Classification algorithms with multi-modal data fusion could accurately distinguish neuromyelitis optica from multiple sclerosis

Antibodies to aquaporin-4 (also known as AQP4-Ab or NMO-IgG) are sensitive and highly specific serum markers of autoimmune neuromyelitis optica (NMO). Second-generation recombinant diagnostic assays can detect AQP4-Ab in >or=80% of patients with NMO, and a role for AQP4-Ab in the pathophysiology of this condition was corroborated by a series of in vitro studies that demonstrated disruption of the blood-brain barrier, impairment of glutamate homeostasis and induction of necrotic cell death by AQP4-Ab-positive serum. Additional evidence for such a role has emerged from clinical observations, including the demonstration of a correlation between serum levels of AQP4-Ab and disease activity. The finding of NMO-like CNS lesions and clinical disease following passive transfer of AQP4-Ab-positive serum in several independent animal studies provided definitive proof for a pathogenic role of AQP4-Ab in vivo. Together, these findings provide a strong rationale for the use of therapies targeted against B cells or antibodies in the treatment of NMO. In this Review, we summarize the latest evidence in support of a direct involvement of AQP4-Ab in the immunopathogenesis of NMO, and critically appraise the diagnostic tests currently available for the detection of this serum reactivity.

Fully automated classification algorithms have been successfully applied to diagnose a wide range of neurological and psychiatric diseases. They are sufficiently robust to handle data from different scanners for many applications and in specific cases outperform radiologists. This article provides an overview of current applications taking structural imaging in Alzheimer's Disease and schizophrenia as well as functional imaging to diagnose depression as examples. In this context, we also report studies aiming to predict the future course of the disease and the response to treatment for the individual. This has obvious clinical relevance but is also important for the design of treatment studies that may aim to include a cohort with a predicted fast disease progression to be more sensitive to detect treatment effects. In the second part, we present our own opinions on i) the role these classification methods can play in the clinical setting; ii) where their limitations are at the moment and iii) how those can be overcome. Specifically, we discuss strategies to deal with disease heterogeneity, diagnostic uncertainties, a probabilistic framework for classification and multi-class classification approaches.