Background: Diagnosis of schizophrenia (SCZ) is made exclusively clinically, since specific biomarkers that can predict the disease accurately remain unknown. Machine learning (ML) represents a promising approach that could support clinicians in the diagnosis of mental disorders. Objectives: A systematic review, according to the PRISMA statement, was conducted to evaluate its accuracy to distinguish SCZ patients from healthy controls. Methods: We systematically searched PubMed, Embase, MEDLINE, PsychINFO and the Cochrane Library through December 2018 using generic terms for ML techniques and SCZ without language or time restriction. Thirty-five studies were included in this review: eight of them used structural neuroimaging, twenty-six used functional neuroimaging and one both, with a minimum accuracy >60% (most of them 75–90%). Sensitivity, Specificity and accuracy were extracted from each publication or obtained directly from authors. Results: Support vector machine, the most frequent technique, if associated with other ML techniques achieved accuracy close to 100%. The prefrontal and temporal cortices appeared to be the most useful brain regions for the diagnosis of SCZ. ML analysis can efficiently detect significantly altered brain connectivity in patients with SCZ (eg, default mode network, visual network, sensorimotor network, frontoparietal network and salience network). Conclusion: The greater accuracy demonstrated by these predictive models and the new models resulting from the integration of multiple ML techniques will be increasingly decisive for early diagnosis and evaluation of the treatment response and to establish the prognosis of patients with SCZ. To achieve a real benefit for patients, the future challenge is to reach an accurate diagnosis not only through clinical evaluation but also with the aid of ML algorithms.

Several studies have investigated the cognitive profile in patients with Anorexia Nervosa (AN) and Bulimia Nervosa (BN); on the contrary few studies have evaluated it in patients with Binge Eating Disorder (BED). The purpose of this study was to compare decision making, central coherence and set-shifting between BED and AN patients. A battery of neuropsychological tests including the Iowa Gambling Task (IGT), the Rey-Osterrieth Complex Figure Test (RCFT), the Wisconsin Card Sorting Test (WCST), the Trial Making Task (TMT) and the Hayling Sentence Completion Task (HSCT) were administered in a sample of 135 women (45 AN, 45 BED, 45 Healthy Controls [HC]). Furthermore, Beck Depression Inventory (BDI) was administered to evaluate depressive symptoms. Years of education, age, Body Mass Index (BMI) and depression severity were considered as covariates in statistical analyses. BED and AN patients showed high rates of cognitive impairment compared to HC on the domains investigated; furthermore, the cognitive profile of BED patients was characterised by poorer decision making and cognitive flexibility compared to patients with AN. Cognitive performance was strongly associated with depressive symptoms. In the present sample, two different neurocognitive profiles emerged: a strong cognitive rigidity and a central coherence based on the details was predominant in patients with AN, while a lack of attention and difficulty in adapting to changes in a new situation seemed to better describe patients with BED. The knowledge of the different cognitive profiles of EDs patients may be important for the planning their psychotherapeutic intervention.

Clozapine (CLZ) is the drug of choice for the treatment of resistant schizophrenia; however, its suitable use is limited by the complex adverse effects’ profile. The best-described adverse effects in the literature are represented by agranulocytosis, myocarditis, sedation, weight gain, hypotension, and drooling; nevertheless, there are other known adverse effects that psychiatrists should readily recognize and manage. This review covers the “rare” and “very rare” known adverse effects of CLZ, which have been accurately described in literature. An extensive search on the basis of predefined criteria was made using CLZ and its combination with adverse effects as keywords in electronic databases. Data show the association between the use of CLZ and uncommon adverse effects, including ischemic colitis, paralytic ileus, hematemesis, gastroesophageal reflux disease, priapism, urinary incontinence, pityriasis rosea, intertriginous erythema, pulmonary thromboembolism, pseudo-pheochromocytoma, periorbital edema, and parotitis, which are influenced by other variables including age, early diagnosis, and previous/current pharmacological therapies. Some of these adverse effects, although unpredictable, are often manageable if promptly recognized and treated. Others are serious and potentially life-threatening. However, an adequate knowledge of the drug, clinical vigilance, and rapid intervention can drastically reduce the morbidity and mortality related to CLZ treatment.