Neuronetwork Approach in the Early Diagnosis of Depression.

BACKGROUND: Depression is a common mental illness, with around 280 million people suffering from depression worldwide. At present, the main way to quantify the severity of depression is through psychometric scales, which entail subjectivity on the part of both patient and clinician. In the last few years, deep (machine) learning is emerging as a more objective approach for measuring depression severity. We now investigate how neural networks might serve for the early diagnosis of depression. SUBJECTS AND METHODS: We searched Medline (Pubmed) for articles published up to June 1, 2023. The search term included Depression AND Diagnostics AND Artificial Intelligence. We did not search for depression studies of machine learning other than neural networks, and selected only those papers attesting to diagnosis or screening for depression. RESULTS: Fifty-four papers met our criteria, among which 14 using facial expression recordings, 14 using EEG, 5 using fMRI, and 5 using audio speech recording analysis, whereas 6 used multimodality approach, two were the text analysis studies, and 8 used other methods. CONCLUSIONS: Research methodologies include both audio and video recordings of clinical interviews, task performance, including their subsequent conversion into text, and resting state studies (EEG, MRI, fMRI). Convolutional neural networks (CNN), including 3D-CNN and 2D-CNN, can obtain diagnostic data from the videos of the facial area. Deep learning in relation to EEG signals is the most commonly used CNN. fMRI approaches use graph convolutional networks and 3D-CNN with voxel connectivity, whereas the text analyses use CNNs, including LSTM (long/short-term memory). Audio recordings are analyzed by a hybrid CNN and support vector machine model. Neural networks are used to analyze biomaterials, gait, polysomnography, ECG, data from wrist wearable devices, and present illness history records. Multimodality studies analyze the fusion of audio features with visual and textual features using LSTM and CNN architectures, a temporal convolutional network, or a recurrent neural network. The accuracy of different hybrid and multimodality models is 78-99%, relative to the standard clinical diagnoses.

G.T. MSRS On-Line Calculator Targeting the Early Diagnosis of Mixed Affective States: the Multicenter Study Project Design on the Approbation and Validity of the Three Language Versions of the Rating Scale.

BACKGROUND: Mixed affective states (MS) are often misdiagnosed by the clinicians and lead to the inappropriate treatment strategies contributing to the severe forms, poor outcome with higher rates of comorbid conditions and worse remission quality in affective and bipolar disorders, as well as to a decreased psychosocial functioning of these patients. The development of reliable tools for the MS assessments or so called the phenomenon of mixity in affective disorders, is still an unmet need of psychiatric research and clinical practice. In this paper, we present PC program "Multilingual IBM-PC on-line calculator for early diagnosis of the mixed affective states" based on the Giuseppe Tavormina Mixed States Rating Scale (G.T. MSRS) (Russian, English, Italian language versions) created by the ICERN group using programming language JavaScript, working for such operation systems (OS) as Windows, Linux, MacOs, Android, iOS, and aims to contribute to the accurate assessment of the presence and severity of the mixed states among affective disorders. SUBJECTS AND METHODS: The G.T. Mixed States Rating Scale on-line calculator consists of 11 items which evaluate various aspects of MS in patients with major depression, bipolar or recurrent depressive disorder. A total score is automatically calculated, considering the type of affective temperament according to the Akiskal's and Tavormina's schemas, thus, the specific sub-groups of MS are differentiated based on the ranges: Medium-light (2-6), Medium (7-12), and High (13-19) Mixity level. The study will enroll 330 participants during two (three months follow-up) visits (110 native speakers in each of the three languages) of both genders aged from 18 till 55 y.o. with the diagnoses of depressive episodes, major depression, bipolar or recurrent depressive disorder according to the DSM-5 criteria. Assessments will be provided by the two investigators (second one will be blinded to the G.T. MSRS results obtained by the first researcher), based on the use of DSM-5 clinical interview, Young Mania Rating Scale, Montgomery-Åsberg Depression Rating Scale, Clinical Global Impression - Severity scale (CGI-S), Clinical Global Impression - Improvement scale (CGI-I), Patient Global Impression of Change (PGIC). RESULTS: The study will assess the agreement between the diagnostic category/clinical impression and the on-line G.T. MSRS calculator use results, its test-retest reliability, and diagnosis stability for further assessment of the on-line G.T. MSRS calculator validity and clinical utility. Secondary variables will evaluate internal reliability and such statistical analyses as Cronbach's alpha, Cohen's Kappa, biserial correction, and agreement between initial and follow-up diagnoses. CONCLUSIONS: Current multicenter validation study of the on-line G.T. MSRS calculator will enhance the understanding of the mixity phenomenon and its clinical implication, aiming to improve the treatment strategies to manage the course of mental disorder, quality of life and psychosocial functioning in patients with affective (bipolar) disorders, accompanied by MS, and a clinical recommendation for the routine administration of the user-friendly on-line G.T. MSRS version in clinical practice.

Post-COVID Neuropsychiatric Complications in Children and Adolescents: a Study Design for Early Diagnosis and Treatment Using Innovative Technologies.

BACKGROUND: The COVID-19 pandemic has had significant impacts on the child and adolescent population, with long-term consequences for physical health, socio-psychological well-being, and cognitive development, which require further investigation. We herein describe a study design protocol for recognizing neuropsychiatric complications associated with pediatric COVID-19, and for developing effective prevention and treatment strategies grounded on the evidence-based findings. METHODS: The study includes two cohorts, each with 163 participants, aged from 7 to 18 years old, and matched by gender. One cohort consisted of individuals with a history of COVID-19, while the other group presents those without such a history. We undertake comprehensive assessments, including neuropsychiatric evaluations, blood tests, and validated questionnaires completed by parents/guardians and by the children themselves. The data analysis is based on machine learning techniques to develop predictive models for COVID-19-associated neuropsychiatric complications in children and adolescents. RESULTS: The first model is focused on a binary classification to distinguish participants with and without a history of COVID-19. The second model clusters significant indicators of clinical dynamics during the follow-up observation period, including the persistence of COVID-19 related somatic and neuropsychiatric symptoms over time. The third model manages the predictors of discrete trajectories in the dynamics of post-COVID-19 states, tailored for personalized prediction modeling of affective, behavioral, cognitive, disturbances (academic/school performance), and somatic symptoms of the long COVID. CONCLUSIONS: The current protocol outlines a comprehensive study design aiming to bring a better understanding of COVID-19-associated neuropsychiatric complications in a population of children and adolescents, and to create a mobile phone-based applications for the diagnosis and treatment of affective, cognitive, and behavioral conditions. The study will inform about the improved management of preventive and personalized care strategies for pediatric COVID-19 patients. Study results support the development of engaging and age-appropriate mobile technologies addressing the needs of this vulnerable population group.

Social Distance Factor Related to the Level of Mental Health Awareness Among the Clinicians.

BACKGROUND: Stigmatization of morbidity in health care workers, the incidence of disease, the disease that interferes with the disease of medical care. Social distancing by clinicians is an integral part of the stigmatization that depends on the behavior of the patient and the level of awareness of the clinician. METHODS: The modified Bogardus Social Distance Self-Assessment Scale (BSDS) was used to evaluate the indicators of social distance phenomena. The assessment was performed by clinicians for the following groups of patients with the following mental disorders: alcohol use disorder, bipolar disorder, depression, drug addiction, epilepsy, mental retardation, schizophrenia. All statistical calculations were performed using IBM SPSS-27 software (IBM Corp. 2021, licensed to Samara State Medical University). P-value ≤ 0.05 was determined as significant for the between-group (PSY vs NPHP) comparisons using a nonparametric Wilcoxon test. RESULTS: The study included 141 clinicians: PSY (n=20; 36.2±4.2 y.o.) and NPHP (n=121; 25.9±2.2 y.o.). The NPHP group included general practitioners (GP)/physicians (n=29; 20.6%), surgeons (n=19; 13.5%), obstetrician-gynecologists (n=26; 18.4%), neurologists (n=11; 7.8%), pediatricians (n=6; 4.3%), and other subspecialists (including urologists, tuberculosis specialists, ophthalmologists, and dermatologists) (n=30; 21.3%). The study included 141 students at the Samara State Medical University who were trained in psychiatry. An anonymous survey was conducted on the BSDS scale before and after training. Our analysis of the data showed that the social distance of clinicians in terms of coverage reaches different values depending on the mental disorder, but with common trends both before and after the psychiatry training course. Mean (SD) social distance scores recurred from 2.8 (1.3) for bipolar disorder to 5.3 (1.5) for addiction in the predevelopment group and 2.9 (1.3), 5.4 (1.4) in the group of clinicians after training, respectively. CONCLUSIONS: Social distancing scores among clinicians in contemporary Russia were highest for drug addicts, and lowest for depression and bipolar disorder. Stigmatization among clinicians appears to affect the delivery of care to certain categories of patients, which requires further study. Higher social distance scores in patients with drug addiction may be associated with higher stigma and lack of compassion towards these patients. Conversely, lower rates of social distancing and the corresponding emotional acceptance of people with depression and bipolar disorder by clinicians may interfere with timely diagnosis and the availability of appropriate early, treatable care. The awareness of clinicians regarding psychopathological manifestations does not affect the level of social distance, but increases it in relation to mentally healthy individuals with normal behavior.

Pharmacogenetic Aspects of COVID-19 Management and Post-COVID-19 Depression Treatment with Fluvoxamine.

BACKGROUND: Quarantine measures with self-isolation of varying duration have been significant psychosocial stressors in the context of the COVID-19 pandemic. The serotonin selective reuptake inhibitor fluvoxamine has been considered as a prophylaxis against depression in early COVID-19 patients, with additional benefits apparently arising from its antiviral activity. In this narrative review, we draw attention to the body of evidence showing efficacy of fluvoxamine in protecting against depressive disorders in COVID-19 patients, while also attenuating the severity of COVID-19 disease, with a notable reduction in the need for intubation and lower mortality. We consider this potential two-fold action of fluvoxamine in the light of its pharmacogenetic and pharmacological profiles. SUBJECTS AND METHODS: Full-text publications in English and Russian in Google Scholar, PubMed, NCBI, Web of Science, and E-Library databases were selected by keywords, solitary and in combination (fluvoxamine, COVID-19, depression, anxiety, antidepressants, adverse reactions) for the period from March 01, 2020 to June 06, 2022. We also analyzed the full-text publications in English and Russian language reporting adverse reactions caused by fluvoxamine use for the period from 2012 to 2022. RESULTS: The literature search yielded 10 papers reporting on the efficacy fluvoxamine in relieving depressive symptoms in COVID-19 patients, and 3 papers on its effect on medical outcome. The preponderance of data indicated a dual therapeutic action of fluvoxamine, and our further literature investigation was informative about drug-drug interactions and genetic factors moderating the antidepressant efficacy of fluvoxamine. CONCLUSIONS: Patients with COVID-19 seeking psychopharmacological treatment for depressive symptoms must be informed of the benefits and risks of fluvoxamine use. Several lines of findings indicate this agent to possess an additional antiviral action. However, optimal dosage regimens and the trade-off with drug-drug interactions remain unclear. Pharmacogenetic testing may assist in evidence-based optimization of fluvoxamine dosages in the context of COVID-19 infection with comorbid depression.

The Efficacy of Mobile Phone-Based Interventions for the Treatment of Depression: A Systematic Meta-Review of Meta-Analyses of Randomized Controlled Trials.

BACKGROUND: Depression is ranked by the World Health Organization as the single largest contributor to global disability. The shortage of health care resources, conditions of social distancing during the present pandemic, and the continuing need of patients with subclinical depression and in remission for supportive therapies, all together motivate a search for new approaches to deliver appropriate and timeous treatment for depression. SUBJECTS AND METHODS: We conducted a systematic literature search of meta-analyses and systematic reviews on the topic of mobile apps for the treatment of depression using the Medline (Pubmed) database during the period ending March 30th, 2022. This review was managed following the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines and entailed a search strategy using key-words related to depressive states and mobile phone apps for depression treatment and management. RESULTS: A total of 15 full-text articles met the inclusion criteria for the current systematic review. 13 of the 15 studies reported on the effectiveness of mobile apps for treating depression, finding a significant reduction in depressive symptoms with small-to-medium positive effect size. Patients with severe depression experienced greater benefits from a behavioral activation app, whereas those with mild depression responded better to a mindfulness app. The impact of clinicians' support is difficult to isolated completely from the particular interventions' effects. CONCLUSIONS: Mobile-based intervention apps present a convenient tool for prevention and supportive therapy of depression. The use of mobile apps may act as an efficient intervention to reduce depression in adult patients regardless the potential contributing factors of gender or co-morbidities, but the role of mobile apps should be contrasted with other digital interventions.

Non-Psychiatrist Healthcare Professionals? Attitudes Toward Patients with Mental Disorders: Lower Scores in Social Distance as a Fragile Facet of Public Stigma Against Depression.

BACKGROUND: The stigmatization by healthcare professionals (HP) of patients suffering from mental disorders is an important problem that interferes with the delivery of medical assistance. Social distancing by HP is an integral part of stigmatization, which differs between various mental disorders, as well as between psychiatrists (PSY) versus nonpsychiatrist healthcare professionals (NPHP). SUBJECTS AND METHODS: The study included 141 HP: PSY (n=20; 36.2±4.2 y.o.) and NPHP (n=121; 25.9±2.2 y.o.). The NPHP group included general practitioners (GP)/physicians (n=29; 20.6%), surgeons (n=19; 13.5%), obstetrician-gynecologists (n=26; 18.4%), neurologists (n=11; 7.8%), pediatricians (n=6; 4.3%), and other subspecialists (including urologists, tuberculosis specialists, ophthalmologists and dermatologists) (n=30; 21.3%). The modified Bogardus Social Distance Self-Assessment Scale (BSDS) was used to evaluate the indicators of social distance phenomena. The assessment was performed by HP for the following groups of patients with the following mental disorders: alcohol use disorder, bipolar disorder, depression, drug addiction, epilepsy, mental retardation, personality disorder, schizophrenia. All statistical calculations were performed using IBM SPSS-27 software (IBM Corp. 2021, licensed to Samara State Medical University). P-value ≤0.05 was determined as significant for the between-group (PSY vs NPHP) comparisons using a nonparametric Mann-Whitney U-test. RESULTS: Our data analysis showed that HP achieved varying social distance scores for patients depending on the type of mental disorder, but with common trends among PSY and NPHPs. The mean (SD) scores of social distance ranged from 3.65(1.50) for depression to 5.25 (1.74) for drug addiction in the PSY, versus 3.44 (1.69), 6.19 (1.37) in NPHP, respectively. As compared to PSY, mean BSDS total scores were greater in the NPHP group, notably in the obstetricians-gynecologist - 6.27(1.40), and GP - 6.62 (0.90) groups, with similar trends of differing attitudes appeared among pediatricians - 7.00 (0.01) - regarding drug addiction, whereas the neurologists demonstrated a tendency towards lower social distance in relation to patients with depression - 2.27 (1.68), and epilepsy - 2.82 (1.47). CONCLUSIONS: Social distance measures by PSY and NPHP groups in contemporary Russia were highest in relation to patients with drug addiction, and lowest scores for depression and epilepsy. Stigmatization among HPs seems to influence health care delivery to certain categories of patients, which calls for further investigation. Higher social distance scores for patients with drug addiction might be related to higher stigma and lack of compassion toward these patients. Conversely, lower scores of social distance and corresponding emotional acceptance of people with depression by HP might interfere in the timely diagnosis and availability of appropriate care at an early stage amenable to treatment. This might reflect the cultural context of depressive mentality in Russia, or elevated prevalence of depressive states among HP. We propose interventions aiming to destigmatize mental disorders by targeting particular subgroups of vulnerable patients and also certain representatives of HP community.

Anxiety, Depression and Suicidality in Healthcare Workers during the COVID-19 Pandemic: The Russian Study Sample of the COMET-G Project.

BACKGROUND: During the COVID-19 pandemic healthcare workers have been under pressure of high workload and an increased risk of contracting the SARS-Cov-2 virus, while confronting the most tragic and devastating aspects of the pandemic-related medical realities. These factors could lead to severe distress with potential consequences for productivity in performing professional duties, and substantially increased risk for affective reactions, including clinical states of anxiety, depression and suicidality as compared to the general population. Thus, we aimed to investigate the changes in rates of anxiety, depression and suicidality in response to the pandemic among medical staff as compared to a sample of the general population and to the period of prepandemic time. SUBJECTS AND METHODS: This study is part of the large-scale, international multicentre COMET-G project. We assessed the extents of anxiety, depression and suicidality risks using the Stait-Trait Anxiety Inventory (STAI) with a cut-off score 39/40, Center for Epidemiologic Studies Depression Scale (CES-D) with a cut-off score 23/24, and the Risk Assessment Suicidality Scale (RASS) with a cut-off score 499/500, respectively, in samples of Russian healthcare workers and the general population. RESULTS: Among 7777 respondents participating in the study, responses to a query about occupation indicated 1216 healthcare workers. 45.8% of medical staff vs 40.4% of non-medical staff (χ2=12.42, p<0.001) reported the increased anxiety, in excess of the clinical anxiety state threshold score of 39 according to the STAI. High suicidality risks, according to a RASS score > 500, were reported by 8.2% of medical professionals vs 10.6% of non-medical personnel (χ2=6.35, p=0.012). The increase in depression rates, including cases of clinical depression according to the threshold of CES-D ≥ 24, did not differ between the groups. CONCLUSIONS: A larger proportion of healthcare system staff, as compared to the general population, reported a significant increase in anxiety in response to the pandemic. Compared to medical doctors, other healthcare system workers had a significantly higher prevalence of depression and suicidality rates. Exploratory analysis suggested that it was not the occupation per se, but rather the burden of meaningful working duties that could be associated with psychological defense mechanisms against depression and suicidality among medical staff.

Interactions between Anxiety Levels and Life Habits Changes in General Population during the Pandemic Lockdown: Decreased Physical Activity, Falling Asleep Late and Internet Browsing about COVID-19 Are Risk Factors for Anxiety, whereas Social Media Use Is not.

BACKGROUND: The COVID-19 pandemic has substantially contributed to increased anxiety rates among the general population worldwide. Pandemic-related health anxiety and worries about getting COVID-19 can lead to generalized anxiety and anxiety somatization, which, together with insalubrious daily life habits, are risk factors of worsening somatic health in people with SARS-Cov-2 infection. SUBJECTS AND METHODS: The current study is a part of the COMET-G project (40 countries, n=55589; approved by the Ethics Committee of the Aristotle University of Thessaloniki), which represents an intermediate analysis of data collected anonymously via online links from a national sample of the Russian general population (n=9936, 31.09±12.16 y.o., 58.7% females) to estimate anxiety using STAI-S and self-reported changes in anxiety and life habits (physical activity, nutrition and weight, internet use, sleep) during the lockdown. All statistical calculations (descriptive statistics, between group comparisons using chi-square test, MANOVA, ANOVA, significant at p<0.05) were performed with IBM SPSS 27. RESULTS: Overall STAI-S scores were 29±5.4, a subjective feeling of anxiety increase was reported in 40.3% of respondents (43.9% significantly > in females), worsening to clinical anxiety in 2.1% (2.4% > in females). 54.2% of respondents reported decreased physical activity, 33.1% gained weight, 72% used internet more often, 52.6% experienced worries related to the information about COVID-19 (56.8% > in females). 88% experienced worsened sleep quality, 69.2% stayed up until late, 23.2% took sleeping pills, and 31% had nightmares in which they felt trapped. To ANOVA, such life habits as reduced physical activity during the lockdown, increased time spent online, internet browsing about COVID-19, tendency to stay up late, use of sleeping pills and disturbing dreams with scenario of being trapped were significantly related to worsening of clinical anxiety. However, eating behaviour, weight changes, and social media use did not contribute to the clinical anxiety increase. CONCLUSIONS: Factors of decreased physical activity and sleep disturbances related to the lockdown, as well as excessive internet browsing for information about COVID-19, emerged as risk factors for increased anxiety, more notably in women than in men. Preventive measures should be targeted against relevant factors imparting anxiety in the vulnerable population.

Use of the Communication Checklist - Self Report (Cc-Sr) in Schizophrenia: Language Impairments Correlate with Poor Premorbid Social Adjustment.

BACKGROUND: The present study reports preliminary results from the multicentre project on the approbation of the Russian language version of the "The Communication Checklist-Self Report" (RL-CC-SR) and its first use in schizophrenia (SZ), aiming to evaluate the contribution of language disturbances in the pathogenesis of this heterogeneous disorder. SUBJECTS AND METHODS: The study evaluated patients' clinical state with the Diagnostic Interview for Psychoses (DIP), and assessed language and communication disturbances (LCD) with the RL-CC-SR in all participants (213 healthy controls (HC), 83 SZ patients, 31 SZ first-degree relatives). Data from the current sample of SZ (n=50), and HC (n=213) was analysed to calculate the relationships between LCD, social and clinical variables using descriptive statistics methods, T-test and Pearson's correlations (SPSS-26, 2019). RESULTS: The quotient scores (<6) and raw scores on all three CC-SR subscales demonstrated prominent LCD in SZ: (i) language structure (LS) (SZ:11.92±8.01, HC:7.54±5.91; p<0.001), (ii) pragmatic skills (PS) (SZ:11.30±10.07, HC:8.71±7.39; p=0.040), (iii) social engagement (SE) (SZ:31.94±11.76, HC:19.42±10.35; p<0.001). In SZ, Pearson correlations of LS scores were significant for the DIP-items Odd Speech (p=0.033), and Social Engagement - Blunted Affect (p=0.042). PS was related to early disease onset (p=0.027), poor premorbid work adjustment (p=0.003), along with LS (p=0.005), and was also linked to poor premorbid social adjustment (p=0.005). CONCLUSIONS: SZ patients are aware of their LCD at all levels of language structure, pragmatics, and nonverbal communication, but are unable to compensate. Disturbances of LS and PS in SZ patients relate to their poor social adjustment and functioning, and may prove to be associated with the primary negative symptoms domain of the disorder and its generally poor outcome.