Predicting outcome in clinically isolated syndrome using machine learning.

We aim to determine if machine learning techniques, such as support vector machines (SVMs), can predict the occurrence of a second clinical attack, which leads to the diagnosis of clinically-definite Multiple Sclerosis (CDMS) in patients with a clinically isolated syndrome (CIS), on the basis of single patient's lesion features and clinical/demographic characteristics. Seventy-four patients at onset of CIS were scanned and clinically reviewed after one and three years. CDMS was used as the gold standard against which SVM classification accuracy was tested. Radiological features related to lesional characteristics on conventional MRI were defined a priori and used in combination with clinical/demographic features in an SVM. Forward recursive feature elimination with 100 bootstraps and a leave-one-out cross-validation was used to find the most predictive feature combinations. 30 % and 44 % of patients developed CDMS within one and three years, respectively. The SVMs correctly predicted the presence (or the absence) of CDMS in 71.4 % of patients (sensitivity/specificity: 77 %/66 %) at 1 year, and in 68 % (60 %/76 %) at 3 years on average over all bootstraps. Combinations of features consistently gave a higher accuracy in predicting outcome than any single feature. Machine-learning-based classifications can be used to provide an "individualised" prediction of conversion to MS from subjects' baseline scans and clinical characteristics, with potential to be incorporated into routine clinical practice.

Characterization of Ca(2+) flows essential in ornithine decarboxylase induction by L-asparagine in rat hepatoma cells using Ca(2+) flow inhibitors.

L-Asparagine stimulates bi-directional Ca(2+) flows and induces ornithine decarboxylase in Reuber H-35 hepatoma cells. Previously it has been shown that these effects are completely, but reversibly inhibited by lanthanum chloride. In this study we examined the role(s) of Ca(2+) flows using more specific Ca(2+) flow inhibitors. It was shown that ornithine decarboxylase induction was inhibited by CdCl(2) and verapamil at concentrations above 1 mu M and 100 mu M respectively, but was unaffected by as much as 300 mu M NiCl(2), 1 mM nifedipine, or 10 mu M omega-conotoxin. Enzyme induction was blocked by the Ca(2+)-ATPase pump antagonists vanadate and Compound 48/80 in a dose-dependent manner. These results, taken together with the observations that extracellular Ca(2+) is essential for enzyme induction but a substantial elevation of cytoplasmic [Ca(2+)] is not, suggest that Ca(2+) inflow independent of the receptor-activated Ca(2+) channels, and the Ca(2+)-ATPase mediated Ca(2+) out-flow, are both important factors in the action of L-asparagine.