Dataset Information

Computational classifiers for predicting the short-term course of Multiple sclerosis.

ABSTRACT: BACKGROUND: The aim of this study was to assess the diagnostic accuracy (sensitivity and specificity) of clinical, imaging and motor evoked potentials (MEP) for predicting the short-term prognosis of multiple sclerosis (MS). METHODS: We obtained clinical data, MRI and MEP from a prospective cohort of 51 patients and 20 matched controls followed for two years. Clinical end-points recorded were: 1) expanded disability status scale (EDSS), 2) disability progression, and 3) new relapses. We constructed computational classifiers (Bayesian, random decision-trees, simple logistic-linear regression-and neural networks) and calculated their accuracy by means of a 10-fold cross-validation method. We also validated our findings with a second cohort of 96 MS patients from a second center. RESULTS: We found that disability at baseline, grey matter volume and MEP were the variables that better correlated with clinical end-points, although their diagnostic accuracy was low. However, classifiers combining the most informative variables, namely baseline disability (EDSS), MRI lesion load and central motor conduction time (CMCT), were much more accurate in predicting future disability. Using the most informative variables (especially EDSS and CMCT) we developed a neural network (NNet) that attained a good performance for predicting the EDSS change. The predictive ability of the neural network was validated in an independent cohort obtaining similar accuracy (80%) for predicting the change in the EDSS two years later. CONCLUSIONS: The usefulness of clinical variables for predicting the course of MS on an individual basis is limited, despite being associated with the disease course. By training a NNet with the most informative variables we achieved a good accuracy for predicting short-term disability.

SUBMITTER: Bejarano B

PROVIDER: S-EPMC3118106 | biostudies-literature | 2011

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Computational classifiers for predicting the short-term course of Multiple sclerosis.

Bejarano Bartolome B Bianco Mariangela M Gonzalez-Moron Dolores D Sepulcre Jorge J Goñi Joaquin J Arcocha Juan J Soto Oscar O Del Carro Ubaldo U Comi Giancarlo G Leocani Letizia L Villoslada Pablo P

BMC neurology 20110607

<h4>Background</h4>The aim of this study was to assess the diagnostic accuracy (sensitivity and specificity) of clinical, imaging and motor evoked potentials (MEP) for predicting the short-term prognosis of multiple sclerosis (MS).<h4>Methods</h4>We obtained clinical data, MRI and MEP from a prospective cohort of 51 patients and 20 matched controls followed for two years. Clinical end-points recorded were: 1) expanded disability status scale (EDSS), 2) disability progression, and 3) new relapses ...[more]

PMID: 21649880

Similar Datasets

Project description:Multiple Sclerosis (MS) progresses at an unpredictable rate, but predictions on the disease course in each patient would be extremely useful to tailor therapy to the individual needs. We explore different machine learning (ML) approaches to predict whether a patient will shift from the initial Relapsing-Remitting (RR) to the Secondary Progressive (SP) form of the disease, using only "real world" data available in clinical routine. The clinical records of 1624 outpatients (207 in the SP phase) attending the MS service of Sant'Andrea hospital, Rome, Italy, were used. Predictions at 180, 360 or 720 days from the last visit were obtained considering either the data of the last available visit (Visit-Oriented setting), comparing four classical ML methods (Random Forest, Support Vector Machine, K-Nearest Neighbours and AdaBoost) or the whole clinical history of each patient (History-Oriented setting), using a Recurrent Neural Network model, specifically designed for historical data. Missing values were handled by removing either all clinical records presenting at least one missing parameter (Feature-saving approach) or the 3 clinical parameters which contained missing values (Record-saving approach). The performances of the classifiers were rated using common indicators, such as Recall (or Sensitivity) and Precision (or Positive predictive value). In the visit-oriented setting, the Record-saving approach yielded Recall values from 70% to 100%, but low Precision (5% to 10%), which however increased to 50% when considering only predictions for which the model returned a probability above a given "confidence threshold". For the History-oriented setting, both indicators increased as prediction time lengthened, reaching values of 67% (Recall) and 42% (Precision) at 720 days. We show how "real world" data can be effectively used to forecast the evolution of MS, leading to high Recall values and propose innovative approaches to improve Precision towards clinically useful values.

Project description:Background:Low vitamin D and/or sun exposure have been associated with increased risk of multiple sclerosis (MS) onset. However, comparatively, few studies have prospectively examined associations between these factors and clinical course. Objectives:To evaluate the association of sun exposure parameters and vitamin D levels with conversion to MS and relapse risk in a prospectively monitored cohort of 145 participants followed after a first demyelinating event up to 5-year review (AusLong Study). Methods:Sun exposure prior to and after onset measured by annual questionnaire; ultraviolet radiation (UVR) "load" estimated by location of residence over the life course and ambient UVR levels. Serum 25-hydroxyvitamin D [25(OH)D] concentrations measured at baseline, 2/3-year, and 5-year review. MS conversion and relapse assessed by neurologist assessment and medical record review. Results:Over two-thirds (69%) of those followed to 5-year review (100/145) converted to MS, with a total of 252 relapses. Higher pre-MS onset sun exposure was associated with reduced risk of MS conversion, with internal consistency between measures and dose-response relationships. Analogous associations were also seen with risk of relapse, albeit less strong. No consistent associations were observed between postonset sun exposure and clinical course, however. Notably, those who increased their sun exposure during follow-up had significantly reduced hazards of MS conversion and relapse. Serum 25(OH)D levels and vitamin D supplementation were not associated with conversion to MS or relapse hazard. Conclusion:We found that preonset sun exposure was protective against subsequent conversion to MS and relapses. While consistent associations between postonset sun exposure or serum 25(OH)D level and clinical course were not evident, possibly masked by behavior change, those participants who markedly increased their sun exposure demonstrated a reduced MS conversion and relapse hazard, suggesting beneficial effects of sun exposure on clinical course.

Dataset Information

Computational classifiers for predicting the short-term course of Multiple sclerosis.

Publications

Computational classifiers for predicting the short-term course of Multiple sclerosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets