ABSTRACT
OBJECTIVE: This study aims to (1) build and validate model-based case definitions for multiple sclerosis (MS) that use trends (ie, trend-based case definitions) and (2) to apply dynamic classification to identify the average number of data years needed for classification (ie, average trend needed). DESIGN: Retrospective cohort study design. PARTICIPANTS: 608 MS cases and 59 620 MS non-cases. SETTING: Data from 1 April 2004 to 31 March 2022 were obtained from the Manitoba Population Research Data Repository. MS case status was ascertained from homecare records and linked to health data. Trend-based case definitions were constructed using multivariate generalised linear mixed models applied to annual numbers of general and specialist physician visits, hospitalisations and MS healthcare contacts or medication dispensations. Dynamic classification, which ascertains cases and non-cases annually, was used to estimate mean classification time. Classification accuracy performance measures, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), proportion correctly classified (PCC) and F1-scores, were compared for trend-based case definitions and a deterministic case definition of 3+MS healthcare contacts or medication dispensations. RESULTS: When applied to the full study period, classification accuracy performance measure estimates for all case definitions exceeded 0.90, except sensitivity and PPV for the trend-based dynamic case definition (0.88, 0.64, respectively). PCC was high for all case definitions (0.94-0.99); F1-scores were lower for the trend-based case definitions compared with the deterministic case definition (0.74-0.93 vs 0.96). Dynamic classification identified 5 years as the average trend needed. When applied to the average trend windows, accuracy estimates for trend-based case definitions were lower than the estimates from the full study period (sensitivity: 0.77-0.89; specificity: 0.90-0.97; PPV: 0.54-0.81; NPV: 0.97-0.99; F1-score: 0.64-0.84). Accuracy estimates for the deterministic case definition remained high, except sensitivity (0.42-0.80). F1-score was variable (0.59-0.89). CONCLUSIONS: Trend-based and deterministic case definitions classifications were similar to a population-based clinician assessment reference standard for multiple measures of classification accuracy. However, accuracy estimates for both trend-based and deterministic case definitions varied as the years of data used for classification were reduced. Dynamic classification appears to be a viable option for identifying the average trend needed for trend-based case definitions.
Subject(s)
Multiple Sclerosis , Humans , Multiple Sclerosis/classification , Manitoba/epidemiology , Retrospective Studies , Female , Male , Adult , Middle AgedABSTRACT
BACKGROUND: Robust predictive models of clinical impairment and worsening in multiple sclerosis (MS) are needed to identify patients at risk and optimize treatment strategies. OBJECTIVE: To evaluate whether machine learning (ML) methods can classify clinical impairment and predict worsening in people with MS (pwMS) and, if so, which combination of clinical and magnetic resonance imaging (MRI) features and ML algorithm is optimal. METHODS: We used baseline clinical and structural MRI data from two MS cohorts (Berlin: n = 125, Amsterdam: n = 330) to evaluate the capability of five ML models in classifying clinical impairment at baseline and predicting future clinical worsening over a follow-up of 2 and 5 years. Clinical worsening was defined by increases in the Expanded Disability Status Scale (EDSS), Timed 25-Foot Walk Test (T25FW), 9-Hole Peg Test (9HPT), or Symbol Digit Modalities Test (SDMT). Different combinations of clinical and volumetric MRI measures were systematically assessed in predicting clinical outcomes. ML models were evaluated using Monte Carlo cross-validation, area under the curve (AUC), and permutation testing to assess significance. RESULTS: The ML models significantly determined clinical impairment at baseline for the Amsterdam cohort, but did not reach significance for predicting clinical worsening over a follow-up of 2 and 5 years. High disability (EDSS ≥ 4) was best determined by a support vector machine (SVM) classifier using clinical and global MRI volumes (AUC = 0.83 ± 0.07, p = 0.015). Impaired cognition (SDMT Z-score ≤ -1.5) was best determined by a SVM using regional MRI volumes (thalamus, ventricles, lesions, and hippocampus), reaching an AUC of 0.73 ± 0.04 (p = 0.008). CONCLUSION: ML models could aid in classifying pwMS with clinical impairment and identify relevant biomarkers, but prediction of clinical worsening is an unmet need.
Subject(s)
Disease Progression , Machine Learning , Magnetic Resonance Imaging , Multiple Sclerosis , Humans , Male , Female , Adult , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis/classification , Multiple Sclerosis/physiopathology , Multiple Sclerosis/diagnosis , Middle Aged , Cohort Studies , Brain/diagnostic imaging , Brain/physiopathology , Disability Evaluation , Follow-Up StudiesABSTRACT
PURPOSE: This study aimed to subtype multiple sclerosis (MS) patients using unsupervised machine learning on white matter (WM) fiber tracts and investigate the implications for cognitive function and disability outcomes. MATERIALS AND METHODS: We utilized the automated fiber quantification (AFQ) method to extract 18 WM fiber tracts from the imaging data of 103 MS patients in total. Unsupervised machine learning techniques were applied to conduct cluster analysis and identify distinct subtypes. Clinical and diffusion tensor imaging (DTI) metrics were compared among the subtypes, and survival analysis was conducted to examine disability progression and cognitive impairment. RESULTS: The clustering analysis revealed three distinct subtypes with variations in fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD). Significant differences were observed in clinical and DTI metrics among the subtypes. Subtype 3 showed the fastest disability progression and cognitive decline, while Subtype 2 exhibited a slower rate, and Subtype 1 fell in between. CONCLUSIONS: Subtyping MS based on WM fiber tracts using unsupervised machine learning identified distinct subtypes with significant cognitive and disability differences. WM abnormalities may serve as biomarkers for predicting disease outcomes, enabling personalized treatment strategies and prognostic predictions for MS patients.
Subject(s)
Diffusion Tensor Imaging , Multiple Sclerosis , Unsupervised Machine Learning , White Matter , Humans , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis/classification , Male , Female , Diffusion Tensor Imaging/methods , Adult , White Matter/diagnostic imaging , White Matter/pathology , Middle Aged , Disease ProgressionABSTRACT
A esclerose múltipla é uma afecção neurológica que envolve distúrbios da deglutição. Muitos estudos têm mostrado associação entre o comprometimento neurológico e o desempenho da deglutição, porém, os resultados têm sido conflitantes. OBJETIVO: Identificar a frequência de disfagia nos pacientes com esclerose múltipla e os indicadores neurológicos que podem representar o desempenho da deglutição. MÉTODO: Neste estudo (estudo transversal), 120 pacientes com esclerose múltipla foram submetidos à avaliação funcional da deglutição por fibronasofaringolaringoscopia, cujos resultados foram comparados com a pontuação das escalas de classificação (Formas Clínicas Evolutivas da Doença, Escala de Incapacidade Funcional por Sistemas e Escala Ampliada de Incapacidade Funcional [Kurtzke Expanded Disability Status Scale]). RESULTADOS: A disfagia foi identificada em 90% dos pacientes. Dentre as formas clínicas, as formas progressivas (primária progressiva e secundária progressiva) apresentaram com maior frequência disfagia grave, enquanto a forma remitente-recorrente apresentou mais frequentemente disfagia leve e moderada. Em relação à Escala de Incapacidade Funcional por Sistemas, as funções cerebelares, do tronco encefálico e mental tiveram associação com a disfagia, especialmente na forma grave. Quanto à Escala Ampliada de Incapacidade Funcional, pontuações mais altas se associaram aos quadros graves de disfagia. CONCLUSÃO: A disfagia é frequente em pacientes com esclerose múltipla, especialmente naqueles com maior comprometimento das funções neurológicas.
Multiple sclerosis is a neurological disease that involves swallowing disorders. Many studies have shown an association between neurological and swallowing performance, but results have been conflicting. OBJECTIVE: To identify the frequency of dysphagia in patients with multiple sclerosis and neurological indicators that can represent the performance of swallowing. METHOD: In this study (cross-sectional) 120 Multiple Sclerosis patients underwent Functional Assessment of Swallowing by flexible nasal-pharyngo-laryngoscopy and the results were compared with the scores of the rating scales: (Clinical Evolving Forms of Disease, Functional Disability Scale for and Scale Systems Extended Functional Disability [Kurtzke Expanded Disability Status Scale]). RESULTS: Dysphagia was found in 90% of patients. Among the clinical forms of the disease, the progressive forms (primary progressive and secondary progressive) were more frequently associated with severe dysphagia, while the relapsing-remitting form presented more often mild and moderate dysphagia. Regarding the Disability Scale for Functional Systems, cerebellar function, brainstem function and mental health were associated with dysphagia, especially in the severe form. Regarding the Extended Functional Disability Scale, higher scores were associated with severe dysphagia. CONCLUSION: Dysphagia is common in MS patients, especially in those with greater impairment of neurological functions.
Subject(s)
Adolescent , Adult , Aged , Female , Humans , Male , Middle Aged , Young Adult , Deglutition Disorders/etiology , Multiple Sclerosis/complications , Cross-Sectional Studies , Disability Evaluation , Deglutition Disorders/classification , Deglutition Disorders/diagnosis , Multiple Sclerosis/classification , Severity of Illness IndexABSTRACT
OBJECTIVES: Epstein-Barr virus has been recently associated with the onset of multiple sclerosis, yet understanding how it elicits autoimmunity remains elusive. We investigated the relation between Epstein-Barr virus reactivation and disease development in different subtypes of multiple sclerosis. METHODS: In the present research, we have determined the Epstein-Barr virus-DNA load by quantitative real-time polymerase chain reaction and Epstein-Barr virus antibody levels by EIA technique in both multiple sclerosis patients (n = 78) and healthy controls (n = 123). RESULTS: Our results demonstrated increased titer of both anti-Epstein-Barr virus-IgG and IgM antibodies in patients (91.02% vs 82.11% in controls, p < 0.001 and 14.1% vs 4.06% in controls, p < 0.001, respectively). Overall, Epstein-Barr virus reactivation was found in 68.75% of subtypes of multiple sclerosis, 4.54% of multiple sclerosis primary subtype, and in only 3.25% of healthy control subjects. Moreover, in samples of patients with disease relapse (exacerbation) cell free viral DNA was elevated in contrast to other patients (p < 0.001). CONCLUSIONS: These findings provide further support for the detrimental effects of Epstein- Barr virus in the reactivation of multiple sclerosis attacks.
Subject(s)
Adolescent , Adult , Female , Humans , Male , Middle Aged , Young Adult , Epstein-Barr Virus Infections/complications , /immunology , Multiple Sclerosis/virology , Antibodies, Viral/blood , Case-Control Studies , DNA, Viral/analysis , Epstein-Barr Virus Infections/diagnosis , Epstein-Barr Virus Infections/immunology , Immunoenzyme Techniques , Iran , Immunoglobulin G/blood , Immunoglobulin M/blood , Multiple Sclerosis/classification , Multiple Sclerosis/immunology , Real-Time Polymerase Chain ReactionABSTRACT
Introducción: Se presentan tres casos de pacientes con esclerosis múltiple (EM),diagnosticadas previo al embarazo, y que fueron evaluadas en la Unidad de MedicinaMaterno-Fetal durante sus controles y parto en el Hospital Universitario de SanIgnacio, centro de referencia nivel IV que atiende población embarazada de altoriesgo obstétrico perteneciente al régimen contributivo. Objetivo: Describir lasformas de presentación, fisiopatología, etiología y cuadro clínico de la EM, así comosu comportamiento en el embarazo. Metodología: Se realizó una búsqueda de laliteratura en las bases PubMed, Medline y Cochrane utilizando las palabras clave, pararecopilar información tanto en inglés como en español desde el 2000 al 2011. Despuésse eligieron artículos de revisión y de investigación en EM y embarazo. Conclusiones:Las pacientes con diagnóstico de EM en el embarazo parecen tener un menor riesgode sufrir una recaída, especialmente durante el último trimestre. Sin embargo, vieneseguido de una alta probabilidad de recaída durante los tres meses posteriores, comose observó en dos de los casos descritos en este estudio...
Introduction: Three cases of patients withmultiple sclerosis (MS), diagnosed before pregnancy,and were evaluated at the Departmentof Maternal-Fetal and birth control during theHospital Universitario San Ignacio, level IV referralcenter serving pregnant population highrisk obstetric pertaining to contributory scheme.Objective: To describe the clinical presentationsof the pathophysiology, etiology and clinicalfeatures of MS, as well as their behavior duringpregnancy. Methodology: Electronic search wasconducted in PubMed, Medline, and Cochraneusing the keywords to collect information inboth English and Spanish from 2000 to 2011. Afterreview articles were selected and research inmultiple sclerosis and pregnancy. Conclusions:There seems to be a lower risk of relapse duringpregnancy and especially during the last quarter.However, it is followed by a high probability ofrelapse within three months, as observed in twocases described in this study...
Subject(s)
Pregnancy/statistics & numerical data , Multiple Sclerosis/classification , Multiple Sclerosis/complications , Multiple Sclerosis/diagnosis , Multiple Sclerosis/prevention & controlABSTRACT
A prevalência de esclerose múltipla (EM) varia consideravelmente no mundo. De acordo com Kurtzke, a América do Sul é considerada região de baixa prevalência (menor que 5 casos:100000 habitantes). OBJETIVO: Descrever a epidemiologia da EM em centro de referência, comparando-a aos achados de oito serviços nacionais. MÉTODO: Através de estudo de incidência, descritivo, prospectivo, longitudinal, foram analisados dados de 118 pacientes, atendidos no Centro de Referência para Atenção ao Paciente Portador de Doença Desmielinizante do Hospital da Restauração - Recife - PE - Brasil (CRAPPDD-HR), entre janeiro de 1987 e março de 2002, com diagnóstico de EM, segundo critérios de Poser. RESULTADOS: Os pacientes foram acompanhados por um a 15 anos. Noventa e cinco (80,5 por cento) pacientes estavam em tratamento específico com imunomoduladores. A prevalência foi igual a 1,36:100000 habitantes. Identificaram-se: predomínio da etnia parda (110 casos, 93,2 por cento); 82 (82,2 por cento) casos clinicamente definidos, 15 (12,7 por cento) laboratorialmente definidos e 6 (5,1 por cento) clinicamente prováveis; número máximo de surtos igual a 46; maior número de casos com EDSS leve, assim como um a 10 anos de doença na forma surto/remissão (SR). A razão de gênero dos 83 casos da forma SR se equivaleu à geral (4,1:1), contudo na forma SR com progressão secundária houve predomínio duas vezes maior para o sexo feminino e na forma primariamente progressiva, 5,5 vezes maior para o sexo masculino. CONCLUSAO: Apesar da presente pesquisa ter se assemelhado aos oito estudos utilizados para comparação, as diferenças constatadas irão requerer novas pesquisas e novas abordagens.
Subject(s)
Humans , Male , Female , Disease Outbreaks , Multiple Sclerosis/epidemiology , Age of Onset , Brazil/epidemiology , Follow-Up Studies , Incidence , Multiple Sclerosis/classification , Prevalence , Prospective Studies , Sex Distribution , Sex FactorsABSTRACT
El tratamiento de la Esclerosis Múltiple ha sufrido un desarrollo vertiginoso durante la última década. En esta revisión se analizan estas nuevas terapias en forma paralela al proceso fisiopatológico del cuadro, de manera conocer detalladamente el mecanismo de acción de cada uno de los fármacos actualmente en uso o en estudio,para el manejo de la Esclerosis Múltiple.
The treatment of Multiple Sclerosis has suffered a tremendous development in the past decade. In this article we review the current an new treatment options with a pathophysiology point of view, so readers will can know drugs available and the mechanism of action of each of them.
Subject(s)
Humans , Male , Adult , Female , Middle Aged , Antigens , Multiple Sclerosis/classification , Multiple Sclerosis/complications , Multiple Sclerosis/epidemiology , Multiple Sclerosis/physiopathology , Multiple Sclerosis/therapy , Pharmacology/classificationABSTRACT
En este resumen se describen algunos intentos de clasificación de la esclerosis múltiple desde el punto de vista funcional, inmunológico, patológico y sintomático. En consideración a este último aspecto, los pacientes afectados son agrupados de acuerdo con su evolución clínica
Subject(s)
Multiple Sclerosis/classification , Multiple Sclerosis/diagnosis , Multiple Sclerosis/physiopathology , Multiple Sclerosis/immunology , Clinical EvolutionABSTRACT
Para determinar la prevalencia de esclerosis múltiple en el partido de Junín (B), Argentina, a 34º de latitud S, se utilizó como estrategia para el hallazgo de casos, aquella aplicable para enfermedades crónicas y raras. Estas estrategias fueron: uso de sistema de registro de prestadores de salud; examen en dos fases; red de muestreo; sistema bola de nieve; fuentes múltiples de información y sensibilización de la población. Nosotros utilizamos el criterio de diagnóstico delineado en el Workshop de la Universidad de Boston de 1982. Para la recolección de datos en pacientes con E.M. o probable enfermedad, usamos el modelo de historia clínica y ficha epidemiológica provista por la Asociación Civil Argentina Anti-Esclerosis Múltiple. Se tomó como día de prevalencia el 1 de enero de 1991 y la tasa de prevalencia de esclerosis múltiple fue 12 por 100.000 habitantes. Zona de riesgo medio. Edad media al diagnóstico era de 30 años para los hombres, 42 años para la mujer, y 36 para ambos sexos. La tasa de prevalencia ha sido significativamente más alta para mujeres que para hombres(AU)
Subject(s)
Humans , Male , Female , Adolescent , Adult , Middle Aged , Multiple Sclerosis/epidemiology , Argentina/epidemiology , Neurology/statistics & numerical data , Multiple Sclerosis/classification , Multiple Sclerosis/diagnosis , Prevalence , Incidence , Cross-Sectional StudiesABSTRACT
Para determinar la prevalencia de esclerosis múltiple en el partido de Junín (B), Argentina, a 34º de latitud S, se utilizó como estrategia para el hallazgo de casos, aquella aplicable para enfermedades crónicas y raras. Estas estrategias fueron: uso de sistema de registro de prestadores de salud; examen en dos fases; red de muestreo; sistema bola de nieve; fuentes múltiples de información y sensibilización de la población. Nosotros utilizamos el criterio de diagnóstico delineado en el Workshop de la Universidad de Boston de 1982. Para la recolección de datos en pacientes con E.M. o probable enfermedad, usamos el modelo de historia clínica y ficha epidemiológica provista por la Asociación Civil Argentina Anti-Esclerosis Múltiple. Se tomó como día de prevalencia el 1 de enero de 1991 y la tasa de prevalencia de esclerosis múltiple fue 12 por 100.000 habitantes. Zona de riesgo medio. Edad media al diagnóstico era de 30 años para los hombres, 42 años para la mujer, y 36 para ambos sexos. La tasa de prevalencia ha sido significativamente más alta para mujeres que para hombres