Predictors of diagnostic transition from major depressive disorder to bipolar disorder: a retrospective observational network study

Who transitions to bipolar disorder? A comparison of major depressive disorder, anxiety, and ADHD

BACKGROUND

Diagnostic delays in Bipolar Disorder (BD) are common and may contribute to worse outcomes. While most studies focus on depression as a primary precursor, both anxiety and attention deficit disorders are also frequent initial diagnoses. In the current study, we utilized a large, diverse electronic health record (EHR) dataset to quantify the rates and correlates of conversion to BD from these major precursor diagnoses.

METHODS

Our study analyzed a comprehensive ten-year EHR dataset from Johns Hopkins Medicine, a diverse urban medical center, to assess and compare the rates and correlates of conversion to BD from Major Depressive Disorder (MDD), anxiety disorders, and ADHD. Risk factors for transition were assessed as time-varying variables in proportional hazards models.

RESULTS

Of the 21,341 patients initially included, 1232 later transitioned to a diagnosis of BD. Adjusted-one-year conversion rates for patients with MDD, anxiety disorders, and ADHD were 4.2 %, 3.4 %, and 4.0 %, respectively, with ten-year rates at 11.4 %, 9.4 %, and 10.9 %, respectively. Age (19-29 years), treatment setting (emergency and inpatient), and psychotropic medications were associated with conversion to BD across all precursor diagnoses. Severe and psychotic forms of MDD were among the strongest risk factors for transitioning to BD. Although risk factors for convertion were similar, transition rates were lower in children, particularly in indivudals with ADHD, who showed a higher rate of BD conversion in adults.

CONCLUSIONS

The highest risk of transitioning to BD was observed in patients initially diagnosed with MDD, though significant risk was also noted in those with initial diagnoses of anxiety disorders and adult ADHD.

Shared and Distinct White Matter Alterations in Major Depression and Bipolar Disorder: A Systematic Review and Meta-Analysis

BACKGROUND

Identifying white matter (WM) microstructural similarities and differences between major depressive disorder (MDD) and bipolar disorder (BD) is an important way to understand the potential neuropathological mechanism in emotional disorders. Numerous diffusion tensor imaging (DTI) studies over recent decades have confirmed the presence of WM anomalies in these two affective disorders, but the results were inconsistent. This study aimed to determine the statistical consistency of DTI findings for BD and MDD by using the coordinate-based meta-analysis (CBMA) approach.

METHODS

We performed a systematic search of tract-based spatial statistics (TBSS) studies comparing MDD or BD with healthy controls (HC) as of June 30, 2024. The seed-based d-mapping (SDM) was applied to investigate fractional anisotropy (FA) changes. Meta-regression was then used to analyze the potential correlations between demographics and neuroimaging alterations.

RESULTS

Regional FA reductions in the body of the corpus callosum (CC) were identified in both of these two diseases. Besides, MDD patients also exhibited decreased FA in the genu and splenium of the CC, as well as the left anterior thalamic projections (ATP), while BD patients showed FA reduction in the left median network, and cingulum in addition to the CC.

CONCLUSIONS

The results highlighted that altered integrity in the body of CC served as the shared basis of MDD and BD, and distinct microstructural WM abnormalities also existed, which might induce the various clinical manifestations of these two affective disorders. The study was registered on PROSPERO (http://www.crd.york.ac.uk/PROSPERO), registration number: CRD42022301929.

Electroencephalography-based endogenous phenotype of diagnostic transition from major depressive disorder to bipolar disorder

The neuropathology of mood disorders, including the diagnostic transition from major depressive disorder (MDD) to bipolar disorder (BD), is poorly understood. This study investigated resting-state electroencephalography (EEG) activity in patients with MDD and those whose diagnosis changed from MDD to BD. Among sixty-eight enrolled patients with MDD, the diagnosis of 17 patients converted to BD during the study period. We applied machine learning techniques to differentiate the two groups using sensor- and source-level EEG features. At the sensor level, patients with BD showed higher theta band power at the AF3 channel and low-alpha band power at the FC5 channel compared to patients with MDD. At the source level, patients with BD showed higher theta band activity in the right anterior cingulate and low-alpha band activity in the left parahippocampal gyrus. These four EEG features were selected for discriminating between BD and MDD with the best classification performance showing an accuracy of 80.88%, a sensitivity of 76.47%, and a specificity of 82.35%. Our findings revealed distinct theta and low-alpha band activities in patients with BD and MDD. These differences could potentially serve as candidate neuromarkers for the diagnosis and diagnostic transition between the two distinct mood disorders.

Patient-derived induced pluripotent stem cells: Tools to advance the understanding and drug discovery in Major Depressive Disorder

Major Depressive Disorder (MDD) is a pleomorphic disease with substantial patterns of symptoms and severity with mensurable deficits in several associated domains. The broad spectrum of phenotypes observed in patients diagnosed with depressive disorders is the reflection of a very complex disease where clusters of biological and external factors (e.g., response/processing of life events, intrapsychic factors) converge and mediate pathogenesis, clinical presentation/phenotypes and trajectory. Patient-derived induced pluripotent stem cells (iPSCs) enable their differentiation into specialised cell types in the central nervous system to explore the pathophysiological substrates of MDD. These models may complement animal models to advance drug discovery and identify therapeutic approaches, such as cell therapy, drug repurposing, and elucidation of drug metabolism, toxicity, and mechanisms of action at the molecular/cellular level, to pave the way for precision psychiatry. Despite the remarkable scientific and clinical progress made over the last few decades, the disease is still poorly understood, the incidence and prevalence continue to increase, and more research is needed to meet clinical demands. This review aims to summarise and provide a critical overview of the research conducted thus far using patient-derived iPSCs for the modelling of psychiatric disorders, with a particular emphasis on MDD.

How to Solve Clinical Challenges in Mood Disorders; Machine Learning Approaches Using Electrophysiological Markers

Differentiating between the diagnoses of mood disorders and other psychiatric disorders, and predicting treatment response in depression has long been a concern for clinicians. Machine learning (ML) is one part of artificial intelligence that focuses on instructing computers to mimic the cognitive abilities of the human brain through training. This study will review the research on the use of ML techniques to differentiate diagnoses and predict treatment responses in mood disorders based on electroencephalography (EEG) data. There have been several attempts to differentiate between the diagnoses of bipolar disorder and major depressive disorder , mood disorders, and other psychiatric disorders using ML techniques found on EEG markers. Previous studies have shown that accuracy varies depending on which EEG markers are used, the sample size, and the ML technique. Also, precise and improved ML approaches can be developed by adapting the various feature selection and validation methods that reflect each disease's characteristics. Although ML faces some limitations and challenges in solving for consistent and improved accuracy in the diagnosis and treatment of mood disorders, it has a great potential to understand mood disorders better and provide valuable tools to personalize both identification and treatment.

Real-world case series of maintenance theta burst stimulation therapy following response to acute theta burst stimulation therapy for difficult-to-treat depression

OBJECTIVE

Treatment and management for difficult-to-treat depression are challenging, especially in a subset of patients who are at high risk for relapse and recurrence. The conditions that represent this subset are recurrent depressive disorder (RDD) and bipolar disorder (BD). In this context, we aimed to examine the effectiveness of maintenance transcranial magnetic stimulation (TMS) on a real-world clinical basis by retrospectively extracting data from the TMS registry data in Tokyo, Japan.

METHODS

Data on patients diagnosed with treatment-resistant RDD and BD who received maintenance intermittent theta burst stimulation (iTBS) weekly after successful treatment with acute iTBS between March 2020 and October 2023 were extracted from the registry.

RESULTS

All patients (21 cases: 10 cases with RDD and 11 cases with BD) could sustain response, and 19 of them further maintained remission. In this study, maintenance iTBS did not exacerbate depressive symptoms in any of the cases, but may rather have the effect of stabilizing the mental condition and preventing recurrence.

CONCLUSIONS

This case series is of great clinical significance because it is the first study to report on the effectiveness of maintenance iTBS for RDD and BD, with a follow-up of more than 2 years. Further validation with a randomized controlled trial design with a larger sample size is warranted.

Antecedents of major depressive, bipolar, and psychotic disorders: A systematic review and meta-analysis of prospective studies

Major depressive, bipolar, or psychotic disorders are preceded by earlier manifestations in behaviours and experiences. We present a synthesis of evidence on associations between person-level antecedents (behaviour, performance, psychopathology) in childhood, adolescence, or early adulthood and later onsets of major depressive disorder, bipolar disorder, or psychotic disorder based on prospective studies published up to September 16, 2022. We screened 11,342 records, identified 460 eligible publications, and extracted 570 risk ratios quantifying the relationships between 52 antecedents and onsets in 198 unique samples with prospective follow-up of 122,766 individuals from a mean age of 12.4 to a mean age of 24.8 for 1522,426 person years of follow-up. We completed meta-analyses of 12 antecedents with adequate data. Psychotic symptoms, depressive symptoms, anxiety, disruptive behaviors, affective lability, and sleep problems were transdiagnostic antecedents associated with onsets of depressive, bipolar, and psychotic disorders. Attention-deficit/hyperactivity and hypomanic symptoms specifically predicted bipolar disorder. While transdiagnostic and diagnosis-specific antecedents inform targeted prevention and help understand pathogenic mechanisms, extensive gaps in evidence indicate potential for improving early risk identification.

Towards global model generalizability: independent cross-site feature evaluation for patient-level risk prediction models using the OHDSI network

BACKGROUND

Predictive models show promise in healthcare, but their successful deployment is challenging due to limited generalizability. Current external validation often focuses on model performance with restricted feature use from the original training data, lacking insights into their suitability at external sites. Our study introduces an innovative methodology for evaluating features during both the development phase and the validation, focusing on creating and validating predictive models for post-surgery patient outcomes with improved generalizability.

METHODS

Electronic health records (EHRs) from 4 countries (United States, United Kingdom, Finland, and Korea) were mapped to the OMOP Common Data Model (CDM), 2008-2019. Machine learning (ML) models were developed to predict post-surgery prolonged opioid use (POU) risks using data collected 6 months before surgery. Both local and cross-site feature selection methods were applied in the development and external validation datasets. Models were developed using Observational Health Data Sciences and Informatics (OHDSI) tools and validated on separate patient cohorts.

RESULTS

Model development included 41 929 patients, 14.6% with POU. The external validation included 31 932 (UK), 23 100 (US), 7295 (Korea), and 3934 (Finland) patients with POU of 44.2%, 22.0%, 15.8%, and 21.8%, respectively. The top-performing model, Lasso logistic regression, achieved an area under the receiver operating characteristic curve (AUROC) of 0.75 during local validation and 0.69 (SD = 0.02) (averaged) in external validation. Models trained with cross-site feature selection significantly outperformed those using only features from the development site through external validation (P < .05).

CONCLUSIONS

Using EHRs across four countries mapped to the OMOP CDM, we developed generalizable predictive models for POU. Our approach demonstrates the significant impact of cross-site feature selection in improving model performance, underscoring the importance of incorporating diverse feature sets from various clinical settings to enhance the generalizability and utility of predictive healthcare models.

Appraising the causal association among depression, anxiety and intracranial aneurysms: Evidence from genetic studies

BACKGROUND

The risk of intracranial aneurysms (IAs) is increased in individuals with depression and anxiety. This indicates that depression and anxiety may contribute to the development of physical disorders. Herein, to investigate the association between genetic variants related to depression and anxiety and the risk of IA, two-sample Mendelian randomization was performed.

METHODS

The genome-wide association study (GWAS) comprised genome-wide genotype data of 2248 clinically well-characterized patients with anxiety and 7992 ethnically matched controls from four European countries. Sex-specific summary-level outcome data were obtained from the GWAS of IA, including 23 cohorts with a total of 10,754 cases and 306,882 controls of European and East Asian ancestry. To improve validity, five varying Mendelian randomization techniques were used in the analysis, namely Mendelian randomization-Egger, weighted median, inverse variance weighted, simple mode, and weighted mode.

RESULTS

The inverse variance weighted results indicated the causal effect of depression on IA (P = 0.03, OR = 1.32 [95 % CI, 1.03-1.70]) and unruptured IA (UIA) (P = 0.02, OR = 1.68 [95 % CI, 1.08-2.61]). However, the causal relationship between depression and subarachnoid hemorrhage (SAH) was not found (P = 0.16). We identified 43 anxiety-associated single-nucleotide polymorphisms as genetic instruments and found no causal relationship between anxiety and IA, UIA, and SAH.

LIMITATIONS

Potential pleiotropy, possible weak instruments, and low statistical power limited our findings.

CONCLUSION

Our MR study suggested a possible causal effect of depression on the increased risk of UIAs. Future research is required to investigate whether rational intervention in depression treatment can help to decrease the societal burden of IAs.

Comparative Analysis of Personality Traits in Major Depressive Disorder and Bipolar Disorder: Impact, Differences, and Associations with Symptoms

Purpose

This cross-sectional study aimed to compare the personality traits of patients with major depressive disorder (MDD) and bipolar disorder (BD) with those of healthy individuals. The goal was to gain insight into the potential impact of personality traits on the development and manifestation of mood disorders.

Methods

One hundred seventy-eight patients with mood disorders were analyzed as either MDD or BD, with each group containing euthymic and depressive members: e-MDD, d-MDD, e-BD, and d-BD. Mood status was assessed using the Young Mania Rating Scale (YMRS), and the 17-item Hamilton Depression Rating Scale (HAMD-17). Ninety-five healthy individuals served as controls. Personality traits were assessed with the Eysenck Personality Questionnaire.

Results

The scores for neuroticism in the patient groups were comparable, but each group had higher scores compared to the control group (P < 0.001). Each patient group exhibited significantly lower scores for extraversion compared to the control group, with e-MDD, d-MDD, and d-BD showing particularly notable differences (P < 0.001); these groups scored significantly lower than the e-BD (P = 0.041, 0.009, 0.038). In patients with BD, there was an inverted association between extraversion score and HAMD total score (P = 0.010, r = -0.27), and a positive association with the YMRS total score (P = 0.022, r = 0.24). In the MDD group, there was a positive association between the neuroticism score and HAMD total score (P = 0.021, r = 0.25).

Conclusion

Patients with mood disorders are characterized by lower extraversion and higher neuroticism. Level of neuroticism associated with depression severity in MDD. Patients with BD may be more extraverted, but their extraversion can be affected by depressive episodes. Extraversion may be a feature of BD, and may differentiate BD from MDD. Personality traits are related to disease diathesis and state, and shaped by symptom manifestations.

Predicting diagnostic conversion from major depressive disorder to bipolar disorder: an EHR based study from Colombia

Bipolar Disorder (BD) is a severe and chronic disorder characterized by recurrent episodes of depression, mania, and/or hypomania. Most BD patients initially present with depressive symptoms, resulting in a delayed diagnosis of BD and poor clinical outcomes. This study leverages electronic health record (EHR) data from the Clínica San Juan de Dios Manizales in Colombia to identify features predictive of the transition from Major Depressive Disorder (MDD) to BD. Analyzing EHR data from 13,607 patients diagnosed with MDD over 15 years, we identified 1,610 cases of conversion to BD. Using a multivariate Cox regression model, we identified severity of the initial MDD episode, the presence of psychosis and hospitalization at first episode, family history of mood or psychotic disorders, female gender to be predictive of the conversion to BD. Additionally, we observed associations with medication classes (prescriptions of mood stabilizers, antipsychotics, and antidepressants) and clinical features (delusions, suicide attempt, suicidal ideation, use of marijuana and alcohol use/abuse) derived from natural language processing (NLP) of clinical notes. Together, these risk factors predicted BD conversion within five years of the initial MDD diagnosis, with a recall of 72% and a precision of 38%. Our study confirms many previously identified risk factors identified through registry-based studies (such as female gender and psychotic depression at the index MDD episode), and identifies novel ones (specifically, suicidal ideation and suicide attempt extracted from clinical notes). These results simultaneously demonstrate the validity of using EHR data for predicting BD conversion as well as underscore its potential for the identification of novel risk factors and improving early diagnosis.

Exploring the Relationship between Mood Disorders and Coexisting Health Conditions: The Focus on Nutraceuticals

Major depressive disorder and bipolar disorder are the leading causes of global disability. Approximately 50% of patients fail to attain remission, prompting a pronounced focus on the significance of dietary patterns and specific nutrients within the pathophysiology of mood disorders. The connection between chronic diseases and mood disorders follows a bidirectional pattern: physical ailments are interrelated with affective disorders, and, concurrently, mood symptoms often precede chronic diseases and have the potential to worsen their prognosis. Nutraceuticals affect factors that could potentially impact the onset of mood disorders: monoamines and brain-derived neurotrophic factor (BDNF) concentrations, neuroinflammation, oxidative stress, and sleep quality. Furthermore, mood disorders rarely manifest in isolation. Typically, such patients concurrently experience other mental disorders or somatic comorbidities: obesity, hypertension, diabetes, polycystic ovary syndrome (PCOS), etc., where providing nutritional support is also pertinent. To optimize the therapeutic approach for individuals with mood disorders, incorporating nutritional support may not solely ameliorate symptoms stemming directly from the mental condition, but also indirectly through interventions targeting comorbidities.

Privacy-Preserving Federated Model Predicting Bipolar Transition in Patients With Depression: Prediction Model Development Study

BACKGROUND

Mood disorder has emerged as a serious concern for public health; in particular, bipolar disorder has a less favorable prognosis than depression. Although prompt recognition of depression conversion to bipolar disorder is needed, early prediction is challenging due to overlapping symptoms. Recently, there have been attempts to develop a prediction model by using federated learning. Federated learning in medical fields is a method for training multi-institutional machine learning models without patient-level data sharing.

OBJECTIVE

This study aims to develop and validate a federated, differentially private multi-institutional bipolar transition prediction model.

METHODS

This retrospective study enrolled patients diagnosed with the first depressive episode at 5 tertiary hospitals in South Korea. We developed models for predicting bipolar transition by using data from 17,631 patients in 4 institutions. Further, we used data from 4541 patients for external validation from 1 institution. We created standardized pipelines to extract large-scale clinical features from the 4 institutions without any code modification. Moreover, we performed feature selection in a federated environment for computational efficiency and applied differential privacy to gradient updates. Finally, we compared the federated and the 4 local models developed with each hospital's data on internal and external validation data sets.

RESULTS

In the internal data set, 279 out of 17,631 patients showed bipolar disorder transition. In the external data set, 39 out of 4541 patients showed bipolar disorder transition. The average performance of the federated model in the internal test (area under the curve [AUC] 0.726) and external validation (AUC 0.719) data sets was higher than that of the other locally developed models (AUC 0.642-0.707 and AUC 0.642-0.699, respectively). In the federated model, classifications were driven by several predictors such as the Charlson index (low scores were associated with bipolar transition, which may be due to younger age), severe depression, anxiolytics, young age, and visiting months (the bipolar transition was associated with seasonality, especially during the spring and summer months).

CONCLUSIONS

We developed and validated a differentially private federated model by using distributed multi-institutional psychiatric data with standardized pipelines in a real-world environment. The federated model performed better than models using local data only.

Establishment of an International Evidence Sharing Network Through Common Data Model for Cardiovascular Research

A retrospective observational study is one of the most widely used research methods in medicine. However, evidence postulated from a single data source likely contains biases such as selection bias, information bias, and confounding bias. Acquiring enough data from multiple institutions is one of the most effective methods to overcome the limitations. However, acquiring data from multiple institutions from many countries requires enormous effort because of financial, technical, ethical, and legal issues as well as standardization of data structure and semantics. The Observational Health Data Sciences and Informatics (OHDSI) research network standardized 928 million unique records or 12% of the world's population into a common structure and meaning and established a research network of 453 data partners from 41 countries around the world. OHDSI is a distributed research network wherein researchers do not own or directly share data but only analyzed results. However, sharing evidence without sharing data is difficult to understand. In this review, we will look at the basic principles of OHDSI, common data model, distributed research networks, and some representative studies in the cardiovascular field using the network. This paper also briefly introduces a Korean distributed research network named FeederNet.

Intrinsic Connectivity and Family Dynamics: Striatolimbic Markers of Risk and Resilience in Youth at Familial Risk for Mood Disorders

BACKGROUND

Few studies to date have characterized functional connectivity (FC) within emotion and reward networks in relation to family dynamics in youth at high familial risk for bipolar disorder (HR-BD) and major depressive disorder (HR-MDD) relative to low-risk youth (LR). Such characterization may advance our understanding of the neural underpinnings of mood disorders and lead to more effective interventions.

METHODS

A total of 139 youth (43 HR-BD, 46 HR-MDD, and 50 LR) aged 12.9 ± 2.7 years were longitudinally followed for 4.5 ± 2.4 years. We characterized differences in striatolimbic FC that distinguished between HR-BD, HR-MDD, and LR and between resilience and conversion to psychopathology. We then examined whether risk status moderated FC-family dynamic associations. Finally, we examined whether baseline between-group FC differences predicted resilence versus conversion to psychopathology.

RESULTS

HR-BD had greater amygdala-middle frontal gyrus and dorsal striatum-middle frontal gyrus FC relative to HR-MDD and LR, and HR-MDD had lower amygdala-fusiform gyrus and dorsal striatum-precentral gyrus FC relative to HR-BD and LR (voxel-level p < .001, cluster-level false discovery rate-corrected p < .05). Resilient youth had greater amygdala-orbitofrontal cortex and ventral striatum-dorsal anterior cingulate cortex FC relative to youth with conversion to psychopathology (voxel-level p < .001, cluster-level false discovery rate-corrected p < .05). Greater family rigidity was inversely associated with amygdala-fusiform gyrus FC across all groups (false discovery rate-corrected p = .017), with a moderating effect of bipolar risk status (HR-BD vs. HR-MDD p < .001; HR-BD vs. LR p = .005). Baseline FC differences did not predict resilence versus conversion to psychopathology.

CONCLUSIONS

Findings represent neural signatures of risk and resilience in emotion and reward processing networks in youth at familial risk for mood disorders that may be targets for novel interventions tailored to the family context.