervous System and leading to irreversible neurological damage, such as long term functional impairment and disability. It has no cure and the symptoms vary widely, depending on the affected regions, amount of damage, and the ability to activate compensatory mechanisms, which constitutes a challenge to evaluate and predict its course. Additionally, relapsing-remitting patients can evolve its course into a secondary progressive, characterized by a slow progression of disability independent of relapses. With clinical information from Multiple Sclerosis patients, we developed a machine learning exploration framework concerning this disease evolution, more specifically to obtain three predictions: one on conversion to secondary progressive course and two on disease severity with rapid accumulation of disability, concerning the 6th and 10th years of progression. For the first case, the best results were obtained within two years: AUC=$$0.86\pm 0.07$$ 0.86 ± 0.07 , sensitivity=$$0.76\pm 0.14$$ 0.76 ± 0.14 and specificity=$$0.77\pm 0.05$$ 0.77 ± 0.05 ; and for the second, the best results were obtained for the 6th year of progression, also within two years: AUC=$$0.89\pm 0.03$$ 0.89 ± 0.03 , sensitivity=$$0.84\pm 0.11$$ 0.84 ± 0.11 , and specificity=$$0.81\pm 0.05$$ 0.81 ± 0.05 . The Expanded Disability Status Scale value, the majority of functional systems, affected functions during relapses, and age at onset were described as the most predictive features. These results demonstrate the possibility of predicting Multiple Sclerosis progression by using machine learning, which may help to understand this disease’s dynamics and thus, advise physicians on medication intake.

Sign in / Sign up

Export Citation Format

Share Document