Machine learning and big data analytics in bipolar disorder: A position paper from the International Society for Bipolar Disorders Big Data Task Force

Towards a neurodevelopmental model of bipolar disorder: a critical review of trait- and state-related functional neuroimaging in adolescents and young adults

Neurodevelopmental mechanisms are increasingly implicated in bipolar disorder (BD), highlighting the importance of their study in young persons. Neuroimaging studies have demonstrated a central role for frontotemporal corticolimbic brain systems that subserve processing and regulation of emotions, and processing of reward in adults with BD. As adolescence and young adulthood (AYA) is a time when fully syndromal BD often emerges, and when these brain systems undergo dynamic maturational changes, the AYA epoch is implicated as a critical period in the neurodevelopment of BD. Functional magnetic resonance imaging (fMRI) studies can be especially informative in identifying the functional neuroanatomy in adolescents and young adults with BD (BDAYA) and at high risk for BD (HR-BDAYA) that is related to acute mood states and trait vulnerability to the disorder. The identification of early emerging brain differences, trait- and state-based, can contribute to the elucidation of the developmental neuropathophysiology of BD, and to the generation of treatment and prevention targets. In this critical review, fMRI studies of BDAYA and HR-BDAYA are discussed, and a preliminary neurodevelopmental model is presented based on a convergence of literature that suggests early emerging dysfunction in subcortical (e.g., amygdalar, striatal, thalamic) and caudal and ventral cortical regions, especially ventral prefrontal cortex (vPFC) and insula, and connections among them, persisting as trait-related features. More rostral and dorsal cortical alterations, and bilaterality progress later, with lateralization, and direction of functional imaging findings differing by mood state. Altered functioning of these brain regions, and regions they are strongly connected to, are implicated in the range of symptoms seen in BD, such as the insula in interoception, precentral gyrus in motor changes, and prefrontal cortex in cognition. Current limitations, and outlook on the future use of neuroimaging evidence to inform interventions and prevent the onset of mood episodes in BDAYA, are outlined.

The application of machine learning techniques in posttraumatic stress disorder: a systematic review and meta-analysis

Posttraumatic stress disorder (PTSD) recently becomes one of the most important mental health concerns. However, no previous study has comprehensively reviewed the application of big data and machine learning (ML) techniques in PTSD. We found 873 studies meet the inclusion criteria and a total of 31 of those in a sample of 210,001 were included in quantitative analysis. ML algorithms were able to discriminate PTSD with an overall accuracy of 0.89. Pooled estimates of classification accuracy from multi-dimensional data (0.96) are higher than single data types (0.86 to 0.90). ML techniques can effectively classify PTSD and models using multi-dimensional data perform better than those using single data types. While selecting optimal combinations of data types and ML algorithms to be clinically applied at the individual level still remains a big challenge, these findings provide insights into the classification, identification, diagnosis and treatment of PTSD.

Digital Tools to Facilitate the Detection and Treatment of Bipolar Disorder: Key Developments and Future Directions

Bipolar disorder (BD) impacts over 40 million people around the world, often manifesting in early adulthood and substantially impacting the quality of life and functioning of individuals. Although early interventions are associated with a better prognosis, the early detection of BD is challenging given the high degree of similarity with other psychiatric conditions, including major depressive disorder, which corroborates the high rates of misdiagnosis. Further, BD has a chronic, relapsing course, and the majority of patients will go on to experience mood relapses despite pharmacological treatment. Digital technologies present promising results to augment early detection of symptoms and enhance BD treatment. In this editorial, we will discuss current findings on the use of digital technologies in the field of BD, while debating the challenges associated with their implementation in clinical practice and the future directions.

Circulating T-cell subsets discrepancy between bipolar disorder and major depressive disorder during mood episodes: A naturalistic, retrospective study of 1015 cases

AIMS

We aimed to investigate whether peripheral T-cell subsets could be a biomarker to distinguish major depressive disorder (MDD) and bipolar disorder (BD).

METHODS

Medical records of hospitalized patients in the Department of Psychiatry, the First Affiliated Hospital, Zhejiang University School of Medicine, from January 2015 to September 2020 with a discharge diagnosis of MDD or BD were reviewed. Patients who underwent peripheral blood examination of T-cell subtype proportions, including CD3+, CD4+, CD8+ T-cell, and natural killer (NK) cells, were enrolled. The Chi-square test, t-test, or one-way analysis of variance were used to analyze group differences. Demographic profiles and T-cell data were used to construct a random forest classifier-based diagnostic model.

RESULTS

Totally, 98 cases of BD mania, 459 cases of BD depression (BD-D), and 458 cases of MDD were included. There were significant differences in the proportions of CD3+, CD4+, CD8+ T-cell, and NK cells among the three groups. Compared with MDD, the BD-D group showed higher CD8+ but lower CD4+ T-cell and a significantly lower ratio of CD4+ and CD8+ proportions. The random forest model achieved an area under the curve of 0.77 (95% confidence interval: 0.71-0.83) to distinguish BD-D from MDD patients.

CONCLUSION

These findings imply that BD and MDD patients may harbor different T-cell inflammatory patterns, which could be a potential diagnostic biomarker for mood disorders.

Prediction of patient admission and readmission in adults from a Colombian cohort with bipolar disorder using artificial intelligence

Introduction

Bipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology.

Aim

To develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques.

Methods

The study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index.

Results

The admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70.

Conclusion

ML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.

Identification of Psycho-Socio-Judicial Trajectories and Factors Associated With Posttraumatic Stress Disorder in People Over 15 Years of Age Who Recently Reported Sexual Assault to a Forensic Medical Center: Protocol for a Multicentric Prospective Study Using Mixed Methods and Artificial Intelligence

BACKGROUND

Sexual assault (SA) can lead to a range of adverse effects on physical, sexual, and mental health, as well as on one's social life, financial stability, and overall quality of life. However, not all people who experience SA will develop negative functional outcomes. Various risk and protective factors can influence psycho-socio-judicial trajectories. However, how these factors influence trauma adaptation and the onset of early posttraumatic stress disorder (PTSD) is not always clear.

OBJECTIVE

Guided by an ecological framework, this project has 3 primary objectives: (1) to describe the 1-year psycho-socio-judicial trajectories of individuals recently exposed to SA who sought consultation with a forensic practitioner; (2) to identify predictive factors for the development of PTSD during the initial forensic examination using artificial intelligence; and (3) to explore the perceptions, needs, and experiences of individuals who have been sexually assaulted.

METHODS

This longitudinal multicentric cohort study uses a mixed methods approach. Quantitative cohort data are collected through an initial questionnaire completed by the physician during the first forensic examination and through follow-up telephone questionnaires at 6 weeks, 3 months, 6 months, and 1 year after the SA. The questionnaires measure factors associated with PTSD, mental, physical, social, and overall functional outcomes, as well as psycho-socio-judicial trajectories. Cohort participants are recruited through their forensic examination at 1 of the 5 participating centers based in France. Eligible participants are aged 15 or older, have experienced SA in the last 30 days, are fluent in French, and can be reached by phone. Qualitative data are gathered through semistructured interviews with cohort participants, individuals who have experienced SA but are not part of the cohort, and professionals involved in their psycho-socio-judicial care.

RESULTS

Bivariate and multivariate analyses will be conducted to examine the associations between each variable and mental, physical, social, and judicial outcomes. Predictive analyses will be performed using multiple prediction algorithms to forecast PTSD. Qualitative data will be integrated with quantitative data to identify psycho-socio-judicial trajectories and enhance the prediction of PTSD. Additionally, data on the perceptions and needs of individuals who have experienced SA will be analyzed independently to gain a deeper understanding of their experiences and requirements.

CONCLUSIONS

This project will collect extensive qualitative and quantitative data that have never been gathered over such an extended period, leading to unprecedented insights into the psycho-socio-judicial trajectories of individuals who have recently experienced SA. It represents the initial phase of developing a functional artificial intelligence tool that forensic practitioners can use to better guide individuals who have recently experienced SA, with the aim of preventing the onset of PTSD. Furthermore, it will contribute to addressing the existing gap in the literature regarding the accessibility and effectiveness of support services for individuals who have experienced SA in Europe. This comprehensive approach, encompassing the entire psycho-socio-judicial continuum and taking into account the viewpoints of SA survivors, will enable the generation of innovative recommendations for enhancing their care across all stages, starting from the initial forensic examination.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/46652.

Predicting the diagnosis of various mental disorders in a mixed cohort using blood-based multi-protein model: a machine learning approach

The lack of objective diagnostic methods for mental disorders challenges the reliability of diagnosis. The study aimed to develop an easily accessible and useable objective method for diagnosing major depressive disorder (MDD), schizophrenia (SZ), bipolar disorder (BPD), and panic disorder (PD) using serum multi-protein. Serum levels of brain-derived neurotrophic factor (BDNF), VGF (non-acronymic), bicaudal C homolog 1 (BICC1), C-reactive protein (CRP), and cortisol, which are generally recognized to be involved in different pathogenesis of various mental disorders, were measured in patients with MDD (n = 50), SZ (n = 50), BPD (n = 55), and PD along with 50 healthy controls (HC). Linear discriminant analysis (LDA) was employed to construct a multi-classification model to classify these mental disorders. Both leave-one-out cross-validation (LOOCV) and fivefold cross-validation were applied to validate the accuracy and stability of the LDA model. All five serum proteins were included in the LDA model, and it was found to display a high overall accuracy of 96.9% when classifying MDD, SZ, BPD, PD, and HC groups. Multi-classification accuracy of the LDA model for LOOCV and fivefold cross-validation (within-study replication) reached 96.9 and 96.5%, respectively, demonstrating the feasibility of the blood-based multi-protein LDA model for classifying common mental disorders in a mixed cohort. The results suggest that combining multiple proteins associated with different pathogeneses of mental disorders using LDA may be a novel and relatively objective method for classifying mental disorders. Clinicians should consider combining multiple serum proteins to diagnose mental disorders objectively.

Suicide risk classification with machine learning techniques in a large Brazilian community sample

Even though suicide is a relatively preventable poor outcome, its prediction remains an elusive task. The main goal of this study was to develop machine learning classifiers to identify increased suicide risk in Brazilians with common mental disorders. With the use of clinical and sociodemographic baseline data (n = 4039 adult participants) from a large Brazilian community sample, we developed several models (Elastic Net, Random Forests, Naïve Bayes, and ensemble) for the classification of increased suicide risk among individuals with common mental disorders. 1120 participants (27.7%) presented increased suicide risk. The Random Forests model achieved the best AUC ROC (0.814), followed by Naive Bayes (0.798) and Elastic Net (0.773). Sensitivity varied from 0.922 (Naive Bayes) to 0.630 (Random Forests), while specificity varied from 0.792 (Random Forests) to 0.473 (Naive Bayes). The ensemble model presented an AUC ROC of 0.811, sensitivity of 0.899, and specificity of 0.510. Features representing depression symptoms were the most relevant for the classification of increased suicide risk. Some of our models presented good performance metrics in the classification of increased suicide risk in the investigated sample, which can provide the means to early preventive interventions.

Prediction of suicide attempts in a prospective cohort study with a nationally representative sample of the US population

BACKGROUND

There is still little knowledge of objective suicide risk stratification.

METHODS

This study aims to develop models using machine-learning approaches to predict suicide attempt (1) among survey participants in a nationally representative sample and (2) among participants with lifetime major depressive episodes. We used a cohort called the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC) that was conducted in two waves and included a nationally representative sample of the adult population in the United States. Wave 1 involved 43 093 respondents and wave 2 involved 34 653 completed face-to-face reinterviews with wave 1 participants. Predictor variables included clinical, stressful life events, and sociodemographic variables from wave 1; outcome included suicide attempt between wave 1 and wave 2.

RESULTS

The model built with elastic net regularization distinguished individuals who had attempted suicide from those who had not with an area under the ROC curve (AUC) of 0.89, balanced accuracy 81.86%, specificity 89.22%, and sensitivity 74.51% for the general population. For participants with lifetime major depressive episodes, AUC was 0.89, balanced accuracy 81.64%, specificity 85.86%, and sensitivity 77.42%. The most important predictor variables were a diagnosis of borderline personality disorder, post-traumatic stress disorder, and being of Asian descent for the model in all participants; and previous suicide attempt, borderline personality disorder, and overnight stay in hospital because of depressive symptoms for the model in participants with lifetime major depressive episodes. Random forest and artificial neural networks had similar performance.

CONCLUSIONS

Risk for suicide attempt can be estimated with high accuracy.

Distinguishing between depression in bipolar disorder and unipolar depression using magnetic resonance imaging: a systematic review

OBJECTIVES

Magnetic resonance imaging (MRI) studies comparing bipolar and unipolar depression characterize pathophysiological differences between these conditions. However, it is difficult to interpret the current literature due to differences in MRI modalities, analysis methods, and study designs.

METHODS

We conducted a systematic review of publications using MRI to compare individuals with bipolar and unipolar depression. We grouped studies according to MRI modality and task design. Within the discussion, we critically evaluated and summarized the functional MRI research and then further complemented these findings by reviewing the structural MRI literature.

RESULTS

We identified 88 MRI publications comparing participants with bipolar depression and unipolar depressive disorder. Compared to individuals with unipolar depression, participants with bipolar disorder exhibited heightened function, increased within network connectivity, and reduced grey matter volume in salience and central executive network brain regions. Group differences in default mode network function were less consistent but more closely associated with depressive symptoms in participants with unipolar depression but distractibility in bipolar depression.

CONCLUSIONS

When comparing mood disorder groups, the neuroimaging evidence suggests that individuals with bipolar disorder are more influenced by emotional and sensory processing when responding to their environment. In contrast, depressive symptoms and neurofunctional response to emotional stimuli were more closely associated with reduced central executive function and less adaptive cognitive control of emotionally oriented brain regions in unipolar depression. Researchers now need to replicate and refine network-level trends in these heterogeneous mood disorders and further characterize MRI markers associated with early disease onset, progression, and recovery.

Machine learning applied to healthcare: a conceptual review

The technological inference in procedures applied to healthcare is frequently investigated in order to understand the real contribution to decision-making and clinical improvement. In this context, the theoretical field of machine learning has suitably presented itself. The objective of this research is to identify the main machine learning algorithms used in healthcare through the methodology of a systematic literature review. Considering the time frame of the last twenty years, 173 studies were mined based on established criteria, which allowed the grouping of algorithms into typologies. Supervised Learning, Unsupervised Learning, and Deep Learning were the groups derived from the studies mined, establishing 59 works employed. We expect that this research will stimulate investigations towards machine learning applications in healthcare.

Clinical profiles of subsequent stages in bipolar disorder: Results from the Dutch Bipolar Cohort

INTRODUCTION

The manifestation of bipolar disorder (BD) is hypothesized to be determined by clinical characteristics such as familial loading, childhood abuse, age at onset, illness duration, comorbid psychiatric disorders, addiction, treatment resistance, and premorbid cognitive functioning. Which of these are associated with a more severe course and worse outcome is currently unknown. Our objective is to find a combination of clinical characteristics associated with advancement to subsequent stages in two clinical staging models for BD.

METHODS

Using cross-sectional data from the Dutch Bipolar Cohort, staging was applied to determine the progression of bipolar-I-disorder (BD-I; N = 1396). Model A is primarily defined by recurrence of mood episodes, ranging from prodromal to chronicity. Model B is defined by level of inter-episodic functioning, ranging from prodromal to inability to function autonomously. For both models, ordinal logistic regression was conducted to test which clinical characteristics are associated with subsequent stages.

RESULTS

For model A, familial loading, childhood abuse, earlier onset, longer illness duration, psychiatric comorbidity, and treatment resistance were all predictors for a higher stage in contrast to addiction and cognitive functioning. For model B, childhood abuse, psychiatric comorbidity, cognitive functioning, and treatment resistance were predictors for a more severe stage, whereas age at onset, illness duration, and addiction were not.

DISCUSSION/CONCLUSIONS

Differences in clinical characteristics across stages support the construct validity of both staging models. Characteristics associated with a higher stage largely overlapped across both models. This study is a first step toward determining different clinical profiles, with a corresponding course and outcome.

Identifying posttraumatic stress disorder staging from clinical and sociodemographic features: a proof-of-concept study using a machine learning approach

This proof-of-concept study aimed to investigate the viability of a predictive model to support posttraumatic stress disorder (PTSD) staging. We performed a naturalistic, cross-sectional study at two Brazilian centers: the Psychological Trauma Research and Treatment (NET-Trauma) Program at Universidade Federal of Rio Grande do Sul, and the Program for Research and Care on Violence and PTSD (PROVE), at Universidade Federal of São Paulo. Five supervised machine-learning algorithms were tested: Elastic Net, Gradient Boosting Machine, Random Forest, Support Vector Machine, and C5.0, using clinical (Clinician-Administered PTSD Scale version 5) and sociodemographic features. A hundred and twelve patients were enrolled (61 from NET-Trauma and 51 from PROVE). We found a model with four classes suitable for the PTSD staging, with best performance metrics using the C5.0 algorithm to CAPS-5 15-items plus sociodemographic features, with an accuracy of 65.6% for the train dataset and 52.9% for the test dataset (both significant). The number of symptoms, CAPS-5 total score, global severity score, and presence of current/previous trauma events appear as main features to predict PTSD staging. This is the first study to evaluate staging in PTSD with machine learning algorithms using accessible clinical and sociodemographic features, which may be used in future research.

Bipolar Disorder Related Hospitalizations - a Descriptive Nationwide Study Using a Big Data Approach

Bipolar Disorder (BD) is a mental disorder which frequently requires long hospitalizations and need for acute psychiatric care. The aim of this study was to describe a nationwide perspective of BD related hospitalizations and to use a BigData based approach in mental health research. We performed a retrospective observational study using a nationwide hospitalization database containing all hospitalizations registered in Portuguese public hospitals from 2008-2015. Hospitalizations with a primary diagnosis of BD were selected based on International Classification of Diseases version 9, Clinical Modification (ICD-9-CM) codes of diagnosis 296.xx (excluding 296.2x; 296.3x and 296.9x). From 20,807 hospitalizations belonging to 13,300 patients, around 33.4% occurred in male patients with a median length of stay of 16.0 days and a mean age of 47.9 years. The most common hospitalization diagnosis in BD has the code 296.4x (manic episode) representing 34.3% of all hospitalizations, followed by the code 296.5x (depressed episode) with 21.4%. The mean estimated hospitalization charge was 3,508.5€ per episode, with a total charge of 73M€ in the 8-year period of this study.This is a nationwide study giving a broad perspective of the BD hospitalization panorama at a national level. We found important differences in hospitalization characteristics by sex, age and primary diagnosis.

Predictors of suicide attempt in patients with obsessive-compulsive disorder: an exploratory study with machine learning analysis

BACKGROUND

Patients with obsessive-compulsive disorder (OCD) are at increased risk for suicide attempt (SA) compared to the general population. However, the significant risk factors for SA in this population remains unclear - whether these factors are associated with the disorder itself or related to extrinsic factors, such as comorbidities and sociodemographic variables. This study aimed to identify predictors of SA in OCD patients using a machine learning algorithm.

METHODS

A total of 959 outpatients with OCD were included. An elastic net model was performed to recognize the predictors of SA among OCD patients, using clinical and sociodemographic variables.

RESULTS

The prevalence of SA in our sample was 10.8%. Relevant predictors of SA founded by the elastic net algorithm were the following: previous suicide planning, previous suicide thoughts, lifetime depressive episode, and intermittent explosive disorder. Our elastic net model had a good performance and found an area under the curve of 0.95.

CONCLUSIONS

This is the first study to evaluate risk factors for SA among OCD patients using machine learning algorithms. Our results demonstrate an accurate risk algorithm can be created using clinical and sociodemographic variables. All aspects of suicidal phenomena need to be carefully investigated by clinicians in every evaluation of OCD patients. Particular attention should be given to comorbidity with depressive symptoms.

Machine learning approaches for prediction of bipolar disorder based on biological, clinical and neuropsychological markers: a systematic review and meta-analysis

Applying machine learning (ML) to objective markers may overcome prognosis uncertainty due to the subjective nature of the diagnosis of bipolar disorder (BD). This PRISMA-compliant meta-analysis provides new systematic evidence of the BD classification accuracy reached by different markers and ML algorithms. We focused on neuroimaging, electrophysiological techniques, peripheral biomarkers, genetic data, neuropsychological or clinical measures, and multimodal approaches. PubMed, Embase and Scopus were searched through 3^rd December 2020. Meta-analyses were performed using random-effect models. Overall, 81 studies were included in this systematic review and 65 in the meta-analysis (11,336 participants, 3,903 BD). The overall pooled classification accuracy was 0.77 (95%CI[0.75;0.80]). Despite subgroup analyses for diagnostic comparison group, psychiatric disorders, marker, ML algorithm, and validation procedure were not significant, linear discriminant analysis significantly outperformed support vector machine for peripheral biomarkers (p=0.03). Sample size was inversely related to accuracy. Evidence of publication bias was detected. Ultimately, although ML reached a high accuracy in differentiating BD from other psychiatric disorders, best practices in methodology are needed for the advancement of future studies.

What we learn about bipolar disorder from large-scale neuroimaging: Findings and future directions from the ENIGMA Bipolar Disorder Working Group

MRI-derived brain measures offer a link between genes, the environment and behavior and have been widely studied in bipolar disorder (BD). However, many neuroimaging studies of BD have been underpowered, leading to varied results and uncertainty regarding effects. The Enhancing Neuro Imaging Genetics through Meta-Analysis (ENIGMA) Bipolar Disorder Working Group was formed in 2012 to empower discoveries, generate consensus findings and inform future hypothesis-driven studies of BD. Through this effort, over 150 researchers from 20 countries and 55 institutions pool data and resources to produce the largest neuroimaging studies of BD ever conducted. The ENIGMA Bipolar Disorder Working Group applies standardized processing and analysis techniques to empower large-scale meta- and mega-analyses of multimodal brain MRI and improve the replicability of studies relating brain variation to clinical and genetic data. Initial BD Working Group studies reveal widespread patterns of lower cortical thickness, subcortical volume and disrupted white matter integrity associated with BD. Findings also include mapping brain alterations of common medications like lithium, symptom patterns and clinical risk profiles and have provided further insights into the pathophysiological mechanisms of BD. Here we discuss key findings from the BD working group, its ongoing projects and future directions for large-scale, collaborative studies of mental illness.

Exploring machine learning to predict depressive relapses of bipolar disorder patients

BACKGROUND

Bipolar disorder (BD) is a chronic mood disorder characterized by recurrent episodes of mania or hypomania and depression, expressed by changes in energy levels and behavior. However, most of relapse studies use evidence-based approaches with statistical methods. With the advance of the precision medicine this study aims to use machine learning (ML) approaches as a possible predictor in depressive relapses in BD.

METHOD

Four accepted and well used ML algorithms (Support Vector Machines, Random Forests, Naïve Bayes, and Multilayer Perceptron) were applied to the Systematic Treatment Enhancement Program for Bipolar Disorder (STEP-BD) dataset in a cohort of 800 patients (507 patients presented depressive relapse and 293 did not), who became euthymic during the study and were followed for one year.

RESULTS

The ML algorithms presented reasonable performance in the prediction task, ranging from 61 to 80% in the F-measure. The Random Forest algorithm obtained a higher average of performance (Relapse Group 68%; No Relapse Group 74%). The three most important mood symptoms observed in the relapse visit (Random Forest) were: interest; depression mood and energy.

LIMITATIONS

Social and psychological parameters such as marital status, social support system, personality traits, might be an important predictor in depressive relapses, although we did not compute this data in our study.

CONCLUSIONS

Our findings indicate that applying precision medicine models by means of machine learning in BD studies could be feasible as a sensible approach to better support medical decision-making in the BD treatment and prevention of future relapses.

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.

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.

Artificial Intelligence for Mental Health Care: Clinical Applications, Barriers, Facilitators, and Artificial Wisdom

Artificial intelligence (AI) is increasingly employed in health care fields such as oncology, radiology, and dermatology. However, the use of AI in mental health care and neurobiological research has been modest. Given the high morbidity and mortality in people with psychiatric disorders, coupled with a worsening shortage of mental health care providers, there is an urgent need for AI to help identify high-risk individuals and provide interventions to prevent and treat mental illnesses. While published research on AI in neuropsychiatry is rather limited, there is a growing number of successful examples of AI's use with electronic health records, brain imaging, sensor-based monitoring systems, and social media platforms to predict, classify, or subgroup mental illnesses as well as problems such as suicidality. This article is the product of a study group held at the American College of Neuropsychopharmacology conference in 2019. It provides an overview of AI approaches in mental health care, seeking to help with clinical diagnosis, prognosis, and treatment, as well as clinical and technological challenges, focusing on multiple illustrative publications. Although AI could help redefine mental illnesses more objectively, identify them at a prodromal stage, personalize treatments, and empower patients in their own care, it must address issues of bias, privacy, transparency, and other ethical concerns. These aspirations reflect human wisdom, which is more strongly associated than intelligence with individual and societal well-being. Thus, the future AI or artificial wisdom could provide technology that enables more compassionate and ethically sound care to diverse groups of people.

Automatic Diagnosis of Bipolar Disorder Using Optical Coherence Tomography Data and Artificial Intelligence

Background: The aim of this study is to explore an objective approach that aids the diagnosis of bipolar disorder (BD), based on optical coherence tomography (OCT) data which are analyzed using artificial intelligence. Methods: Structural analyses of nine layers of the retina were analyzed in 17 type I BD patients and 42 controls, according to the areas defined by the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The most discriminating variables made up the feature vector of several automatic classifiers: Gaussian Naive Bayes, K-nearest neighbors and support vector machines. Results: BD patients presented retinal thinning affecting most layers, compared to controls. The retinal thickness of the parafoveolar area showed a high capacity to discriminate BD subjects from healthy individuals, specifically for the ganglion cell (area under the curve (AUC) = 0.82) and internal plexiform (AUC = 0.83) layers. The best classifier showed an accuracy of 0.95 for classifying BD versus controls, using as variables of the feature vector the IPL (inner nasal region) and the INL (outer nasal and inner inferior regions) thickness. Conclusions: Our patients with BD present structural alterations in the retina, and artificial intelligence seem to be a useful tool in BD diagnosis, but larger studies are needed to confirm our findings.

Reflection on modern methods: building causal evidence within high-dimensional molecular epidemiological studies of moderate size

This commentary provides a practical perspective on epidemiological analysis within a single high-dimensional study of moderate size to consider a causal question. In this setting, non-causal confounding is important. This occurs when a factor is a determinant of outcome and the underlying association between exposure and the factor is non-causal. That is, the association arises due to chance, confounding or other bias rather than reflecting that exposure and the factor are causally related. In particular, the influence of technical processing factors must be accounted for by pre-processing measures to remove artefact or to control for these factors such as batch run. Work steps include the evaluation of alternative non-causal explanations for observed exposure-disease associations and strategies to obtain the highest level of causal inference possible within the study. A systematic approach is required to work through a question set and obtain insights on not only the exposure-disease association but also the multifactorial causal structure of the underlying data where possible. The appropriate inclusion of molecular findings will enhance the quest to better understand multifactorial disease causation in modern observational epidemiological studies.

Treatment-resistant bipolar depression: concepts and challenges for novel interventions

Treatment-resistant bipolar depression (TRBD) has been reported in about one-quarter of patients with bipolar disorders, and few interventions have shown clear and established effectiveness. We conducted a narrative review of the published medical literature to identify papers discussing treatment-resistant depression concepts and novel interventions for bipolar depression that focus on TRBD. We searched for potentially relevant English-language articles published in the last decade. Selected articles (based on the title and abstract) were retrieved for a more detailed evaluation. A number of promising new interventions, both pharmacological and non-pharmacological, are being investigated for TRBD treatment, including ketamine, lurasidone, D-cycloserine, pioglitazone, N-acetylcysteine, angiotensin-converting enzyme inhibitors, angiotensin II type 1 receptor blockers, cyclooxygenase 2 inhibitors, magnetic seizure therapy, intermittent theta-burst stimulation, deep transcranial magnetic stimulation, vagus nerve stimulation therapy, and deep brain stimulation. Although there is no consensus about the concept of TRBD, better clarification of the neurobiology associated with treatment non-response could help identify novel strategies. More research is warranted, mainly focusing on personalizing current treatments to optimize response and remission rates.

Pharmacological treatment profiles in the FACE-BD cohort: An unsupervised machine learning study, applied to a nationwide bipolar cohort✰

BACKGROUND

Despite thorough and validated clinical guidelines based on bipolar disorders subtypes, large pharmacological treatment heterogeneity remains in these patients. There is limited knowledge about the different treatment combinations used and their influence on patient outcomes. We attempted to determine profiles of patients based on their treatments and to understand the clinical characteristics associated with these treatment profiles.

METHODS

This multicentre longitudinal study was performed on a French nationwide bipolar cohort database. We performed hierarchical agglomerative clustering to search for clusters of individuals based on their treatments during the first year following inclusion. We then compared patient clinical characteristics according to these clusters.

RESULTS

Four groups were identified among the 1795 included patients: group 1 ("heterogeneous" n = 1099), group 2 ("lithium" n = 265), group 3 ("valproate" n = 268), and group 4 ("lamotrigine" n = 163). Proportion of bipolar 1 disorder, in groups 1 to 4 were: 48.2%, 57.0%, 48.9% and 32.5%. Groups 1 and 4 had greater functional impact at baseline and a less favorable clinical and functioning evolution at one-year follow-up, especially on GAF and FAST scales.

LIMITATIONS

The one-year period used for the analysis of mood stabilizing treatments remains short in the evolution of bipolar disorder.

CONCLUSIONS

Treatment profiles are associated with functional evolution of patients and were not clearly determined by bipolar subtypes. These profiles seem to group together common patient phenotypes. These findings do not seem to be influenced by the duration of disease prior to inclusion and neither by the number of treatments used during the follow-up period.

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.

Socio-demographic and clinical predictors of outcome to long-term treatment with lithium in bipolar disorders: a systematic review of the contemporary literature and recommendations from the ISBD/IGSLI Task Force on treatment with lithium

Objective

To identify possible socio-demographic and clinical factors associated with Good Outcome (GO) as compared with Poor Outcome (PO) in adult patients diagnosed with Bipolar Disorder (BD) who received long-term treatment with lithium.

Methods

A comprehensive search of major electronic databases was performed to identify relevant studies that included adults patients (18 years or older) with a diagnosis of BD and reported sociodemographic and/or clinical variables associated with treatment response and/or with illness outcome during long-term treatment to lithium (> = 6 months). The quality of the studies was scored using the Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies from the National Institute of Health.

Results

Following review, 34 publications (from 31 independent datasets) were eligible for inclusion in this review. Most of them (n = 25) used a retrospective design. Only 11 studies were graded as good or borderline good quality. Forty-three potential predictors of outcome to lithium were identified. Four factors were associated with PO to lithium: alcohol use disorder; personality disorders; higher lifetime number of hospital admissions and rapid cycling pattern. Two factors were associated with GO in patients treated with lithium: good social support and episodic evolution of BD. However, when the synthesis of findings was limited to the highest (good or borderline good) quality studies (11 studies), only higher lifetime number of hospitalization admissions remained associated with PO to lithium and no associations remained for GO to lithium.

Conclusion

Despite decades of research on lithium and its clinical use, besides lifetime number of hospital admissions, no factor being consistently associated with GO or PO to lithium was identified. Hence, there remains a substantial gap in our understanding of predictors of outcome of lithium treatment indicating there is a need of high quality research on large representative samples.

Early identification of bipolar disorder among young adults - a 22-year community birth cohort

OBJECTIVE

We set forth to build a prediction model of individuals who would develop bipolar disorder (BD) using machine learning techniques in a large birth cohort.

METHODS

A total of 3748 subjects were studied at birth, 11, 15, 18, and 22 years of age in a community birth cohort. We used the elastic net algorithm with 10-fold cross-validation to predict which individuals would develop BD at endpoint (22 years) at each follow-up visit before diagnosis (from birth up to 18 years). Afterward, we used the best model to calculate the subgroups of subjects at higher and lower risk of developing BD and analyzed the clinical differences among them.

RESULTS

A total of 107 (2.8%) individuals within the cohort presented with BD type I, 26 (0.6%) with BD type II, and 87 (2.3%) with BD not otherwise specified. Frequency of female individuals was 58.82% (n = 150) in the BD sample and 53.02% (n = 1868) among the unaffected population. The model with variables assessed at the 18-year follow-up visit achieved the best performance: AUC 0.82 (CI 0.75-0.88), balanced accuracy 0.75, sensitivity 0.72, and specificity 0.77. The most important variables to detect BD at the 18-year follow-up visit were suicide risk, generalized anxiety disorder, parental physical abuse, and financial problems. Additionally, the high-risk subgroup of BD showed a high frequency of drug use and depressive symptoms.

CONCLUSIONS

We developed a risk calculator for BD incorporating both demographic and clinical variables from a 22-year birth cohort. Our findings support previous studies in high-risk samples showing the significance of suicide risk and generalized anxiety disorder prior to the onset of BD, and highlight the role of social factors and adverse life events.

Neurobiology of bipolar disorders: a review of genetic components, signaling pathways, biochemical changes, and neuroimaging findings

Bipolar disorder (BD) is a chronic mental illness characterized by changes in mood that alternate between mania and hypomania or between depression and mixed states, often associated with functional impairment. Although effective pharmacological and non-pharmacological treatments are available, several patients with BD remain symptomatic. The advance in the understanding of the neurobiology underlying BD could help in the identification of new therapeutic targets as well as biomarkers for early detection, prognosis, and response to treatment in BD. In this review, we discuss genetic, epigenetic, molecular, physiological and neuroimaging findings associated with the neurobiology of BD. Despite the advances in the pathophysiological knowledge of BD, the diagnosis and management of the disease are still essentially clinical. Given the complexity of the brain and the close relationship between environmental exposure and brain function, initiatives that incorporate genetic, epigenetic, molecular, physiological, clinical, environmental data, and brain imaging are necessary to produce information that can be translated into prevention and better outcomes for patients with BD.

Neuroanatomic and Functional Neuroimaging Findings

The search for brain morphology findings that could explain behavioral disorders has gone through a long path in the history of psychiatry. With the advance of brain imaging technology, studies have been able to identify brain morphology and neural circuits associated with the pathophysiology of mental illnesses, such as bipolar disorders (BD). Promising results have also shown the potential of neuroimaging findings in the identification of outcome predictors and response to treatment among patients with BD. In this chapter, we present brain imaging structural and functional findings associated with BD, as well as their hypothesized relationship with the pathophysiological aspects of that condition and their potential clinical applications.

The Discovery of Clinically Applicable Biomarkers for Bipolar Disorder: A Review of Candidate and Proteomic Approaches

Bipolar disorder (BD) is a severe psychiatric condition which affects innumerable people across the globe. The etiopathogenesis of BD is multi-faceted with genetic, environmental and psychosocial factors playing a role. Hitherto, the diagnosis and management of BD are purely on empirical grounds as we lack confirmed biomarkers for this condition. In this regard, hypothesis-driven investigations have been unable to identify clinically applicable biomarkers, steering the field towards newer technologies. Innovative, state-of-the-art techniques like multiplex immunoassays and mass spectrometry can potentially investigate the entire proteome. By detecting up or down regulated proteins, novel biomarkers are identified and new postulates about the etiopathogenesis of BD are specified. Hence, biological pathways are uncovered which are involved in the initiation and advancement of the disease and new therapeutic targets are identified. In this manuscript, the extant literature is thoroughly reviewed and the latest findings on candidate BD biomarkers are provided, followed by an overview of the proteomic approaches. It was found that due to the heterogeneous nature of BD no single biomarker is feasible, instead a panel of tests is more likely to be useful. With the application of latest technologies, it is expected that validated biomarkers will be discovered which will be useful as diagnostic tools and help in the delivery of individually tailored therapies to the patients.

Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions

OBJECTIVES

The existence of anatomofunctional brain abnormalities in bipolar disorder (BD) is now well established by magnetic resonance imaging (MRI) studies. To create diagnostic and prognostic tools, as well as identifying biologically valid subtypes of BD, research has recently turned towards the use of machine learning (ML) techniques. We assessed both supervised ML and unsupervised ML studies in BD to evaluate their robustness, reproducibility and the potential need for improvement.

METHOD

We systematically searched for studies using ML algorithms based on MRI data of patients with BD until February 2019.

RESULT

We identified 47 studies, 45 using supervised ML techniques and 2 including unsupervised ML analyses. Among supervised studies, 43 focused on diagnostic classification. The reported accuracies for classification of BD ranged between (a) 57% and 100%, for BD vs healthy controls; (b) 49.5% and 93.1% for BD vs patients with major depressive disorder; and (c) 50% and 96.2% for BD vs patients with schizophrenia. Reported accuracies for discriminating subjects genetically at risk for BD (either from control or from patients with BD) ranged between 64.3% and 88.93%.

CONCLUSIONS

Although there are strong methodological limitations in previous studies and an important need for replication in large multicentric samples, the conclusions of our review bring hope of future computer-aided diagnosis of BD and pave the way for other applications, such as treatment response prediction. To reinforce the reliability of future results we provide methodological suggestions for good practice in conducting and reporting MRI-based ML studies in BD.

Differential biomarker signatures in unipolar and bipolar depression: A machine learning approach

OBJECTIVE

This study used machine learning techniques combined with peripheral biomarker measurements to build signatures to help differentiating (1) patients with bipolar depression from patients with unipolar depression, and (2) patients with bipolar depression or unipolar depression from healthy controls.

METHODS

We assessed serum levels of interleukin-2, interleukin-4, interleukin-6, interleukin-10, tumor necrosis factor-α, interferon-γ, interleukin-17A, brain-derived neurotrophic factor, lipid peroxidation and oxidative protein damage in 54 outpatients with bipolar depression, 54 outpatients with unipolar depression and 54 healthy controls, matched by sex and age. Depressive symptoms were assessed using the Hamilton Depression Rating Scale. Variable selection was performed with recursive feature elimination with a linear support vector machine kernel, and the leave-one-out cross-validation method was used to test and validate our model.

RESULTS

Bipolar vs unipolar depression classification achieved an area under the receiver operating characteristics (ROC) curve (AUC) of 0.69, with 0.62 sensitivity and 0.66 specificity using three selected biomarkers (interleukin-4, thiobarbituric acid reactive substances and interleukin-10). For the comparison of bipolar depression vs healthy controls, the model retained five variables (interleukin-6, interleukin-4, thiobarbituric acid reactive substances, carbonyl and interleukin-17A), with an AUC of 0.70, 0.62 sensitivity and 0.7 specificity. Finally, unipolar depression vs healthy controls comparison retained seven variables (interleukin-6, Carbonyl, brain-derived neurotrophic factor, interleukin-10, interleukin-17A, interleukin-4 and tumor necrosis factor-α), with an AUC of 0.74, a sensitivity of 0.68 and 0.70 specificity.

CONCLUSION

Our findings show the potential of machine learning models to aid in clinical practice, leading to more objective assessment. Future studies will examine the possibility of combining peripheral blood biomarker data with other biological data to develop more accurate signatures.

Precision non-implantable neuromodulation therapies: a perspective for the depressed brain

Current first-line treatments for major depressive disorder (MDD) include pharmacotherapy and cognitive-behavioral therapy. However, one-third of depressed patients do not achieve remission after multiple medication trials, and psychotherapy can be costly and time-consuming. Although non-implantable neuromodulation (NIN) techniques such as transcranial magnetic stimulation, transcranial direct current stimulation, electroconvulsive therapy, and magnetic seizure therapy are gaining momentum for treating MDD, the efficacy of non-convulsive techniques is still modest, whereas use of convulsive modalities is limited by their cognitive side effects. In this context, we propose that NIN techniques could benefit from a precision-oriented approach. In this review, we discuss the challenges and opportunities in implementing such a framework, focusing on enhancing NIN effects via a combination of individualized cognitive interventions, using closed-loop approaches, identifying multimodal biomarkers, using computer electric field modeling to guide targeting and quantify dosage, and using machine learning algorithms to integrate data collected at multiple biological levels and identify clinical responders. Though promising, this framework is currently limited, as previous studies have employed small samples and did not sufficiently explore pathophysiological mechanisms associated with NIN response and side effects. Moreover, cost-effectiveness analyses have not been performed. Nevertheless, further advancements in clinical trials of NIN could shift the field toward a more “precision-oriented” practice.

The use of machine learning techniques in trauma-related disorders: a systematic review

Establishing the diagnosis of trauma-related disorders such as Acute Stress Disorder (ASD) and Posttraumatic Stress Disorder (PTSD) have always been a challenge in clinical practice and in academic research, due to clinical and biological heterogeneity. Machine learning (ML) techniques can be applied to improve classification of disorders, to predict outcomes or to determine person-specific treatment selection. We aim to review the existing literature on the use of machine learning techniques in the assessment of subjects with ASD or PTSD. We systematically searched PubMed, Embase and Web of Science for articles published in any language up to May 2019. We found 806 abstracts and included 49 studies in our review. Most of the included studies used multiple levels of biological data to predict risk factors or to identify early symptoms related to PTSD. Other studies used ML classification techniques to distinguish individuals with ASD or PTSD from other psychiatric disorder or from trauma-exposed and healthy controls. We also found studies that attempted to define outcome profiles using clustering techniques and studies that assessed the relationship among symptoms using network analysis. Finally, we proposed a quality assessment in this review, evaluating methodological and technical features on machine learning studies. We concluded that etiologic and clinical heterogeneity of ASD/PTSD patients is suitable to machine learning techniques and a major challenge for the future is to use it in clinical practice for the benefit of patients in an individual level.