Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation

Common and disease-specific patterns of functional connectivity and topology alterations across unipolar and bipolar disorder during depressive episodes: a transdiagnostic study

Bipolar disorder (BD) and unipolar depression (UD) are defined as distinct diagnostic categories. However, due to some common clinical and pathophysiological features, it is a clinical challenge to distinguish them, especially in the early stages of BD. This study aimed to explore the common and disease-specific connectivity patterns in BD and UD. This study was constructed over 181 BD, 265 UD and 204 healthy controls. In addition, an independent group of 90 patients initially diagnosed with major depressive disorder at the baseline and then transferred to BD with the episodes of mania/hypomania during follow-up, was identified as initial depressive episode BD (IDE-BD). All participants completed resting-state functional magnetic resonance imaging (R-fMRI) at recruitment. Both network-based analysis and graph theory analysis were applied. Both BD and UD showed decreased functional connectivity (FC) in the whole brain network. The shared aberrant network across groups of patients with depressive episode (BD, IDE-BD and UD) mainly involves the visual network (VN), somatomotor networks (SMN) and default mode network (DMN). Analysis of the topological properties over the three networks showed that decreased clustering coefficient was found in BD, IDE-BD and UD, however, decreased shortest path length and increased global efficiency were only found in BD and IDE-BD but not in UD. The study indicate that VN, SMN, and DMN, which involve stimuli reception and abstraction, emotion processing, and guiding external movements, are common abnormalities in affective disorders. The network separation dysfunction in these networks is shared by BD and UD, however, the network integration dysfunction is specific to BD. The aberrant network integration functions in BD and IDE-BD might be valuable diagnostic biomarkers.

Pharmaco-Multiomics: A New Frontier in Precision Psychiatry

The landscape of psychiatric care is poised for transformation through the integration of pharmaco-multiomics, encompassing genomics, proteomics, metabolomics, transcriptomics, epigenomics, and microbiomics. This review discusses how these approaches can revolutionize personalized treatment strategies in psychiatry by providing a nuanced understanding of the molecular bases of psychiatric disorders and individual pharmacotherapy responses. With nearly one billion affected individuals globally, the shortcomings of traditional treatments, characterized by inconsistent efficacy and frequent adverse effects, are increasingly evident. Advanced computational technologies such as artificial intelligence (AI) and machine learning (ML) play crucial roles in processing and integrating complex omics data, enhancing predictive accuracy, and creating tailored therapeutic strategies. To effectively harness the potential of pharmaco-multiomics approaches in psychiatry, it is crucial to address challenges such as high costs, technological demands, and disparate healthcare systems. Additionally, navigating stringent ethical considerations, including data security, potential discrimination, and ensuring equitable access, is essential for the full realization of this approach. This process requires ongoing validation and comprehensive integration efforts. By analyzing recent advances and elucidating how different omic dimensions contribute to therapeutic customization, this review aims to highlight the promising role of pharmaco-multiomics in enhancing patient outcomes and shifting psychiatric treatments from a one-size-fits-all approach towards a more precise and patient-centered model of care.

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

OBJECTIVES

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

METHODS

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

RESULTS

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

LIMITATIONS

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

CONCLUSIONS

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

Genome-Wide Association Study of Treatment-Resistant Depression: Shared Biology With Metabolic Traits

OBJECTIVE

Treatment-resistant depression (TRD) occurs in roughly one-third of all individuals with major depressive disorder (MDD). Although research has suggested a significant common variant genetic component of liability to TRD, with heritability estimated at 8% when compared with non-treatment-resistant MDD, no replicated genetic loci have been identified, and the genetic architecture of TRD remains unclear. A key barrier to this work has been the paucity of adequately powered cohorts for investigation, largely because of the challenge in prospectively investigating this phenotype. The objective of this study was to perform a well-powered genetic study of TRD.

METHODS

Using receipt of electroconvulsive therapy (ECT) as a surrogate for TRD, the authors applied standard machine learning methods to electronic health record data to derive predicted probabilities of receiving ECT. These probabilities were then applied as a quantitative trait in a genome-wide association study of 154,433 genotyped patients across four large biobanks.

RESULTS

Heritability estimates ranged from 2% to 4.2%, and significant genetic overlap was observed with cognition, attention deficit hyperactivity disorder, schizophrenia, alcohol and smoking traits, and body mass index. Two genome-wide significant loci were identified, both previously implicated in metabolic traits, suggesting shared biology and potential pharmacological implications.

CONCLUSIONS

This work provides support for the utility of estimation of disease probability for genomic investigation and provides insights into the genetic architecture and biology of TRD.

Based on white matter microstructure to early identify bipolar disorder from patients with depressive episode

OBJECTIVE

Because of similar clinical manifestations, bipolar disorder (BD) patients are often misdiagnosed as major depressive disorder (MDD). This study aimed to compare the difference between depressed patients later converting to BD and unipolar depression (UD) according to diffusion tensor imaging (DTI).

METHOD

Patients with MDD (562 participants) in depressive episode states and healthy controls (HCs) (145 participants) were recruited over 10 years. Demographic and magnetic resonance imaging (MRI) data were collected at the time of recruitment. All patients with MDD were followed up for 5 years and classified into the transfer to BD (tBD) group (83 participants) and UD group (160 participants) according to the follow-up results. DTI and functional magnetic resonance imaging at baseline were compared.

RESULTS

Common abnormalities were found in both tBD and UD groups, including left superior cerebellar peduncle (SCP.L), right anterior limb of the internal capsule (ALIC.R), right superior fronto-occipital fasciculus (SFOF.R), and right inferior fronto-occipital fasciculus (IFOF.R). The tBD showed more extensive abnormalities than the UD in the body of corpus callosum, fornix, left superior corona radiata, left posterior corona radiata, left superior longitudinal fasciculus, and left superior fronto-occipital fasciculus.

CONCLUSION

The study demonstrated the common and distinct abnormalities of tBD and UD when compared to HC. The tBD group showed more extensive disruptions of white matter integrity, which could be a potential biomarker for the early identification of BD.

Development and multi-site external validation of a generalizable risk prediction model for bipolar disorder

Bipolar disorder is a leading contributor to disability, premature mortality, and suicide. Early identification of risk for bipolar disorder using generalizable predictive models trained on diverse cohorts around the United States could improve targeted assessment of high risk individuals, reduce misdiagnosis, and improve the allocation of limited mental health resources. This observational case-control study intended to develop and validate generalizable predictive models of bipolar disorder as part of the multisite, multinational PsycheMERGE Network across diverse and large biobanks with linked electronic health records (EHRs) from three academic medical centers: in the Northeast (Massachusetts General Brigham), the Mid-Atlantic (Geisinger) and the Mid-South (Vanderbilt University Medical Center). Predictive models were developed and valid with multiple algorithms at each study site: random forests, gradient boosting machines, penalized regression, including stacked ensemble learning algorithms combining them. Predictors were limited to widely available EHR-based features agnostic to a common data model including demographics, diagnostic codes, and medications. The main study outcome was bipolar disorder diagnosis as defined by the International Cohort Collection for Bipolar Disorder, 2015. In total, the study included records for 3,529,569 patients including 12,533 cases (0.3%) of bipolar disorder. After internal and external validation, algorithms demonstrated optimal performance in their respective development sites. The stacked ensemble achieved the best combination of overall discrimination (AUC = 0.82-0.87) and calibration performance with positive predictive values above 5% in the highest risk quantiles at all three study sites. In conclusion, generalizable predictive models of risk for bipolar disorder can be feasibly developed across diverse sites to enable precision medicine. Comparison of a range of machine learning methods indicated that an ensemble approach provides the best performance overall but required local retraining. These models will be disseminated via the PsycheMERGE Network website.

Identifying misdiagnosed bipolar disorder using support vector machine: feature selection based on fMRI of follow-up confirmed affective disorders

Nearly a quarter of bipolar disorder (BD) patients were misdiagnosed as major depressive disorder (MDD) patients, which cannot be corrected until mania/hypomania develops. It is important to recognize these obstacles so that the appropriate treatment can be initiated. Thus, we sought to distinguish patients with BD from MDD, especially to identify misdiagnosed BD before mania/hypomania, and further explore potential trait features that allow accurate differential diagnosis independent of state matters. Functional magnetic resonance imaging scans were performed at baseline on 92 MDD patients and 48 BD patients. The MDD patients were then followed up for more than two years. After follow-up, 23 patients transformed into BD (tBD), and 69 patients whose diagnoses remained unchanged were eligible for unipolar depression (UD). A support vector machine classifier was trained on the amygdala-based functional connectivity (FC) of 48 BD and 50 UD patients using a novel region-based feature selection. Then, the classifier was tested on the dataset, encompassing tBD and the remaining UD. It performed well for known BD and UD and can also distinguish tBD from UD with an accuracy of 81%, sensitivity of 82.6%, specificity of 79%, and AUC of 74.6%, respectively. Feature selection results revealed that ten regions within the cortico-limbic neural circuit contributed most to classification. Furthermore, in the FC comparisons among diseases, BD and tBD shared almost overlapped FC patterns in the cortico-limbic neural circuit, and both of them presented pronounced differences in most regions within the circuit compared with UD. The FC values of the most discriminating brain regions had no prominent correlations with the severity of depression, anxiety, and mania/hypomania (FDR correction). It suggests that BD possesses some trait features in the cortico-limbic neural circuit, rendering it dichotomized by the classifier based on known-diagnosis data.

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.

Establishment of a Public Mental Health Database for Research Purposes in the Ferrara Province: Development and Preliminary Evaluation Study

Background

The immediate use of data exported from electronic health records (EHRs) for research is often limited by the necessity to transform data elements into an actual data set.

Objective

This paper describes the methodology for establishing a data set that originated from an EHR registry that included clinical, health service, and sociodemographic information.

Methods

The Extract, Transform, Load process was applied to raw data collected at the Integrated Department of Mental Health and Pathological Addictions in Ferrara, Italy, from 1925 to February 18, 2021, to build the new, anonymized Ferrara-Psychiatry (FEPSY) database. Information collected before the first EHR was implemented (ie, in 1991) was excluded. An unsupervised cluster analysis was performed to identify patient subgroups to support the proof of concept.

Results

The FEPSY database included 3,861,432 records on 46,222 patients. Since 1991, each year, a median of 1404 (IQR 1117.5-1757.7) patients had newly accessed care, and a median of 7300 (IQR 6109.5-9397.5) patients were actively receiving care. Among 38,022 patients with a mental disorder, 2 clusters were identified; the first predominantly included male patients who were aged 25 to 34 years at first presentation and were living with their parents, and the second predominantly included female patients who were aged 35 to 44 years and were living with their own families.

Conclusions

The process for building the FEPSY database proved to be robust and replicable with similar health care data, even when they were not originally conceived for research purposes. The FEPSY database will enable future in-depth analyses regarding the epidemiology and social determinants of mental disorders, access to mental health care, and resource utilization.

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.

Development and Multi-Site External Validation of a Generalizable Risk Prediction Model for Bipolar Disorder

Bipolar disorder is a leading contributor to disability, premature mortality, and suicide. Early identification of risk for bipolar disorder using generalizable predictive models trained on diverse cohorts around the United States could improve targeted assessment of high risk individuals, reduce misdiagnosis, and improve the allocation of limited mental health resources. This observational case-control study intended to develop and validate generalizable predictive models of bipolar disorder as part of the multisite, multinational PsycheMERGE Consortium across diverse and large biobanks with linked electronic health records (EHRs) from three academic medical centers: in the Northeast (Massachusetts General Brigham), the Mid-Atlantic (Geisinger) and the Mid-South (Vanderbilt University Medical Center). Predictive models were developed and validated with multiple algorithms at each study site: random forests, gradient boosting machines, penalized regression, including stacked ensemble learning algorithms combining them. Predictors were limited to widely available EHR-based features agnostic to a common data model including demographics, diagnostic codes, and medications. The main study outcome was bipolar disorder diagnosis as defined by the International Cohort Collection for Bipolar Disorder, 2015. In total, the study included records for 3,529,569 patients including 12,533 cases (0.3%) of bipolar disorder. After internal and external validation, algorithms demonstrated optimal performance in their respective development sites. The stacked ensemble achieved the best combination of overall discrimination (AUC = 0.82 - 0.87) and calibration performance with positive predictive values above 5% in the highest risk quantiles at all three study sites. In conclusion, generalizable predictive models of risk for bipolar disorder can be feasibly developed across diverse sites to enable precision medicine. Comparison of a range of machine learning methods indicated that an ensemble approach provides the best performance overall but required local retraining. These models will be disseminated via the PsycheMERGE Consortium website.

Real-world evidence of age-independent electroconvulsive therapy efficacy: A retrospective cohort study

OBJECTIVES

Electroconvulsive therapy (ECT) is an effective treatment for depressive disorders and approved for use in adolescents and adults, but it is unclear whether efficacy or cognitive side effect burden differs with age or if effectiveness in usual clinical practice matches that in prospective studies. We examined the effects of ECT on depression and cognition in a large clinical cohort.

METHODS

A retrospective cohort study of patients ages 16 and older receiving ECT between 2011 and 2020 and who were evaluated with the Quick Inventory of Depressive Symptomatology (QIDS), the Behavior and Symptom Identification Scale-24 (BASIS-24), and the Montreal Cognitive Assessment (MoCA) at baseline and after treatment #10.

RESULTS

Among 1698 patients, ECT was associated with a decrease in depression symptoms (QIDS reduction from 17.1 ± 4.9 to 10.1 ± 5.2) and improvement in self-reported mental health (BASIS-24 scores improved from 1.92 ± 0.55 to 1.17 ± 0.60). There was a reduction in MoCA scores from 25.8 ± 3.1 to 25.4 ± 3.1. In multivariate models, age was not associated with a differential QIDS or BASIS-24 response, but older age was associated with a lesser reduction in MoCA.

CONCLUSION

Among 1698 patients aged 16 and older, ECT was associated with improvement in depression and overall self-reported mental health, with a slight decrease in cognition. Age was not associated with changes in efficacy, but older age was associated with a lesser cognitive change as measured by the MoCA. These results provide normative data of real-world effectiveness of ECT, and add further support to its utility in patients with severe psychiatric illness.

Alterations of Plasma Lipids in Adult Women With Major Depressive Disorder and Bipolar Depression

Lipidomics has been established as a potential tool for the investigation of mental diseases. However, the composition analysis and the comparison of the peripheral lipids regarding adult women with major depressive depression (MDD) or bipolar depression (BPD) has been poorly addressed. In the present study, age-matched female individuals with MDD (n = 28), BPD (n = 22) and healthy controls (HC, n = 25) were enrolled. Clinical symptoms were assessed and the plasma samples were analyzed by comprehensive lipid profiling based on liquid chromatography-mass spectrometry (LC/MS). We found that the composition of lipids was remarkably changed in the patients with MDD and BPD when compared to HC or compared to each other. Moreover, we identified diagnostic potential biomarkers comprising 20 lipids that can distinguish MDD from HC (area under the curve, AUC = 0.897) and 8 lipids that can distinguish BPD from HC (AUC = 0.784), as well as 13 lipids were identified to distinguish MDD from BPD with moderate reliability (AUC = 0.860). This study provides further understanding of abnormal lipid metabolism in adult women with MDD and BPD and may develop lipid classifiers able to effectively discriminate MDD from BPD and HC.

The promise of machine learning in predicting treatment outcomes in psychiatry

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real-world clinical practice. Relatively few retrospective studies to-date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.