A machine learning algorithm to differentiate bipolar disorder from major depressive disorder using an online mental health questionnaire and blood biomarker data

Developing Peripheral Biochemical Biomarkers of Brain Disorders: Insights from Zebrafish Models

High prevalence of human brain disorders necessitates development of the reliable peripheral biomarkers as diagnostic and disease-monitoring tools. In addition to clinical studies, animal models markedly advance studying of non-brain abnormalities associated with brain pathogenesis. The zebrafish (Danio rerio) is becoming increasingly popular as an animal model organism in translational neuroscience. These fish share some practical advantages over mammalian models together with high genetic homology and evolutionarily conserved biochemical and neurobehavioral phenotypes, thus enabling large-scale modeling of human brain diseases. Here, we review mounting evidence on peripheral biomarkers of brain disorders in zebrafish models, focusing on altered biochemistry (lipids, carbohydrates, proteins, and other non-signal molecules, as well as metabolic reactions and activity of enzymes). Collectively, these data strongly support the utility of zebrafish (from a systems biology standpoint) to study peripheral manifestations of brain disorders, as well as highlight potential applications of biochemical biomarkers in zebrafish models to biomarker-based drug discovery and development.

Identification of Predictors of Mood Disorder Misdiagnosis and Subsequent Help-Seeking Behavior in Individuals With Depressive Symptoms: Gradient-Boosted Tree Machine Learning Approach

BACKGROUND

Misdiagnosis and delayed help-seeking cause significant burden for individuals with mood disorders such as major depressive disorder and bipolar disorder. Misdiagnosis can lead to inappropriate treatment, while delayed help-seeking can result in more severe symptoms, functional impairment, and poor treatment response. Such challenges are common in individuals with major depressive disorder and bipolar disorder due to the overlap of symptoms with other mental and physical health conditions, as well as, stigma and insufficient understanding of these disorders.

OBJECTIVE

In this study, we aimed to identify factors that may contribute to mood disorder misdiagnosis and delayed help-seeking.

METHODS

Participants with current depressive symptoms were recruited online and data were collected using an extensive digital mental health questionnaire, with the World Health Organization World Mental Health Composite International Diagnostic Interview delivered via telephone. A series of predictive gradient-boosted tree algorithms were trained and validated to identify the most important predictors of misdiagnosis and subsequent help-seeking in misdiagnosed individuals.

RESULTS

The analysis included data from 924 symptomatic individuals for predicting misdiagnosis and from a subset of 379 misdiagnosed participants who provided follow-up information when predicting help-seeking. Models achieved good predictive power, with area under the receiver operating characteristic curve of 0.75 and 0.71 for misdiagnosis and help-seeking, respectively. The most predictive features with respect to misdiagnosis were high severity of depressed mood, instability of self-image, the involvement of a psychiatrist in diagnosing depression, higher age at depression diagnosis, and reckless spending. Regarding help-seeking behavior, the strongest predictors included shorter time elapsed since last speaking to a general practitioner about mental health, sleep problems disrupting daily tasks, taking antidepressant medication, and being diagnosed with depression at younger ages.

CONCLUSIONS

This study provides a novel, machine learning-based approach to understand the interplay of factors that may contribute to the misdiagnosis and subsequent help-seeking in patients experiencing low mood. The present findings can inform the development of targeted interventions to improve early detection and appropriate treatment of individuals with mood disorders.

Metabolomic Biomarker Signatures for Bipolar and Unipolar Depression

Importance

Bipolar disorder (BD) is frequently misdiagnosed as major depressive disorder (MDD) because of overlapping symptoms and the lack of objective diagnostic tools.

Objective

To identify a reproducible metabolomic biomarker signature in patient dried blood spots (DBSs) that differentiates BD from MDD during depressive episodes and assess its added value when combined with self-reported patient information.

Design, Setting, and Participants

This diagnostic analysis used samples and data from the Delta study, conducted in the UK between April 27, 2018, and February 6, 2020. The primary objective was to identify BD in patients with a recent (within the past 5 years) diagnosis of MDD and current depressive symptoms (Patient Health Questionnaire-9 score of 5 or more). Participants were recruited online through voluntary response sampling. The analysis was carried out between February 2022 and July 2023.

Main Outcomes and Measures

Patient data were collected using a purpose-built online questionnaire (n = 635 questions). DBS metabolites (n = 630) were analyzed using a targeted mass spectrometry-based platform. Mood disorder diagnoses were established using the Composite International Diagnostic Interview.

Results

Of 241 patients in the discovery cohort, 170 (70.5%) were female; 67 (27.8%) were subsequently diagnosed with BD and 174 (72.2%) were confirmed as having MDD; and the mean (SD) age was 28.1 (7.1) years. Of 30 participants in the validation cohort, 16 (53%) were female; 9 (30%) were diagnosed with BD and 21 (70%) with MDD; and the mean (SD) age was 25.4 (6.3) years. DBS metabolite levels were assessed in 241 patients with depressive symptoms with a recent diagnosis of MDD, of whom 67 were subsequently diagnosed with BD by the Composite International Diagnostic Interview and 174 were confirmed as having MDD. The identified 17-biomarker panel provided a mean (SD) cross-validated area under the receiver operating characteristic curve (AUROC) of 0.71 (SD, 0.12; P < .001), with ceramide d18:0/24:1 emerging as the strongest biomarker. Combining biomarker data with patient-reported information significantly enhanced diagnostic performance of models based on extensive demographic data, PHQ-9 scores, and the outcomes from the Mood Disorder Questionnaire. The identified biomarkers were correlated primarily with lifetime manic symptoms and were validated in a separate group of patients who received a new clinical diagnosis of MDD (n = 21) or BD (n = 9) during the study's 1-year follow-up period, with a mean (SD) AUROC of 0.73 (0.06; P < .001).

Conclusions and Relevance

This study provides a proof of concept for developing an accessible biomarker test to facilitate the differential diagnosis of BD and MDD and highlights the potential involvement of ceramides in the pathophysiological mechanisms of mood disorders.

Enhancing the efficacy of depression detection system using optimal feature selection from EHR

Diagnosing depression at an early stage is crucial and majorly depends on the clinician's skill. The present work aims to develop an automated tool for assisting the diagnostic procedure of depression using multiple machine-learning techniques. The dataset of sample size 4184 used in this study contains biometric and demographic information of individuals with or without depression, accessed from the University of Nice Sophia-Antipolis. The Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) are used for classifying the depressed from the control group. To enhance the computational efficiency, various feature selection algorithms like Recursive Feature Elimination (RFE), Mutual Information (MI) and three bio-inspired techniques, viz. Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Firefly Algorithms (FA) have been incorporated. To enhance the feature selection process further, majority voting is carried out in all possible combinations of three, four and five feature selection techniques. These feature selection techniques bring down the feature set size significantly to a mean of 33 from the actual size of 61 which is a reduction of 45.90%. The classification accuracy of the enhanced model varies between 84.18% and 88.46%, which is a significant improvement in performance as compared to the pre-existing models (83.76-85.89%). The proposed predictive models outperform the pre-existing classification models without feature selection and thereby enhancing both the performance and efficiency of the diagnostic process.

Dissecting clinical and biological heterogeneity in clinical states of bipolar disorder: a 10-year retrospective study from China

Objectives

To dissect clinical and biological heterogeneity in clinical states of bipolar disorder (BD), and investigate if neuropsychological symptomatology, comorbidity, vital signs, and blood laboratory indicators are predictors of distinct BD states.

Methods

A retrospective BD cohort was established with data extracted from a Chinese hospital's electronic medical records (EMR) between 2009 and 2018. Subjects were inpatients with a main discharge diagnosis of BD and were assessed for clinical state at hospitalization. We categorized all subjects into manic state, depressive state, and mixed state. Four machine learning classifiers were utilized to classify the subjects. A Shapley additive explanations (SHAP) algorithm was applied to the classifiers to aid in quantifying and visualizing the contributions of each feature that drive patient-specific classifications.

Results

A sample of 3,085 records was included (38.54% as manic, 56.69% as depressive, and 4.77% as mixed state). Mixed state showed more severe suicidal ideation and psychomotor abnormalities, while depressive state showed more common anxiety, sleep, and somatic-related symptoms and more comorbid conditions. Higher levels of body temperature, pulse, and systolic and diastolic blood pressures were present during manic episodes. Xgboost achieved the best AUC of 88.54% in manic/depressive states classification; Logistic regression and Random forest achieved the best AUCs of 75.5 and 75% in manic/mixed states and depressive/mixed states classifications, respectively. Myocardial enzymes and the non-enzymatic antioxidant uric acid and bilirubin contributed significantly to distinguish BD clinical states.

Conclusion

The observed novel biological associations with BD clinical states confirm that biological heterogeneity contributes to clinical heterogeneity of BD.

Diagnosing psychiatric disorders from history of present illness using a large-scale linguistic model

AIM

Recent advances in natural language processing models are expected to provide diagnostic assistance in psychiatry from the history of present illness (HPI). However, existing studies have been limited, with the target diseases including only major diseases, small sample sizes, or no comparison with diagnoses made by psychiatrists to ensure accuracy. Therefore, we formulated an accurate diagnostic model that covers all psychiatric disorders.

METHODS

HPIs and diagnoses were extracted from discharge summaries of 2,642 cases at the Nara Medical University Hospital, Japan, from 21 May 2007, to 31 May 31 2021. The diagnoses were classified into 11 classes according to the code from ICD-10 Chapter V. Using UTH-BERT pre-trained on the electronic medical records of the University of Tokyo Hospital, Japan, we predicted the main diagnoses at discharge based on HPIs and compared the concordance rate with the results of psychiatrists. The psychiatrists were divided into two groups: semi-Designated with 3-4 years of experience and Residents with only 2 months of experience.

RESULTS

The model's match rate was 74.3%, compared to 71.5% for the semi-Designated psychiatrists and 69.4% for the Residents. If the cases were limited to those correctly answered by the semi-Designated group, the model and the Residents performed at 84.9% and 83.3%, respectively.

CONCLUSION

We demonstrated that the model matched the diagnosis predicted from the HPI with a high probability to the principal diagnosis at discharge. Hence, the model can provide diagnostic suggestions in actual clinical practice.

Biomarkers in psychiatric disorders

Psychiatric disorders represent a significant socioeconomic and healthcare burden worldwide. Of these, schizophrenia, bipolar disorder, major depressive disorder and anxiety are among the most prevalent. Unfortunately, diagnosis remains problematic and largely complicated by the lack of disease specific biomarkers. Accordingly, much research has focused on elucidating these conditions to more fully understand underlying pathophysiology and potentially identify biomarkers, especially those of early stage disease. In this chapter, we review current status of this endeavor as well as the potential development of novel biomarkers for clinical applications and future research study.

Identification of a diagnostic model and molecular subtypes of major depressive disorder based on endoplasmic reticulum stress-related genes

Subject

Major depressive disorder (MDD) negatively affects patients' behaviours and daily lives. Due to the high heterogeneity and complex pathological features of MDD, its diagnosis remains challenging. Evidence suggests that endoplasmic reticulum stress (ERS) is involved in the pathogenesis of MDD; however, relevant diagnostic markers have not been well studied. This study aimed to screen for ERS genes with potential diagnostic value in MDD.

Methods

Gene expression data on MDD samples were downloaded from the GEO database, and ERS-related genes were obtained from the GeneCards and MSigDB databases. Differentially expressed genes (DEGs) in MDD patients and healthy subjects were identified and then integrated with ERS genes. ERS diagnostic model and nomogram were developed based on biomarkers screened using the LASSO method. The diagnostic performance of this model was evaluated. ERS-associated subtypes were identified. CIBERSORT and GSEA were used to explore the differences between the different subtypes. Finally, WGCNA was performed to identify hub genes related to the subtypes.

Results

A diagnostic model was developed based on seven ERS genes: KCNE1, PDIA4, STAU1, TMED4, MGST1, RCN1, and SHC1. The validation analysis showed that this model had a good diagnostic performance. KCNE1 expression was positively correlated with M0 macrophages and negatively correlated with resting CD4+ memory T cells. Two subtypes (SubA and SubB) were identified, and these two subtypes showed different ER score. The SubB group showed higher immune infiltration than the SubA group. Finally, NCF4, NCF2, CSF3R, and FPR2 were identified as hub genes associated with ERS molecular subtypes.

Conclusion

Our current study provides novel diagnostic biomarkers for MDD from an ERS perspective, and these findings further facilitate the use of precision medicine in MDD.

A New Artificial Intelligence Approach Using Extreme Learning Machine as the Potentially Effective Model to Predict and Analyze the Diagnosis of Anemia

The procedure to diagnose anemia is time-consuming and resource-intensive due to the existence of a multitude of symptoms that can be felt physically or seen visually. Anemia also has several forms, which can be distinguished based on several characteristics. It is possible to diagnose anemia through a quick, affordable, and easily accessible laboratory test known as the complete blood count (CBC), but the method cannot directly identify different kinds of anemia. Therefore, further tests are required to establish a gold standard for the type of anemia in a patient. These tests are uncommon in settings that offer healthcare on a smaller scale because they require expensive equipment. Moreover, it is also difficult to discern between beta thalassemia trait (BTT), iron deficiency anemia (IDA), hemoglobin E (HbE), and combination anemias despite the presence of multiple red blood cell (RBC) formulas and indices with differing optimal cutoff values. This is due to the existence of several varieties of anemia in individuals, making it difficult to distinguish between BTT, IDA, HbE, and combinations. Therefore, a more precise and automated prediction model is proposed to distinguish these four types to accelerate the identification process for doctors. Historical data were retrieved from the Laboratory of the Department of Clinical Pathology and Laboratory Medicine, Faculty of Medicine, Public Health, and Nursing, Universitas Gadjah Mada, Yogyakarta, Indonesia for this purpose. Furthermore, the model was developed using the algorithm for the extreme learning machine (ELM). This was followed by the measurement of the performance using the confusion matrix and 190 data representing the four classes, and the results showed 99.21% accuracy, 98.44% sensitivity, 99.30% precision, and an F1 score of 98.84%.

The centrality of working memory networks in differentiating bipolar type I depression from unipolar depression: A task-fMRI study

OBJECTIVES

Up to 70%-80% of patients with bipolar disorder are misdiagnosed as having major depressive disorder (MDD), leading to both delayed intervention and worsening disability. Differences in the cognitive neurophysiology may serve to distinguish between the depressive phase of type 1 bipolar disorder (BDD-I) from MDD, though this remains to be demonstrated. To this end, we investigate the discriminatory signal in the topological organization of the functional connectome during a working memory (WM) task in BDD-I and MDD, as a candidate identification approach.

METHODS

We calculated and compared the degree centrality (DC) at the whole-brain voxel-wise level in 31 patients with BDD-I, 35 patients with MDD, and 80 healthy controls (HCs) during an n-back task. We further extracted the distinct DC patterns in the two patient groups under different WM loads and used machine learning approaches to determine the distinguishing ability of the DC map.

RESULTS

Patients with BDD-I had lower accuracy and longer reaction time (RT) than HCs at high WM loads. BDD-I is characterized by decreased DC in the default mode network (DMN) and the sensorimotor network (SMN) when facing high WM load. In contrast, MDD is characterized by increased DC in the DMN during high WM load. Higher WM load resulted in better classification performance, with the distinct aberrant DC maps under 2-back load discriminating the two disorders with 90.91% accuracy.

CONCLUSIONS

The distributed brain connectivity during high WM load provides novel insights into the neurophysiological mechanisms underlying cognitive impairment of depression. This could potentially distinguish BDD-I from MDD if replicated in future large-scale evaluations of first-episode depression with longitudinal confirmation of diagnostic transition.

Wearable chemical sensors for biomarker discovery in the omics era

Biomarkers are crucial biological indicators in medical diagnostics and therapy. However, the process of biomarker discovery and validation is hindered by a lack of standardized protocols for analytical studies, storage and sample collection. Wearable chemical sensors provide a real-time, non-invasive alternative to typical laboratory blood analysis, and are an effective tool for exploring novel biomarkers in alternative body fluids, such as sweat, saliva, tears and interstitial fluid. These devices may enable remote at-home personalized health monitoring and substantially reduce the healthcare costs. This Review introduces criteria, strategies and technologies involved in biomarker discovery using wearable chemical sensors. Electrochemical and optical detection techniques are discussed, along with the materials and system-level considerations for wearable chemical sensors. Lastly, this Review describes how the large sets of temporal data collected by wearable sensors, coupled with modern data analysis approaches, would open the door for discovering new biomarkers towards precision medicine.

Lifestyle, Demographic and Socio-Economic Determinants of Mental Health Disorders of Employees in the European Countries

Ensuring the health and well-being of workers should be a top priority for employers and governments. The aim of the article is to evaluate and rank the importance of mental health determinants: lifestyle, demographic factors and socio-economic status. The research study is based on EHIS 2013-2015 data for a sample of N = 140,791 employees from 30 European countries. The results obtained using machine learning techniques such as gradient-boosted trees and SHAPley values show that the mental health of European employees is strongly determined by the BMI, age and social support from close people. The next vital features are alcohol consumption, an unmet need for health care and sports activity, followed by the affordability of medicine or treatment, income and occupation. The wide range of variables clearly indicates that there is an important role for governments to play in order to minimize the risk of mental disorders across various socio-economic groups. It is also a signal for businesses to help boost the mental health of their employees by creating holistic, mentally friendly working conditions, such as offering time-management training, implementing morning briefings, offering quiet areas, making employees feel valued, educating them about depression and burnout symptoms, and promoting a healthy lifestyle.

Using decision-analysis modelling to estimate the economic impact of the identification of unrecognised bipolar disorder in primary care: the untapped potential of screening

Background

Patients with bipolar disorder are often unrecognised and misdiagnosed with major depressive disorder leading to higher direct costs and pressure on the medical system. Novel screening tools may mitigate the problem. This study was aimed at investigating the direct costs of bipolar disorder misdiagnosis in the general population, evaluating the impact of a novel bipolar disorder screening algorithm, and comparing it to the established Mood Disorder Questionnaire. A decision analysis model was built to quantify the utility of one-time screening for bipolar disorder in primary care adults presenting with a depressive episode. A hypothetical population of interest comprised a healthcare system of one million users, corresponding to 15,000 help-seekers diagnosed with major depressive disorder annually, followed for five years. The model was used to calculate the impact of screening for bipolar disorder, compared to no screening, in terms of accuracy and total direct costs to a third-party payer at varying diagnostic cut-offs. Decision curve analysis was used to evaluate clinical utility.

Results

Compared to no screening, one-time screening for bipolar disorder using the algorithm reduced the number of misdiagnoses from 680 to 260, and overall direct costs from $50,936 to $49,513 per patient, accounting for $21.3 million savings over the five-year period. The algorithm outperformed the Mood Disorder Questionnaire, which yielded 367 misdiagnoses and $18.3 million savings over the same time. Decision curve analysis showed the screening model was beneficial.

Conclusions

Utilisation of bipolar disorder screening strategies could lead to a substantial reduction in human suffering by reducing misdiagnosis, and also lessen the healthcare costs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40345-022-00261-9.

Verbal learning, working memory, and attention/vigilance may be candidate phenotypes of bipolar II depression in Chinese Han nationality

OBJECTIVES

Bipolar II depression (BD-II) is a subtype of bipolar disorder with recurrent depressive, manic, and frequent depressive episodes as the main clinical manifestations. This study aimed to compare the cognitive function of patients with BD-II with those of healthy siblings and controls to explore the internal phenotype of BD-II in the field of cognitive function.

METHODS

66 BD-II patients, 58 healthy siblings, and 55 healthy controls were assessed with the Trail Making Test (TMT), Digit Symbol Coding Test (DSCT), Category Fluency, Hopkins Verbal Learning Test-Revised (HVLTR), Brief Visuospatial Memory Test-Revised (BVMT-R), Wechsler Memory Scale 3rd ed. Spatial Span Subtest (WMS-III SS), Neuropsychological Assessment Battery Mazes (NABM), Continuous Performance Test, and Identical Pairs (CPT-IP).

RESULTS

Patients with BD-II showed cognitive deficits in visual learning, reasoning and problem solving, verbal learning, attention/vigilance, working memory, and speed of processing. Healthy siblings showed cognitive deficits in reasoning and problem solving, verbal learning, attention/vigilance, working memory, and speed of processing. Substantial differences were observed among the three groups in reasoning and problem solving.

CONCLUSIONS

Verbal learning, working memory, and attention/vigilance may be potential endophenotypes that can be used to identify BD-II among Han Chinese in the early stage.

An insight into diagnosis of depression using machine learning techniques: a systematic review

BACKGROUND

In this modern era, depression is one of the most prevalent mental disorders from which millions of individuals are affected today. The symptoms of depression are heterogeneous and often coincide with other disorders such as bipolar disorder, Parkinson's, schizophrenia, etc. It is a serious mental illness that may lead to other health problems if left untreated. Currently, identifying individuals with depression is totally based on the expertise of the clinician's experience. In order to assist clinicians in identifying the characteristics and classifying depressed people, different types of data modalities and machine learning techniques have been incorporated by researchers in this field. This study aims to find the answers to some important questions related to the trend of publications, data modality, machine learning models, dataset usage, pre-processing techniques and feature extraction and selection techniques that are prevalent and guide the direction of future research on depression diagnosis.

METHODS

This systematic review was conducted using a broad range of articles from two major databases: IEEE Xplore and PubMed. Studies ranging from the years 2011 to April 2021 were retrieved from the databases resulting in a total of 590 articles (53 articles from the IEEE Xplore database and 537 articles from the PubMed database). Out of those, the articles which satisfied the defined inclusion criteria were investigated for further analysis.

RESULTS

A total of 135 articles were identified and analysed for this review. High growth in the number of publications has been observed in recent years. Furthermore, significant diversity in the use of data modalities and machine learning classifiers has also been noted in this study. fMRI data with an SVM classifier was found to be the most popular choice among researchers. In most of the studies, data scarcity and small sample size, particularly for neuroimaging data are major concerns. The use of identical data pre-processing tools for similar data modalities can be seen. This study also provides statistical analysis of the current framework with respect to the modality, machine learning classifier, sample size and accuracy by applying one-way ANOVA and the Tukey - Kramer test.

CONCLUSION

The results indicate that an effective fusion of machine learning techniques with a potential data modality has a promising future for assisting clinicians in automatic depression diagnosis.

The Current State and Validity of Digital Assessment Tools for Psychiatry: Systematic Review

BACKGROUND

Given the role digital technologies are likely to play in the future of mental health care, there is a need for a comprehensive appraisal of the current state and validity (ie, screening or diagnostic accuracy) of digital mental health assessments.

OBJECTIVE

The aim of this review is to explore the current state and validity of question-and-answer-based digital tools for diagnosing and screening psychiatric conditions in adults.

METHODS

This systematic review was based on the Population, Intervention, Comparison, and Outcome framework and was carried out in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. MEDLINE, Embase, Cochrane Library, ASSIA, Web of Science Core Collection, CINAHL, and PsycINFO were systematically searched for articles published between 2005 and 2021. A descriptive evaluation of the study characteristics and digital solutions and a quantitative appraisal of the screening or diagnostic accuracy of the included tools were conducted. Risk of bias and applicability were assessed using the revised tool for the Quality Assessment of Diagnostic Accuracy Studies 2.

RESULTS

A total of 28 studies met the inclusion criteria, with the most frequently evaluated conditions encompassing generalized anxiety disorder, major depressive disorder, and any depressive disorder. Most of the studies used digitized versions of existing pen-and-paper questionnaires, with findings revealing poor to excellent screening or diagnostic accuracy (sensitivity=0.32-1.00, specificity=0.37-1.00, area under the receiver operating characteristic curve=0.57-0.98) and a high risk of bias for most of the included studies.

CONCLUSIONS

The field of digital mental health tools is in its early stages, and high-quality evidence is lacking.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/25382.

The Effects of Research Activities on Biomedical Students' Mental Health: A National Cross-Sectional Study

Mental health disorders are prevalent among biomedical students, and scientific research is one of their main activities, yet less is known about the relationship between research activities and mental health among these students. The aim of this cross-sectional study was to assess the associations between research activities and mental health and to identify the potential risk factors for anxiety and depression among biomedical students in China. This study enrolled 1,079 participants between November 2020 and December 2020 from 29 Chinese provinces and collected participants' basic characteristics, work situations, scientific achievements, and potential stress sources via an online questionnaire. Anxiety and depression were evaluated by two widely used scales, the Generalized Anxiety Disorder-7 (GAD-7) and the Patient Health Questionnaire-9 (PHQ-9), respectively. The study also assessed the associations between scientific research duration and mental health. Univariate and multivariate analyses were performed to identify the predictors of anxiety and depression. Among the participants, 39.02% scored as having moderate to severe anxiety, and 37.54% scored as having moderate to severe depression. When the Youden index reached its maximum, the optimal cutoff was 7.17 h for the GAD-7 and 6.83 h for the PHQ-9. After adjustment for confounders, a longer research work duration was significantly associated with a higher anxiety [odds ratio (OR) = 1.32, 95% confidence interval (CI): 1.21-1.44, p < 0.01] and depression (OR = 1.27, 95% CI: 1.17-1.39, p < 0.01). Of all the participants working for 7 h a day, 37.04% had already published at least one paper and 25.93% had at least one Science Citation Index paper. Anxiety and depression are common among biomedical students. The research work duration of 7 h a day is the best cutoff for mental health, and it is associated with acceptable scientific research achievements. Not more than 7 h a day on research is recommended for biomedical students to maintain a balance between mental health and scientific research achievements.

Personality, symptom, and demographic correlates of perceived efficacy of selective serotonin reuptake inhibitor monotherapy among current users with low mood: A data-driven approach

BACKGROUND

Selective serotonin reuptake inhibitors (SSRIs) are often the first-line treatment option for depressive symptoms, however their efficacy varies across patients. Identifying predictors of response to SSRIs could facilitate personalised treatment of depression and improve treatment outcomes. The aim of this study was to develop a data-driven formulation of demographic, personality, and symptom-level factors associated with subjective response to SSRI treatment.

METHODS

Participants were recruited online and data were collected retrospectively through an extensive digital mental health questionnaire. Extreme gradient boosting classification with nested cross-validation was used to identify factors distinguishing between individuals with low (n=37) and high (n=111) perceived benefit from SSRI treatment.

RESULTS

The algorithm demonstrated a good predictive performance (test AUC=.88±.07). Positive affectivity was the strongest predictor of response to SSRIs and a major confounder of the remaining associations. After controlling for positive affectivity, as well as current wellbeing, severity of current depressive symptoms, and multicollinearity, only low positive affectivity, chronic pain, sleep problems, and unemployment remained significantly associated with diminished subjective response to SSRIs.

LIMITATIONS

This was an exploratory analysis of data collected at a single time point, for a study which had a different primary aim. Therefore, the results may not reflect causal relationships, and require validation in future prospective studies. Furthermore, the data were self-reported by internet users, which could affect integrity of the dataset and limit generalisability of the results.

CONCLUSIONS

Our findings suggest that demographic, personality, and symptom data may offer a potential cost-effective and efficient framework for SSRI treatment outcome prediction.

Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach

Routine monitoring of lithium levels is common clinical practice. This is because the lithium prediction strategies available developed by previous studies are still limited due to insufficient prediction performance. Thus, we used machine learning approaches to predict lithium concentration in a large real-world dataset. Real-world data from multicenter electronic medical records were used in different machine learning algorithms to predict: (1) whether the serum level was 0.6–1.2 mmol/L or 0.0–0.6 mmol/L (binary prediction), and (2) its concentration value (continuous prediction). We developed models from 1505 samples through 5-fold cross-validation and used 204 independent samples to test their performance by evaluating their accuracy. Moreover, we ranked the most important clinical features in different models and reconstructed three reduced models with fewer clinical features. For binary and continuous predictions, the average accuracy of these models was 0.70–0.73 and 0.68–0.75, respectively. Seven features were listed as important features related to serum lithium levels of 0.6–1.2 mmol/L or higher lithium concentration, namely older age, lower systolic blood pressure, higher daily and last doses of lithium prescription, concomitant psychotropic drugs with valproic acid and -pine drugs, and comorbid substance-related disorders. After reducing the features in the three new predictive models, the binary or continuous models still had an average accuracy of 0.67–0.74. Machine learning processes complex clinical data and provides a potential tool for predicting lithium concentration. This may help in clinical decision-making and reduce the frequency of serum level monitoring.

Toward an Extended Definition of Major Depressive Disorder Symptomatology: Digital Assessment and Cross-validation Study

Background

Diagnosing major depressive disorder (MDD) is challenging, with diagnostic manuals failing to capture the wide range of clinical symptoms that are endorsed by individuals with this condition.

Objective

This study aims to provide evidence for an extended definition of MDD symptomatology.

Methods

Symptom data were collected via a digital assessment developed for a delta study. Random forest classification with nested cross-validation was used to distinguish between individuals with MDD and those with subthreshold symptomatology of the disorder using disorder-specific symptoms and transdiagnostic symptoms. The diagnostic performance of the Patient Health Questionnaire–9 was also examined.

Results

A depression-specific model demonstrated good predictive performance when distinguishing between individuals with MDD (n=64) and those with subthreshold depression (n=140) (area under the receiver operating characteristic curve=0.89; sensitivity=82.4%; specificity=81.3%; accuracy=81.6%). The inclusion of transdiagnostic symptoms of psychopathology, including symptoms of depression, generalized anxiety disorder, insomnia, emotional instability, and panic disorder, significantly improved the model performance (area under the receiver operating characteristic curve=0.95; sensitivity=86.5%; specificity=90.8%; accuracy=89.5%). The Patient Health Questionnaire–9 was excellent at identifying MDD but overdiagnosed the condition (sensitivity=92.2%; specificity=54.3%; accuracy=66.2%).

Conclusions

Our findings are in line with the notion that current diagnostic practices may present an overly narrow conception of mental health. Furthermore, our study provides proof-of-concept support for the clinical utility of a digital assessment to inform clinical decision-making in the evaluation of MDD.

Machine Learning-Based Behavioral Diagnostic Tools for Depression: Advances, Challenges, and Future Directions

The psychiatric diagnostic procedure is currently based on self-reports that are subject to personal biases. Therefore, the diagnostic process would benefit greatly from data-driven tools that can enhance accuracy and specificity. In recent years, many studies have achieved promising results in detecting and diagnosing depression based on machine learning (ML) analysis. Despite these favorable results in depression diagnosis, which are primarily based on ML analysis of neuroimaging data, most patients do not have access to neuroimaging tools. Hence, objective assessment tools are needed that can be easily integrated into the routine psychiatric diagnostic process. One solution is to use behavioral data, which can be easily collected while still maintaining objectivity. The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders. We classified these studies into two main categories: (a) laboratory-based assessments and (b) data mining, the latter of which we further divided into two sub-groups: (i) social media usage and movement sensors data and (ii) demographic and clinical information. The paper discusses the advantages and challenges in this field and suggests future research directions and implementations. The paper's overarching aim is to serve as a first step in synthetizing existing knowledge about ML-based behavioral diagnosis studies in order to develop interventions and individually tailored treatments in the future.

The Delta Study - Prevalence and characteristics of mood disorders in 924 individuals with low mood: Results of the of the World Health Organization Composite International Diagnostic Interview (CIDI)

OBJECTIVES

The Delta Study was undertaken to improve the diagnosis of mood disorders in individuals presenting with low mood. The current study aimed to estimate the prevalence and explore the characteristics of mood disorders in participants of the Delta Study, and discuss their implications for clinical practice.

METHODS

Individuals with low mood (Patients Health Questionnaire-9 score ≥5) and either no previous mood disorder diagnosis (baseline low mood group, n = 429), a recent (≤5 years) clinical diagnosis of MDD (baseline MDD group, n = 441) or a previous clinical diagnosis of BD (established BD group, n = 54), were recruited online. Self-reported demographic and clinical data were collected through an extensive online mental health questionnaire and mood disorder diagnoses were determined with the World Health Organization Composite International Diagnostic Interview (CIDI).

RESULTS

The prevalence of BD and MDD in the baseline low mood group was 24% and 36%, respectively. The prevalence of BD among individuals with a recent diagnosis of MDD was 31%. Participants with BD in both baseline low mood and baseline MDD groups were characterized by a younger age at onset of the first low mood episode, more severe depressive symptoms and lower wellbeing, relative to the MDD or low mood groups. Approximately half the individuals with BD diagnosed as MDD (49%) had experienced (hypo)manic symptoms prior to being diagnosed with MDD.

CONCLUSIONS

The current results confirm high under- and misdiagnosis rates of mood disorders in individuals presenting with low mood, potentially leading to worsening of symptoms and decreased well-being, and indicate the need for improved mental health triage in primary care.

Impact of a Web-Based Psychiatric Assessment on the Mental Health and Well-Being of Individuals Presenting With Depressive Symptoms: Longitudinal Observational Study

BACKGROUND

Web-based assessments of mental health concerns hold great potential for earlier, more cost-effective, and more accurate diagnoses of psychiatric conditions than that achieved with traditional interview-based methods.

OBJECTIVE

The aim of this study was to assess the impact of a comprehensive web-based mental health assessment on the mental health and well-being of over 2000 individuals presenting with symptoms of depression.

METHODS

Individuals presenting with depressive symptoms completed a web-based assessment that screened for mood and other psychiatric conditions. After completing the assessment, the study participants received a report containing their assessment results along with personalized psychoeducation. After 6 and 12 months, participants were asked to rate the usefulness of the web-based assessment on different mental health-related outcomes and to self-report on their recent help-seeking behavior, diagnoses, medication, and lifestyle changes. In addition, general mental well-being was assessed at baseline and both follow-ups using the Warwick-Edinburgh Mental Well-being Scale (WEMWBS).

RESULTS

Data from all participants who completed either the 6-month or the 12-month follow-up (N=2064) were analyzed. The majority of study participants rated the study as useful for their subjective mental well-being. This included talking more openly (1314/1939, 67.77%) and understanding one's mental health problems better (1083/1939, 55.85%). Although most participants (1477/1939, 76.17%) found their assessment results useful, only a small proportion (302/2064, 14.63%) subsequently discussed them with a mental health professional, leading to only a small number of study participants receiving a new diagnosis (110/2064, 5.33%). Among those who were reviewed, new mood disorder diagnoses were predicted by the digital algorithm with high sensitivity (above 70%), and nearly half of the participants with new diagnoses also had a corresponding change in medication. Furthermore, participants' subjective well-being significantly improved over 12 months (baseline WEMWBS score: mean 35.24, SD 8.11; 12-month WEMWBS score: mean 41.19, SD 10.59). Significant positive predictors of follow-up subjective well-being included talking more openly, exercising more, and having been reviewed by a psychiatrist.

CONCLUSIONS

Our results suggest that completing a web-based mental health assessment and receiving personalized psychoeducation are associated with subjective mental health improvements, facilitated by increased self-awareness and subsequent use of self-help interventions. Integrating web-based mental health assessments within primary and/or secondary care services could benefit patients further and expedite earlier diagnosis and effective treatment.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/18453.

Construction and Analysis of a Diagnostic Model Based on Differential Expression Genes in Patients With Major Depressive Disorder

Background: Major depressive disorder (MDD) is a common and severe psychiatric disorder with a heavy burden on the individual and society. However, the prevalence varies significantly owing to the lack of auxiliary diagnostic biomarkers. To identify the shared differential expression genes (DEGs) with potential diagnostic value in both the hippocampus and whole blood, a systematic and integrated bioinformatics analysis was carried out. Methods: Two datasets from the Gene Expression Omnibus database (GSE53987 and GSE98793) were downloaded and analyzed separately. A weighted gene co-expression network analysis was performed to construct the co-expression gene network of DEGs from GSE53987, and the most disease-related module was extracted. The shared DEGs from the module and GSE98793 were identified using a Venn diagram. Functional pathway prediction was used to identify the most disease-related DEGs. Finally, several DEGs were chosen, and their potential diagnostic value was determined by receiver operating characteristic curve analysis. Results: After weighted gene co-expression network analysis, the most MDD-related module (MEgrey) was identified, and 623 DEGs were extracted from this module. The intersection between MEgrey and GSE98793 was calculated, and 163 common DEGs were identified. The co-expression network of 163 DEGs from these was then reconstructed. All hub genes were identified based on the connective degree of the reconstructed co-expression network. Based on the results of functional pathway enrichment, 17 candidate hub genes were identified. Finally, logistic regression and receiver operating characteristic curves showed that three candidate hub genes (CEP350, SMAD5, and HSPG2) had relatively high auxiliary value in the diagnosis of MDD. Conclusion: Our results showed that the combination of CEP350, SMAD5, and HSPG2 has a relatively high diagnostic value for MDD. Pathway enrichment analysis also showed that these genes may play an important role in the pathogenesis of MDD. These results suggest a potentially important role for this gene combination in clinical practice.