An Enhanced Multiple Sclerosis Disease Diagnosis via an Ensemble Approach.
Ontology highlight
ABSTRACT:
SUBMITTER: Torkey H
PROVIDER: S-EPMC9316893 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women's Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in Expanded Disability Status Scale (EDSS) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients' clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms (SVM, Logistic Regression, and Random Forest) and three ensemble learning approaches (XGBoost, LightGBM, and a Meta-learner L). A "threshold" was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, Pyramidal Function, and Ambulatory Index were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course.
| S-EPMC7567781 | biostudies-literature
Project description:OBJECTIVE:Evidence for a role of microglia in the pathogenesis of multiple sclerosis (MS) is growing. We investigated association of microglial markers at time of diagnostic lumbar puncture (LP) with different aspects of disease activity (relapses, disability, magnetic resonance imaging parameters) up to 6?years later in a cohort of 143 patients. METHODS:In cerebrospinal fluid (CSF), we measured 3 macrophage and microglia-related proteins, chitotriosidase (CHIT1), chitinase-3-like protein 1 (CHI3L1 or YKL-40), and soluble triggering receptor expressed on myeloid cells 2 (sTREM2), as well as a marker of neuronal damage, neurofilament light chain (NfL), using enzyme-linked immunosorbent assay and electrochemiluminescence. We investigated the same microglia-related markers in publicly available RNA expression data from postmortem brain tissue. RESULTS:CHIT1 levels at diagnostic LP correlated with 2 aspects of long-term disease activity after correction for multiple testing. First, CHIT1 increased with reduced tissue integrity in lesions at a median 3?years later (p = 9.6E-04). Second, CHIT1 reflected disease severity at a median 5?years later (p = 1.2E-04). Together with known clinical covariates, CHIT1 levels explained 12% and 27% of variance in these 2 measures, respectively, and were able to distinguish slow and fast disability progression (area under the curve = 85%). CHIT1 was the best discriminator of chronic active versus chronic inactive lesions and the only marker correlated with NfL (r = 0.3, p = 0.0019). Associations with disease activity were, however, independent of NfL. INTERPRETATION:CHIT1 CSF levels measured during the diagnostic LP reflect microglial activation early on in MS and can be considered a valuable prognostic biomarker for future disease activity. ANN NEUROL 2020;87:633-645.
| S-EPMC7187166 | biostudies-literature
Project description:Pediatric-onset multiple sclerosis (POMS) is a rare neuroinflammatory and neurodegenerative disease that has a significant impact on long-term physical and cognitive patient outcomes. A small percentage of multiple sclerosis (MS) diagnoses occur before the age of 18 years. Before treatment initiation, a careful differential diagnosis and exclusion of other similar acquired demyelinating syndromes such as anti-aquaporin-4-associated neuromyelitis optica spectrum disorder (AQP4-NMOSD) and myelin oligodendrocyte glycoprotein antibody spectrum disorder (MOGSD) is warranted. The recent 2017 changes to the McDonald criteria can successfully predict up to 71% of MS diagnoses and have good specificity of 95% and sensitivity of 71%. Additional measures such as the presence of T1-weighted hypointense lesions and/or contrast-enhancing lesions significantly increase the accuracy of diagnosis. In adults, early use of disease-modifying therapies (DMTs) is instrumental to a better long-term prognosis, including lower rates of relapse and disability worsening, and numerous FDA-approved therapies for adult-onset MS are available. However, unlike their adult counterparts, the development, testing, and regulatory approval of POMS treatments have been significantly slower and hindered by logistic and/or ethical considerations. Currently, only two MS DMTs (fingolimod and teriflunomide) have been tested in large phase III trials and approved by regulatory agencies for use in POMS. First-line therapies not approved by the FDA for use in children (interferon-β and glatiramer acetate) are also commonly used and result in a significant reduction in inflammatory activity when compared with non-treated POMS patients. An increasing number of POMS patients are now treated with moderate efficacy therapies such as dimethyl fumarate and high-efficacy therapies such as natalizumab, anti-CD20 monoclonal antibodies, anti-CD52 monoclonal antibodies, and/or autologous hematopoietic stem cell transplantation. These high-efficacy DMTs generally provide additional reduction in inflammatory activity when compared with the first-line medications (up to 62% of relapse-rate reduction). Therefore, a number of phase II and III trials are currently investigating their efficacy and safety in POMS patients. In this review, we discuss potential changes in the regulatory approval process for POMS patients that are recommended for DMTs already approved for the adult MS population, including smaller sample size for pharmacokinetic/pharmacodynamic studies, MRI-centered primary outcomes, and/or inclusion of teenagers in the adult trials.
| S-EPMC8697541 | biostudies-literature
Project description:Increasing evidence points to an important role for neutrophils in participating in the pathogenesis of the human demyelinating disease MS and the animal model EAE. Therefore, a better understanding of the signals controlling migration of neutrophils as well as evaluating the role of these cells in demyelination is important to define cellular components that contribute to disease in MS patients. In this study, we examined the functional role of the chemokine CXCL1 in contributing to neuroinflammation and demyelination in EAE. Using transgenic mice in which expression of CXCL1 is under the control of a tetracycline-inducible promoter active within glial fibrillary acidic protein-positive cells, we have shown that sustained CXCL1 expression within the CNS increased the severity of clinical and histologic disease that was independent of an increase in the frequency of encephalitogenic Th1 and Th17 cells. Rather, disease was associated with enhanced recruitment of CD11b+ Ly6G+ neutrophils into the spinal cord. Targeting neutrophils resulted in a reduction in demyelination arguing for a role for these cells in myelin damage. Collectively, these findings emphasize that CXCL1-mediated attraction of neutrophils into the CNS augments demyelination suggesting that this signaling pathway may offer new targets for therapeutic intervention.
| S-EPMC6033633 | biostudies-literature
Project description:The roles of the microbiome and innate immunity in the pathogenesis of multiple sclerosis (MS) remain unclear. We have previously documented abnormally low levels of a microbiome-derived Toll-like receptor (TLR)2-stimulating bacterial lipid in the blood of MS patients and postulated that this is indicative of a deficiency in the innate immune regulating function of the microbiome in MS. We postulated further that the resulting enhanced TLR2 responsiveness plays a critical role in the pathogenesis of MS. As proof-of-concept, we reported that decreasing systemic TLR2 responsiveness by administering very low-dose TLR2 ligands attenuated significantly the mouse model of MS, experimental autoimmune encephalomyelitis. Studies of Toll-like receptor responses in patients with MS have been conflicting. Importantly, most of these investigations have focused on the response to TLR4 ligation and few have characterized TLR2 responses in MS. In the present study, our goal was to characterize TLR2 responses of MS patients using multiple approaches. Studying a total of 26 MS patients and 32 healthy controls, we now document for the first time that a large fraction of MS patients (50%) demonstrate enhanced responsiveness to TLR2 stimulation. Interestingly, the enhanced TLR2 responders include a significant fraction of those with progressive forms of MS, a subset of patients considered unresponsive to adaptive immune system-targeting therapies. Our results suggest the presence of a pathologically relevant TLR2 related innate immune abnormality in patients with both relapsing-remitting and progressive MS. These findings may have significant implications for understanding the role of innate immunity in the pathogenesis of MS.
| S-EPMC6150258 | biostudies-literature
Project description:Multiple sclerosis is a chronic autoimmune disease of the central nervous system that results in varying degrees of disability. Progressive multiple sclerosis, characterized by a steady increase in neurological disability independently of relapses, can occur from onset (primary progressive) or after a relapsing-remitting course (secondary progressive). As opposed to active inflammation seen in the relapsing-remitting phases of the disease, the gradual worsening of disability in progressive multiple sclerosis results from complex immune mechanisms and neurodegeneration. A few anti-inflammatory disease-modifying therapies with a modest but significant effect on measures of disease progression have been approved for the treatment of progressive multiple sclerosis. The treatment effect of anti-inflammatory agents is particularly observed in the subgroup of patients with younger age and evidence of disease activity. For this reason, a significant effort is underway to develop molecules with the potential to induce myelin repair or halt the degenerative process. Appropriate trial methodology and the development of clinically meaningful disability outcome measures along with imaging and biological biomarkers of progression have a significant impact on the ability to measure the efficacy of potential medications that may reverse disease progression. In this issue, we will review current evidence on the physiopathology, diagnosis, measurement of disability, and treatment of progressive multiple sclerosis.
| S-EPMC6784028 | biostudies-literature
Project description:Among people with multiple sclerosis, cognitive impairment occurs commonly and is a potent predictor of disability. Some multiple sclerosis patients present with severe cognitive impairment, and distinguishing multiple sclerosis-related cognitive impairment from co-existent progressive neurodegenerative diseases such as Alzheimer disease poses a diagnostic challenge. The use of biomarkers such as PET and CSF proteins may facilitate this distinction. The study was a retrospective, descriptive study on convenience samples of separate cohorts, one of cognitively impaired multiple sclerosis patients evaluated on autopsy to demonstrate coincidence of both multiple sclerosis and neurodegenerative cognitive diseases. The second cohort were cognitively impaired multiple sclerosis patients evaluated by biomarker to investigate possible additional neurodegenerative cognitive disorders contributing to the cognitive impairment. We investigated selected biomarkers among 31 severely impaired patients (biomarker cohort) and 12 severely impaired patients assessed at autopsy and selected 24 (23 biomarker cohort, 1 autopsy cohort) had comprehensive neurocognitive testing. Biomarker cohort investigations included 18F-Fluorodeoxyglucose PET and/or CSF amyloid Aβ1-42, phospho-tau and total tau levels. The autopsy cohort was evaluated with comprehensive neuropathological assessment for aetiology of cognitive impairment. The cohorts shared similar sex, age at multiple sclerosis onset and multiple sclerosis clinical course. The autopsy-cohort patients were older at diagnosis (69.5 versus 57 years, P = 0.006), had longer disease duration [median (range) 20 years (3-59) versus 9 (1-32), P = 0.001] and had more impaired bedside mental status scores at last follow-up [Kokmen median (range) 23 (1-38) versus 31 (9-34) P = 0.01]. Autopsy-cohort patients confirmed, or excluded, coexistent neurogenerative disease by neuropathology gold standard. Most biomarker-cohort patients had informative results evaluating coexistent neurogenerative disease. Biomarkers may be useful in indicating a coexistent neurodegenerative disease earlier, and in life, in patients with multiple sclerosis and significant cognitive impairment.
| S-EPMC9272064 | biostudies-literature
Project description:OBJECTIVE:To summarize major clinical trials which evaluate the efficacy and safety data of approved disease modifying agents for the treatment of various types of multiple sclerosis. DATA SOURCES:A MEDLINE (1966 to August 2008) search of clinical trials using the terms multiple sclerosis, interferon, glatiramer, mitoxantrone and natalizumab was performed. A manual bibliographic search was also conducted. English-language articles identified from the searches were evaluated. New agents under investigation in phase 3 clinical trials were identified using www.clinicaltrials.gov. STUDY SELECTION #ENTITYSTARTX00026; DATA EXTRACTION:Relevant information was identified and selected based on clinical relevance and evidence-based strength. Prescribing information leaflets were used to provide usual dosage, contraindications, precautions, monitoring parameters and other relevant drug-specific information. DATA SYNTHESIS:Interferon beta products are more efficacious for the treatment of relapsing-remitting multiple sclerosis. Interferon beta 1-b also delayed the time to diagnosis of definite multiple sclerosis and reduced brain lesion burden in patients with clinical isolated syndrome. Glatiramer and natalizumab have both established efficacy in relapsing forms of multiple sclerosis; whereas mitoxantrone is more commonly used in patients with advanced disease. There are limited data the comparative efficacy among different disease modifying agents. New agents currently under investigation have showed promising results and may offer more treatment options in the future. CONCLUSIONS:MS is a complex and devastating disease with challenging treatment considerations and approaches. Interferon beta products continue to be the mainstay of therapy in many patients, however, other treatments are proving to be at least as effective in the management of various types of MS. Newer compounds are being developed and studied with much anticipation and promise for the clinical management of the disease.
| S-EPMC3024587 | biostudies-other
Project description:Multiple sclerosis (MS) is an inflammatory demyelinating disease of the central nervous system (CNS) with varied clinical presentations and heterogeneous histopathological features. The underlying immunological abnormalities in MS lead to various neurological and autoimmune manifestations. There is strong evidence that MS is, at least in part, an immune-mediated disease. There is less evidence that MS is a classical autoimmune disease, even though many authors state this in the description of the disease. We show the evidence that both supports and refutes the autoimmune hypothesis. In addition, we present an alternate hypothesis based on virus infection to explain the pathogenesis of MS.
| S-EPMC3361990 | biostudies-other
Project description:Each year, more than 400,000 people die of malaria. Malaria is a mosquito-borne transmissible infection that affects humans and other animals. According to World Health Organization (WHO), 1.5 billion malaria cases and 7.6 million related deaths have been prevented from 2000 to 2019. Malaria is a disease that can be treated if early detected. We propose a support decision system for detecting malaria from microscopic peripheral blood cells images through convolutional neural networks (CNN). The proposed model is based on EfficientNetB0 architecture. The results are validated with 10-fold stratified cross-validation. This paper presents the classification findings using images from malaria patients and normal patients. The proposed approach is compared and outperforms the related work. Furthermore, the proposed ensemble method shows a recall value of 98.82%, a precision value of 97.74%, an F1-score of 98.28% and a ROC value of 99.76%. This work suggests that EfficientNet is a reliable architecture for automatic medical diagnostics of malaria.Supplementary informationThe online version contains supplementary material available at 10.1007/s11042-022-12624-6.
| S-EPMC8964254 | biostudies-literature