BACKGROUND: Schizophrenia is a severe psychiatric disorder associated with a significant negative impact. Early diagnosis and treatment of schizophrenia has a favorable effect on the clinical outcome and patients quality of life. In this context, machine learning techniques open up new opportunities for a more accurate diagnosis and prediction of the clinical features of this illness. AIM: This literature review is aimed to search for information on the use of machine learning techniques in the prediction and diagnosis of schizophrenia and the determination of its clinical features. METHODS: The Google Scholar, PubMed, and eLIBRARY.ru databases were used to search for relevant data. The review included articles that had been published not earlier than January 1, 2010, and not later than March 31, 2023. Combinations of the following keywords were applied for search queries: machine learning, deep learning, schizophrenia, neural network, predictors, artificial intelligence, diagnostics, suicide, depressive, insomnia, and cognitive. Original articles regardless of their design were included in the review. Descriptive analysis was used to summarize the retrieved data. RESULTS: Machine learning techniques are widely used in the functional assessment of patients with schizophrenia. They are used for interpretation of MRI, EEG, and actigraphy findings. Also, models created using machine learning algorithms can analyze speech, behavior, and the creativity of people and these data can be used for the diagnosis of psychiatric disorders. It has been found that different machine learning-based models can help specialists predict and diagnose schizophrenia based on medical history and genetic data, as well as epigenetic information. Machine learning techniques can also be used to build effective models that can help specialists diagnose and predict clinical manifestations and complications of schizophrenia, such as insomnia, depressive symptoms, suicide risk, aggressive behavior, and changes in cognitive functions over time. CONCLUSION: Machine learning techniques play an important role in psychiatry, as they have been used in models that help specialists in the diagnosis of schizophrenia and determination of its clinical features. The use of machine learning algorithms is one of the most promising direction in psychiatry, and it can significantly improve the effectiveness of the diagnosis and treatment of schizophrenia.

Valproic acid (VPA) and its salts (sodium calcium magnesium and orotic) are psychotropic drugs that are widely used in neurology and psychiatry. The long-term use of VPA increases the risk of developing adverse drug reactions (ADRs), among which metabolic syndrome (MetS) plays a special role. MetS belongs to a cluster of metabolic conditions such as abdominal obesity, high blood pressure, high blood glucose, high serum triglycerides, and low serum high-density lipoprotein. Valproate-induced MetS (VPA-MetS) is a common ADR that needs an updated multidisciplinary approach to its prevention and diagnosis. In this review, we consider the results of studies of blood (serum and plasma) and the urinary biomarkers of VPA-MetS. These metabolic biomarkers may provide the key to the development of a new multidisciplinary personalized strategy for the prevention and diagnosis of VPA-MetS in patients with neurological diseases, psychiatric disorders, and addiction diseases.

Antipsychotic (AP)—induced adverse drug reactions (ADRs) are a current problem of biological and clinical psychiatry. Despite the development of new generations of APs, the problem of AP-induced ADRs has not been solved and continues to be actively studied. One of the important mechanisms for the development of AP-induced ADRs is a genetically-determined impairment of AP efflux across the blood-brain barrier (BBB). We present a narrative review of publications in databases (PubMed, Springer, Scopus, Web of Science E-Library) and online resources: The Human Protein Atlas; GeneCards: The Human Gene Database; US National Library of Medicine; SNPedia; OMIM Online Mendelian Inheritance in Man; The PharmGKB. The role of 15 transport proteins involved in the efflux of drugs and other xenobiotics across cell membranes (P-gp, TAP1, TAP2, MDR3, BSEP, MRP1, MRP2, MRP3, MRP4, MRP5, MRP6, MRP7, MRP8, MRP9, BCRP) was analyzed. The important role of three transporter proteins (P-gp, BCRP, MRP1) in the efflux of APs through the BBB was shown, as well as the association of the functional activity and expression of these transport proteins with low-functional and non-functional single nucleotide variants (SNVs)/polymorphisms of the ABCB1, ABCG2, ABCC1 genes, encoding these transport proteins, respectively, in patients with schizophrenia spectrum disorders (SSDs). The authors propose a new pharmacogenetic panel “Transporter protein (PT)—Antipsychotic (AP) Pharmacogenetic test (PGx)” (PTAP-PGx), which allows the evaluation of the cumulative contribution of the studied genetic biomarkers of the impairment of AP efflux through the BBB. The authors also propose a riskometer for PTAP-PGx and a decision-making algorithm for psychiatrists. Conclusions: Understanding the role of the transportation of impaired APs across the BBB and the use of genetic biomarkers for its disruption may make it possible to reduce the frequency and severity of AP-induced ADRs, since this risk can be partially modified by the personalized selection of APs and their dosing rates, taking into account the genetic predisposition of the patient with SSD.

Background: Delirium Tremens (DT) is known to be a serious complication of alcohol withdrawal syndrome (AWS). Neurotransmitter abnormalities, inflammation, and increased permeability are associated with the pathogenesis of AWS and DT. However, the biomarkers of these conditions are still poorly understood. Methods: In this work, biochemical, hematologic, inflammatory, and gut permeability biomarkers were investigated in the following three groups: healthy controls (n = 75), severe AWS patients with DT (n = 28), and mild/moderate AWS without DT (n = 97). Blood sampling was performed after resolution of the acute condition (on 5 ± 1 day after admission) to collect clinical information from patients and to investigate associations with clinical scales. Biomarker analysis was performed using automated analyzers and ELISA. Inflammatory biomarkers included the erythrocyte sedimentation rate (ESR), high-sensitivity C-reactive protein (hsCRP), and platelet-to-lymphocyte ratio (PLR). Results: Among the biochemical biomarkers, only glucose, total cholesterol, and alanine aminotransferase (ALT) changed significantly in the analyzed groups. A multiple regression analysis showed that age and ALT were independent predictors of the CIWA-Ar score. Hematologic biomarker analysis showed an increased white blood cell count, and the elevated size and greater size variability of red blood cells and platelets (MCV, RDWc, and PDWc) in two groups of patients. Gut permeability biomarkers (FABP2, LBP, and zonulin) did not change, but were associated with comorbid pathologies (alcohol liver disease and pancreatitis). The increase in inflammatory biomarkers (ESR and PLR) was more evident in AWS patients with DT. Cluster analysis confirmed the existence of a subgroup of patients with evidence of high inflammation, and such a subgroup was more frequent in DT patients. Conclusions: These findings contribute to the understanding of biomarker variability in AWS patients with and without DT and support the heterogeneity of patients by the level of inflammation.

The majority of patients with alcohol dependence syndrome suffer from sleep disorders, particularly insomnia, associated with a number of critical clinical aspects, increased suicide risk, anxiety and depression. The authors of relevant publications indicate associations between polymorphic melatonin genes and melatonin metabolism and symptoms of sleep disorders. However, the literature review failed to reveal any studies on the role of genetic polymorphism of circadian rhythm regulators in sleep disorders in patients with alcohol dependence.Objective: to determine the associations of polymorphic variants of genes HTR2A, MTNR1A, MTNR1B, CLOCK, DRD2 with sleep disorders risk in alcohol dependence syndrome.Patients and methods. 307 patients with alcohol dependence syndrome were screened, including 61 women (21%) and 246 (79%) men (mean age – 41.92±7.9 years). The presence and severity of sleep disorders were assessed by the Insomnia Severity Index. In addition, 10 ml of venous blood sample was obtained from all participants. Genotyping of single nucleotide variants of HTR2A (rs6313), MTNR1A (rs34532313), MTNR1B (rs10830963), CLOCK (rs1801260), DRD2 (rs1800497) genes was performed using real-time polymerase chain reaction. Statistical analysis of the data was conducted using parametric and nonparametric methods.Results and discussion. The carriage of the *G allele of the polymorphic variant of the MTNR1B (rs10830963) gene, and its genotypes are associated with a greater risk of insomnia than the carriage of *С/*С genotype. The carriage of the *С allele of the polymorphic variant of the CLOCK (rs1801260) gene, as well as the *С/*Т genotype, are associated with the presence of sleep disorders. No associations between polymorphic variants of the HTR2A (rs6313), DRD2 (rs1800497) genes and insomnia risk were detected in patients with alcohol dependence syndrome.Conclusion. The found associations reveal prospects for future research on melatonin's role in the pathophysiology of sleep disorders in patients with alcohol dependence and pathogenetic therapy for insomnia.

   Objective: to compare the severity of the relationship between mental state and insomnia of medical students working and not working as nurses.   Materials and methods: research methods — sociological, psychometric, statistical. The study was conducted at the Bashkir State Medical University (BSMU) from February to April 2022. Data collection was carried out using Google Forms. Study group №1 — 172 students working as nurses. The proportion of males is 41 % (70/172), females — 59 % (102/172). The average age was 21-23 years. Study group № 1 — 66 non-working students. Among the studied 16.7 % (11/66) men, 83.3 % (55/66) women. The average age is 21-23 years. SCL-90-R (Symptom Check List-90-Revised), Insomnia Severity Index (ISI), Pittsburgh Sleep Quality Index (PSQI) were used as methods. Statistical processing was carried out using Microsoft Excel, STATISTICA 10, Spearman correlation coefficient, U — Mann-whitney test.   Results: the degree of manifestation of insomnia in the study group № 1 and № 2 positively correlates with both all SCL-90-R scales and second-order indices. when comparing the studied groups, it was found that the mental state of non-working students is more unstable, the quality of sleep is worse.   Conclusions: the relationship between the mental state and insomniac disorders in medical students, both working as nurses and not working, has been established. we assume that students who do not work as nurses have low adaptive abilities, as a result of which their mental state is accompanied by more pronounced insomniac disorders.