A peripheral inflammatory signature discriminates bipolar from unipolar depression: A machine learning approach

Machine learning-based discrimination of unipolar depression and bipolar disorder with streamlined shortlist in adolescents of different ages

BACKGROUND

Variations in symptoms and indistinguishable depression episodes of unipolar depression (UD) and bipolar disorder (BD) make the discrimination difficult and time-consuming. For adolescents with high disease prevalence, an efficient diagnostic tool is important for the discrimination and treatment of BU and UD.

METHODS

This multi-center cross-sectional study involved 1587 UD and 246 BD adolescents aged 12-18. A combination of standard questionnaires and demographic information was collected for the construction of a full-item list. The unequal patient number was balanced with three data balancing algorithms, and 4 machine learning algorithms were compared for the discrimination ability of UD and BD in three age groups: all ages, 12-15 and 16-18. Random forest (RF) with the highest accuracy were used to rank the importance of features/items and construct the 25-item shortlist. A separate dataset was used for the final performance evaluation with the shortlist, and the discrimination ability for UD and BD was investigated.

RESULTS

RF performed the best for UD and BD discrimination in all 3 age groups (AUC 0.88-0.90). The most important features that differentiate UD from BD belong to Parental Bonding Instrument (PBI) and Loneliness Scale of the University of California at Los Angeles (UCLA). With RF and the 25-item shortlist, the diagnostic accuracy can still reach around 80 %, achieving 95 % of the accuracy levels obtained with all features.

CONCLUSIONS

Through machine learning algorithms, the most influencing factors for UD and BD classification were recombined and applied for rapid diagnosis. This highly feasible method holds the potential for convenient and accurate diagnosis of young patients in research and clinical practice.

Machine learning applied to the prediction of relapse, hospitalization, and suicide in bipolar disorder using neuroimaging and clinical data: A systematic review

BACKGROUND

Bipolar disorder (BD) is associated with increased morbidity/mortality. Adverse outcome prediction might help with the management of patients with BD.

METHODS

We systematically reviewed the performance of machine learning (ML) studies in predicting adverse outcomes (relapse or recurrence, hospital admission, and suicide-related events) in patients with BD. Demographic, clinical, and neuroimaging-related poor outcome predictors were also reviewed. Three databases (PubMed, Scopus, and Web of Science) were explored from inception to July 2023.

RESULTS

Eighteen studies, accounting for >30,000 patients, were included. Support vector machine, decision trees, random forest, and logistic regression were the most frequently used ML algorithms. ML models' area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity ranged from 0.71 to 0.98, 72.7-92.8 %, and 59.0-95.2 % for relapse/recurrence prediction (4 studies (3 on relapses and 1 on recurrences). The corresponding values were 0.78-0.88, 21.4-100 %, and 77.0-99.7 % for hospital admissions (3 studies, 21,266 patients), and 0.71-0.99, 44.4-97.9 %, and 38.9-95.0 % for suicide-related events (10 studies, 5558 patients). Also, one study addressed a combination of the interest outcomes. Adverse outcome predictors included early onset BD, BD type I, comorbid psychiatric or substance use disorder, circadian rhythm disruption, hospitalization characteristics, and neuroimaging parameters, including increased dynamic amplitude of low-frequency fluctuation, decreased frontolimbic functional connectivity and aberrant dynamic functional connectivity in corticostriatal circuitry.

CONCLUSIONS

ML models can predict adverse outcomes of BD with relatively acceptable performance measures. Future studies with larger samples and nested cross-validation validation should be conducted to reach more reliable results.

Effectiveness of artificial intelligence in detecting and managing depressive disorders: Systematic review

OBJECTIVES

This study underscores the importance of exploring AI's creative applications in treating depressive disorders to revolutionize mental health care. Through innovative integration of AI technologies, the research confirms their positive effects on preventing, diagnosing, and treating depression. The systematic review establishes an evidence base for AI in depression management, offering directions for effective interventions.

METHODS

This systematic literature review investigates the effectiveness of AI in depression management by analyzing studies from January 1, 2017, to May 31, 2022. Utilizing search engines like IEEE Xplore, PubMed, and Web of Science, the review focused on keywords such as Depression/Mental Health, Machine Learning/Artificial Intelligence, and Prediction/Diagnosis. The analysis of 95 documents involved classification based on use, data type, and algorithm type.

RESULTS

The study revealed that AI in depression management excelled in accuracy, particularly in monitoring and prediction. Biomarker-derived data demonstrated the highest accuracy, with the CNN algorithm proving most effective. The findings affirm the therapeutic benefits of AI, including treatment, detection, and disease prediction, highlighting its potential in analyzing monitored data for depression management.

LIMITATIONS

This study exclusively examined the application of AI in individuals with depressive disorders. Interpretation should be cautious due to the limited scope of subjects to this specific population.

CONCLUSIONS

To introduce digital healthcare and therapies for ongoing depression management, it's crucial to present empirical evidence on the medical fee payment system, safety, and efficacy. These findings support enhanced medical accessibility through digital healthcare, offering personalized disease management for patients seeking non-face-to-face treatment.

Simultaneous Utilization of Mood Disorder Questionnaire and Bipolar Spectrum Diagnostic Scale for Machine Learning-Based Classification of Patients With Bipolar Disorders and Depressive Disorders

OBJECTIVE

Bipolar and depressive disorders are distinct disorders with clearly different clinical courses, however, distinguishing between them often presents clinical challenges. This study investigates the utility of self-report questionnaires, the Mood Disorder Questionnaire (MDQ) and Bipolar Spectrum Diagnostic Scale (BSDS), with machine learning-based multivariate analysis, to classify patients with bipolar and depressive disorders.

METHODS

A total of 189 patients with bipolar disorders and depressive disorders were included in the study, and all participants completed both the MDQ and BSDS questionnaires. Machine-learning classifiers, including support vector machine (SVM) and linear discriminant analysis (LDA), were exploited for multivariate analysis. Classification performance was assessed through cross-validation.

RESULTS

Both MDQ and BSDS demonstrated significant differences in each item and total scores between the two groups. Machine learning-based multivariate analysis, including SVM, achieved excellent discrimination levels with area under the ROC curve (AUC) values exceeding 0.8 for each questionnaire individually. In particular, the combination of MDQ and BSDS further improved classification performance, yielding an AUC of 0.8762.

CONCLUSION

This study suggests the application of machine learning to MDQ and BSDS can assist in distinguishing between bipolar and depressive disorders. The potential of combining high-dimensional psychiatric data with machine learning-based multivariate analysis as an effective approach to psychiatric disorders.

Peripheral biomarkers to differentiate bipolar depression from major depressive disorder: a real-world retrospective study

BACKGROUND

Bipolar depression (BPD) is often misdiagnosed as a major depressive disorder (MDD) in clinical practice, which may be attributed to a lack of robust biomarkers indicative of differentiated diagnosis. This study analysed the differences in various hormones and inflammatory markers to explore peripheral biomarkers that differentiate BPD from MDD patients.

METHODS

A total of 2,048 BPD and MDD patients were included. A panel of blood tests was performed to determine the levels of sex hormones, stress hormones, and immune-related indicators. Propensity score matching (PSM) was used to control for the effect of potential confounders between two groups and further a receiver operating characteristic (ROC) curve was used to analyse the potential biomarkers for differentiating BPD from MDD.

RESULTS

Compared to patients with MDD, patients with BPD expressed a longer duration of illness, more hospitalisations within five years, and an earlier age of onset, along with fewer comorbid psychotic symptoms. In terms of biochemical parameters, MDD patients presented higher IgA and IgM levels, while BPD patients featured more elevated neutrophil and monocyte counts. ROC analysis suggested that combined biological indicators and clinical features could moderately distinguish between BPD and MDD. In addition, different biological features exist in BPD and MDD patients of different ages and sexes.

CONCLUSIONS

Differential peripheral biological parameters were observed between BPD and MDD, which may be age-sex specific, and a combined diagnostic model that integrates clinical characteristics and biochemical indicators has a moderate accuracy in distinguishing BPD from MDD.

Preferential and sustained platelet activation in COVID-19 survivors with mental disorders

Pre-existing mental disorders are considered a risk factor for severe COVID-19 outcomes, possibly because of higher vascular burden. Moreover, an unconventional platelet activation characterizes COVID-19 and contributes to inflammatory and thrombotic manifestations. In the light of the inflammation theory of mental disorders, we hypothesized that patients with mental disorders could be sensitive to the SARS-CoV-2 elicited platelet activation. We investigated platelet activation in 141 COVID-19 survivors at one month after clearance of the virus, comparing subjects with or without an established pre-existing diagnosis of mental disorder according to the DSM-5. We found that platelets from patients with a positive history of psychiatric disorder underwent unconventional activation more frequently than conventional activation or no activation at all. Such preferential activation was not detected when platelets from patients without a previous psychiatric diagnosis were studied. When testing the effects of age, sex, and psychiatric history on the platelet activation, GLZM multivariate analysis confirmed the significant effect of diagnosis only. These findings suggest a preferential platelet activation during acute COVID-19 in patients with a pre-existing psychiatric disorder, mediated by mechanisms associated with thromboinflammation. This event could have contributed to the higher risk of severe outcome in the psychiatric population.

Association of psychiatric disorders with clinical diagnosis of long COVID in US veterans

BACKGROUND

Psychiatric disorders may be a risk factor for long COVID, broadly defined as COVID-19 conditions continuing three months post-acute infection. In US Veterans with high psychiatric burden, we examined associations between psychiatric disorders and clinical diagnosis of long COVID.

METHODS

We conducted a retrospective cohort study using health records from VA patients with a positive SARS-CoV-2 test from February 2020 to February 2023. Generalized linear models estimated associations between any psychiatric disorder and likelihood of subsequent diagnosis with long COVID (i.e. two or more long COVID clinical codes). Models were adjusted for socio-demographic, medical, and behavioral factors. Secondary models examined individual psychiatric disorders and age-stratified associations.

RESULTS

Among 660 217 VA patients with positive SARS-CoV-2 tests, 56.3% had at least one psychiatric disorder diagnosis and 1.4% were diagnosed with long COVID. Individuals with any psychiatric disorder had higher risk for long COVID diagnosis in models adjusted for socio-demographic factors, vaccination status, smoking, and medical comorbidities (relative risk, RR = 1.28, 95% CI 1.21-1.35), with the strongest associations in younger individuals. Considering specific disorders, depressive, anxiety, and stress-related disorders were associated with increased risk for long COVID diagnoses (RRs = 1.36-1.48), but associations were in the opposite direction for substance use and psychotic disorders (RRs = 0.78-0.88).

CONCLUSIONS

Psychiatric disorder diagnoses were associated with increased long COVID diagnosis risk in VA patients, with the strongest associations observed in younger individuals. Improved surveillance, treatment, and prevention for COVID-19 and its long-term sequelae should be considered for individuals with psychiatric conditions.

Inflammatory mediators in major depression and bipolar disorder

Major depressive disorder (MDD) and bipolar disorder (BD) are highly disabling illnesses defined by different psychopathological, neuroimaging, and cognitive profiles. In the last decades, immune dysregulation has received increasing attention as a central factor in the pathophysiology of these disorders. Several aspects of immune dysregulations have been investigated, including, low-grade inflammation cytokines, chemokines, cell populations, gene expression, and markers of both peripheral and central immune activation. Understanding the distinct immune profiles characterizing the two disorders is indeed of crucial importance for differential diagnosis and the implementation of personalized treatment strategies. In this paper, we reviewed the current literature on the dysregulation of the immune response system focusing our attention on studies using inflammatory markers to discriminate between MDD and BD. High heterogeneity characterized the available literature, reflecting the heterogeneity of the disorders. Common alterations in the immune response system include high pro-inflammatory cytokines such as IL-6 and TNF-α. On the contrary, a greater involvement of chemokines and markers associated with innate immunity has been reported in BD together with dynamic changes in T cells with differentiation defects during childhood which normalize in adulthood, whereas classic mediators of immune responses such as IL-4 and IL-10 are present in MDD together with signs of immune-senescence.

Low-dose interleukin 2 antidepressant potentiation in unipolar and bipolar depression: Safety, efficacy, and immunological biomarkers

Immune-inflammatory mechanisms are promising targets for antidepressant pharmacology. Immune cell abnormalities have been reported in mood disorders showing a partial T cell defect. Following this line of reasoning we defined an antidepressant potentiation treatment with add-on low-dose interleukin 2 (IL-2). IL-2 is a T-cell growth factor which has proven anti-inflammatory efficacy in autoimmune conditions, increasing thymic production of naïve CD4 + T cells, and possibly correcting the partial T cell defect observed in mood disorders. We performed a single-center, randomised, double-blind, placebo-controlled phase II trial evaluating the safety, clinical efficacy and biological responses of low-dose IL-2 in depressed patients with major depressive (MDD) or bipolar disorder (BD). 36 consecutively recruited inpatients at the Mood Disorder Unit were randomised in a 2:1 ratio to receive either aldesleukin (12 MDD and 12 BD) or placebo (6 MDD and 6 BD). Active treatment significantly potentiated antidepressant response to ongoing SSRI/SNRI treatment in both diagnostic groups, and expanded the population of T regulatory, T helper 2, and percentage of Naive CD4+/CD8 + immune cells. Changes in cell frequences were rapidly induced in the first five days of treatment, and predicted the later improvement of depression severity. No serious adverse effect was observed. This is the first randomised control trial (RCT) evidence supporting the hypothesis that treatment to strengthen the T cell system could be a successful way to correct the immuno-inflammatory abnormalities associated with mood disorders, and potentiate antidepressant response.

Artificial Intelligence and Healthcare: A Journey through History, Present Innovations, and Future Possibilities

Artificial intelligence (AI) has emerged as a powerful tool in healthcare significantly impacting practices from diagnostics to treatment delivery and patient management. This article examines the progress of AI in healthcare, starting from the field's inception in the 1960s to present-day innovative applications in areas such as precision medicine, robotic surgery, and drug development. In addition, the impact of the COVID-19 pandemic on the acceleration of the use of AI in technologies such as telemedicine and chatbots to enhance accessibility and improve medical education is also explored. Looking forward, the paper speculates on the promising future of AI in healthcare while critically addressing the ethical and societal considerations that accompany the integration of AI technologies. Furthermore, the potential to mitigate health disparities and the ethical implications surrounding data usage and patient privacy are discussed, emphasizing the need for evolving guidelines to govern AI's application in healthcare.

Human umbilical cord mesenchymal stem cells reverse depression in rats induced by chronic unpredictable mild stress combined with lipopolysaccharide

BACKGROUND

Inflammation and oxidative stress are considered crucial to the pathogenesis of depression. Rat models of depression can be created by combined treatments of chronic unpredictable mild stress (CUMS) and lipopolysaccharide (LPS). Behaviors associated with depression could be improved by treatment with mesenchymal stem cells (MSCs) owing to immunomodulatory functions of the cells. Therapeutic potentials of the MSCs to reverse pro-inflammatory cytokines, proteins, and metabolites were identified by transcriptomic, proteomic, and metabolomic analysis, respectively.

METHODS

A depression model was established in male SD rats by 2 weeks of CUMS combined with LPS. The models were verified by behavioral tests, namely SPT, OFT, EPM, and qRT-PCR for pro-inflammatory cytokines. Such depressed rats were administered human umbilical cord MSCs (hUC-MSCs) via the tail vein once a week for 2 and 4 weeks. The homing capacity was confirmed by detection of the fluorescent dye on day 7 after the hUC-MSCs were labeled with CM-Dil and administered. The expression of GFAP in astrocytes serves as a biomarker of CNS disorders and IBA1 in microglia serves as a marker of microglia activation were detected by immunohistochemistry at 2 and 4 weeks after final administration of hUC-MSCs. At the same time, transcriptomics of rat hippocampal tissue, proteomic and metabolomic analysis of the serum from the normal, depressed, and treated rats were also compared.

RESULTS

Reliable models of rat depression were successfully induced by treatments of CUMS combined with LPS. Rat depression behaviors, pro-inflammatory cytokines, and morphological disorders of the hippocampus associated with depression were reversed in 4 weeks by hUC-MSC treatment. hUC-MSCs could reach the hippocampus CA1 region through the blood circulation on day 7 after administration owing to the disruption of blood brain barrier (BBB) by microglial activation from depression. Differentiations of whole-genome expression, protein, and metabolite profiles between the normal and depression-modeled rats, which were analyzed by transcriptomic, proteomics, and metabolomics, further verified the high association with depression behaviors.

CONCLUSIONS

Rat depression can be reversed or recovered by treatment with hUC-MSCs.

Choroid plexus volume is increased in mood disorders and associates with circulating inflammatory cytokines

Depressed patients exhibit altered levels of immune-inflammatory markers both in the peripheral blood and in the cerebrospinal fluid (CSF) and inflammatory processes have been widely implicated in the pathophysiology of mood disorders. The Choroid Plexus (ChP), located at the base of each of the four brain ventricles, regulates the exchange of substances between the blood and CSF and several evidence supported a key role for ChP as a neuro-immunological interface between the brain and circulating immune cells. Given the role of ChP as a regulatory gate between periphery, CSF spaces and the brain, we compared ChP volumes in patients with bipolar disorder (BP) or major depressive disorder (MDD) and healthy controls, exploring their association with history of illness and levels of circulating cytokines. Plasma levels of inflammatory markers and MRI scans were acquired for 73 MDD, 79 BD and 72 age- and sex-matched healthy controls (HC). Patients with either BD or MDD had higher ChP volumes than HC. With increasing age, the bilateral ChP volume was larger in patients, an effect driven by the duration of illness; while only minor effects were observed in HC. Right ChP volumes were proportional to higher levels of circulating cytokines in the clinical groups, including IFN-γ, IL-13 and IL-17. Specific effects in the two diagnostic groups were observed when considering the left ChP, with positive association with IL-1ra, IL-13, IL-17, and CCL3 in BD, and negative associations with IL-2, IL-4, IL-1ra, and IFN-γ in MDD. These results suggest that ChP could represent a reliable and easy-to-assess biomarker to evaluate the brain effects of inflammatory status in mood disorders, contributing to personalized diagnosis and tailored treatment strategies.

Identification of Plasma Inflammatory Markers of Adolescent Depression Using the Olink Proteomics Platform

Purpose

The quality of life of worldwide adolescents has been seriously affected by depression. Notably, the inflammatory response is closely associated with the pathophysiology of depression. The present study applied a novel targeted proteomics technology, Olink proximity extension assay (PEA), to profile circulating immune-related proteins in adolescents with depression.

Methods

In the present study, the expression levels of 92 inflammation-related proteins were compared between adolescents with depression (ADs) (n=15) and healthy controls (HCs) (n=15), using the OLINK PEA inflammation panel. We further validated 5 top proteins that were identified through KEGG and GO analyses between 40 HCs and 50 ADs, including CCL4, CXCL5, CXCL6, CXCL11, and IL-18 using enzyme linked immunosorbent assay (ELISA).

Results

We identified 13 differentially expressed proteins between the two cohorts, including 5 up-regulated and 8 down-regulated proteins. Among them, the TRAIL protein levels were significantly negatively correlated with the HAMA-14 score (r=-0.538, p= 0.038), and the levels of transforming growth factor α (TGF-α) were significantly associated with a change in appetite (r = -0.658, p = 0.008). After validation by ELISA, CCL4, CXCL5, CXCL11, and IL-18 showed significant changes between ADs and HCs (p < 0.05), while CXCL6 showed an up-regulated tendency in ADs (p=0.0673). The pooled diagnostic efficacy (area under the curve [AUC]) of these five inflammation markers in clinical diagnosis for adolescent depression was 0.819 (95% CI: 0.735-0.904).

Conclusion

We report a number of inflammation-related plasma biomarkers, which uncover a potential involvement of chemokines, cytokines, and cytokine receptors in adolescent depression. Their roles in the pathophysiology of depression need to be further elucidated.

Neuropsychiatric Outcomes and Sleep Dysfunction in COVID-19 Patients: Risk Factors and Mechanisms

The ongoing global health crisis due to the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has significantly impacted all aspects of life. While the majority of early research following the coronavirus disease caused by SARS-CoV-2 (COVID-19) has focused on the physiological effects of the virus, a substantial body of subsequent studies has shown that the psychological burden of the infection is also considerable. Patients, even without mental illness history, were at increased susceptibility to developing mental health and sleep disturbances during or after the COVID-19 infection. Viral neurotropism and inflammatory storm damaging the blood-brain barrier have been proposed as possible mechanisms for mental health manifestations, along with stressful psychological factors and indirect consequences such as thrombosis and hypoxia. The virus has been found to infect peripheral olfactory neurons and exploit axonal migration pathways, exhibiting metabolic changes in astrocytes that are detrimental to fueling neurons and building neurotransmitters. Patients with COVID-19 present dysregulated and overactive immune responses, resulting in impaired neuronal function and viability, adversely affecting sleep and emotion regulation. Additionally, several risk factors have been associated with the neuropsychiatric sequelae of the infection, such as female sex, age, preexisting neuropathologies, severity of initial disease and sociological status. This review aimed to provide an overview of mental health symptoms and sleep disturbances developed during COVID-19 and to analyze the underlying mechanisms and risk factors of psychological distress and sleep dysfunction.

Can Brain-Derived Neurotrophic Factor Be Considered a Biomarker for Bipolar Disorder? An Analysis of the Current Evidence

Brain-derived neurotrophic factor (BDNF) plays a key role in brain development, contributing to neuronal survival and neuroplasticity. Previous works have found that BDNF is involved in several neurological or psychiatric diseases. In this review, we aimed to collect all available data on BDNF and bipolar disorder (BD) and assess if BDNF could be considered a biomarker for BD. We searched the most relevant medical databases and included studies reporting original data on BDNF circulating levels or Val66Met polymorphism. Only articles including a direct comparison with healthy controls (HC) and patients diagnosed with BD according to international classification systems were included. Of the 2430 identified articles, 29 were included in the present review. Results of the present review show a reduction in BDNF circulating levels during acute phases of BD compared to HC, which increase after effective therapy of the disorders. The Val66Met polymorphism was related to features usually associated with worse outcomes. High heterogeneity has been observed regarding sample size, clinical differences of included patients, and data analysis approaches, reducing comparisons among studies. Although more studies are needed, BDNF seems to be a promising biomarker for BD.

Association of Single Nucleotide Polymorphisms of Cytokine Genes with Depression, Schizophrenia and Bipolar Disorder

Immune gene variants are known to be associated with the risk of psychiatric disorders, their clinical manifestations, and their response to therapy. This narrative review summarizes the current literature over the past decade on the association of polymorphic variants of cytokine genes with risk, severity, and response to treatment for severe mental disorders such as bipolar disorder, depression, and schizophrenia. A search of literature in databases was carried out using keywords related to depressive disorder, bipolar disorder, schizophrenia, inflammation, and cytokines. Gene lists were extracted from publications to identify common genes and pathways for these mental disorders. Associations between polymorphic variants of the IL1B, IL6, and TNFA genes were the most replicated and relevant in depression. Polymorphic variants of the IL1B, IL6, IL6R, IL10, IL17A, and TNFA genes have been associated with schizophrenia. Bipolar disorder has mainly been associated with polymorphic variants of the IL1B gene. Interestingly, the IL6R gene polymorphism (rs2228145) was associated with all three diseases. Some cytokine genes have also been associated with clinical presentation and response to pharmacotherapy. There is also evidence that some specific polymorphic variants may affect the expression of cytokine genes. Thus, the data from this review indicate a link between neuroinflammation and severe mental disorders.

Machine Learning for the Prediction of Depression Progression from Inflammation Markers

Major depressive disorder is one of the major contributors to disability worldwide with an estimated prevalence of 4%. Depression is a heterogeneous disease often characterized by an undefined pathogenesis and multifactorial phenotype that complicate diagnosis and follow-up. Translational research and identification of objective biomarkers including inflammation can assist clinicians in diagnosing depression and disease progression. Investigating inflammation markers using machine learning methods combines recent understanding of the pathogenesis of depression associated with inflammatory changes as part of chronic disease progression that aims to highlight complex interactions. In this paper, 721 patients attending a diabetes health screening clinic (DiabHealth) were classified into no depression (none) to minimal depression (none-minimal), mild depression, and moderate to severe depression (moderate-severe) based on the Patient Health Questionnaire (PHQ-9). Logistic Regression, K-nearest Neighbors, Support Vector Machine, Random Forest, Multi-layer Perceptron, and Extreme Gradient Boosting were applied and compared to predict depression level from inflammatory marker data that included C-reactive protein (CRP), Interleukin (IL)-6, IL-1β, IL-10, Complement Component 5a (C5a), D-Dimer, Monocyte Chemoattractant Protein (MCP)-1, and Insulin-like Growth Factor (IGF)-1. MCP-1 and IL-1β were the most significant inflammatory markers for the classification performance of depression level. Extreme Gradient Boosting outperformed the models achieving the highest accuracy and Area Under the Receiver Operator Curve (AUC) of 0.89 and 0.95, respectively.Clinical Relevance- The findings of this study show the potential of machine learning models to aid in clinical practice, leading to a more objective assessment of depression level based on the involvement of MCP-1 and IL-1β inflammatory markers with disease progression.

Elevated Systemic Levels of Markers Reflecting Intestinal Barrier Dysfunction and Inflammasome Activation Are Correlated in Severe Mental Illness

BACKGROUND AND HYPOTHESIS

Gut microbiota alterations have been reported in severe mental illness (SMI) but fewer studies have probed for signs of gut barrier disruption and inflammation. We hypothesized that gut leakage of microbial products due to intestinal inflammation could contribute to systemic inflammasome activation in SMI.

STUDY DESIGN

We measured plasma levels of the chemokine CCL25 and soluble mucosal vascular addressin cell adhesion molecule-1 (sMAdCAM-1) as markers of T cell homing, adhesion and inflammation in the gut, lipopolysaccharide binding protein (LBP) and intestinal fatty acid binding protein (I-FABP) as markers of bacterial translocation and gut barrier dysfunction, in a large SMI cohort (n = 567) including schizophrenia (SCZ, n = 389) and affective disorder (AFF, n = 178), relative to healthy controls (HC, n = 418). We assessed associations with plasma IL-18 and IL-18BPa and leukocyte mRNA expression of NLRP3 and NLRC4 as markers of inflammasome activation.

STUDY RESULTS

Our main findings were: (1) higher levels of sMAdCAM-1 (P = .002), I-FABP (P = 7.6E-11), CCL25 (P = 9.6E-05) and LBP (P = 2.6E-04) in SMI compared to HC in age, sex, BMI, CRP and freezer storage time adjusted analysis; (2) the highest levels of sMAdCAM-1 and CCL25 (both P = 2.6E-04) were observed in SCZ and I-FABP (P = 2.5E-10) and LBP (3) in AFF; and (3), I-FABP correlated with IL-18BPa levels and LBP correlated with NLRC4.

CONCLUSIONS

Our findings support that intestinal barrier inflammation and dysfunction in SMI could contribute to systemic inflammation through inflammasome activation.

Differences in intracellular protein levels in monocytes and CD4+ lymphocytes between bipolar depressed patients and healthy controls: A pilot study with tyramine-based signal-amplified flow cytometry

BACKGROUND

Molecular biomarkers for bipolar disorder (BD) that distinguish it from other manifestations of depressive symptoms remain unknown. The aim of this study was to determine if a very sensitive tyramine-based signal-amplification technology for flow cytometry (CellPrint™) could facilitate the identification of cell-specific analyte expression profiles of peripheral blood cells for bipolar depression (BPD) versus healthy controls (HCs).

METHODS

The diagnosis of psychiatric disorders was ascertained with Mini International Neuropsychiatric Interview for DSM-5. Expression levels for eighteen protein analytes previously shown to be related to bipolar disorder were assessed with CellPrint™ in CD4⁺ T cells and monocytes of bipolar patients and HCs. Implementation of protein-protein interaction (PPI) network and pathway analysis was subsequently used to identify new analytes and pathways for subsequent interrogations.

RESULTS

Fourteen drug-naïve or -free patients with bipolar I or II depression and 17 healthy controls (HCs) were enrolled. The most distinguishable changes in analyte expression based on t-tests included GSK3β, HMGB1, IRS2, phospho-GSK3αβ, phospho-RELA, and TSPO in CD4⁺ T cells and calmodulin, GSK3β, IRS2, and phospho-HS1 in monocytes. Subsequent PPI and pathway analysis indicated that prolactin, leptin, BDNF, and interleukin-3 signal pathways were significantly different between bipolar patients and HCs.

LIMITATION

The sample size of the study was small and 2 patients were on medications.

CONCLUSION

In this pilot study, CellPrint™ was able to detect differences in cell-specific protein levels between BPD patients and HCs. A subsequent study including samples from patients with BPD, major depressive disorder, and HCs is warranted.

Associations of white blood cell and platelet counts with specific depressive symptom dimensions in patients with bipolar disorder: Analysis of data from the FACE-BD cohort

Evidences suggest that inflammation is increased in a subgroup of patients with depression. Moreover, increased peripheral inflammatory markers (cells and proteins) are associated with some, but not all depressive symptoms. On the other hand, similar studies on bipolar disorders mainly focused on blood cytokines. Here, we analysed data from a large (N = 3440), well-characterized cohort of individuals with bipolar disorder using Kendall partial rank correlation, multivariate linear regression, and network analyses to determine whether peripheral blood cell counts are associated with depression severity, its symptoms, and dimensions. Based on the self-reported 16-Item Quick Inventory of Depressive Symptomatology questionnaire scores, we preselected symptom dimensions based on literature and data-driven principal component analysis. We found that the counts of all blood cell types were only marginally associated with depression severity. Conversely, white blood cell count was significantly associated with the sickness dimension and its four components (anhedonia, slowing down, fatigue, and appetite loss). Platelet count was associated with the insomnia/restlessness dimension and its components (initial, middle, late insomnia and restlessness). Principal component analyses corroborated these results. Platelet count was also associated with suicidal ideation. In analyses stratified by sex, the white blood cell count-sickness dimension association remained significant only in men, and the platelet count-insomnia/restlessness dimension association only in women. Without implying causation, these results suggest that peripheral blood cell counts might be associated with different depressive symptoms in individuals with bipolar disorder, and that white blood cells might be implicated in sickness symptoms and platelets in insomnia/agitation and suicidal ideation.

Applications of Speech Analysis in Psychiatry

ABSTRACT

The need for objective measurement in psychiatry has stimulated interest in alternative indicators of the presence and severity of illness. Speech may offer a source of information that bridges the subjective and objective in the assessment of mental disorders. We systematically reviewed the literature for articles exploring speech analysis for psychiatric applications. The utility of speech analysis depends on how accurately speech features represent clinical symptoms within and across disorders. We identified four domains of the application of speech analysis in the literature: diagnostic classification, assessment of illness severity, prediction of onset of illness, and prognosis and treatment outcomes. We discuss the findings in each of these domains, with a focus on how types of speech features characterize different aspects of psychopathology. Models that bring together multiple speech features can distinguish speakers with psychiatric disorders from healthy controls with high accuracy. Differentiating between types of mental disorders and symptom dimensions are more complex problems that expose the transdiagnostic nature of speech features. Convergent progress in speech research and computer sciences opens avenues for implementing speech analysis to enhance objectivity of assessment in clinical practice. Application of speech analysis will need to address issues of ethics and equity, including the potential to perpetuate discriminatory bias through models that learn from clinical assessment data. Methods that mitigate bias are available and should play a key role in the implementation of speech analysis.

Involvement of inflammatory responses in the brain to the onset of major depressive disorder due to stress exposure

Major depressive disorder (MDD) is a multifactorial disease affected by several environmental factors. Although several potential onset hypotheses have been identified, the molecular mechanisms underlying the pathogenesis of this disorder remain unclear. Several recent studies have suggested that among many environmental factors, inflammation and immune abnormalities in the brain or the peripheral tissues are associated with the onset of MDDs. Furthermore, several stress-related hypotheses have been proposed to explain the onset of MDDs. Thus, inflammation or immune abnormalities can be considered stress responses that occur within the brain or other tissues and are regarded as one of the mechanisms underlying the stress hypothesis of MDDs. Therefore, we introduce several current advances in inflammation studies in the brain that might be related to the pathophysiology of MDD due to stress exposure in this review.

The human physiology of well-being: A systematic review on the association between neurotransmitters, hormones, inflammatory markers, the microbiome and well-being

To understand the pathways through which well-being contributes to health, we performed a systematic review according to the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines on the association between well-being and physiological markers in four categories, neurotransmitters, hormones, inflammatory markers, and microbiome. We identified 91 studies. Neurotransmitter studies (k_{number of studies}=9) reported only a possible positive association between serotonin and well-being. For the hormone studies (k = 48), a lower momentary cortisol level was related to higher well-being (meta-analytic r = -0.06), and a steeper diurnal slope of cortisol levels. Inflammatory marker studies (k = 36) reported negative or non-significant relations with well-being, with meta-analytic estimates of respectively r = -0.07 and r = -0.05 for C-reactive protein and interleukin-6. Microbiome studies (k = 4) reported inconsistent associations between different bacteria abundance and well-being. The results indicate possible but small roles of serotonin, cortisol, and inflammatory markers in explaining differences in well-being. The inconsistent and limited results for other markers and microbiome require further research. Future directions for a complete picture of the physiological factors underlying well-being are proposed.

Systemic inflammatory regulators and 7 major psychiatric disorders: A two-sample Mendelian randomization study

Systemic inflammation has been thought to play a considerable part in psychiatric disorders. However, the causal relationships between systemic inflammation and psychiatric disorders and the directions of the causal effects remain elusive and need further investigation. By leveraging the summary statistics of genome-wide association studies, the standard inverse variance weighted method was applied to assess the causal associations among 41 systemic inflammatory regulators and 7 major psychiatric disorders, including attention-deficit/hyperactivity disorder (ADHD), anorexia nervosa (AN), autism spectrum disorder (ASD), bipolar disorder (BIP), major depression disorder (MDD), obsessive-compulsive disorder (OCD), and schizophrenia (SCZ), within a two-sample bidirectional Mendelian randomization analysis. Additionally, the weighted median test and the Mendelian randomization pleiotropy residual sum and outlier test were conducted for sensitivity analyses. The results suggested a total of 15 unique systemic inflammatory regulators might be causally associated with disease risk, including 2 for ADHD, 4 for AN, 2 for ASD, 2 for MDD, 2 for OCD, and 5 for SCZ. Among them, the genetically predicted concentration of basic fibroblast growth factor was significantly related to AN at the Bonferroni-corrected threshold (Odds ratio = 0.403, 95% confidence interval = (0.261, 0.622), P = 4.03 × 10^-5). Furthermore, the concentrations of 9 systemic inflammatory regulators might be influenced by neuropsychiatric disorders, including 2 by ADHD, 2 by BIP, 3 by MDD, and 2 by SCZ, and the causal effects of ASD, AN, and OCD need to be further assessed when more significant genetic variants are identified in the future. Overall, this study provides additional insights into the relationships between systemic inflammation and psychiatric disorders and may provide new clues regarding the aetiology, diagnosis and treatment of psychiatric disorders.

Antidepressant psychopharmacology: is inflammation a future target?

Raised inflammatory setpoints have been associated with major depression and its detrimental consequences on brain function, as they lead to increased production of cytokines, changes in gene expression and activated brain microglia. Three main lines of evidence support immune-inflammatory mechanisms as targets for the treatment of depression. First, higher inflammation hampers response to antidepressants, and effective antidepressant treatment decreases inflammation. Second, conventional antidepressants share immune-modulatory and anti-inflammatory properties, which could affect inflammation during the depression. Third, anti-inflammatory and immune-modulatory treatments proved superior to placebo in randomized controlled antidepressant trials. New targets and new pharmacologic treatment for immune-mediated inflammatory diseases have been identified and tested in several medical settings and interest is warranted for testing them as antidepressants.

A serum proteomic study of two case-control cohorts identifies novel biomarkers for bipolar disorder

We set out to identify novel protein associations with potential as clinically viable biomarkers for bipolar disorder. To this end, we used proximity extension assay to analyze 201 unique proteins in blood serum from two independent cohorts comprising patients with bipolar disorder and healthy controls (total n = 493). We identified 32 proteins significantly associated with bipolar disorder in both case-control cohorts after adjusting for relevant covariates. Twenty-two findings are novel to bipolar disorder, but 10 proteins have previously been associated with bipolar disorder: chitinase-3-like protein 1, C-C motif chemokine 3 (CCL3), CCL4, CCL20, CCL25, interleukin 10, growth/differentiation factor-15, matrilysin (MMP-7), pro-adrenomedullin, and TNF-R1. Next, we estimated the variance in serum protein concentrations explained by psychiatric drugs and found that some case-control associations may have been driven by psychiatric drugs. The highest variance explained was observed between lithium use and MMP-7, and in post-hoc analyses and found that the serum concentration of MMP-7 was positively associated with serum lithium concentration, duration of lithium therapy, and inversely associated with estimated glomerular filtration rate in an interaction with lithium. This is noteworthy given that MMP-7 has been suggested as a mediator of renal tubulointerstitial fibrosis, which is characteristic of lithium-induced nephropathy. Finally, we used machine learning to evaluate the classification performance of the studied biomarkers but the average performance in unseen data was fair to moderate (area under the receiver operating curve = 0.72). Taken together, our serum biomarker findings provide novel insight to the etiopathology of bipolar disorder, and we present a suggestive biomarker for lithium-induced nephropathy.

Psychological Symptoms in COVID-19 Patients: Insights into Pathophysiology and Risk Factors of Long COVID-19

There is growing evidence of studies associating COVID-19 survivors with increased mental health consequences. Mental health implications related to a COVID-19 infection include both acute and long-term consequences. Here we discuss COVID-19-associated psychiatric sequelae, particularly anxiety, depression, and post-traumatic stress disorder (PTSD), drawing parallels to past coronavirus outbreaks. A literature search was completed across three databases, using keywords to search for relevant articles. The cause may directly correlate to the infection through both direct and indirect mechanisms, but the underlying etiology appears more complex and multifactorial, involving environmental, psychological, and biological factors. Although most risk factors and prevalence rates vary across various studies, being of the female gender and having a history of psychiatric disorders seem consistent. Several studies will be presented, demonstrating COVID-19 survivors presenting higher rates of mental health consequences than the general population. The possible mechanisms by which the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) enters the brain, affecting the central nervous system (CNS) and causing these psychiatric sequelae, will be discussed, particularly concerning the SARS-CoV-2 entry via the angiotensin-converting enzyme 2 (ACE-2) receptors and the implications of the immune inflammatory signaling on neuropsychiatric disorders. Some possible therapeutic options will also be considered.

A Predictive Model of Risk Factors for Conversion From Major Depressive Disorder to Bipolar Disorder Based on Clinical Characteristics and Circadian Rhythm Gene Polymorphisms

BACKGROUND

Bipolar disorder (BD) is easy to be misdiagnosed as major depressive disorder (MDD), which may contribute to a delay in treatment and affect prognosis. Circadian rhythm dysfunction is significantly associated with conversion from MDD to BD. So far, there has been no study that has revealed a relationship between circadian rhythm gene polymorphism and MDD-to-BD conversion. Furthermore, the prediction of MDD-to-BD conversion has not been made by integrating multidimensional data. The study combined clinical and genetic factors to establish a predictive model through machine learning (ML) for MDD-to-BD conversion.

METHOD

By following up for 5 years, 70 patients with MDD and 68 patients with BD were included in this study at last. Single nucleotide polymorphisms (SNPs) of the circadian rhythm genes were selected for detection. The R software was used to operate feature screening and establish a predictive model. The predictive model was established by logistic regression, which was performed by four evaluation methods.

RESULTS

It was found that age of onset was a risk factor for MDD-to-BD conversion. The younger the age of onset, the higher the risk of BD. Furthermore, suicide attempts and the number of hospitalizations were associated with MDD-to-BD conversion. Eleven circadian rhythm gene polymorphisms were associated with MDD-to-BD conversion by feature screening. These factors were used to establish two models, and 4 evaluation methods proved that the model with clinical characteristics and SNPs had the better predictive ability.

CONCLUSION

The risk factors for MDD-to-BD conversion have been found, and a predictive model has been established, with a specific guiding significance for clinical diagnosis.

Are serum levels of inflammatory markers associated with the severity of symptoms of bipolar disorder?

BACKGROUND

To explore the relationship between serum levels of inflammatory markers and symptomatic severity of bipolar disorder (BD).

MATERIALS AND METHODS

A cross-sectional study was conducted on 126 BD patients with current depressive episode (BDD), 102 BD patients with current mixed or (hypo)manic episode (BDM) and 94 healthy controls (HC). All participants were drug-naïve and had no current active physical illness associated with inflammatory response or history of substance abuse. Fasting serum levels of CRP, leptin (LEP), adiponectin (ADP), visfatin (VIS), TNF-α, IL-2, IL-6, IL-10, IL-17), and monocyte chemoattractant protein-1 (MCP-1) were measured with enzyme-linked immunosorbent assay (ELISA). Symptomatic severity of BD was assessed with HAMD-17 and YMRS. Generalized linear model was used to determine the association between the serum levels of inflammatory markers and symptomatic severity of BD.

RESULTS

The serum levels of IL-6, IL-10 and IL-17, and the IL-6/IL-10 ratio were significantly lower in mild BDD than in HC. In moderate BDD, the serum levels of MCP, IL-6 and IL-17 were significantly lower than in HC. In severe BDD, the serum level of ADP, MCP-1, IL-10 and IL-17and the IL-17/IL-10 ratio were significantly lower than in HC. The serum levels of TNF-α and the IL-6/IL-10 ratio were significantly higher in mild BDM than in HC. In moderate BDM, the serum level of VIS, IL-2, and IL-17 were significantly higher than in HC, but the IL-6/IL-10 ratio was significantly lower than in control. In severe BDM, the serum levels of IL-6 and IL-17 and the ratios of IL-6/IL-10 and IL-17/IL-10 were significantly lower than in HC, but the neutrophil/lymphocyte ratio was significantly higher than in HC.

CONCLUSION

In BDD, immune-inhibition is persistently predominant, while in mild-to-moderate BDM, immune system is activated but inhibited in severe BDM. The dynamic change of serum inflammatory markers suggests that alteration of peripheral inflammatory markers in BD is state-dependent instead of trait-marked.

Does Low Grade Systemic Inflammation Have a Role in Chronic Pain?

One of the major clinical manifestations of peripheral neuropathy, either resulting from trauma or diseases, is chronic pain. While it significantly impacts patients’ quality of life, the underlying mechanisms remain elusive, and treatment is not satisfactory. Systemic chronic inflammation (SCI) that we are referring to in this perspective is a state of low-grade, persistent, non-infective inflammation, being found in many physiological and pathological conditions. Distinct from acute inflammation, which is a protective process fighting against intruders, SCI might have harmful effects. It has been associated with many chronic non-communicable diseases. We hypothesize that SCI could be a predisposing and/or precipitating factor in the development of chronic pain, as well as associated comorbidities. We reviewed evidence from human clinical studies indicating the coexistence of SCI with various types of chronic pain. We also collated existing data about the sources of SCI and who could have it, showing that those individuals or patients having SCI usually have higher prevalence of chronic pain and psychological comorbidities. We thus elaborate on the need for further research in the connection between SCI and chronic pain. Several hypotheses have been proposed to explain these complex interactions.

A Study of the Recent Trends of Immunology: Key Challenges, Domains, Applications, Datasets, and Future Directions

The human immune system is very complex. Understanding it traditionally required specialized knowledge and expertise along with years of study. However, in recent times, the introduction of technologies such as AIoMT (Artificial Intelligence of Medical Things), genetic intelligence algorithms, smart immunological methodologies, etc., has made this process easier. These technologies can observe relations and patterns that humans do and recognize patterns that are unobservable by humans. Furthermore, these technologies have also enabled us to understand better the different types of cells in the immune system, their structures, their importance, and their impact on our immunity, particularly in the case of debilitating diseases such as cancer. The undertaken study explores the AI methodologies currently in the field of immunology. The initial part of this study explains the integration of AI in healthcare and how it has changed the face of the medical industry. It also details the current applications of AI in the different healthcare domains and the key challenges faced when trying to integrate AI with healthcare, along with the recent developments and contributions in this field by other researchers. The core part of this study is focused on exploring the most common classifications of health diseases, immunology, and its key subdomains. The later part of the study presents a statistical analysis of the contributions in AI in the different domains of immunology and an in-depth review of the machine learning and deep learning methodologies and algorithms that can and have been applied in the field of immunology. We have also analyzed a list of machine learning and deep learning datasets about the different subdomains of immunology. Finally, in the end, the presented study discusses the future research directions in the field of AI in immunology and provides some possible solutions for the same.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review

Background

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

Objective

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

Methods

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

Results

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

Conclusions

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

CCL4 induces inflammatory signalling and barrier disruption in the neurovascular endothelium

Background

During neuroinflammation many chemokines alter the function of the blood-brain barrier (BBB) that regulates the entry of macromolecules and immune cells into the brain. As the milieu of the brain is altered, biochemical and structural changes contribute to the pathogenesis of neuroinflammation and may impact on neurogenesis. The chemokine CCL4, previously known as MIP-1β, is upregulated in a wide variety of central nervous system disorders, including multiple sclerosis, where it is thought to play a key role in the neuroinflammatory process. However, the effect of CCL4 on BBB endothelial cells (ECs) is unknown.

Materials and methods

Expression and distribution of CCR5, phosphorylated p38, F-actin, zonula occludens-1 (ZO-1) and vascular endothelial cadherin (VE-cadherin) were analysed in the human BBB EC line hCMEC/D3 by Western blot and/or immunofluorescence in the presence and absence of CCL4. Barrier modulation in response to CCL4 using hCMEC/D3 monolayers was assessed by measuring molecular flux of 70 ​kDa RITC-dextran and transendothelial lymphocyte migration. Permeability changes in response to CCL4 in vivo were measured by an occlusion technique in pial microvessels of Wistar rats and by fluorescein angiography in mouse retinae.

Results

CCR5, the receptor for CCL4, was expressed in hCMEC/D3 cells. CCL4 stimulation led to phosphorylation of p38 and the formation of actin stress fibres, both indicative of intracellular chemokine signalling. The distribution of junctional proteins was also altered in response to CCL4: junctional ZO-1 was reduced by circa 60% within 60 ​min. In addition, surface VE-cadherin was redistributed through internalisation. Consistent with these changes, CCL4 induced hyperpermeability in vitro and in vivo and increased transmigration of lymphocytes across monolayers of hCMEC/D3 cells.

Conclusion

These results show that CCL4 can modify BBB function and may contribute to disease pathogenesis.

•

The chemokine CCL4 induced phosphorylation of P38 in an in vitro model of the blood-brain barrier (BBB).

•

CCL4 treatment resulted in reduction of plasma membrane VE-cadherin and junctional ZO-1.

•

CCL4 induced neurovascular barrier breakdown in vitro and in vivo.

Precision Psychiatry: Machine learning as a tool to find new pharmacological targets

There is an increasing amount of data arising from neurobehavioral sciences and medical records that cannot be adequately analyzed by traditional research methods. New drugs develop at a slow rate and seem unsatisfactory for the majority of neurobehavioral disorders. Machine learning (ML) techniques, instead, can incorporate psychopathological, computational, cognitive, and neurobiological underpinning knowledge leading to a refinement of detection, diagnosis, prognosis, treatment, research, and support. Machine and deep learning methods are currently used to accelerate the process of discovering new pharmacological targets and drugs.

OBJECTIVE

The present work reviews current evidence regarding the contribution of machine learning to the discovery of new drug targets.

METHODS

Scientific articles from PubMed, SCOPUS, EMBASE, and Web of Science Core Collection published until May 2021 were included in this review.

RESULTS

The most significant areas of research are schizophrenia, depression and anxiety, Alzheimer´s disease, and substance use disorders. ML techniques have pinpointed target gene candidates and pathways, new molecular substances, and several biomarkers regarding psychiatric disorders. Drug repositioning studies using ML have identified multiple drug candidates as promising therapeutic agents.

CONCLUSION

Next-generation ML techniques and subsequent deep learning may power new findings regarding the discovery of new pharmacological agents by bridging the gap between biological data and chemical drug information.

The future of immunopsychiatry: Three milestones to clinical innovation

Psychoneuroimmunology, the area of research dedicated to understanding the fundamental interactions between the central nervous system and the immune system, has given rise to the development of Immunopsychiatry, a new discipline which harnesses the immune system to produce beneficial outcomes for mental health problems. Immunopsychiatry has the potential to become a clinically relevant specialty area in psychiatric practice, but has not yet been adopted by the wider mental health community. This paper aims to map out the future trajectory of Immunopsychiatry on its road towards science-to-policy knowledge translation and clinical implementation. Three critical milestones which will need to be reached in order for Immunopsychiatry to fulfil its promise for clinical innovation are discussed: a clear definition of patients who fall within the immunopsychiatric continuum; demonstration of well-defined clinical benefit and incorporation in clinical guidelines; and convergence with other paradigms in biological psychiatry.

Blood cytokines differentiate bipolar disorder and major depressive disorder during a major depressive episode: Initial discovery and independent sample replication

Bipolar disorder (BD) diagnosis currently relies on assessment of clinical symptoms, mainly retrospective and subject to memory bias. BD is often misdiagnosed as Major Depressive Disorder (MDD) resulting in ineffective treatment and worsened clinical outcome. The primary purpose of this study was to identify blood biomarkers that discriminate MDD from BD patients when in a depressed state. We have used clinical data and serum samples from two independent naturalistic cohorts of patients with a Major Depressive Episode (MDE) who fulfilled the criteria of either BD or MDD at inclusion. The discovery and replication cohorts consisted of 462 and 133 patients respectively. Patients were clinically assessed using standard diagnostic interviews, and clinical variables including current treatments were recorded. Blood was collected and serum assessed for levels of 31 cytokines using a sensitive multiplex assay. A penalized logistic regression model combined with nonparametric bootstrap was subsequently used to identify cytokines associated with BD. Interleukin (IL)-6, IL-10, IL-15, IL-27 and C-X-C ligand chemokine (CXCL)-10 were positively associated with BD in the discovery cohort. Of the five cytokines identified as discriminant features in the discovery cohort, IL-10, IL-15 and IL-27 were also positively associated with BD in the replication cohort therefore providing an external validation to our finding. Should our results be validated in a prospective cohort, they could provide new insights into the pathophysiological mechanisms of mood disorders.

T helper cells in depression: central role of Th17 cells

Depression is one of the most common neuropsychiatric disorders in the world. While conventional pharmaceutical therapy targets monoaminergic pathway dysfunction, it has not been totally successful in terms of positive outcomes, remission, and preventing relapses. There is an increasing amount of evidence that neuroinflammation may play a significant part in the pathophysiology of depression. Among the key components of the neuroinflammatory pathways already known to be active are the T helper (Th) cells, especially Th17 cells. While various preclinical and clinical studies have reported increased levels of Th17 cells in both serum and brain tissue of laboratory model animals, contradictory results have argued against a pertinent role of Th17 cells in depression. Recent studies have also revealed a role for more pathogenic and inflammatory subsets of Th17 in depression, as well as IL-17A and Th17 cells in non-responsiveness to conventional antidepressant therapy. Despite recent advances, there is still a significant knowledge gap concerning the exact mechanism by which Th17 cells influence neuroinflammation in depression. This review first provides a short introduction to the major findings that led to the discovery of the role of Th cells in depression. The major subsets of Th cells known to be involved in neuroimmunology of depression, such as Th1, Th17, and T regulatory cells, are subsequently described, with an in-depth discussion on current knowledge about Th17 cells in depression.

Effective Antidepressant Chronotherapeutics (Sleep Deprivation and Light Therapy) Normalize the IL-1β:IL-1ra Ratio in Bipolar Depression

Background

Mood disorders associate with peripheral markers of low-grade inflammation, among which circulating levels of interleukin-1β (IL-1β) consistently predict diagnosis and poor outcomes. Antidepressant chronotherapeutics (total sleep deprivation and light therapy, TSD+LT) prompts response in drug-resistant bipolar depression, but its effect on peripheral inflammation were never assessed. Here we explored the effects of TSD+LT on IL-1β signaling.

Methods

We studied the ratio between IL-1β and its receptor antagonist (IL-1β:IL1ra) in 33 healthy participants, and in 26 inpatients with a major depressive episode in course of Bipolar Disorder, before and after treatment with three cycles of repeated TSD+LT, interspersed with sleep recovery nights, administered during 1 week. Treatment effects of mood and on IL-1β:IL1ra were analyzed in the context of the Generalized Linear Model (GLM).

Results

At baseline, patients had higher IL-1β, IL1ra, and IL-1β:IL1ra than controls. Treatment significantly decreased IL-1β:IL1ra, by decreasing IL-1β and increasing IL1ra, the effect being proportional to baseline levels and normalizing values. Patients with higher baseline levels showed the highest decrease in IL-1β:IL-1ra, which associated with the immediate antidepressant response at the first cycle; while patients with lower baseline values showed negligible changes in the IL-1β:IL-1ra, unrelated to treatment response.

Conclusion

We observed a parallel change of inflammatory biomarkers and severity of depression after chronotherapeutics, suggesting that a reduction in inflammation associated with depression could contribute to the mechanism of action of TSD+LT, and warranting interest for controlled studies addressing the role of inflammation in the recovery from bipolar depression.

Identification of lncRNA NR_028138.1 as a biomarker and construction of a ceRNA network for bipolar disorder

The pathogenesis of bipolar disorder (BD), a chronic mood disorder, is largely unknown. Noncoding RNAs play important roles in the pathogenesis of BD. However, little is known about the correlations of long noncoding RNAs (lncRNAs) with BD. Illumina high-throughput sequencing in BD patients and normal controls was used to identify differentially expressed (DE) genes. Two-step real-time quantitative reverse transcription polymerase chain reaction (qRT-PCR) was used to validate DE-RNAs in the first cohort (50 BD and 50 control subjects). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways and lncRNA-mRNA coexpression and lncRNA-microRNA (miRNA)-messenger RNA (mRNA) competing endogenous RNA (ceRNA) network analyses were used to predict the functions of DE-RNAs. Receiver operating characteristic (ROC) curve analysis and logistic regression were applied to evaluate diagnostic performance in an additional testing group (80 BD and 66 control subjects). A total of 576 significantly DE-lncRNAs and 262 DE-mRNAs were identified in BD patients, and 95 lncRNA-miRNA-mRNA interactions were used to construct a ceRNA regulatory network. Analysis of the first cohort showed that six RNAs (NR_028138.1, TCONS_00018621, TCONS_00002186, TNF, PID1, and SDK1) were differentially expressed in the BD group (P < 0.01). NR_028138.1 was used to establish a BD diagnostic model (area under the ROC curve 0.923, P < 0.004, 95% CI: 0.830-0.999). Verification in the second cohort revealed uniformly significant differences in NR_028138.1 (P < 0.0001). This study constructed a ceRNA regulatory network and provided a hypothesis for the pathogenesis of BD. NR_028138.1 was identified as a central element involved in the transcriptional regulation in BD and a potential biomarker.

Persistent psychopathology and neurocognitive impairment in COVID-19 survivors: Effect of inflammatory biomarkers at three-month follow-up

COVID-19 outbreak is associated with mental health implications during viral infection and at short-term follow-up. Data on psychiatric and cognitive sequelae at medium-term follow-up are still lacking. During an ongoing prospective cohort study, the psychopathological and cognitive status of 226 COVID-19 pneumonia survivors (149 male, mean age 58) were prospectively evaluated one and three months after hospital discharge. Psychiatric clinical interview, self-report questionnaires, and neuropsychological profiling of verbal memory, working memory, psychomotor coordination, executive functions, attention and information processing, and verbal fluency were performed. Three months after discharge from the hospital, 35.8% still self-rated symptoms in the clinical range in at least one psychopathological dimension. We observed persistent depressive symptomatology, while PTSD, anxiety, and insomnia decreased during follow-up. Sex, previous psychiatric history, and the presence of depression at one month affected the depressive symptomatology at three months. Regardless of clinical physical severity, 78% of the sample showed poor performances in at least one cognitive domain, with executive functions and psychomotor coordination being impaired in 50% and 57% of the sample. Baseline systemic immune-inflammation index (SII), which reflects the immune response and systemic inflammation based on peripheral lymphocyte, neutrophil, and platelet counts, predicted self-rated depressive symptomatology and cognitive impairment at three-months follow-up; and changes of SII predicted changes of depression during follow-up. Neurocognitive impairments associated with severity of depressive psychopathology, and processing speed, verbal memory and fluency, and psychomotor coordination were predicted by baseline SII. We hypothesize that COVID-19 could result in prolonged systemic inflammation that predisposes patients to persistent depression and associated neurocognitive dysfunction. The linkage between inflammation, depression, and neurocognition in patients with COVID-19 should be investigated in long-term longitudinal studies, to better personalize treatment options for COVID-19 survivors.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review (Preprint).. [DOI: 10.2196/preprints.29749] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

OBJECTIVE

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

METHODS

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

RESULTS

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

CONCLUSIONS

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

Cytokines changes associated with electroconvulsive therapy in patients with treatment-resistant depression: a Meta-analysis

One third of depressive patients do not achieve remission after several steps of treatment and are considered as treatment resistant. Electroconvulsive therapy (ECT) improves symptoms in 70 to 90% of such cases. Resistant depression is associated with a dysregulation of the immune system with a dysbalance between the pro- and the anti-inflammatory cytokines. Therefore, we aimed to measure the kinetic of cytokines levels before, during and at the end of ECT. To test this hypothesis, we performed a meta-analysis assessing cytokines plasma levels before, during and after ECT in patients with major depressive disorders. After a systematic database search, means and standard deviations were extracted to calculate standardized mean differences. We found that IL-6 levels increased after 1 or 2 ECT session (p = 0.01) then decrease after 4 ECT sessions (p < 0.01) with no difference at the end of ECT (p = 0.94). A small number of studies were included and there was heterogeneity across them. The present meta-analysis reveals that ECT induces an initial increase of IL-6 levels and a potential decrease of TNF-α levels. No changes on IL-4 and IL-10 levels were found. Further work is necessary to clarify the impact of ECT on peripheral cytokines.

Personalized Medicine Using Neuroimmunological Biomarkers in Depressive Disorders

Major depressive disorder (MDD) is associated with increased suicidal risk and reduced productivity at work. Neuroimmunology, the study of the immune system and nervous system, provides further insight into the pathogenesis and outcome of MDD. Cytokines are the main modulators of neuroimmunology, and their levels are somewhat entangled in depressive disorders as they affect depressive symptoms and are affected by antidepressant treatment. The use of cytokine-derived medication as a treatment option for MDD is currently a topic of interest. Although not very promising, cytokines are also considered as possible prognostic or diagnostic markers for depression. The machine learning approach is a powerful tool for pattern recognition and has been used in psychiatry for finding useful patterns in data that have translational meaning and can be incorporated in daily clinical practice. This review focuses on the current knowledge of neuroimmunology and depression and the possible use of machine learning to widen our understanding of the topic.

Emerging Neurological and Psychobiological Aspects of COVID-19 Infection

The SARS-CoV-2 virus, first reported in December 2019 in China, is the causative agent of the current COVID-19 pandemic that, at the time of writing (1 November 2020) has infected almost 43 million people and caused the death of more than 1 million people. The spectrum of clinical manifestations observed during COVID-19 infection varies from asymptomatic to critical life-threatening clinical conditions. Emerging evidence shows that COVID-19 affects far more organs than just the respiratory system, including the heart, kidneys, blood vessels, liver, as well as the central nervous system (CNS) and the peripheral nervous system (PNS). It is also becoming clear that the neurological and psychological disturbances that occur during the acute phase of the infection may persist well beyond the recovery. The aim of this review is to propel further this emerging and relevant field of research related to the pathophysiology of neurological manifestation of COVID-19 infection (Neuro-COVID). We will summarize the PNS and CNS symptoms experienced by people with COVID-19 both during infection and in the recovery phase. Diagnostic and pharmacological findings in this field of study are strongly warranted to address the neurological and psychological symptoms of COVID-19.

Proinflammatory Cytokines Predict Brain Metabolite Concentrations in the Anterior Cingulate Cortex of Patients With Bipolar Disorder

Bipolar disorder (BD) is a severe psychiatric illness characterized by abnormalities in the immune/inflammatory function and in brain metabolism. Evidences suggest that inflammation may affect the levels of brain metabolites as measured by single-proton magnetic resonance spectroscopy (¹H-MRS). The aim of the study was to investigate whether a wide panel of inflammatory markers (i.e., cytokines, chemokines, and growth factors) can predict brain metabolite concentrations of glutamate, myo-inositol, N-acetylaspartate, and glutathione in a sample of 63 bipolar patients and 49 healthy controls. Three cytokines influenced brain metabolite concentrations: IL-9 positively predicts glutamate, IL-1β positively predicts Myo-inositol, and CCL5 positively predicts N-acetylaspartate concentrations. Furthermore, patients showed higher concentrations of glutamate, Myo-inositol, and glutathione and lower concentrations of N-acetylaspartate in respect to healthy controls. Our results confirm that inflammation in BD alters brain metabolism, through mechanisms possibly including the production of reactive oxygen species and glia activation.