Prediction of clinical depression scores and detection of changes in whole-brain using resting-state functional MRI data with partial least squares regression

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.

A deep learning approach for mental health quality prediction using functional network connectivity and assessment data

While one can characterize mental health using questionnaires, such tools do not provide direct insight into the underlying biology. By linking approaches that visualize brain activity to questionnaires in the context of individualized prediction, we can gain new insights into the biology and behavioral aspects of brain health. Resting-state fMRI (rs-fMRI) can be used to identify biomarkers of these conditions and study patterns of abnormal connectivity. In this work, we estimate mental health quality for individual participants using static functional network connectivity (sFNC) data from rs-fMRI. The deep learning model uses the sFNC data as input to predict four categories of mental health quality and visualize the neural patterns indicative of each group. We used guided gradient class activation maps (guided Grad-CAM) to identify the most discriminative sFNC patterns. The effectiveness of this model was validated using the UK Biobank dataset, in which we showed that our approach outperformed four alternative models by 4-18% accuracy. The proposed model's performance evaluation yielded a classification accuracy of 76%, 78%, 88%, and 98% for the excellent, good, fair, and poor mental health categories, with poor mental health accuracy being the highest. The findings show distinct sFNC patterns across each group. The patterns associated with excellent mental health consist of the cerebellar-subcortical regions, whereas the most prominent areas in the poor mental health category are in the sensorimotor and visual domains. Thus the combination of rs-fMRI and deep learning opens a promising path for developing a comprehensive framework to evaluate and measure mental health. Moreover, this approach had the potential to guide the development of personalized interventions and enable the monitoring of treatment response. Overall this highlights the crucial role of advanced imaging modalities and deep learning algorithms in advancing our understanding and management of mental health.

Multi-parametric MRI can detect enhanced myelination in the Gli1 -/- mouse brain

This study investigated the potential of combining multiple MR parameters to enhance the characterization of myelin in the mouse brain. We collected ex vivo multi-parametric MR data at 7 Tesla from control and Gli1 -/- mice; the latter exhibit enhanced myelination at postnatal day 10 (P10) in the corpus callosum and cortex. The MR data included relaxivity, magnetization transfer, and diffusion measurements, each targeting distinct myelin properties. This analysis was followed by and compared to myelin basic protein (MBP) staining of the same samples. Although a majority of the MR parameters included in this study showed significant differences in the corpus callosum between the control and Gli1 -/- mice, only T 2 , T 1 /T 2, and radial diffusivity (RD) demonstrated a significant correlation with MBP values. Based on data from the corpus callosum, partial least square regression suggested that combining T 2 , T 1 /T 2 , and inhomogeneous magnetization transfer ratio could explain approximately 80% of the variance in the MBP values. Myelin predictions based on these three parameters yielded stronger correlations with the MBP values in the P10 mouse brain corpus callosum than any single MR parameter. In the motor cortex, combining T 2 , T 1 /T 2, and radial kurtosis could explain over 90% of the variance in the MBP values at P10. This study demonstrates the utility of multi-parametric MRI in improving the detection of myelin changes in the mouse brain.

Aberrant resting-state co-activation network dynamics in major depressive disorder

Major depressive disorder (MDD) is a globally prevalent and highly disabling disease characterized by dysfunction of large-scale brain networks. Previous studies have found that static functional connectivity is not sufficient to reflect the complicated and time-varying properties of the brain. The underlying dynamic interactions between brain functional networks of MDD remain largely unknown, and it is also unclear whether neuroimaging-based dynamic properties are sufficiently robust to discriminate individuals with MDD from healthy controls since the diagnosis of MDD mainly depends on symptom-based criteria evaluated by clinical observation. Resting-state functional magnetic resonance imaging (fMRI) data of 221 MDD patients and 215 healthy controls were shared by REST-meta-MDD consortium. We investigated the spatial-temporal dynamics of MDD using co-activation pattern analysis and made individual diagnoses using support vector machine (SVM). We found that MDD patients exhibited aberrant dynamic properties (such as dwell time, occurrence rate, transition probability, and entropy of Markov trajectories) in some transient networks including subcortical network (SCN), activated default mode network (DMN), de-activated SCN-cerebellum network, a joint network, activated attention network (ATN), and de-activated DMN-ATN, where some dynamic properties were indicative of depressive symptoms. The trajectories of other networks to deactivated DMN-ATN were more accessible in MDD patients. Subgroup analyses also showed subtle dynamic changes in first-episode drug-naïve (FEDN) MDD patients. Finally, SVM achieved preferable accuracies of 84.69%, 76.77%, and 88.10% in discriminating patients with MDD, FEDN MDD, and recurrent MDD from healthy controls with their dynamic metrics. Our findings reveal that MDD is characterized by aberrant dynamic fluctuations of brain network and the feasibility of discriminating MDD patients using dynamic properties, which provide novel insights into the neural mechanism of MDD.

The diagnostic performance of machine learning based on resting-state functional magnetic resonance imaging data for major depressive disorders: a systematic review and meta-analysis

Objective

Machine learning (ML) has been widely used to detect and evaluate major depressive disorder (MDD) using neuroimaging data, i.e., resting-state functional magnetic resonance imaging (rs-fMRI). However, the diagnostic efficiency is unknown. The aim of the study is to conduct an updated meta-analysis to evaluate the diagnostic performance of ML based on rs-fMRI data for MDD.

Methods

English databases were searched for relevant studies. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) was used to assess the methodological quality of the included studies. A random-effects meta-analytic model was implemented to investigate the diagnostic efficiency, including sensitivity, specificity, diagnostic odds ratio (DOR), and area under the curve (AUC). Regression meta-analysis and subgroup analysis were performed to investigate the cause of heterogeneity.

Results

Thirty-one studies were included in this meta-analysis. The pooled sensitivity, specificity, DOR, and AUC with 95% confidence intervals were 0.80 (0.75, 0.83), 0.83 (0.74, 0.82), 14.00 (9, 22.00), and 0.86 (0.83, 0.89), respectively. Substantial heterogeneity was observed among the studies included. The meta-regression showed that the leave-one-out cross-validation (loocv) (sensitivity: p < 0.01, specificity: p < 0.001), graph theory (sensitivity: p < 0.05, specificity: p < 0.01), n > 100 (sensitivity: p < 0.001, specificity: p < 0.001), simens equipment (sensitivity: p < 0.01, specificity: p < 0.001), 3.0T field strength (Sensitivity: p < 0.001, specificity: p = 0.04), and Beck Depression Inventory (BDI) (sensitivity: p = 0.04, specificity: p = 0.06) might be the sources of heterogeneity. Furthermore, the subgroup analysis showed that the sample size (n > 100: sensitivity: 0.71, specificity: 0.72, n < 100: sensitivity: 0.81, specificity: 0.79), the different levels of disease evaluated by the Hamilton Depression Rating Scale (HDRS/HAMD) (mild vs. moderate vs. severe: sensitivity: 0.52 vs. 0.86 vs. 0.89, specificity: 0.62 vs. 0.78 vs. 0.82, respectively), the depression scales in patients with comparable levels of severity. (BDI vs. HDRS/HAMD: sensitivity: 0.86 vs. 0.87, specificity: 0.78 vs. 0.80, respectively), and the features (graph vs. functional connectivity: sensitivity: 0.84 vs. 0.86, specificity: 0.76 vs. 0.78, respectively) selected might be the causes of heterogeneity.

Conclusion

ML showed high accuracy for the automatic diagnosis of MDD. Future studies are warranted to promote the potential use of these classification algorithms in clinical settings.

Unsupervised cross-domain functional MRI adaptation for automated major depressive disorder identification

Resting-state functional magnetic resonance imaging (rs-fMRI) data have been widely used for automated diagnosis of brain disorders such as major depressive disorder (MDD) to assist in timely intervention. Multi-site fMRI data have been increasingly employed to augment sample size and improve statistical power for investigating MDD. However, previous studies usually suffer from significant inter-site heterogeneity caused for instance by differences in scanners and/or scanning protocols. To address this issue, we develop a novel discrepancy-based unsupervised cross-domain fMRI adaptation framework (called UFA-Net) for automated MDD identification. The proposed UFA-Net is designed to model spatio-temporal fMRI patterns of labeled source and unlabeled target samples via an attention-guided graph convolution module, and also leverage a maximum mean discrepancy constrained module for unsupervised cross-site feature alignment between two domains. To the best of our knowledge, this is one of the first attempts to explore unsupervised rs-fMRI adaptation for cross-site MDD identification. Extensive evaluation on 681 subjects from two imaging sites shows that the proposed method outperforms several state-of-the-art methods. Our method helps localize disease-associated functional connectivity abnormalities and is therefore well interpretable and can facilitate fMRI-based analysis of MDD in clinical practice.

Ensemble graph neural network model for classification of major depressive disorder using whole-brain functional connectivity

Major depressive disorder (MDD) is characterized by impairments in mood and cognitive functioning, and it is a prominent source of global disability and stress. A functional magnetic resonance imaging (fMRI) can aid clinicians in their assessments of individuals for the identification of MDD. Herein, we employ a deep learning approach to the issue of MDD classification. Resting-state fMRI data from 821 individuals with MDD and 765 healthy controls (HCs) is employed for investigation. An ensemble model based on graph neural network (GNN) has been created with the goal of identifying patients with MDD among HCs as well as differentiation between first-episode and recurrent MDDs. The graph convolutional network (GCN), graph attention network (GAT), and GraphSAGE models serve as a base models for the ensemble model that was developed with individual whole-brain functional networks. The ensemble's performance is evaluated using upsampling and downsampling, along with 10-fold cross-validation. The ensemble model achieved an upsampling accuracy of 71.18% and a downsampling accuracy of 70.24% for MDD and HC classification. While comparing first-episode patients with recurrent patients, the upsampling accuracy is 77.78% and the downsampling accuracy is 71.96%. According to the findings of this study, the proposed GNN-based ensemble model achieves a higher level of accuracy and suggests that our model produces can assist healthcare professionals in identifying MDD.

A Model of Normality Inspired Deep Learning Framework for Depression Relapse Prediction Using Audiovisual Data

BACKGROUND

Depression (Major Depressive Disorder) is one of the most common mental illnesses. According to the World Health Organization, more than 300 million people in the world are affected. A first depressive episode can be solved by a spontaneous remission within 6 to 12 months. It has been shown that depression affects speech production and facial expressions. Although numerous studies are proposed in the literature for depression recognition using audiovisual cues, depression relapse using audiovisual cues has not been studied in the literature.

METHOD

In this paper, we propose a deep learning-based approach for depression recognition and depression relapse prediction using audiovisual data. For more versatility and reusability, the proposed approach is based on a Model of Normality inspired framework where we define depression relapse by the closeness of the audiovisual patterns of a subject after a symptom-free period to the audiovisual patterns of depressed subjects. A model of Normality is an anomaly detection distance-based approach that computes a distance of normality between the deep audiovisual encoding of a test sample and a learned representation from audiovisual encodings of anomaly-free data.

RESULTS

The proposed approach shows a very promising results with an accuracy of 87.4% and a F1-score of 82.3% for relapse/depression prediction using a Leave-One-Subject-Out training strategy on the DAIC-Woz dataset.

CONCLUSION

The proposed model of normality-based framework is accurate in detecting depression and in predicting depression relapse. A prospective monitoring system is proposed for assisting depressed patients. The proposed framework is easily extensible and others modalities will be integrated in future works.

Cerebellar and basal ganglia motor network predicts trait depression and hyperactivity

In the human brain, the cerebellum (CB) and basal ganglia (BG) are implicated in cognition-, emotion-, and motor-related cortical processes and are highly interconnected, both to cortical regions via separate, trans-thalamic pathways and to each other via subcortical disynaptic pathways. We previously demonstrated a distinction between cognitive and motor CB-BG networks (CCBN, MCBN, respectively) as it relates to cortical network integration in healthy young adults, suggesting the subcortical networks separately support cortical networks. The CB and BG are also implicated in the pathophysiology of schizophrenia, Parkinson's, and compulsive behavior; thus, integration within subcortical CB-BG networks may be related to transdiagnostic symptomology. Here, we asked whether CCBN or MCBN integration predicted Achenbach Self-Report scores for anxiety, depression, intrusive thoughts, hyperactivity and inactivity, and cognitive performance in a community sample of young adults. We computed global efficiency for each CB-BG network and 7 canonical resting-state networks for all right-handed participants in the Human Connectome Project 1200 release with a complete set of preprocessed resting-state functional MRI data (N = 783). We used multivariate regression to control for substance abuse and age, and permutation testing with exchangeability blocks to control for family relationships. MCBN integration negatively predicted depression and hyperactivity, and positively predicted cortical network integration. CCBN integration predicted cortical network integration (except for the emotional network) and marginally predicted a positive relationship with hyperactivity, indicating a potential dichotomy between cognitive and motor CB-BG networks and hyperactivity. These results highlight the importance of CB-BG interactions as they relate to motivation and symptoms of depression.

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.

A neural network approach to optimising treatments for depression using data from specialist and community psychiatric services in Australia, New Zealand and Japan

This study investigated the application of a recurrent neural network for optimising pharmacological treatment for depression. A clinical dataset of 458 participants from specialist and community psychiatric services in Australia, New Zealand and Japan were extracted from an existing custom-built, web-based tool called Psynary . This data, which included baseline and self-completed reviews, was used to train and refine a novel algorithm which was a fully connected network feature extractor and long short-term memory algorithm was firstly trained in isolation and then integrated and annealed using slow learning rates due to the low dimensionality of the data. The accuracy of predicting depression remission before processing patient review data was 49.8%. After processing only 2 reviews, the accuracy was 76.5%. When considering a change in medication, the precision of changing medications was 97.4% and the recall was 71.4% . The medications with predicted best results were antipsychotics (88%) and selective serotonin reuptake inhibitors (87.9%). This is the first study that has created an all-in-one algorithm for optimising treatments for all subtypes of depression. Reducing treatment optimisation time for patients suffering with depression may lead to earlier remission and hence reduce the high levels of disability associated with the condition. Furthermore, in a setting where mental health conditions are increasing strain on mental health services, the utilisation of web-based tools for remote monitoring and machine/deep learning algorithms may assist clinicians in both specialist and primary care in extending specialist mental healthcare to a larger patient community.

Resting-state brain activity can predict target-independent aptitude in fMRI-neurofeedback training

Neurofeedback (NF) aptitude, which refers to an individual's ability to change brain activity through NF training, has been reported to vary significantly from person to person. The prediction of individual NF aptitudes is critical in clinical applications to screen patients suitable for NF treatment. In the present study, we extracted the resting-state functional brain connectivity (FC) markers of NF aptitude, independent of NF-targeting brain regions. We combined the data from fMRI-NF studies targeting four different brain regions at two independent sites (obtained from 59 healthy adults and six patients with major depressive disorder) to collect resting-state fMRI data associated with aptitude scores in subsequent fMRI-NF training. We then trained the multiple regression models to predict the individual NF aptitude scores from the resting-state fMRI data using a discovery dataset from one site and identified six resting-state FCs that predicted NF aptitude. Subsequently, the reproducibility of the prediction model was validated using independent test data from another site. The identified FC model revealed that the posterior cingulate cortex was the functional hub among the brain regions and formed predictive resting-state FCs, suggesting that NF aptitude may be involved in the attentional mode-orientation modulation system's characteristics in task-free resting-state brain activity.

Machine Learning-Based Definition of Symptom Clusters and Selection of Antidepressants for Depressive Syndrome

The current polythetic and operational criteria for major depression inevitably contribute to the heterogeneity of depressive syndromes. The heterogeneity of depressive syndrome has been criticized using the concept of language game in Wittgensteinian philosophy. Moreover, “a symptom- or endophenotype-based approach, rather than a diagnosis-based approach, has been proposed” as the “next-generation treatment for mental disorders” by Thomas Insel. Understanding the heterogeneity renders promise for personalized medicine to treat cases of depressive syndrome, in terms of both defining symptom clusters and selecting antidepressants. Machine learning algorithms have emerged as a tool for personalized medicine by handling clinical big data that can be used as predictors for subtype classification and treatment outcome prediction. The large clinical cohort data from the Sequenced Treatment Alternatives to Relieve Depression (STAR*D), Combining Medications to Enhance Depression Outcome (CO-MED), and the German Research Network on Depression (GRND) have recently began to be acknowledged as useful sources for machine learning-based depression research with regard to cost effectiveness and generalizability. In addition, noninvasive biological tools such as functional and resting state magnetic resonance imaging techniques are widely combined with machine learning methods to detect intrinsic endophenotypes of depression. This review highlights recent studies that have used clinical cohort or brain imaging data and have addressed machine learning-based approaches to defining symptom clusters and selecting antidepressants. Potentially applicable suggestions to realize machine learning-based personalized medicine for depressive syndrome are also provided herein.

Semi-supervised random forest regression model based on co-training and grouping with information entropy for evaluation of depression symptoms severity

Semi-supervised learning has always been a hot topic in machine learning. It uses a large number of unlabeled data to improve the performance of the model. This paper combines the co-training strategy and random forest to propose a novel semi-supervised regression algorithm: semi-supervised random forest regression model based on co-training and grouping with information entropy (E-CoGRF), and applies it to the evaluation of depression symptoms severity. The algorithm inherits the ensemble characteristics of random forest, and combines well with co-training. In order to balance the accuracy and diversity of co-training random forests, the algorithm proposes a grouping strategy to decision trees. Moreover, the information entropy is used to measure the confidence, which avoids unnecessary repeated training and improves the efficiency of the model. In the practical application of evaluation of depression symptoms severity, we collect cognitive behavioral data of emotional conflict based on the depressive affective disorder. And on this basis, feature construction and normalization preprocessing are carried out. Finally, the test is conducted on 35 labeled and 80 unlabeled depression patients. The result shows that the proposed algorithm obtains MAE (Mean Absolute Error) = 3.63 and RMSE (Root Mean Squared Error) = 4.50, which is better than other semi-supervised regression algorithms. The proposed method effectively solves the modeling difficulties caused by insufficient labeled samples, and has important reference value for the diagnosis of depression symptoms severity.

Resting-state brain metabolic fingerprinting clusters (biomarkers) and predictive models for major depression in multiple myeloma patients

Background

Major depression is a common comorbidity in cancer patients. Oncology clinics lack practical, objective tools for simultaneous evaluation of cancer and major depression. Fludeoxyglucose F-18 positron emission tomography–computed tomography (FDG PET/CT) is universally applied in modern medicine.

Methods

We used a retrospective analysis of whole-body FDG PET/CT images to identify brain regional metabolic patterns of major depression in multiple myeloma patients. The study included 134 multiple myeloma (MM) patients, 38 with major depression (group 1) and 96 without major depression (group 2).

Results

In the current study, Statistic Parameter Mapping (SPM) demonstrated that the major depression patient group (n = 38) had significant regional metabolic differences (clusters of continuous voxels) as compared to the non-major depression group (n = 96) with the criteria of height threshold T = 4.38 and extent threshold > 100 voxels. The five significant hypo- and three hyper-metabolic clusters from the computed T contrast maps were localized on the glass-brain view, consistent with published brain metabolic changes in major depression patients. Subsequently, using these clusters as features for classification learner, the fine tree and medium tree algorithms from 25 classification algorithms best fitted our data (accuracy 0.85%; AUC 0.88; sensitivity 79%; and specificity 88%).

Conclusion

This study demonstrated that whole-body FDG PET/CT scans could provide added value for screening for major depression in cancer patients in addition to staging and evaluating response to chemoradiation therapies.

Translational application of neuroimaging in major depressive disorder: a review of psychoradiological studies

Major depressive disorder (MDD) causes great decrements in health and quality of life with increments in healthcare costs, but the causes and pathogenesis of depression remain largely unknown, which greatly prevent its early detection and effective treatment. With the advancement of neuroimaging approaches, numerous functional and structural alterations in the brain have been detected in MDD and more recently attempts have been made to apply these findings to clinical practice. In this review, we provide an updated summary of the progress in translational application of psychoradiological findings in MDD with a specified focus on potential clinical usage. The foreseeable clinical applications for different MRI modalities were introduced according to their role in disorder classification, subtyping, and prediction. While evidence of cerebral structural and functional changes associated with MDD classification and subtyping was heterogeneous and/or sparse, the ACC and hippocampus have been consistently suggested to be important biomarkers in predicting treatment selection and treatment response. These findings underlined the potential utility of brain biomarkers for clinical practice.

Personality classification enhances blood metabolome analysis and biotyping for major depressive disorders: two-species investigation

BACKGROUND

The relationship between depression and personality has long been suggested, however, biomarker investigations for depression have mostly overlooked this connection.

METHODS

We collected personality traits from 100 drug-free patients with major depressive disorders (MDD) and 100 healthy controls based on the Five-Factor Model (FFM) such as Neuroticism (N) and Extraversion (E), and also obtained 63 plasma metabolites profiles by LCMS-based metabolome analysis.

RESULTS

Partitional clustering analysis using the NEO-FFI data classified all subjects into three major clusters. Eighty-six subjects belonging to Cluster 1 (C1: less personality-biased group) constituted half of MDD patients and half of healthy controls. C2 constituted 50 subjects mainly MDD patients (N ^high + E ^low), and C3 constituted 64 subjects mainly healthy subjects (N ^low + E ^high). Using metabolome information, the machine learning model was optimized to discriminate MDD patients from healthy controls among all subjects and C1, respectively. The performance of the model for all subjects was moderate (AUC = 0. 715), while the performance was extremely improved when limited to C1 (AUC = 0. 907). Tryptophan-pathway plasma metabolites including tryptophan, serotonin and kynurenine were significantly lower in MDD patients especially among C1. We also validated metabolomic findings using a social-defeat mice model of stress-induced depression.

LIMITATIONS

A case-control study design and sample size is not large.

CONCLUSIONS

Our results suggest that personality classification enhances blood biomarker analysis for MDD patients and further translational investigations should be conducted to clarify the biological relationship between personality traits, stress and depression.

The Value of Neuroimaging Techniques in the Translation and Transdiagnostic Validation of Psychiatric Diagnoses - Selective Review

Psychiatric diagnosis has long been perceived as more of an art than a science since its foundations lie within the observation, and the self-report of the patients themselves and objective diagnostic biomarkers are lacking. Furthermore, the diagnostic tools in use not only stray away from the conventional medical framework but also remain invalidated with evidence-based concepts. However, neuroscience, as a source of valid objective knowledge has initiated the process of a paradigm shift underlined by the main concept of psychiatric disorders being "brain disorders". It is also a bridge closing the explanatory gap among the different fields of medicine via the translation of the knowledge within a multidisciplinary framework. The contemporary neuroimaging methods, such as fMRI provide researchers with an entirely new set of tools to reform the current status quo by creating an opportunity to define and validate objective biomarkers that can be translated into clinical practice. Combining multiple neuroimaging techniques with the knowledge of the role of genetic factors, neurochemical imbalance and neuroinflammatory processes in the etiopathophysiology of psychiatric disorders is a step towards a comprehensive biological explanation of psychiatric disorders and a final differentiation of psychiatry as a well-founded medical science. In addition, the neuroscientific knowledge gained thus far suggests a necessity for directional change to exploring multidisciplinary concepts, such as multiple causality and dimensionality of psychiatric symptoms and disorders. A concomitant viewpoint transition of the notion of validity in psychiatry with a focus on an integrative validatory approach may facilitate the building of a collaborative bridge above the wall existing between the scientific fields analyzing the mind and those studying the brain.

Common Brain Networks Between Major Depressive-Disorder Diagnosis and Symptoms of Depression That Are Validated for Independent Cohorts

Large-scale neuroimaging data acquired and shared by multiple institutions are essential to advance neuroscientific understanding of pathophysiological mechanisms in psychiatric disorders, such as major depressive disorder (MDD). About 75% of studies that have applied machine learning technique to neuroimaging have been based on diagnoses by clinicians. However, an increasing number of studies have highlighted the difficulty in finding a clear association between existing clinical diagnostic categories and neurobiological abnormalities. Here, using resting-state functional magnetic resonance imaging, we determined and validated resting-state functional connectivity related to depression symptoms that were thought to be directly related to neurobiological abnormalities. We then compared the resting-state functional connectivity related to depression symptoms with that related to depression diagnosis that we recently identified. In particular, for the discovery dataset with 477 participants from 4 imaging sites, we removed site differences using our recently developed harmonization method and developed a brain network prediction model of depression symptoms (Beck Depression Inventory-II [BDI] score). The prediction model significantly predicted BDI score for an independent validation dataset with 439 participants from 4 different imaging sites. Finally, we found 3 common functional connections between those related to depression symptoms and those related to MDD diagnosis. These findings contribute to a deeper understanding of the neural circuitry of depressive symptoms in MDD, a hetero-symptomatic population, revealing the neural basis of MDD.

Prediction of Depression Severity Scores Based on Functional Connectivity and Complexity of the EEG Signal

BACKGROUND

Depression is one of the most common mental disorders and the leading cause of functional disabilities. This study aims to specify whether functional connectivity and complexity of brain activity can predict the severity of depression (Beck Depression Inventory-II scores).

METHODS

Resting-state, eyes-closed EEG data were recorded from 60 depressed patients. A phase synchronization measure was used to estimate functional connectivity between all pairs of the EEG channels in the delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), and beta (13-30 Hz) frequency bands. To quantify the local value of functional connectivity, 2 graph theory metrics, degree, and clustering coefficient (CC), were measured. Moreover, Lempel-Ziv complexity (LZC) and fuzzy entropy (FuzzyEn) were used to measure the complexity of the EEG signal.

RESULTS

Through correlation analysis, a significant negative relationship was found between graph metrics and depression severity in the alpha band. This association was strongly positive for the complexity measures in alpha and delta bands. Also, the linear regression model represented a substantial performance of depression severity prediction based on EEG features of the alpha band (r = 0.839; P < .0001, root mean square error score of 7.69).

CONCLUSION

We found that the brain activity of patients with depression was related to depression severity. Abnormal brain activity reflects an increase in the severity of depression. The presented regression model provides a quantitative depression severity prediction, which can inform the development of EEG state and exhibit potential desirable application for the medical treatment of the depressive disorder.

Memory enhancement in Argentinian women during postpartum by the dietary intake of lignans and anthocyanins

Due to their polyphenolic content, vegetable foods have neuroprotective effects which provide health benefits for specific human groups. Thus, they may be a useful dietary component for women who experience mnesic variations during postpartum, and here we examined the hypothesis that polyphenols can differentially enhance memory functioning. In particular, we aimed to associate the dietary intake of polyphenols with different memory systems in Argentinian postpartum women. The daily intakes of polyphenol groups were calculated using a validated food frequency questionnaire and the Phenol-Explorer database. Short-term memory (STM), long-term memory (LTM), learning (L), lexical-semantic memory (LSM), and working memory (WM) were assessed. Partial Least Squares (PLS) regression models were used to analyze the dietary polyphenols (predictors) and memory domains (responses), taking into account demographic, obstetric, and psychological factors. The sample included 71 women, with an average age of 29.59 years (SE = 0.73). Most of these women lived in a couple (91%), were unemployed (63%), and had ≥12 years of formal education (72%). STM, LTM, L, and LSM correlated with lignans and anthocyanins, with LTM also being correlated with flavanones, flavonols, and tyrosols, and L and LSM also being associated with flavonols. A significant correlation was also found between WM and lignans. In conclusion, a cognitive improvement was demonstrated, mainly associated with the intake of lignans and anthocyanins, in the STM, LTM, WM, L, and LSM systems of postpartum women. This is the first study to our knowledge suggesting a role of polyphenolic effects on memory functioning during postpartum.

Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises

The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move toward a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continuously behavioral phenotype from neuroimaging data, opening up an exciting opportunity to describe the human brain at the single-subject level. In this survey, we provide an overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade. We first review regression-based approaches and highlight connectome-based predictive modeling, which has grown in popularity in recent years. Next, we systematically describe recent representative studies using these tools in the context of cognitive function, symptom severity, personality traits, and emotion processing. Finally, we highlight a few challenges related to combining multimodal data, longitudinal prediction, external validations, and the employment of deep learning methods that have emerged from our review of the existing literature, as well as present some promising and challenging future directions.

Anhedonia in chronic pain and prescription opioid misuse

BACKGROUND

Both acute and chronic pain can disrupt reward processing. Moreover, prolonged prescription opioid use and depressed mood are common in chronic pain samples. Despite the prevalence of these risk factors for anhedonia, little is known about anhedonia in chronic pain populations.

METHODS

We conducted a large-scale, systematic study of anhedonia in chronic pain, focusing on its relationship with opioid use/misuse, pain severity, and depression. Chronic pain patients across four distinct samples (N = 488) completed the Snaith-Hamilton Pleasure Scale (SHAPS), measures of opioid use, pain severity and depression, as well as the Current Opioid Misuse Measure (COMM). We used a meta-analytic approach to determine reference levels of anhedonia in healthy samples spanning a variety of countries and diverse age groups, extracting SHAPS scores from 58 published studies totaling 2664 psychiatrically healthy participants.

RESULTS

Compared to healthy samples, chronic pain patients showed higher levels of anhedonia, with ~25% of patients scoring above the standard anhedonia cut-off. This difference was not primarily driven by depression levels, which explained less than 25% of variance in anhedonia scores. Neither opioid use duration, dose, nor pain severity alone was significantly associated with anhedonia. Yet, there was a clear effect of opioid misuse, with opioid misusers (COMM ⩾13) reporting greater anhedonia than non-misusers. Opioid misuse remained a significant predictor of anhedonia even after controlling for pain severity, depression and opioid dose.

CONCLUSIONS

Study results suggest that both chronic pain and opioid misuse contribute to anhedonia, which may, in turn, drive further pain and misuse.

Identifying resting-state effective connectivity abnormalities in drug-naïve major depressive disorder diagnosis via graph convolutional networks

Major depressive disorder (MDD) is a leading cause of disability; its symptoms interfere with social, occupational, interpersonal, and academic functioning. However, the diagnosis of MDD is still made by phenomenological approach. The advent of neuroimaging techniques allowed numerous studies to use resting-state functional magnetic resonance imaging (rs-fMRI) and estimate functional connectivity for brain-disease identification. Recently, attempts have been made to investigate effective connectivity (EC) that represents causal relations among regions of interest. In the meantime, to identify meaningful phenotypes for clinical diagnosis, graph-based approaches such as graph convolutional networks (GCNs) have been leveraged recently to explore complex pairwise similarities in imaging/nonimaging features among subjects. In this study, we validate the use of EC for MDD identification by estimating its measures via a group sparse representation along with a structured equation modeling approach in a whole-brain data-driven manner from rs-fMRI. To distinguish drug-naïve MDD patients from healthy controls, we utilize spectral GCNs based on a population graph to successfully integrate EC and nonimaging phenotypic information. Furthermore, we devise a novel sensitivity analysis method to investigate the discriminant connections for MDD identification in our trained GCNs. Our experimental results validated the effectiveness of our method in various scenarios, and we identified altered connectivities associated with the diagnosis of MDD.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

Depression Scale Prediction with Cross-Sample Entropy and Deep Learning

A two-stage deep learning-based scheme is presented to predict the Hamilton Depression Scale (HAM-D) in this study. First, the cross-sample entropy (CSE) that allows assessing the degree of similarity of two data series are evaluated for the 90 brain regions of interest partitioned according to Automated Anatomical Labeling. The obtained CSE maps are then converted to 3D CSE volumes to serve as the inputs to the deep learning network models for the HAM-D scale level classification and prediction. The efficacy of the proposed scheme was illustrated by the resting-state functional magnetic resonance imaging data from 38 patients. From the results, the root mean square errors for the HAM-D scale prediction obtained during training, validation, and testing were 2.73, 2.66, and 2.18, which were less than those of a scheme having only a regression stage.

Quantitative Identification of Major Depression Based on Resting-State Dynamic Functional Connectivity: A Machine Learning Approach

Introduction

Developing a machine learning-based approach which could provide quantitative identification of major depressive disorder (MDD) is essential for the diagnosis and intervention of this disorder. However, the performances of traditional algorithms using static functional connectivity (SFC) measures were unsatisfactory. In the present work, we exploit the hidden information embedded in dynamic functional connectivity (DFC) and developed an accurate and objective image-based diagnosis system for MDD.

Methods

MRI images were collected from 99 participants including 56 healthy controls and 43 MDD patients. DFC was calculated using a sliding-window algorithm. A non-linear support vector machine (SVM) approach was then used with the DFC matrices as features to distinguish MDD patients from healthy controls. The spatiotemporal characteristics of the most discriminative features were then investigated.

Results

The area under the curve (AUC) of the SVM classifier with DFC measures reached 0.9913, while this value is only 0.8685 for the algorithm using SFC measures. Spatially, the most discriminative 28 connections distributed in the visual network (VN), somatomotor network (SMN), dorsal attention network (DAN), ventral attention network (VAN), limbic network (LN), frontoparietal network (FPN), and default mode network (DMN), etc. Notably, a large portion of these connections were associated with the FPN, DMN, and VN. Temporally, the most discriminative connections transited from the cortex to deeper regions.

Conclusion

The results clearly suggested that DFC is superior to SFC and provide a reliable quantitative identification method for MDD. Our findings may furnish a better understanding of the neural mechanisms of MDD as well as improve accurate diagnosis and early intervention of this disorder.

Enhancing Multi-Center Generalization of Machine Learning-Based Depression Diagnosis From Resting-State fMRI

Resting-state fMRI has the potential to help doctors detect abnormal behavior in brain activity and to diagnose patients with depression. However, resting-state fMRI has a bias depending on the scanner site, which makes it difficult to diagnose depression at a new site. In this paper, we propose methods to improve the performance of the diagnosis of major depressive disorder (MDD) at an independent site by reducing the site bias effects using regression. For this, we used a subgroup of healthy subjects of the independent site to regress out site bias. We further improved the classification performance of patients with depression by focusing on melancholic depressive disorder. Our proposed methods would be useful to apply depression classifiers to subjects at completely new sites.

Partial Least Squares Regression Performs Well in MRI-Based Individualized Estimations

Estimation of individuals' cognitive, behavioral and demographic (CBD) variables based on MRI has attracted much research interest in the past decade, and effective machine learning techniques are of great importance for these estimations. Partial least squares regression (PLSR) is an attractive machine learning technique that can accommodate both single- and multi-label learning in a simple framework, while its potential for MRI-based estimations of CBD variables remains to be explored. In this study, we systemically investigated the performance of PLSR in MRI-based estimations of individuals' CBD variables, especially its performance in simultaneous estimation of multiple CBD variables (multi-label learning). We performed the study on the dataset included in the HCP S1200 release. Resting state functional connections (RSFCs) were used as features, and a total of 10 CBD variables (e.g., age, gender, grip strength, and picture vocabulary) were estimated. The results showed that PLSR performed well in both single- and multi-label learning. In fact, the present estimations were better than those reported in literatures, as indicated by stronger correlations between the estimated and actual CBD variables, as well as high gender classification accuracy (97.8% in this study). Moreover, the RSFCs that contributed to the estimations exhibited strong correlations with the CBD variable estimated, that is, PLSR algorithm automatically selected the RSFCs closely related to one CBD variable to establish predictive models for the variable. Besides, the estimation accuracies based on RSFCs among 100, 200, and 300 regions of interest (ROIs) were higher than those based on RSFCs among 15, 25, and 50 ROIs; the estimation accuracies based on RSFCs evaluated using partial correlation were higher than those based on RSFCs evaluated using full correlation. In addition to the aforementioned virtues, PLSR is efficient in model training and testing, and it is simple and easy to use. Therefore, PLSR can be a favorable choice for future MRI-based estimations of CBD variables.

Hub distribution of the brain functional networks of newborns prenatally exposed to maternal depression and SSRI antidepressants

BACKGROUND

Prenatal maternal depression (PMD) and selective serotonin reuptake inhibitor (SSRI) antidepressants are associated with increased developmental risk in infants. Reports suggest that PMD is associated with hyperconnectivity of the insula and the amygdala, while SSRI exposure is associated with hyperconnectivity of the auditory network in the infant brain. However, associations between functional brain organization and PMD and/or SSRI exposure are not well understood.

METHODS

We examined the relation between PMD or SSRI exposure and neonatal brain functional organization. Infants of control (n = 17), depressed SSRI-treated (n = 20) and depressed-only (HAM-D ≥ 8) (n = 16) women, underwent resting-state functional magnetic resonance imaging at postnatal Day 6. At 6 months, temperament was assessed using Infant Behavioral Questionnaire (IBQ). We applied GTA and partial least square regression (PLSR) to the resting-state time series to assess group differences in modularity, and connector and provincial hubs.

RESULTS

Modularity was similar across all groups. The depressed-only group showed higher connector hub values in the left anterior cingulate, insula, and caudate as well as higher provincial hub values in the amygdala compared to the control group. The SSRI group showed higher provincial hub values in Heschl's gyrus relative to the depressed-only group. PLSR showed that newborns' hub values predicted 10% of the variability in infant temperament at 6 months, suggesting different developmental patterns between groups.

CONCLUSIONS

Prenatal exposures to maternal depression and SSRIs have differential impacts on neonatal functional brain organization. Hub values at 6 days predict variance in temperament between infant groups at 6 months of age.

Machine learning in major depression: From classification to treatment outcome prediction

AIMS

Major depression disorder (MDD) is the single greatest cause of disability and morbidity, and affects about 10% of the population worldwide. Currently, there are no clinically useful diagnostic biomarkers that are able to confirm a diagnosis of MDD from bipolar disorder (BD) in the early depressive episode. Therefore, exploring translational biomarkers of mood disorders based on machine learning is in pressing need, though it is challenging, but with great potential to improve our understanding of these disorders.

DISCUSSIONS

In this study, we review popular machine-learning methods used for brain imaging classification and predictions, and provide an overview of studies, specifically for MDD, that have used magnetic resonance imaging data to either (a) classify MDDs from controls or other mood disorders or (b) investigate treatment outcome predictors for individual patients. Finally, challenges, future directions, and potential limitations related to MDD biomarker identification are also discussed, with a goal of offering a comprehensive overview that may help readers to better understand the applications of neuroimaging data mining in depression.

CONCLUSIONS

We hope such efforts may highlight the need for an urgently needed paradigm shift in treatment, to guide personalized optimal clinical care.

Exploring the prediction of emotional valence and pharmacologic effect across fMRI studies of antidepressants

Background

Clinically approved antidepressants modulate the brain's emotional valence circuits, suggesting that the response of these circuits could serve as a biomarker for screening candidate antidepressant drugs. However, it is necessary that these modulations can be reliably detected. Here, we apply a cross-validated predictive model to classify emotional valence and pharmacologic effect across eleven task-based fMRI datasets (n = 306) exploring the effect of antidepressant administration on emotional face processing.

Methods

We created subject-level contrast of parameter estimates of the emotional faces task and used the Shen whole-brain parcellation scheme to define 268 subject-level features that trained a cross-validated gradient-boosting machine protocol to classify emotional valence (fearful vs happy face visual conditions) and pharmacologic effect (drug vs placebo administration) within and across studies.

Results

We found patterns of brain activity that classify emotional valence with a statistically significant level of accuracy (70% across-all-subjects; range from 50 to 87% across-study). Our classifier failed to consistently discriminate drug from placebo. Subject population (healthy or unhealthy), treatment group (drug or placebo), and drug administration protocol (dose and duration) affected this accuracy with similar populations better predicting one another.

Conclusions

We found limited evidence that antidepressants modulated brain response in a consistent manner, however found a consistent signature for emotional valence. Variable functional patterns across studies suggest that predictive modeling can inform biomarker development in mental health and in pharmacotherapy development. Our results suggest that case-controlled designs and more standardized protocols are required for functional imaging to provide robust biomarkers for drug development.

•

The emotional faces task can evaluate the brain's fMRI response to antidepressants.

•

We found a consistent signature for emotional valence across 11 such datasets.

•

We found limited evidence for consistent antidepressant response.

•

Case-controlled designs and more standardized protocols could increase this yield.

A novel gene-expression-signature-based model for prediction of response to Tripterysium glycosides tablet for rheumatoid arthritis patients

Background

Approximately 30% of rheumatoid arthritis (RA) patients treated with Tripterysium glycosides (TG) tablets fail to achieve clinical improvement, implying the essentiality of predictive biomarkers and tools. Herein, we aimed to identify possible biomarkers predictive of therapeutic effects of TG tablets in RA.

Methods

Gene expression profile in peripheral blood mononuclear cells obtained from a discovery cohort treated with TG tablets was detected by Affymetrix EG1.0 arrays. Then, a list of candidate gene biomarkers of response to TG tablets were identified by integrating differential expression data analysis and gene signal transduction network analysis. After that, a partial-least-squares (PLS) model based on the expression levels of the candidate gene biomarkers in RA patients was constructed and evaluated using a validation cohort.

Results

Six candidate gene biomarkers (MX1, OASL, SPINK1, CRK, GRAPL and RNF2) were identified to be predictors of TG therapy. Following the construction of a PLS-based model using their expression levels in peripheral blood, both the 5-fold cross-validation and independent dataset validations showed the high predictive efficiency of this model, and demonstrated a distinguished improvement of the PLS-model based on six candidate gene biomarkers’ expression in combination over the commonly used clinical and inflammatory parameters, as well as the gene biomarkers alone, in predicting RA patients’ response to TG tablets.

Conclusions

This hypothesis-generating study identified MX1, OASL, SPINK1, CRK, GRAPL and RNF2 as novel targets for RA therapeutic intervention, and the PLS model based on the expression levels of these candidate biomarkers may have a potential prognostic value in RA patients treated with TG tablets.

Electronic supplementary material

The online version of this article (10.1186/s12967-018-1549-9) contains supplementary material, which is available to authorized users.