Discrete Box-Constrained Minimax Classifier for Uncertain and Imbalanced Class Proportions.

This paper aims to build a supervised classifier for dealing with imbalanced datasets, uncertain class proportions, dependencies between features, the presence of both numeric and categorical features, and arbitrary loss functions. The Bayes classifier suffers when prior probability shifts occur between the training and testing sets. A solution is to look for an equalizer decision rule whose class-conditional risks are equal. Such a classifier corresponds to a minimax classifier when it maximizes the Bayes risk. We develop a novel box-constrained minimax classifier which takes into account some constraints on the priors to control the risk maximization. We analyze the empirical Bayes risk with respect to the box-constrained priors for discrete inputs. We show that this risk is a concave non-differentiable multivariate piecewise affine function. A projected subgradient algorithm is derived to maximize this empirical Bayes risk over the box-constrained simplex. Its convergence is established and its speed is bounded. The optimization algorithm is scalable when the number of classes is large. The robustness of our classifier is studied on diverse databases. Our classifier, jointly applied with a clustering algorithm to process mixed attributes, tends to equalize the class-conditional risks while being not too pessimistic.

Reduced serum levels of pro-inflammatory chemokines in fragile X syndrome.

BACKGROUND: Fragile X syndrome (FXS) is the most frequent cause of inherited intellectual disability and the most commonly identified monogenic cause of autism. Recent studies have shown that long-term pathological consequences of FXS are not solely confined to the central nervous system (CNS) but rather extend to other physiological dysfunctions in peripheral organs. To gain insights into possible immune dysfunctions in FXS, we profiled a large panel of immune-related biomarkers in the serum of FXS patients and healthy controls. METHODS: We have used a sensitive and robust Electro Chemi Luminescence (ECL)-based immunoassay to measure the levels of 52 cytokines in the serum of n = 25 FXS patients and n = 29 healthy controls. We then used univariate statistics and multivariate analysis, as well as an advanced unsupervised clustering method, to identify combinations of immune-related biomarkers that could discriminate FXS patients from healthy individuals. RESULTS: While the majority of the tested cytokines were present at similar levels in FXS patients and healthy individuals, nine chemokines, CCL2, CCL3, CCL4, CCL11, CCL13, CCL17, CCL22, CCL26 and CXCL10, were present at much lower levels in FXS patients. Using robust regression, we show that six of these biomarkers (CCL2, CCL3, CCL11, CCL22, CCL26 and CXCL10) were negatively associated with FXS diagnosis. Finally, applying the K-sparse unsupervised clustering method to the biomarker dataset allowed for the identification of two subsets of individuals, which essentially matched the FXS and healthy control categories. CONCLUSIONS: Our data show that FXS patients exhibit reduced serum levels of several chemokines and may therefore exhibit impaired immune responses. The present study also highlights the power of unsupervised clustering methods to identify combinations of biomarkers for diagnosis and prognosis in medicine.

Correction: Stratification and prediction of remission in first-episode psychosis patients: the OPTiMiSE cohort study.

The original Article did not feature the list of collaborators. This has now been corrected in the PDF and HTML versions of this Article.

Stratification and prediction of remission in first-episode psychosis patients: the OPTiMiSE cohort study.

Early response to first-line antipsychotic treatments is strongly associated with positive long-term symptomatic and functional outcome in psychosis. Unfortunately, attempts to identify reliable predictors of treatment response in first-episode psychosis (FEP) patients have not yet been successful. One reason for this could be that FEP patients are highly heterogeneous in terms of symptom expression and underlying disease biological mechanisms, thereby impeding the identification of one-size-fits-all predictors of treatment response. We have used a clustering approach to stratify 325 FEP patients into four clinical subtypes, termed C1A, C1B, C2A and C2B, based on their symptoms assessed using the Positive and Negative Syndrome Scale (PANSS) scale. Compared to C1B, C2A and C2B patients, those from the C1A subtype exhibited the most severe symptoms and were the most at risk of being non-remitters when treated with the second-generation antipsychotic drug amisulpride. Before treatment, C1A patients exhibited higher serum levels of several pro-inflammatory cytokines and inflammation-associated biomarkers therefore validating our stratification approach on external biological measures. Most importantly, in the C1A subtype, but not others, lower serum levels of interleukin (IL)-15, higher serum levels of C-X-C motif chemokine 12 (CXCL12), previous exposure to cytomegalovirus (CMV), use of recreational drugs and being younger were all associated with higher odds of being non-remitters 4 weeks after treatment. The predictive value of this model was good (mean area under the curve (AUC) = 0.73 ± 0.10), and its specificity and sensitivity were 45 ± 0.09% and 83 ± 0.03%, respectively. Further validation and replication of these results in clinical trials would pave the way for the development of a blood-based assisted clinical decision support system in psychosis.