Classifying Major Depressive Disorder Using Multimodal MRI Data: A Personalized Federated Algorithm

The authors investigated the theoretical and clinical role of depression among cocaine abusers in treatment. Eighty-nine cocaine-abusing patients underwent 2 weeks of substance abuse treatment. Posttreatment major depressive disorder, depressive symptoms before and after substance abuse treatment, and alcohol diagnoses were assessed and their relation to pretreatment substance use, cravings in high-risk situations, and 3-month follow-up status was examined. High rates of major depressive disorder were found but were unrelated to pretreatment substance use. The decrease in depressive symptoms during treatment was independent of major depressive disorder or alcohol diagnoses and predicted treatment attrition. Higher levels of depressive symptoms during treatment were associated with greater urge to use cocaine, alcohol, and other drugs in high-risk situations. Concurrent major depressive disorder and depressive symptoms did not predict cocaine use at follow-up. However, patients who had an alcohol relapse episode experienced more depressive symptoms during treatment than did those who abstained. The results highlight the relationship of depression to alcohol use among cocaine abusers and suggest a need for further studies of the association between depression and substance use disorders.

BackgroundThe diagnosis of major depressive disorder (MDD) mainly depends on subjective clinical symptoms, without an acceptable objective biomarker for the clinical application of MDD. Inter-alpha-trypsin inhibitor heavy chain 4 (ITIH4) showed a high specificity as biomarker for the diagnosis and treatment of MDD. The present study aimed to investigate differences in plasma ITIH4 in two different aged MDD patients and underlying pathological mechanisms of plasma ITIH4 in the occurrence and development of MDD.MethodsSixty-five adult MDD patients, 51 adolescent MDD patients, and 64 healthy controls (HCs) were included in the present study. A 14-days’ antidepressive treatment was conducted in all MDD patients. Psychological assessments were performed and plasma ITIH4 and astrocyte-related markers were detected for all participants.Results(1) Plasma levels of ITIH4 in adult MDD patients were significantly higher than adolescent MDD patients and HCs, and significantly increased plasma ITIH4 levels was observed in adolescent MDD patients compared with HCs (2). There were positive correlations between plasma ITIH4 levels and 24-item Hamilton Depression Scale (HAMD-24) scores and plasma glial fibrillary acidic protein (GFAP) levels in MDD patients, however, plasma ITIH4 levels were significantly correlated with age just in adult MDD patients (3). Plasma ITIH4 showed area under the curve values of 0.824 and 0.729 to differentiate adult MDD patients and adolescent MDD patients from HCs, respectively (4). There was significant decrease in plasma levels of ITIH4 between before and after antidepressive treatment in adult MDD patients, but not in adolescent MDD patients (5). Changed value of ITIH4 levels were correlated with the changed value of GFAP levels and changed rate of HAMD-24 scores in adult MDD patients following antidepressive treatment.ConclusionPlasma ITIH4 may be potential plasma biomarkers of MDD with age-related specificity, which was associated with depressive symptoms astrocyte-related pathologic changes, and antidepressive treatment efficacy.

Nine hundred ninety-seven fellows of the American College of Obstetricians and Gynecologists were surveyed by mailed questionnaire regarding their attitudes toward the conceptualization, diagnosis and treatment of premenstrual dysphoric disorder (PMDD) and major depressive disorder (MDD). Hypothesized differences in attitudes based on age, gender and professional identity as a primary care provider versus non-primary care provider were examined. Comparisons between attitudes toward PMDD and MDD were also investigated. Approximately 36% of the questionnaires were completed and returned. Overall attitudes toward PMDD versus MDD were found to be significantly different. Roughly one in three respondents disagreed with statements indicating responsibility for and confidence in their ability to treat MDD, but not PMDD. When significant differences were found for age, gender and professional identity, younger physicians, women physicians and those who self-identified as primary care providers reported attitudes that may be more likely to be associated with diagnosis and treatment of MDD and PMDD in gynecologic practice. For example, about 41% of self-identified non-primary care providers and 14.8% of primary care providers disagreed with the statement ‘treating depression is my responsibility as a gynecologist’. Differences in gynecologists’ attitudes toward MDD versus PMDD may be associated with under-treatment of MDD in gynecologic practice.

Characterizing Major Depressive Disorder (MDD) using alpha-band activity in resting-state electroencephalogram (EEG) combined with MATRICS Consensus Cognitive Battery (MCCB)

Major depressive disorder (MDD) is one of the most common psychiatric disorders that accompany psychophysiological and mood changes. However, the pathophysiology-based disease mechanism of MDD is not yet fully understood, and diagnosis is also conducted through interviews with clinicians and patients. Diagnosis and treatment of MDD are limited due to the absence of biomarkers underlying the pathophysiological mechanisms of MDD. Although various attempts have been made to discover metabolite biomarkers for the diagnosis and treatment response of MDD, problems with sample size and consistency of results have limited clinical application. In addition, it was reported that future biomarker studies must consider exposure to antidepressants, which is the main cause of heterogeneity in depression subgroups. Therefore, the purpose of this study is to discover and validate biomarkers for the diagnosis of depression in consideration of exposure to drug treatment including antidepressants that contribute to the heterogeneity of the MDD subgroup. In the biomarker discovery and validation set, the disease group consisted of a mixture of patients exposed and unexposed to drug treatment including antidepressants for the treatment of MDD. The serum metabolites that differed between the MDD patients and the control group were profiled using mass spectrometry. The validation set including the remission group was used to verify the effectiveness as a biomarker for the diagnosis of depression and determination of remission status. The presence of different metabolites between the two groups was confirmed through serum metabolite profiling between the MDD patient group and the control group. Finally, Acetylcarnitine was selected as a biomarker. In validation, acetylcarnitine was significantly decreased in MDD and was distinguished from remission status. This study confirmed that the discovered acetylcarnitine has potential as a biomarker for diagnosing depression and determining remission status, regardless of exposure to drug treatment including antidepressants.

Background: Major depressive disorder (MDD) is a debilitating condition with a high disease burden and medical comorbidities. There are currently few to no validated biomarkers to guide the diagnosis and treatment of MDD. In the present study, we evaluated the differences between MDD patients and healthy controls (HCs) in terms of cortical haemodynamic responses during a verbal fluency test (VFT) using functional near-infrared spectroscopy (fNIRS) and serum amino acid profiles, and ascertained if these parameters were correlated with clinical characteristics. Methods: Twenty-five (25) patients with MDD and 25 age-, gender-, and ethnicity-matched HCs were recruited for the study. Real-time monitoring of the haemodynamic response during completion of a VFT was quantified using a 52-channel NIRS system. Serum samples were analysed and quantified by liquid chromatography-mass spectrometry for amino acid profiling. Receiver-operating characteristic (ROC) curves were used to classify potential candidate biomarkers. Results: The MDD patients had lower prefrontal and temporal activation during completion of the VFT than HCs. The MDD patients had lower mean concentrations of oxy-Hb in the left orbitofrontal cortex (OFC), and lower serum histidine levels. When the oxy-haemoglobin response was combined with the histidine concentration, the sensitivity and specificity of results improved significantly from 66.7% to 73.3% and from 65.0% to 90.0% respectively, as compared to results based only on the NIRS response. Conclusions: These findings demonstrate the use of combination biomarkers to aid in the diagnosis of MDD. This technique could be a useful approach to detect MDD with greater precision, but additional studies are required to validate the methodology.

In this day and age, depression is still one of the biggest problems in the world. If left untreated, it can lead to suicidal thoughts and attempts. There is a need for proper diagnoses of Major Depressive Disorder (MDD) and evaluation of the early stages to stop the side effects. Early detection is critical to identify a variety of serious conditions. In order to provide safe and effective protection to MDD patients, it is crucial to automate diagnoses and make decision-making tools widely available. Although there are various classification systems for the diagnosis of MDD, no reliable, secure method that meets these requirements has been established to date. In this paper, a federated deep learning-based multimodal system for MDD classification using electroencephalography (EEG) and audio datasets is presented while meeting data privacy requirements. The performance of the federated learning (FL) model was tested on independent and identically distributed (IID) and non-IID data. The study began by extracting features from several pre-trained models and ultimately decided to use bidirectional short-term memory (Bi-LSTM) as the base model, as it had the highest validation accuracy of 91% compared to a convolutional neural network and LSTM with 85% and 89% validation accuracy on audio data, respectively. The Bi-LSTM model also achieved a validation accuracy of 98.9% for EEG data. The FL method was then used to perform experiments on IID and non-IID datasets. The FL-based multimodal model achieved an exceptional training and validation accuracy of 99.9% when trained and evaluated on both IID and non-IIID datasets. These results show that the FL multimodal system performs almost as well as the Bi-LSTM multimodal system and emphasize its suitability for processing IID and non-IIID data. Several clients were found to perform better than conventional pre-trained models in a multimodal framework for federated learning using EEG and audio datasets. The proposed framework stands out from other classification techniques for MDD due to its special features, such as multimodality and data privacy for edge machines with limited resources. Due to these additional features, the framework concept is the most suitable alternative approach for the early classification of MDD patients.

Fluoxetine, cognitive-behavioral therapy, and their combination for adolescents with depression: Treatment for Adolescents with Depression Study (TADS) randomized controlled trial

ABSTRACTResearch has revealed a significant association between several peritraumatic emotional responses and posttraumatic stress disorder (PTSD). Preliminary research has also linked peritraumatic emotional responses with a diagnosis of major depressive disorder (MDD). The majority of this research has been cross-sectional, thereby making it difficult to determine the extent to which the various peritraumatic emotional responses may increase risk for, or serve as a premorbid marker of, PTSD and MDD. This study examined the longitudinal role of peritraumatic emotional responses on the subsequent development of PTSD and MDD in a sample of US military veterans. Whereas a number of peritraumatic emotional responses were concurrently associated with PTSD, only peritraumatic numbness maintained the association with this diagnosis longitudinally. For MDD, peritraumatic numbness was the only emotional response related to the diagnosis both concurrently and longitudinally. Study findings are a preliminary proof of concept that peritraumatic numbness may serve as a premorbid marker for the development of PTSD and MDD following a traumatic event. Implications of these findings for the diagnosis, assessment, and treatment of both PTSD and MDD are discussed.

Drs. Nelson and Papakostas Reply

IntroductionWe aimed to clarify medical expenses in Japanese individuals before and after major depressive disorder (MDD) diagnosis, and to determine whether MDD treatment also reduces medical costs for comorbid physical conditions.MethodsThis was an exploratory, descriptive, retrospective analysis of insurance claims data from JMDC Inc. Cohort A included individuals aged 18–64 years between January 2015 and December 2019. Cohorts B and C included Cohort A individuals with diabetes/hypertension (‘chronic disease’), and sleep/anxiety disorders (‘high depression risk’), respectively. Individuals in Cohorts A–C with an MDD diagnosis were analyzed by year of MDD onset (Cohorts A–CMDD2015–2019). Diagnoses and median medical costs were derived from International Classification of Diseases 10 codes.ResultsTotal medical and non-neuropsychiatric drug costs in MDD onset years were 170,390–182,120 and 8480–9586 yen higher, respectively, for Cohorts AMDD2015–2019 than for Cohort A. In Cohort AMDD2019, total medical and non-neuropsychiatric drug costs increased incrementally from 2015 to 2019 (total changes: + 165,130 and + 7365 yen, respectively), to a greater degree than in Cohort A (+ 10,510 and + 1246 yen, respectively). Neuropsychiatric drug costs increased in the year of MDD onset only and decreased thereafter. After MDD onset, decreases in total medical and non-neuropsychiatric drug costs were observed (Cohorts AMDD2015–2019). Non-neuropsychiatric drug costs also decreased after MDD onset in the chronic disease groups (Cohorts CMDD2015–2019), but not in patients with MDD recurrence.ConclusionTreating MDD reduces medical costs for comorbid physical conditions and may be a useful strategy for improving healthcare efficiency in Japan.Supplementary InformationThe online version contains supplementary material available at 10.1007/s12325-021-01963-9.

Response to antidepressant treatment in major depressive disorder varies substantially between individuals, which lengthens the process of finding effective treatment. The authors sought to determine whether a multimodal machine learning approach could predict early sertraline response in patients with major depressive disorder. They assessed the predictive contribution of MR neuroimaging and clinical assessments at baseline and after 1 week of treatment. This was a preregistered secondary analysis of data from the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study, a multisite double-blind, placebo-controlled randomized clinical trial that included 296 adult outpatients with unmedicated recurrent or chronic major depressive disorder. MR neuroimaging and clinical data were collected before and after 1 week of treatment. Performance in predicting response and remission, collected after 8 weeks, was quantified using balanced accuracy (bAcc) and area under the receiver operating characteristic curve (AUROC) scores. A total of 229 patients were included in the analyses (mean age, 38 years [SD=13]; 66% female). Internal cross-validation performance in predicting response to sertraline (bAcc=68% [SD=10], AUROC=0.73 [SD=0.03]) was significantly better than chance. External cross-validation on data from placebo nonresponders (bAcc=62%, AUROC=0.66) and placebo nonresponders who were switched to sertraline (bAcc=65%, AUROC=0.68) resulted in differences that suggest specificity for sertraline treatment compared with placebo treatment. Finally, multimodal models outperformed unimodal models. The study results confirm that early sertraline treatment response can be predicted; that the models are sertraline specific compared with placebo; that prediction benefits from integrating multimodal MRI data with clinical data; and that perfusion imaging contributes most to these predictions. Using this approach, a lean and effective protocol could individualize sertraline treatment planning to improve psychiatric care.

Previous research suggests that electroconvulsive therapy (ECT)-the criterion standard for the treatment of severe depression-is not as effective when the patient has comorbid borderline personality disorder (BPD). The ECT outcomes of patients with and without BPD were compared in a retrospective chart review to test this claim. We enrolled 137 patients with a diagnosis of major depressive disorder who completed the McLean Screening Instrument for Borderline Personality Disorder. Twenty-nine patients had positive screening scores for BPD. The difference in Patient Health Questionnaire (PHQ-9) scores before and after ECT was compared between patients with and without BPD. Follow-up PHQ-9 scores determined after treatment were collected and analyzed. Electroconvulsive therapy equally improved symptoms of depression as measured by PHQ-9 score in both patients who screened positive and patients who screened negative for BPD. No difference in the increase in PHQ-9 scores between these 2 groups was noted 1 month after treatment (P = 0.19). These data showed that a positive BPD screen does not necessarily predict a poorer response to ECT, nor does it predict greater symptom recurrence after ECT. This does not suggest that ECT is necessarily an appropriate treatment for major depressive disorder in patients with a comorbid BPD, given the limitations of screening instruments.

Major depressive disorder (MDD) is a prevalent brain disorder affecting more than 2% of the world's population. Due to the lack of well-specific biomarkers, it is difficult to distinguish MDD from other diseases with similar clinical symptoms (such as Alzheimer's disease and cerebral thrombosis). In this work, we provided a strategy to address this issue by constructing a combinatorial biomarker of serum glial fibrillary acidic protein (GFAP) and neurofilament light chain (NFL). To achieve the convenient and sensitive detection of two proteins, we developed an electrochemical immunosandwich sensor using two metal-ion-doped carbon dots (Pb-CDs and Cu-CDs) as probes for signal output. Each probe contains approximately 300 Pb2+ or 200 Cu2+, providing excellent signal amplification. This method achieved detection limits of 0.3 pg mL-1 for GFAP and 0.2 pg mL-1 for NFL, lower than most of the reported detection limits. Analysis of real serum samples showed that the concentration ratio of GFAP to NFL, which is associated with the relative degree of brain inflammation and neurodegeneration, is suitable for not only distinguishing MDD from healthy individuals but also specifically distinguishing MDD from Alzheimer's disease and cerebral thrombosis. The good specificity gives the combinatorial GFAP/NFL biomarker broad application prospects in the screening, diagnosis, and treatment of MDD.

Major depressive disorder (MDD) is a highly prevalent and disabling condition with a high disease burden. There are currently no validated biomarkers for the diagnosis and treatment of MDD. This study assessed serum amino acid metabolite changes between MDD patients and healthy controls (HCs) and their association with disease severity and diagnostic utility. In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. For amino acid profiling, serum samples were analysed and quantified by liquid chromatography-mass spectrometry (LC-MS). Receiver-operating characteristic (ROC) curves were used to classify putative candidate biomarkers. MDD patients had significantly higher serum levels of glutamic acid, aspartic acid and glycine but lower levels of 3-Hydroxykynurenine; glutamic acid and phenylalanine levels also correlated with depression severity. Combining these four metabolites allowed for accurate discrimination of MDD patients and HCs, with 65.7% of depressed patients and 62.9% of HCs correctly classified. Glutamic acid, aspartic acid, glycine and 3-Hydroxykynurenine may serve as potential diagnostic biomarkers, whereas glutamic acid and phenylalanine may be markers for depression severity. To elucidate the association between these indicators and clinical features, it is necessary to conduct additional studies with larger sample sizes that involve a spectrum of depressive symptomatology.