Early differential diagnosis of several motor neuron diseases (MNDs) is extremely challenging due to the high number of overlapped symptoms. The routine clinical practice is based on clinical history and examination, usually accompanied by electrophysiological tests. However, although previous studies have demonstrated the involvement of altered metabolic pathways, biomarker-based monitoring tools are still far from being applied. In this study, we aim at characterizing and discriminating patients with involvement of both upper and lower motor neurons (i.e., amyotrophic lateral sclerosis (ALS) patients) from those with selective involvement of the lower motor neuron (LMND), by using blood data exclusively. To this end, in the last ten years, we built a database including 692 blood data and related clinical observations from 55 ALS and LMND patients. Each blood sample was described by 108 analytes. Starting from this outstanding number of features, we performed a characterization of the two groups of patients through statistical and classification analyses of blood data. Specifically, we implemented a support vector machine with recursive feature elimination (SVM-RFE) to automatically diagnose each patient into the ALS or LMND groups and to recognize whether they had a fast or slow disease progression. The classification strategy through the RFE algorithm also allowed us to reveal the most informative subset of blood analytes including novel potential biomarkers of MNDs. Our results show that we successfully devised subject-independent classifiers for the differential diagnosis and prognosis of ALS and LMND with remarkable average accuracy (up to 94%), using blood data exclusively.

This article has been accepted for publication and undergone full peer review but has not been through the copyediting, typesetting, pagination and proofreading process which may lead to differences between this version and the Version of Record. Please cite this article as

Background: Previous studies find that survival in ALS is associated with increased plasma creatinine and uric acid concentrations. Although oxidative stress is thought to shorten ALS survival, evidence for this hypothesis is sparse.Objectives: To evaluate the associations between multiple biomarkers measured at baseline and survival in patients with fully phenotyped ALS. The patients were enrolled in a prospective multicenter study (COSMOS).Methods: Data and biospecimens were collected at the time of first clinical evaluation. ALSFRS-R and % forced vital capacity (%FVC ) were used to assess ALS clinical status. We measured two urinary biomarkers of oxidative stress in overnight-fasting, spot first morning voids: isoprostane, a product of lipid peroxidation, and 8-oxodeoxyguanosine (8-oxo-dG), a product of DNA oxidation; both were adjusted for hydration status using specific gravity. Plasma creatinine, extensive lipid profile, and uric acid were also determined. Time from symptom onset to death was estimated as the sum of the reported number of months from symptom onset to baseline evaluation and the number of months from baseline evaluation to death. Associations were evaluated using Cox proportional hazard models, controlling for potential confounders.Results: 355 patients were enrolled in COSMOS, of whom 324 had ALSFRS-R data, 325 had %FVC data and between 342 and 346 had data on biomarkers. Mean (+ standard deviation (SD)) values of urinary isoprostane and 8-oxo-dG, both adjusted for specific gravity, were 1.63 ng/ml (0.98) and 4.88 ng/ml (3.77), respectively. Mean plasma creatinine was 0.80 mg/dl (0.20) and mean uric acid was 5.08 mg/dl (1.34). After controlling for age, sex, race, ethnicity, educational attainment, region of onset, smoking, BMI and dietary caloric and fat intake, each unit increase in serum creatinine was associated with a hazard ratio of 0.51 (95% confidence interval (CI) 0.25, 1.04; p ¼ 0.06), indicating longer survival time. Each unit increase in isoprostane was associated with a hazard ratio of 1.09 (95% CI 0.97, 1.22; p ¼ 0.13), indicating shorter survival time. Neither uric acid nor 8-oxo-dG were associated with survival.Discussion and conclusions: In this population, we found associations between plasma creatinine and isoprostane and survival in ALS, such that higher plasma creatinine and lower urinary isoprostane were associated with longer survival, although the latter relationship was not statistically significant. For plasma creatinine, these results are similar to others reported in the literature. To our knowledge, this is the first time the association with isoprostane was found.