Diagnosis of major depressive disorder by combining multimodal information from heart rate dynamics and serum proteomics using machine-learning algorithm

Predicting the severity of mood and neuropsychiatric symptoms from digital biomarkers using wearable physiological data and deep learning

Neuropsychiatric symptoms (NPS) and mood disorders are common in individuals with mild cognitive impairment (MCI) and increase the risk of progression to dementia. Wearable devices collecting physiological and behavioral data can help in remote, passive, and continuous monitoring of moods and NPS, overcoming limitations and inconveniences of current assessment methods. In this longitudinal study, we examined the predictive ability of digital biomarkers based on sensor data from a wrist-worn wearable to determine the severity of NPS and mood disorders on a daily basis in older adults with predominant MCI. In addition to conventional physiological biomarkers, such as heart rate variability and skin conductance levels, we leveraged deep-learning features derived from physiological data using a self-supervised convolutional autoencoder. Models combining common digital biomarkers and deep features predicted depression severity scores with a correlation of r = 0.73 on average, total severity of mood disorder symptoms with r = 0.67, and mild behavioral impairment scores with r = 0.69 in the study population. Our findings demonstrated the potential of physiological biomarkers collected from wearables and deep learning methods to be used for the continuous and unobtrusive assessments of mental health symptoms in older adults, including those with MCI. TRIAL REGISTRATION: This trial was registered with ClinicalTrials.gov (NCT05059353) on September 28, 2021, titled "Effectiveness and Safety of a Digitally Based Multidomain Intervention for Mild Cognitive Impairment".

Evaluation of a Nondepleted Plasma Multiprotein-Based Model for Discriminating Psychiatric Disorders Using Multiple Reaction Monitoring-Mass Spectrometry: Proof-of-Concept Study

Psychiatric evaluation relies on subjective symptoms and behavioral observation, which sometimes leads to misdiagnosis. Despite previous efforts to utilize plasma proteins as objective markers, the depletion method is time-consuming. Therefore, this study aimed to enhance previous quantification methods and construct objective discriminative models for major psychiatric disorders using nondepleted plasma. Multiple reaction monitoring-mass spectrometry (MRM-MS) assays for quantifying 453 peptides in nondepleted plasma from 132 individuals [35 major depressive disorder (MDD), 47 bipolar disorder (BD), 23 schizophrenia (SCZ) patients, and 27 healthy controls (HC)] were developed. Pairwise discriminative models for MDD, BD, and SCZ, and a discriminative model between patients and HC were constructed by machine learning approaches. In addition, the proteins from nondepleted plasma-based discriminative models were compared with previously developed depleted plasma-based discriminative models. Discriminative models for MDD versus BD, BD versus SCZ, MDD versus SCZ, and patients versus HC were constructed with 11 to 13 proteins and showed reasonable performances (AUROC = 0.890-0.955). Most of the shared proteins between nondepleted and depleted plasma models had consistent directions of expression levels and were associated with neural signaling, inflammatory, and lipid metabolism pathways. These results suggest that multiprotein markers from nondepleted plasma have a potential role in psychiatric evaluation.

Heart rate variability (HRV) as a way to understand associations between the autonomic nervous system (ANS) and affective states: A critical review of the literature

Evidence suggests affective disorders such as depression and bipolar disorder are characterised by dysregulated autonomic nervous system (ANS) activity. These findings suggest ANS dysregulation may be involved in the pathogenesis of affective disorders. Different affective states are characterised by different ANS activity patterns (i.e., an increase or decrease in sympathetic or parasympathetic activity). To understand how ANS abnormalities are involved in the development of affective disorders, it is important to understand how affective states correlate with ANS activity before their onset. Using heart rate variability (HRV) as a tool to measure ANS activity, this review aimed to look at associations between affective states and HRV in non-clinical populations (i.e., in those without medical and psychiatric disorders). Searches on PubMed and Google Scholar were completed using the following search terms: heart rate variability, autonomic nervous system, sympathetic nervous system, parasympathetic nervous system, affective state, mood and emotion in all possible combinations. All but one of the studies examined (N = 13), demonstrated significant associations between affect and HRV. Findings suggest negative affect, encompassing both diffused longer-term experiences (i.e., mood) as well as more focused short-term experiences (i.e., emotions), may be associated with a reduction in parasympathetic activity as measured through HRV parameters known to quantify parasympathetic activity (e.g., high frequency (HF)-HRV). HRV measures typically linked to reduction in parasympathetic activity appear to be linked to negative affective states in non-clinical populations. However, given the complex and possibly non-linear relationship between HRV and parasympathetic activity, further studies need to clarify specificity of these findings. Future studies should investigate the potential utility of HRV measures as biomarkers for monitoring changes in affective states and for early detection of onset and relapse of depression in patients with affective disorders.

Applying Self-Supervised Representation Learning for Emotion Recognition Using Physiological Signals

The use of machine learning (ML) techniques in affective computing applications focuses on improving the user experience in emotion recognition. The collection of input data (e.g., physiological signals), together with expert annotations are part of the established standard supervised learning methodology used to train human emotion recognition models. However, these models generally require large amounts of labeled data, which is expensive and impractical in the healthcare context, in which data annotation requires even more expert knowledge. To address this problem, this paper explores the use of the self-supervised learning (SSL) paradigm in the development of emotion recognition methods. This approach makes it possible to learn representations directly from unlabeled signals and subsequently use them to classify affective states. This paper presents the key concepts of emotions and how SSL methods can be applied to recognize affective states. We experimentally analyze and compare self-supervised and fully supervised training of a convolutional neural network designed to recognize emotions. The experimental results using three emotion datasets demonstrate that self-supervised representations can learn widely useful features that improve data efficiency, are widely transferable, are competitive when compared to their fully supervised counterparts, and do not require the data to be labeled for learning.

Combined HTR1A/1B methylation and human functional connectome to recognize patients with MDD

OBJECTIVES

This study aimed to use a machine-learning method to identify HTR1A/1B methylation and resting-state functional connectivity (rsFC) related to the diagnosis of MDD, then try to build classification models for MDD diagnosis based on the identified features.

METHODS

Peripheral blood samples were collected from all recruited participants, and part of the participants underwent the resting-state fMRI scan. Features including HTR1A/1B methylation and rsFC were calculated. Then, the initial feature sets of epigenetics and neuroimaging were separately input into an all-relevant feature selection to generate significant discriminative power for MDD diagnosis. Random forest classifiers were constructed and evaluated based on identified features. In addition, the SHapley Additive exPlanations (SHAP) method was adapted to interpret the diagnostic model.

RESULTS

A combination of selected HTR1A/1B methylation and rsFC feature sets achieved better performance than using either one alone - a distinction between MDD and healthy control groups was achieved at 81.78% classification accuracy and 0.8948 AUC.

CONCLUSION

A high classification accuracy can be achieved by combining multidimensional information from epigenetics and cerebral radiomic features in MDD. Our approach can be helpful for accurate clinical diagnosis of MDD and further exploring the pathogenesis of MDD.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSION

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

Appositeness of Optimized and Reliable Machine Learning for Healthcare: A Survey

Machine Learning (ML) has been categorized as a branch of Artificial Intelligence (AI) under the Computer Science domain wherein programmable machines imitate human learning behavior with the help of statistical methods and data. The Healthcare industry is one of the largest and busiest sectors in the world, functioning with an extensive amount of manual moderation at every stage. Most of the clinical documents concerning patient care are hand-written by experts, selective reports are machine-generated. This process elevates the chances of misdiagnosis thereby, imposing a risk to a patient's life. Recent technological adoptions for automating manual operations have witnessed extensive use of ML in its applications. The paper surveys the applicability of ML approaches in automating medical systems. The paper discusses most of the optimized statistical ML frameworks that encourage better service delivery in clinical aspects. The universal adoption of various Deep Learning (DL) and ML techniques as the underlying systems for a variety of wellness applications, is delineated by challenges and elevated by myriads of security. This work tries to recognize a variety of vulnerabilities occurring in medical procurement, admitting the concerns over its predictive performance from a privacy point of view. Finally providing possible risk delimiting facts and directions for active challenges in the future.

Potential Biomarkers for Predicting Depression in Diabetes Mellitus

Objective: To identify the potential biomarkers for predicting depression in diabetes mellitus using support vector machine to analyze routine biochemical tests and vital signs between two groups: subjects with both diabetes mellitus and depression, and subjects with diabetes mellitus alone. Methods: Electronic medical records upon admission and biochemical tests and vital signs of 135 patients with both diabetes mellitus and depression and 187 patients with diabetes mellitus alone were identified for this retrospective study. After matching on factors of age and sex, the two groups (n = 72 for each group) were classified by the recursive feature elimination-based support vector machine, of which, the training data, validation data, and testing data were split for ranking the parameters, determine the optimal parameters, and assess classification performance. The biomarkers were identified by 10-fold cross validation. Results: The experimental results identified 8 predictive biomarkers with classification accuracy of 78%. The 8 biomarkers are magnesium, cholesterol, AST/ALT, percentage of monocytes, bilirubin indirect, triglyceride, lactic dehydrogenase, and diastolic blood pressure. Receiver operating characteristic curve analysis was also adopted with area under the curve being 0.72. Conclusions: Some biochemical parameters may be potential biomarkers to predict depression among the subjects with diabetes mellitus.

Predictive protein markers for depression severity in mood disorders: A preliminary trans-diagnostic approach study

Depression is a common symptom of many mental disorders, especially major depressive disorder (MDD) and bipolar disorder (BD). Previous studies have reported that these diseases share common pathophysiological pathways; therefore, this study elucidated whether the plasma levels of protein markers related to common depressive symptoms differed between patients with BD and those with MDD. Plasma samples of 71 patients with mood disorders and clinical manifestations were analyzed in this study. After depleting the abundant proteins, liquid chromatography-tandem mass spectrometry and label-free quantification were performed. Five proteins, viz., cholesteryl ester transfer protein (CETP), apolipoprotein D (APOD), mannan-binding lectin serine protease 2 (MASP2), Ig lambda chain V-II region BO (IGLV2-8) and Ig kappa chain V-III region NG9 (IGKV3-20) were negatively associated with the total scores of the Hamilton depression rating scale (HAM-D), after adjusting for the covariates. CETP and APOD also showed significant negative correlations with the anhedonia/retardation and guilt/agitation scores of the HAM-D. Four proteins, namely, Ig kappa chain V-II region TEW (IGKC; IGKV2D-28), Ig lambda variable 5-45 (IGLV5-45), complement factor H (CFH) and attractin (ATRN), showed significant associations with anhedonia/retardation after adjusting for covariates. Proteins that significantly correlated with the symptoms could predict the remission state of depression (area under the curve [AUC], 0.83) and anhedonia/retardation (AUC, 0.80). Bioinformatics analysis revealed that complement activation, immune response, and lipid metabolism were significantly enriched pathways. Although our study design was cross-sectional and no controls were included, protein markers identified in this preliminary study will be further investigated in our subsequent longitudinal study.

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

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

Quantitative Proteomic Approach for Discriminating Major Depressive Disorder and Bipolar Disorder by Multiple Reaction Monitoring-Mass Spectrometry

Because major depressive disorder (MDD) and bipolar disorder (BD) manifest with similar symptoms, misdiagnosis is a persistent issue, necessitating their differentiation through objective methods. This study was aimed to differentiate between these disorders using a targeted proteomic approach. Multiple reaction monitoring-mass spectrometry (MRM-MS) analysis was performed to quantify protein targets regarding the two disorders in plasma samples of 270 individuals (90 MDD, 90 BD, and 90 healthy controls (HCs)). In the training set (72 MDD and 72 BD), a generalizable model comprising nine proteins was developed. The model was evaluated in the test set (18 MDD and 18 BD). The model demonstrated a good performance (area under the curve (AUC) >0.8) in discriminating MDD from BD in the training (AUC = 0.84) and test sets (AUC = 0.81) and in distinguishing MDD from BD without current hypomanic/manic/mixed symptoms (90 MDD and 75 BD) (AUC = 0.83). Subsequently, the model demonstrated excellent performance for drug-free MDD versus BD (11 MDD and 10 BD) (AUC = 0.96) and good performance for MDD versus HC (AUC = 0.87) and BD versus HC (AUC = 0.86). Furthermore, the nine proteins were associated with neuro, oxidative/nitrosative stress, and immunity/inflammation-related biological functions. This proof-of-concept study introduces a potential model for distinguishing between the two disorders.

Feature of Heart Rate Variability and Metabolic Mechanism in Female College Students with Depression

Purpose

To explore the effects of depression on cardiac autonomic nerve function and related metabolic pathways, the heart rate variability (HRV) and urinary differential metabolites were detected on the college students with depression.

Methods

12 female freshmen with depression were filtered by the Beck Depression Inventory (BDI-II) and Self-rating Depression Scale (SDS). By wearing an HRV monitoring system, time domain indexes and frequency domain indexes were measured over 24 hours. Liquid chromatography–mass spectrometry (LC-MS) was used to detect their urinary differential metabolites. Differential metabolites were identified by principal component analysis (PCA) and orthogonal projections to latent structures discriminant analysis (OPLS-DA). The metabolic pathways related to these differential metabolites were analyzed by the MetPA database.

Results

Stress time was significantly increased, and recovery time was markedly decreased in the depression group compared with the control group (p < 0.001). Standard deviation of the normal-to-normal R interval (SDNN), root mean square of the beat-to-beat differences (RMSSD), high frequency (HF), and low frequency (LF) were decreased significantly (p < 0.001). Standard deviation of the normal-to-normal R interval (SDNN), root mean square of the beat-to-beat differences (RMSSD), high frequency (HF), and low frequency (LF) were decreased significantly (

Conclusion

Some autonomic nervous system disruption, high stress, and poor fatigue recovery were confirmed in college students with depression. The metabolic mechanism involved the disruption of coenzyme Q biosynthesis, glycine-serine-threonine metabolism, tyrosine metabolism, pyrimidine metabolism, and steroid metabolism under daily stress.

Anxiety Disorders and the Brain's Resting State Networks: From Altered Spatiotemporal Synchronization to Psychopathological Symptoms

Anxiety disorders include a variety of different disorders including panic disorder (PD), social anxiety disorder (SAD), generalized anxiety disorder (GAD), and phobias. We here focus our review on GAD, SAD, and PD and put a specific emphasis on resting state networks and the coupling between the brain and the heart as all anxiety disorders exhibit abnormal perception of their own heartbeat in some way or the other. Resting state functional connectivity (rsFC) studies demonstrate abnormalities in default-mode network (DMN) in all anxiety disorders, e.g., mostly decreases in rsFC of DMN. In contrast, resting state fMRI shows increased rsFC in salience network (SN) (SAD, GAD) and/or somato-motor/sensory network (SMN) (PD). Since rsFC is coherence- or phase-based operating in the infraslow frequency domain (0.01-0.1 Hz), these data suggest spatiotemporal hypo- or hyper-synchronization in DMN and SMN/SN, respectively. These abnormalities in the neural network's spatiotemporal synchronization may, in turn, impact phase-based temporal synchronization of neural and cardiac activities resulting in decreased (DMN) or increased (SMN/SN) neuro-cardiac coupling in anxiety disorders. That, in turn, may be related to the various psychopathological symptoms like unstable sense of self (as based on unstable DMN showing spatiotemporal hypo-synchronization), increased emotions and specifically anxiety (as related to increased SN showing spatiotemporal hyper-synchronization), and increased bodily awareness (mediated by increased SMN with spatiotemporal hyper-synchronization) in anxiety disorders. Taken together, we here suggest altered spatiotemporal synchronization of neural and cardiac activity within the brain's resting state to underlie various psychopathological symptoms in anxiety disorders. Such spatiotemporal basis of psychopathological symptoms is well compatible with the recently suggested "Spatiotemporal Psychopathology."

Integrating proteomic, sociodemographic and clinical data to predict future depression diagnosis in subthreshold symptomatic individuals

Individuals with subthreshold depression have an increased risk of developing major depressive disorder (MDD). The aim of this study was to develop a prediction model to predict the probability of MDD onset in subthreshold individuals, based on their proteomic, sociodemographic and clinical data. To this end, we analysed 198 features (146 peptides representing 77 serum proteins (measured using MRM-MS), 22 sociodemographic factors and 30 clinical features) in 86 first-episode MDD patients (training set patient group), 37 subthreshold individuals who developed MDD within two or four years (extrapolation test set patient group), and 86 subthreshold individuals who did not develop MDD within four years (shared reference group). To ensure the development of a robust and reproducible model, we applied feature extraction and model averaging across a set of 100 models obtained from repeated application of group LASSO regression with ten-fold cross-validation on the training set. This resulted in a 12-feature prediction model consisting of six serum proteins (AACT, APOE, APOH, FETUA, HBA and PHLD), three sociodemographic factors (body mass index, childhood trauma and education level) and three depressive symptoms (sadness, fatigue and leaden paralysis). Importantly, the model demonstrated a fair performance in predicting future MDD diagnosis of subthreshold individuals in the extrapolation test set (AUC = 0.75), which involved going beyond the scope of the model. These findings suggest that it may be possible to detect disease indications in subthreshold individuals up to four years prior to diagnosis, which has important clinical implications regarding the identification and treatment of high-risk individuals.

Distinct Profiles of Cell-Free MicroRNAs in Plasma of Veterans with Post-Traumatic Stress Disorder

Dysregulation of circulating microRNAs (miRNAs) in body fluids has been reported in psychiatric disorders such as schizophrenia, bipolar disorder, major depressive disorder, and post-traumatic stress disorder (PTSD). Recent studies of various diseases showed that extracellular vesicles (EV) in body fluids can provide different spectra of circulating miRNAs and disease-associated signatures from whole fluid or EV-depleted fraction. However, the association of miRNAs in EVs to PTSD has not been studied. In this study, we performed a comprehensive profiling of miRNAs in whole plasma, extracellular vesicles (EV) and EV-depleted plasma (EVD) samples collected from combat veterans with PTSD and matched controls by utilizing a next-generation sequencing (NGS) platform. In total, 520 circulating miRNAs were quantified from 24 male Iraq and Afghanistan combat veterans with (n = 12) and without (n = 12) PTSD. The overall miRNA profiles in whole plasma, EV and EVD fractions were different and miRNAs affected by PTSD were also distinct in each sample type. The concentration changes of miR-203a-3p in EV and miR-339-5p in EVD were confirmed in an independent validation cohort that consisted of 20 veterans (10 with and 10 without PTSD) using qPCR. The target genes of these two miRNAs were involved in signaling pathways and comorbid conditions associated with PTSD (e.g., neurotransmitter systems such as dopaminergic and serotonergic signaling, inflammatory response, and cardiovascular diseases). Our findings suggest that PTSD may have different impacts on miRNAs encapsulated in vesicles and outside of vesicles. Further studies using larger samples are needed to evaluate the utility of these miRNAs as diagnostic biomarkers for PTSD.

Automatic detection of major depressive disorder using electrodermal activity

Major depressive disorder (MDD) is a common psychiatric disorder and the leading cause of disability worldwide. However, current methods used to diagnose depression mainly rely on clinical interviews and self-reported scales of depressive symptoms, which lack objectivity and efficiency. To address this challenge, we present a machine learning approach to screen for MDD using electrodermal activity (EDA). Participants included 30 patients with MDD and 37 healthy controls. Their EDA was measured during five experimental phases consisted of baseline, mental arithmetic task, recovery from the stress task, relaxation task, and recovery from the relaxation task, which elicited multiple alterations in autonomic activity. Selected EDA features were extracted from each phase, and differential EDA features between two distinct phases were evaluated. By using these features as input data and performing feature selection with SVM-RFE, 74% accuracy, 74% sensitivity, and 71% specificity could be achieved by our decision tree classifier. The most relevant features selected by SVM-RFE included differential EDA features and features from the stress and relaxation tasks. These findings suggest that automatic detection of depression based on EDA features is feasible and that monitoring changes in physiological signal when a subject is experiencing autonomic arousal and recovery may enhance discrimination power.

Heart Rate Variability as Indicator of Clinical State in Depression

Background: Depression is a severe disease with great burdens for the affected individuals and public health care systems. Autonomic nervous system (ANS) dysfunction indexed by measures of heart rate variability (HRV) has repeatedly been associated with depression. However, HRV parameters are subject to a wide range of multi-factorial influences and underlying mechanisms in depression are still unclear. HRV parameters have been proposed to be promising candidates for diagnostic or predictive bio-markers for depression but necessary longitudinal design studies investigating the relationship between HRV and depression are scarce. Methods: The sample in this study consisted of 62 depressive individuals without antidepressant medication prior to assessment and 65 healthy controls. Fifteen minute blocks of resting ECGs were recorded 1-2 days before onset of antidepressant treatment and 2 weeks thereafter. The ECGs were pre-processed to extract inter-beat-intervals. Linear and non-linear methods were used to extract HRV parameters. ANOVAS were performed to investigate group differences between depressive patients and healthy controls. Associations between the change in severity of depression and HRV parameters were assessed in a repeated measurements design. Results: Analyses revealed HRV parameter differences between the groups of depressive patients and healthy controls at baseline. Further results show differences in HRV parameters within subjects after 2 weeks of antidepressant treatment. Change in HRV parameter values correlated with changes in symptom severity of depression. Discussion: The current results provide further insight into the relationship between HRV parameters and depression. This may help to underpin utilization of HRV parameters are bio-maker for disease state in depression. Results are discussed within a theoretical framework to link arousal and ANS regulation in depression.

Proteomic Differences in Blood Plasma Associated with Antidepressant Treatment Response

The current inability of clinical psychiatry to objectively select the most appropriate treatment is a major factor contributing to the severity and clinical burden of major depressive disorder (MDD). Here, we have attempted to identify plasma protein signatures in 39 MDD patients to predict response over a 6-week treatment period with antidepressants. LC-MS/MS analysis showed that differences in the levels of 29 proteins at baseline were found in the group with a favorable treatment outcome. Most of these proteins were components of metabolism or immune response pathways as well as multiple components of the coagulation cascade. After 6 weeks of treatment, 43 proteins were altered in responders of which 2 (alpha-actinin and nardilysin) had been identified at baseline. In addition, 46 proteins were altered in non-responders and 9 of these (alpha-actinin, alpha-2-macroglobulin, apolipoprotein B-100, attractin, C-reactive protein, fibrinogen alpha chain, fibrinogen beta chain, nardilysin and serine/threonine-protein kinase Chk1) had been identified at baseline. However, it should be stressed that the small sample size precludes generalization of the main results. Further studies to validate these as potential biomarkers of antidepressant treatment response are warranted considering the potential importance to the field of psychiatric disorders. This study provides the groundwork for development of novel objective clinical tests that can help psychiatrists in the clinical management of MDD through improved prediction and monitoring of patient responses to antidepressant treatments.