Leveraging Machine Learning Approaches for Predicting Antidepressant Treatment Response Using Electroencephalography (EEG) and Clinical Data

Fractal Analysis of Electrophysiological Signals to Detect and Monitor Depression: What We Know So Far?

Depression is currently one of the most complicated public health problems with the rising number of patients, increasing partly due to pandemics, but also due to increased existential insecurities and complicated aetiology of disease. Besides the tsunami of mental health issues, there are limitations imposed by ambiguous clinical rules of assessment of the symptoms and obsolete and inefficient standard therapy approaches. Here we are summarizing the neuroimaging results pointing out the actual complexity of the disease and novel attempts to detect depression that are evidence-based, mostly related to electrophysiology. It is repeatedly shown that the complexity of resting-state EEG recorded in patients suffering from depression is increased compared to healthy controls. We are discussing here how that can be interpreted and what we can learn about future effective therapies. Also, there is evidence that novel options of treatment, like different modalities of electromagnetic stimulation, are successful just because they are capable of decreasing that aberrated complexity. And complexity measures extracted from electrophysiological signals of depression patients can serve as excellent features for further machine learning models in order to automatize detection. In addition, after initial detection and even selection of responders for further therapy route, it is possible to monitor the therapeutic flow for one person, which leads us to possible tailored treatment for patients suffering from depression.

Non-linear processing and reinforcement learning to predict rTMS treatment response in depression

BACKGROUND

Forecasting the efficacy of repetitive transcranial magnetic stimulation (rTMS) therapy can lead to substantial time and cost savings by preventing futile treatments. To achieve this objective, we've formulated a machine learning approach aimed at categorizing patients with major depressive disorder (MDD) into two groups: individuals who respond (R) positively to rTMS treatment and those who do not respond (NR).

METHODS

Preceding the commencement of treatment, we obtained resting-state EEG data from 106 patients diagnosed with MDD, employing 32 electrodes for data collection. These patients then underwent a 7-week course of rTMS therapy, and 54 of them exhibited positive responses to the treatment. Employing Independent Component Analysis (ICA) on the EEG data, we successfully pinpointed relevant brain sources that could potentially serve as markers of neural activity within the dorsolateral prefrontal cortex (DLPFC). These identified sources were further scrutinized to estimate the sources of activity within the sensor domain. Then, we integrated supplementary physiological data and implemented specific criteria to yield more realistic estimations when compared to conventional EEG analysis. In the end, we selected components corresponding to the DLPFC region within the sensor domain. Features were derived from the time-series data of these relevant independent components. To identify the most significant features, we used Reinforcement Learning (RL). In categorizing patients into two groups - R and NR to rTMS treatment - we utilized three distinct classification algorithms including K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Multilayer Perceptron (MLP). We assessed the performance of these classifiers through a ten-fold cross-validation method. Additionally, we conducted a statistical test to evaluate the discriminative capacity of these features between responders and non-responders, opening the door for further exploration in this field.

RESULTS

We identified EEG features that can anticipate the response to rTMS treatment. The most robust discriminators included EEG beta power, the sum of bispectrum diagonal elements in the delta and beta frequency bands. When these features were combined into a single vector, the classification of responders and non-responders achieved impressive performance, with an accuracy of 95.28 %, specificity at 94.23 %, sensitivity reaching 96.29 %, and precision standing at 94.54 %, all achieved using SVM.

CONCLUSIONS

The results of this study suggest that the proposed approach, utilizing power, non-linear, and bispectral features extracted from relevant independent component time-series, has the capability to forecast the treatment outcome of rTMS for MDD patients based solely on a single pre-treatment EEG recording session. The achieved findings demonstrate the superior performance of our method compared to previous techniques.

Neurosteroids: mechanistic considerations and clinical prospects

Like other classes of treatments described in this issue's section, neuroactive steroids have been studied for decades but have risen as a new class of rapid-acting, durable antidepressants with a distinct mechanism of action from previous antidepressant treatments and from other compounds covered in this issue. Neuroactive steroids are natural derivatives of progesterone but are proving effective as exogenous treatments. The best understood mechanism is that of positive allosteric modulation of GABAA receptors, where subunit selectivity may promote their profile of action. Mechanistically, there is some reason to think that neuroactive steroids may separate themselves from liabilities of other GABA modulators, although research is ongoing. It is also possible that intracellular targets, including inflammatory pathways, may be relevant to beneficial actions. Strengths and opportunities for further development include exploiting non-GABAergic targets, structural analogs, enzymatic production of natural steroids, precursor loading, and novel formulations. The molecular mechanisms of behavioral effects are not fully understood, but study of brain network states involved in emotional processing demonstrate a robust influence on affective states not evident with at least some other GABAergic drugs including benzodiazepines. Ongoing studies with neuroactive steroids will further elucidate the brain and behavioral effects of these compounds as well as likely underpinnings of disease.

Predicting acupuncture efficacy for major depressive disorder using baseline clinical variables: A machine learning study

Acupuncture is a viable treatment option for major depressive disorder (MDD). However, its effectiveness varies among patients. This study aimed to develop a model to predict the efficacy of acupuncture therapy for MDD using machine learning and baseline clinical variables. A total of 124 patients with MDD from five research centers were included in our machine learning study. All patients underwent acupuncture treatment for 6 weeks and the efficacy of the treatment was evaluated using the Hamilton Depression Scale-17 (HAMD-17). The max-relevance and min-redundancy (mRMR) algorithm and Pearson correlation analysis were used for selecting 11 significant features from 26 baseline clinical variables for model training. We compared the performance of five machine learning models, including logistic regression, support vector machine, K-nearest neighbor, random forest, and XgBoost, in predicting the effect of acupuncture in relieving major depression. Among the five models, XgBoost performed the best with an area under the receiver operating characteristic curve (AUC) of 0.835, an accuracy of 0.730, a sensitivity of 0.670, a specificity of 0.774, and an F1 score of 0.751. The key predictive variables identified were anxiety score in the self-rating depression scale (SDS), the traditional Chinese medicine syndrome of deficiency in both heart and spleen, and body mass index (BMI). The study demonstrates that the developed model can help physicians predict the patients who will benefit from acupuncture treatment, which is of positive significance for improving the clinical efficacy of acupuncture on MDD.

Predictive Biomarkers of Treatment Response in Major Depressive Disorder

Major depressive disorder (MDD) is a highly prevalent, debilitating disorder with a high rate of treatment resistance. One strategy to improve treatment outcomes is to identify patient-specific, pre-intervention factors that can predict treatment success. Neurophysiological measures such as electroencephalography (EEG), which measures the brain's electrical activity from sensors on the scalp, offer one promising approach for predicting treatment response for psychiatric illnesses, including MDD. In this study, a secondary data analysis was conducted on the publicly available Two Decades Brainclinics Research Archive for Insights in Neurophysiology (TDBRAIN) database. Logistic regression modeling was used to predict treatment response, defined as at least a 50% improvement on the Beck's Depression Inventory, in 119 MDD patients receiving repetitive transcranial magnetic stimulation (rTMS). The results show that both age and baseline symptom severity were significant predictors of rTMS treatment response, with older individuals and more severe depression scores associated with decreased odds of a positive treatment response. EEG measures contributed predictive power to these models; however, these improvements in outcome predictability only trended towards statistical significance. These findings provide confirmation of previous demographic and clinical predictors, while pointing to EEG metrics that may provide predictive information in future studies.

Machine learning prediction will be part of future treatment of depression

Machine learning (ML) is changing the way that medicine is practiced. While already clinically utilised in diagnostic radiology and outcome prediction in intensive care unit, ML approaches in psychiatry remain nascent. Implementing ML algorithms in psychiatry, particularly in the treatment of depression, is significantly more challenging than other areas of medicine in part because of the less demarcated disease nosology and greater variability in practice. Given the current exiguous capacity of clinicians to predict patient and treatment outcomes in depression, there is a significantly greater need for better predictive capability. Early studies have shown promising results. ML predictions were significantly better than chance within the sequenced treatment alternatives to relieve depression (STAR*D) trial (accuracy 64.6%, p < 0.0001) and combining medications to enhance depression outcomes (COMED) randomised Controlled Trial (RCT) (accuracy 59.6%, p = 0.043), with similar results found in larger scale, retrospective studies. The greater flexibility and dimensionality of ML approaches has been demonstrated in studies incorporating diverse input variables including electroencephalography scans, achieving 88% accuracy for treatment response, and cognitive test scores, achieving up to 72% accuracy for treatment response. The predicting response to depression treatment (PReDicT) trial tested ML informed prescribing of antidepressants against standard therapy and found there was both better outcomes for anxiety and functional endpoints despite the algorithm only having a balanced accuracy of 57.5%. Impeding the progress of ML algorithms in psychiatry are pragmatic hurdles, including accuracy, expense, acceptability and comprehensibility, and ethical hurdles, including medicolegal liability, clinical autonomy and data privacy. Notwithstanding impediments, it is clear that ML prediction algorithms will be part of depression treatment in the future and clinicians should be prepared for their arrival.

Machine learning and EEG can classify passive viewing of discrete categories of visual stimuli but not the observation of pain

Previous studies have demonstrated the potential of machine learning (ML) in classifying physical pain from non-pain states using electroencephalographic (EEG) data. However, the application of ML to EEG data to categorise the observation of pain versus non-pain images of human facial expressions or scenes depicting pain being inflicted has not been explored. The present study aimed to address this by training Random Forest (RF) models on cortical event-related potentials (ERPs) recorded while participants passively viewed faces displaying either pain or neutral expressions, as well as action scenes depicting pain or matched non-pain (neutral) scenarios. Ninety-one participants were recruited across three samples, which included a model development group (n = 40) and a cross-subject validation group (n = 51). Additionally, 25 participants from the model development group completed a second experimental session, providing a within-subject temporal validation sample. The analysis of ERPs revealed an enhanced N170 component in response to faces compared to action scenes. Moreover, an increased late positive potential (LPP) was observed during the viewing of pain scenes compared to neutral scenes. Additionally, an enhanced P3 response was found when participants viewed faces displaying pain expressions compared to neutral expressions. Subsequently, three RF models were developed to classify images into faces and scenes, neutral and pain scenes, and neutral and pain expressions. The RF model achieved classification accuracies of 75%, 64%, and 69% for cross-validation, cross-subject, and within-subject classifications, respectively, along with reasonably calibrated predictions for the classification of face versus scene images. However, the RF model was unable to classify pain versus neutral stimuli above chance levels when presented with subsequent tasks involving images from either category. These results expand upon previous findings by externally validating the use of ML in classifying ERPs related to different categories of visual images, namely faces and scenes. The results also indicate the limitations of ML in distinguishing pain and non-pain connotations using ERP responses to the passive viewing of visually similar images.

Developing an Electroencephalography-Based Model for Predicting Response to Antidepressant Medication

Importance

Untreated depression is a growing public health concern, with patients often facing a prolonged trial-and-error process in search of effective treatment. Developing a predictive model for treatment response in clinical practice remains challenging.

Objective

To establish a model based on electroencephalography (EEG) to predict response to 2 distinct selective serotonin reuptake inhibitor (SSRI) medications.

Design, Setting, and Participants

This prognostic study developed a predictive model using EEG data collected between 2011 and 2017 from 2 independent cohorts of participants with depression: 1 from the first Canadian Biomarker Integration Network in Depression (CAN-BIND) group and the other from the Establishing Moderators and Biosignatures of Antidepressant Response for Clinical Care (EMBARC) consortium. Eligible participants included those aged 18 to 65 years who had a diagnosis of major depressive disorder. Data were analyzed from January to December 2022.

Exposures

In an open-label trial, CAN-BIND participants received an 8-week treatment regimen of escitalopram treatment (10-20 mg), and EMBARC participants were randomized in a double-blind trial to receive an 8-week sertraline (50-200 mg) treatment or placebo treatment.

Main Outcomes and Measures

The model's performance was estimated using balanced accuracy, specificity, and sensitivity metrics. The model used data from the CAN-BIND cohort for internal validation, and data from the treatment group of the EMBARC cohort for external validation. At week 8, response to treatment was defined as a 50% or greater reduction in the primary, clinician-rated scale of depression severity.

Results

The CAN-BIND cohort included 125 participants (mean [SD] age, 36.4 [13.0] years; 78 [62.4%] women), and the EMBARC sertraline treatment group included 105 participants (mean [SD] age, 38.4 [13.8] years; 72 [68.6%] women). The model achieved a balanced accuracy of 64.2% (95% CI, 55.8%-72.6%), sensitivity of 66.1% (95% CI, 53.7%-78.5%), and specificity of 62.3% (95% CI, 50.1%-73.8%) during internal validation with CAN-BIND. During external validation with EMBARC, the model achieved a balanced accuracy of 63.7% (95% CI, 54.5%-72.8%), sensitivity of 58.8% (95% CI, 45.3%-72.3%), and specificity of 68.5% (95% CI, 56.1%-80.9%). Additionally, the balanced accuracy for the EMBARC placebo group (118 participants) was 48.7% (95% CI, 39.3%-58.0%), the sensitivity was 50.0% (95% CI, 35.2%-64.8%), and the specificity was 47.3% (95% CI, 35.9%-58.7%), suggesting the model's specificity in predicting SSRIs treatment response.

Conclusions and Relevance

In this prognostic study, an EEG-based model was developed and validated in 2 independent cohorts. The model showed promising accuracy in predicting treatment response to 2 distinct SSRIs, suggesting potential applications for personalized depression treatment.

Prediction of Diagnosis and Treatment Response in Adolescents With Depression by Using a Smartphone App and Deep Learning Approaches: Usability Study

BACKGROUND

Lack of quantifiable biomarkers is a major obstacle in diagnosing and treating depression. In adolescents, increasing suicidality during antidepressant treatment further complicates the problem.

OBJECTIVE

We sought to evaluate digital biomarkers for the diagnosis and treatment response of depression in adolescents through a newly developed smartphone app.

METHODS

We developed the Smart Healthcare System for Teens At Risk for Depression and Suicide app for Android-based smartphones. This app passively collected data reflecting the social and behavioral activities of adolescents, such as their smartphone usage time, physical movement distance, and the number of phone calls and text messages during the study period. Our study consisted of 24 adolescents (mean age 15.4 [SD 1.4] years, 17 girls) with major depressive disorder (MDD) diagnosed with Kiddie Schedule for Affective Disorders and Schizophrenia for School-Age Children-Present and Lifetime Version and 10 healthy controls (mean age 13.8 [SD 0.6] years, 5 girls). After 1 week's baseline data collection, adolescents with MDD were treated with escitalopram in an 8-week, open-label trial. Participants were monitored for 5 weeks, including the baseline data collection period. Their psychiatric status was measured every week. Depression severity was measured using the Children's Depression Rating Scale-Revised and Clinical Global Impressions-Severity. The Columbia Suicide Severity Rating Scale was administered in order to assess suicide severity. We applied the deep learning approach for the analysis of the data. Deep neural network was employed for diagnosis classification, and neural network with weighted fuzzy membership functions was used for feature selection.

RESULTS

We could predict the diagnosis of depression with training accuracy of 96.3% and 3-fold validation accuracy of 77%. Of the 24 adolescents with MDD, 10 responded to antidepressant treatments. We predicted the treatment response of adolescents with MDD with training accuracy of 94.2% and 3-fold validation accuracy of 76%. Adolescents with MDD tended to move longer distances and use smartphones for longer periods of time compared to controls. The deep learning analysis showed that smartphone usage time was the most important feature in distinguishing adolescents with MDD from controls. Prominent differences were not observed in the pattern of each feature between the treatment responders and nonresponders. The deep learning analysis revealed that the total length of calls received as the most important feature predicting antidepressant response in adolescents with MDD.

CONCLUSIONS

Our smartphone app demonstrated preliminary evidence of predicting diagnosis and treatment response in depressed adolescents. This is the first study to predict the treatment response of adolescents with MDD by examining smartphone-based objective data with deep learning approaches.

AI-assisted prediction of differential response to antidepressant classes using electronic health records

Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response to four antidepressants classes (SSRI, SNRI, bupropion, and mirtazapine) 4 to 12 weeks after antidepressant initiation. The final data set comprised 17,556 patients. Predictors were derived from both structured and unstructured EHR data and models accounted for features predictive of treatment selection to minimize confounding by indication. Outcome labels were derived through expert chart review and AI-automated imputation. Regularized generalized linear model (GLM), random forest, gradient boosting machine (GBM), and deep neural network (DNN) models were trained and their performance compared. Predictor importance scores were derived using SHapley Additive exPlanations (SHAP). All models demonstrated similarly good prediction performance (AUROCs ≥ 0.70, AUPRCs ≥ 0.68). The models can estimate differential treatment response probabilities both between patients and between antidepressant classes for the same patient. In addition, patient-specific factors driving response probabilities for each antidepressant class can be generated. We show that antidepressant response can be accurately predicted from real-world EHR data with AI modeling, and our approach could inform further development of clinical decision support systems for more effective treatment selection.

Deep learning and machine learning in psychiatry: a survey of current progress in depression detection, diagnosis and treatment

Informatics paradigms for brain and mental health research have seen significant advances in recent years. These developments can largely be attributed to the emergence of new technologies such as machine learning, deep learning, and artificial intelligence. Data-driven methods have the potential to support mental health care by providing more precise and personalised approaches to detection, diagnosis, and treatment of depression. In particular, precision psychiatry is an emerging field that utilises advanced computational techniques to achieve a more individualised approach to mental health care. This survey provides an overview of the ways in which artificial intelligence is currently being used to support precision psychiatry. Advanced algorithms are being used to support all phases of the treatment cycle. These systems have the potential to identify individuals suffering from mental health conditions, allowing them to receive the care they need and tailor treatments to individual patients who are mostly to benefit. Additionally, unsupervised learning techniques are breaking down existing discrete diagnostic categories and highlighting the vast disease heterogeneity observed within depression diagnoses. Artificial intelligence also provides the opportunity to shift towards evidence-based treatment prescription, moving away from existing methods based on group averages. However, our analysis suggests there are several limitations currently inhibiting the progress of data-driven paradigms in care. Significantly, none of the surveyed articles demonstrate empirically improved patient outcomes over existing methods. Furthermore, greater consideration needs to be given to uncertainty quantification, model validation, constructing interdisciplinary teams of researchers, improved access to diverse data and standardised definitions within the field. Empirical validation of computer algorithms via randomised control trials which demonstrate measurable improvement to patient outcomes are the next step in progressing models to clinical implementation.

Classification of major depressive disorder using an attention-guided unified deep convolutional neural network and individual structural covariance network

Major depressive disorder (MDD) is the second leading cause of disability worldwide. Currently, the structural magnetic resonance imaging-based MDD diagnosis models mainly utilize local grayscale information or morphological characteristics in a single site with small samples. Emerging evidence has demonstrated that different brain structures in different circuits have distinct developmental timing, but mature coordinately within the same functional circuit. Thus, establishing an attention-guided unified classification framework with deep learning and individual structural covariance networks in a large multisite dataset could facilitate developing an accurate diagnosis strategy. Our results showed that attention-guided classification could improve the classification accuracy from primary 75.1% to ultimate 76.54%. Furthermore, the discriminative features of regional covariance connectivities and local structural characteristics were found to be mainly located in prefrontal cortex, insula, superior temporal cortex, and cingulate cortex, which have been widely reported to be closely associated with depression. Our study demonstrated that our attention-guided unified deep learning framework may be an effective tool for MDD diagnosis. The identified covariance connectivities and structural features may serve as biomarkers for MDD.

Machine learning approaches and non-linear processing of extracted components in frontal region to predict rTMS treatment response in major depressive disorder

Predicting the therapeutic result of repetitive transcranial magnetic stimulation (rTMS) treatment could save time and costs as ineffective treatment can be avoided. To this end, we presented a machine-learning-based strategy for classifying patients with major depression disorder (MDD) into responders (R) and nonresponders (NR) to rTMS treatment. Resting state EEG data were recorded using 32 electrodes from 88 MDD patients before treatment. Then, patients underwent 7 weeks of rTMS, and 46 of them responded to treatment. By applying Independent Component Analysis (ICA) on EEG, we identified the relevant brain sources as possible indicators of neural activity in the dorsolateral prefrontal cortex (DLPFC). This was served through estimating the generators of activity in the sensor domain. Subsequently, we added physiological information and placed certain terms and conditions to offer a far more realistic estimation than the classic EEG. Ultimately, those components mapped in accordance with the region of the DLPFC in the sensor domain were chosen. Features extracted from the relevant ICs time series included permutation entropy (PE), fractal dimension (FD), Lempel-Ziv Complexity (LZC), power spectral density, correlation dimension (CD), features based on bispectrum, frontal and prefrontal cordance, and a combination of them. The most relevant features were selected by a Genetic Algorithm (GA). For classifying two groups of R and NR, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) were applied to predict rTMS treatment response. To evaluate the performance of classifiers, a 10-fold cross-validation method was employed. A statistical test was used to assess the capability of features in differentiating R and NR for further research. EEG characteristics that can predict rTMS treatment response were discovered. The strongest discriminative indicators were EEG beta power, the sum of bispectrum diagonal elements in delta and beta bands, and CD. The Combined feature vector classified R and NR with a high performance of 94.31% accuracy, 92.85% specificity, 95.65% sensitivity, and 92.85% precision using SVM. This result indicates that our proposed method with power and nonlinear and bispectral features from relevant ICs time-series can predict the treatment outcome of rTMS for MDD patients only by one session pretreatment EEG recording. The obtained results show that the proposed method outperforms previous methods.

Modern Methods of Diagnostics and Treatment of Neurodegenerative Diseases and Depression

This paper discusses the promising areas of research into machine learning applications for the prevention and correction of neurodegenerative and depressive disorders. These two groups of disorders are among the leading causes of decline in the quality of life in the world when estimated using disability-adjusted years. Despite decades of research, the development of new approaches for the assessment (especially pre-clinical) and correction of neurodegenerative diseases and depressive disorders remains among the priority areas of research in neurophysiology, psychology, genetics, and interdisciplinary medicine. Contemporary machine learning technologies and medical data infrastructure create new research opportunities. However, reaching a consensus on the application of new machine learning methods and their integration with the existing standards of care and assessment is still a challenge to overcome before the innovations could be widely introduced to clinics. The research on the development of clinical predictions and classification algorithms contributes towards creating a unified approach to the use of growing clinical data. This unified approach should integrate the requirements of medical professionals, researchers, and governmental regulators. In the current paper, the current state of research into neurodegenerative and depressive disorders is presented.

Reinforcement learning deficits exhibited by postnatal PCP-treated rats enable deep neural network classification

The ability to appropriately update the value of a given action is a critical component of flexible decision making. Several psychiatric disorders, including schizophrenia, are associated with impairments in flexible decision making that can be evaluated using the probabilistic reversal learning (PRL) task. The PRL task has been reverse-translated for use in rodents. Disrupting glutamate neurotransmission during early postnatal neurodevelopment in rodents has induced behavioral, cognitive, and neuropathophysiological abnormalities relevant to schizophrenia. Here, we tested the hypothesis that using the NMDA receptor antagonist phencyclidine (PCP) to disrupt postnatal glutamatergic transmission in rats would lead to impaired decision making in the PRL. Consistent with this hypothesis, compared to controls the postnatal PCP-treated rats completed fewer reversals and exhibited disruptions in reward and punishment sensitivity (i.e., win-stay and lose-shift responding, respectively). Moreover, computational analysis of behavior revealed that postnatal PCP-treatment resulted in a pronounced impairment in the learning rate throughout PRL testing. Finally, a deep neural network (DNN) trained on the rodent behavior could accurately predict the treatment group of subjects. These data demonstrate that disrupting early postnatal glutamatergic neurotransmission impairs flexible decision making and provides evidence that DNNs can be trained on behavioral datasets to accurately predict the treatment group of new subjects, highlighting the potential for DNNs to aid in the diagnosis of schizophrenia.

The Role of Alpha Oscillations among the Main Neuropsychiatric Disorders in the Adult and Developing Human Brain: Evidence from the Last 10 Years of Research

Alpha oscillations (7-13 Hz) are the dominant rhythm in both the resting and active brain. Accordingly, translational research has provided evidence for the involvement of aberrant alpha activity in the onset of symptomatological features underlying syndromes such as autism, schizophrenia, major depression, and Attention Deficit and Hyperactivity Disorder (ADHD). However, findings on the matter are difficult to reconcile due to the variety of paradigms, analyses, and clinical phenotypes at play, not to mention recent technical and methodological advances in this domain. Herein, we seek to address this issue by reviewing the literature gathered on this topic over the last ten years. For each neuropsychiatric disorder, a dedicated section will be provided, containing a concise account of the current models proposing characteristic alterations of alpha rhythms as a core mechanism to trigger the associated symptomatology, as well as a summary of the most relevant studies and scientific contributions issued throughout the last decade. We conclude with some advice and recommendations that might improve future inquiries within this field.

Computational approaches to treatment response prediction in major depression using brain activity and behavioral data: A systematic review

Major depressive disorder is a heterogeneous diagnostic category with multiple available treatments. With the goal of optimizing treatment selection, researchers are developing computational models that attempt to predict treatment response based on various pretreatment measures. In this paper, we review studies that use brain activity data to predict treatment response. Our aim is to highlight and clarify important methodological differences between various studies that relate to the incorporation of domain knowledge, specifically within two approaches delineated as data-driven and theory-driven. We argue that theory-driven generative modeling, which explicitly models information processing in the brain and thus can capture disease mechanisms, is a promising emerging approach that is only beginning to be utilized in treatment response prediction. The predictors extracted via such models could improve interpretability, which is critical for clinical decision-making. We also identify several methodological limitations across the reviewed studies and provide suggestions for addressing them. Namely, we consider problems with dichotomizing treatment outcomes, the importance of investigating more than one treatment in a given study for differential treatment response predictions, the need for a patient-centered approach for defining treatment outcomes, and finally, the use of internal and external validation methods for improving model generalizability.

Predicting treatment response using EEG in major depressive disorder: A machine-learning meta-analysis

Selecting a course of treatment in psychiatry remains a trial-and-error process, and this long-standing clinical challenge has prompted an increased focus on predictive models of treatment response using machine learning techniques. Electroencephalography (EEG) represents a cost-effective and scalable potential measure to predict treatment response to major depressive disorder. We performed separate meta-analyses to determine the ability of models to distinguish between responders and non-responders using EEG across treatments, as well as a performed subgroup analysis of response to transcranial magnetic stimulation (rTMS), and antidepressants (Registration Number: CRD42021257477) in Major Depressive Disorder by searching PubMed, Scopus, and Web of Science for articles published between January 1960 and February 2022. We included 15 studies that predicted treatment responses among patients with major depressive disorder using machine-learning techniques. Within a random-effects model with a restricted maximum likelihood estimator comprising 758 patients, the pooled accuracy across studies was 83.93% (95% CI: 78.90-89.29), with an Area-Under-the-Curve (AUC) of 0.850 (95% CI: 0.747-0.890), and partial AUC of 0.779. The average sensitivity and specificity across models were 77.96% (95% CI: 60.05-88.70), and 84.60% (95% CI: 67.89-92.39), respectively. In a subgroup analysis, greater performance was observed in predicting response to rTMS (Pooled accuracy: 85.70% (95% CI: 77.45-94.83), Area-Under-the-Curve (AUC): 0.928, partial AUC: 0.844), relative to antidepressants (Pooled accuracy: 81.41% (95% CI: 77.45-94.83, AUC: 0.895, pAUC: 0.821). Furthermore, across all meta-analyses, the specificity (true negatives) of EEG models was greater than the sensitivity (true positives), suggesting that EEG models thus far better identify non-responders than responders to treatment in MDD. Studies varied widely in important features across models, although relevant features included absolute and relative power in frontal and temporal electrodes, measures of connectivity, and asymmetry across hemispheres. Predictive models of treatment response using EEG hold promise in major depressive disorder, although there is a need for prospective model validation in independent datasets, and a greater emphasis on replicating physiological markers. Crucially, standardization in cut-off values and clinical scales for defining clinical response and non-response will aid in the reproducibility of findings and the clinical utility of predictive models. Furthermore, several models thus far have used data from open-label trials with small sample sizes and evaluated performance in the absence of training and testing sets, which increases the risk of statistical overfitting. Large consortium studies are required to establish predictive signatures of treatment response using EEG, and better elucidate the replicability of specific markers. Additionally, it is speculated that greater performance was observed in rTMS models, since EEG is assessing neural networks more likely to be directly targeted by rTMS, comprising electrical activity primarily near the surface of the cortex. Prospectively, there is a need for models that examine the comparative effectiveness of multiple treatments across the same patients. However, this will require a thoughtful consideration towards cumulative treatment effects, and whether washout periods between treatments should be utilised. Regardless, longitudinal cross-over trials comparing multiple treatments across the same group of patients will be an important prerequisite step to both facilitate precision psychiatry and identify generalizable physiological predictors of response between and across treatment options.

Predictors of nonresponse to dupilumab in patients with atopic dermatitis: A machine learning analysis

BACKGROUND

Many patients with atopic dermatitis (AD) have a suboptimal response to systemic therapy.

OBJECTIVE

This study assessed predictors of nonresponse to dupilumab in patients with AD.

METHODS

Data (April 2017 through June 2019) for patients aged ≥12 years with AD (ICD-9/10-CM: 691.8/L20.x) who initiated dupilumab on or after April 1, 2017 (index date) were collected from an electronic health record and insurance claims database. Nonresponse indicators (dupilumab discontinuation, addition of another systemic therapy or phototherapy, addition of a high-potency topical corticosteroid, AD-related hospital visit, AD-related emergency room visit, incident skin infection) were predicted from available demographic and clinical variables using machine learning.

RESULTS

Among 419 patients (mean age: 45 years), 145 (35%) experienced ≥1 indicator of nonresponse in the 6-month post-index period. In patients with ≥1 indicator, the most common was dupilumab discontinuation (47% [68/145]). Of note, this analysis could not capture nonmedical reasons of dupilumab discontinuation (eg, cost, access). The most common predictors of nonresponse were a claim for ibuprofen (in 69% of patients with a nonresponse indicator) and Quan-Charlson Comorbidity Index value of 3-4 (59%).

CONCLUSION

Systemic dupilumab therapy for AD can be associated with a relatively high prevalence of nonresponse indicators. Factors associated with these indicators -ie, predictors of nonresponse- may be used to optimize disease management.

Bibliometric Analysis of Quantitative Electroencephalogram Research in Neuropsychiatric Disorders From 2000 to 2021

BACKGROUND

With the development of quantitative electroencephalography (QEEG), an increasing number of studies have been published on the clinical use of QEEG in the past two decades, particularly in the diagnosis, treatment, and prognosis of neuropsychiatric disorders. However, to date, the current status and developing trends of this research field have not been systematically analyzed from a macroscopic perspective. The present study aimed to identify the hot spots, knowledge base, and frontiers of QEEG research in neuropsychiatric disorders from 2000 to 2021 through bibliometric analysis.

METHODS

QEEG-related publications in the neuropsychiatric field from 2000 to 2021 were retrieved from the Web of Science Core Collection (WOSCC). CiteSpace and VOSviewer software programs, and the online literature analysis platform (bibliometric.com) were employed to perform bibliographic and visualized analysis.

RESULTS

A total of 1,904 publications between 2000 and 2021 were retrieved. The number of QEEG-related publications in neuropsychiatric disorders increased steadily from 2000 to 2021, and research in psychiatric disorders requires more attention in comparison to research in neurological disorders. During the last two decades, QEEG has been mainly applied in neurodegenerative diseases, cerebrovascular diseases, and mental disorders to reveal the pathological mechanisms, assist clinical diagnosis, and promote the selection of effective treatments. The recent hot topics focused on QEEG utilization in neurodegenerative disorders like Alzheimer's and Parkinson's disease, traumatic brain injury and related cerebrovascular diseases, epilepsy and seizure, attention-deficit hyperactivity disorder, and other mental disorders like major depressive disorder and schizophrenia. In addition, studies to cross-validate QEEG biomarkers, develop new biomarkers (e.g., functional connectivity and complexity), and extract compound biomarkers by machine learning were the emerging trends.

CONCLUSION

The present study integrated bibliometric information on the current status, the knowledge base, and future directions of QEEG studies in neuropsychiatric disorders from a macroscopic perspective. It may provide valuable insights for researchers focusing on the utilization of QEEG in this field.

Abnormal Reginal Homogeneity in Left Anterior Cingulum Cortex and Precentral Gyrus as a Potential Neuroimaging Biomarker for First-Episode Major Depressive Disorder

OBJECTIVE

There is no objective method to diagnose major depressive disorder (MDD). This study explored the neuroimaging biomarkers using the support vector machine (SVM) method for the diagnosis of MDD.

METHODS

52 MDD patients and 45 healthy controls (HCs) were involved in resting-state functional magnetic resonance imaging (rs-fMRI) scanning. Imaging data were analyzed with the regional homogeneity (ReHo) and SVM methods.

RESULTS

Compared with HCs, MDD patients showed increased ReHo in the left anterior cingulum cortex (ACC) and decreased ReHo in the left precentral gyrus (PG). No correlations were detected between the ReHo values and the Hamilton Rating Scale for Depression (HRSD) scores. The SVM results showed a diagnostic accuracy of 98.96% (96/97). Increased ReHo in the left ACC, and decreased ReHo in the left PG were illustrated, along with a sensitivity of 98.07%(51/52) and a specificity of100% (45/45).

CONCLUSION

Our results suggest that abnormal regional neural activity in the left ACC and PG may play a key role in the pathophysiological process of first-episode MDD. Moreover, the combination of ReHo values in the left ACC and precentral gyrusmay serve as a neuroimaging biomarker for first-episode MDD.

Machine learning in the prediction of depression treatment outcomes: a systematic review and meta-analysis

BACKGROUND

Multiple treatments are effective for major depressive disorder (MDD), but the outcomes of each treatment vary broadly among individuals. Accurate prediction of outcomes is needed to help select a treatment that is likely to work for a given person. We aim to examine the performance of machine learning methods in delivering replicable predictions of treatment outcomes.

METHODS

Of 7732 non-duplicate records identified through literature search, we retained 59 eligible reports and extracted data on sample, treatment, predictors, machine learning method, and treatment outcome prediction. A minimum sample size of 100 and an adequate validation method were used to identify adequate-quality studies. The effects of study features on prediction accuracy were tested with mixed-effects models. Fifty-four of the studies provided accuracy estimates or other estimates that allowed calculation of balanced accuracy of predicting outcomes of treatment.

RESULTS

Eight adequate-quality studies reported a mean accuracy of 0.63 [95% confidence interval (CI) 0.56-0.71], which was significantly lower than a mean accuracy of 0.75 (95% CI 0.72-0.78) in the other 46 studies. Among the adequate-quality studies, accuracies were higher when predicting treatment resistance (0.69) and lower when predicting remission (0.60) or response (0.56). The choice of machine learning method, feature selection, and the ratio of features to individuals were not associated with reported accuracy.

CONCLUSIONS

The negative relationship between study quality and prediction accuracy, combined with a lack of independent replication, invites caution when evaluating the potential of machine learning applications for personalizing the treatment of depression.

The promise of machine learning in predicting treatment outcomes in psychiatry

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

EEG and Sleep Effects of Tramadol Suggest Potential Antidepressant Effects with Different Mechanisms of Action

Tramadol is a widely used, centrally acting, opioid analgesic compound, with additional inhibitory effects on the synaptic reuptake of serotonin and noradrenaline, as well as on the 5-HT₂ and NMDA receptors. Preclinical and clinical evidence also suggests its therapeutic potential in the treatment of depression and anxiety. The effects of most widely used antidepressants on sleep and quantitative electroencephalogram (qEEG) are well characterized; however, such studies of tramadol are scarce. Our aim was to characterize the effects of tramadol on sleep architecture and qEEG in different sleep–wake stages. EEG-equipped Wistar rats were treated with tramadol (0, 5, 15 and 45 mg/kg) at the beginning of the passive phase, and EEG, electromyogram and motor activity were recorded. Tramadol dose-dependently reduced the time spent in rapid eye movement (REM) sleep and increased the REM onset latency. Lower doses of tramadol had wake-promoting effects in the first hours, while 45 mg/kg of tramadol promoted sleep first, but induced wakefulness thereafter. During non-REM sleep, tramadol (15 and 45 mg/kg) increased delta and decreased alpha power, while all doses increased gamma power. In conclusion, the sleep-related and qEEG effects of tramadol suggest antidepressant-like properties, including specific beneficial effects in selected patient groups, and raise the possibility of a faster acting antidepressant action.

Clinical Diagnosis of Psychiatry Based on Electroencephalography

At present, neurophysiological signals used for neuro feedback are EEG (Electroencephalogram), functional magnetic resonance imaging. Among them, the acquisition of EEG signals has the advantages of non-invasive way with low cost. It has been widely used in brain-machine interface technology in recent years. Important progress has been made in rehabilitation and environmental control. However, neural feedback and brainmachine interface technology are completely similar in signal acquisition, signal feature extraction, and pattern classification. Therefore, the related research results of brain-machine interface can be used to closely cooperate with clinical needs to research and develop neural feedback technology based on EEG. Based on neurophysiology and brain-machine interface technology, this paper develops a neural feedback training system based on the acquisition and analysis of human EEG signals. Aiming at the autonomous rhythm components in the EEG signal, such as sensorimotor rhythm and alpha rhythm, the characteristic parameters are extracted through real-time EEG signal processing to generate feedback information, and the subject is self-regulated and trained from a physiological-psychological perspective by providing adjuvant treatment, a practical and stable treatment platform for the clinic.

Predicting Neuroimaging Biomarkers for Antidepressant Selection in Early Treatment of Depression

BACKGROUND

Due to the biological heterogeneity, 60%-70% of patients with major depressive disorder (MDD) do not respond to or achieve remission from first-line antidepressants. Predicting neuroimaging biomarkers for early antidepressant treatment could guide initial antidepressant therapy.

PURPOSE

To assess for neuroimaging biomarkers for antidepressant selection in early antidepressant treatment.

STUDY TYPE

Prospective.

SUBJECTS

A total of 85 MDD patients from the major site and 33 MDD patients from an out-of-sample test site.

FIELD STRENGTH/SEQUENCE

A 3.0 T, T1-weighted imaging using a magnetization-prepared rapid acquisition gradient-echo sequence and diffusion tensor imaging (DTI) using an echo-planar sequence.

ASSESSMENT

Baseline DTI data of patients who achieved early improvement after 2-weeks of antidepressant treatment (selective serotonin reuptake inhibitors [SSRI] or serotonin-norepinephrine reuptake inhibitors [SNRI]) were analyzed. An ensemble model was constructed using data from the major site and then applied to assess the early response of patients at the out-of-sample test site.

STATISTICAL TESTS

Support vector machine combined with leave-one-out cross-validation were applied to construct the whole model from individual base models from different brain regions. Discriminative biomarkers were evaluated by calculating the changes in sensitivity and specificity obtained when removing a single base model from the whole model, the base model being removed changing in each run.

RESULTS

Training performance over MDD patients at the major site achieved 75% accuracy while performance with accuracy of 70% was achieved in the out-of-sample test site. Assessing sensitivity and specificity changes following the removal of single base models from the prominent model highlighted the functions of two neural circuitries: SSRI-related emotion regulation circuitry, centered on the hippocampus (sensitivity changes: 10%) and amygdala (sensitivity changes: 11%); and SNRI-related emotion and reward circuitry, centered on the putamen (specificity changes: 8%) and orbital part of superior frontal gyrus (specificity changes: 12%).

DATA CONCLUSION

These findings support future research on clinical antidepressant selection for MDD.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

Major Depressive Disorder Classification Based on Different Convolutional Neural Network Models: Deep Learning Approach

The human brain is characterized by complex structural, functional connections that integrate unique cognitive characteristics. There is a fundamental hurdle for the evaluation of both structural and functional connections of the brain and the effects in the diagnosis and treatment of neurodegenerative diseases. Currently, there is no clinically specific diagnostic biomarker capable of confirming the diagnosis of major depressive disorder (MDD). Therefore, exploring translational biomarkers of mood disorders based on deep learning (DL) has valuable potential with its recently underlined promising outcomes. In this article, an electroencephalography (EEG)-based diagnosis model for MDD is built through advanced computational neuroscience methodology coupled with a deep convolutional neural network (CNN) approach. EEG recordings are analyzed by modeling 3 different deep CNN structure, namely, ResNet-50, MobileNet, Inception-v3, in order to dichotomize MDD patients and healthy controls. EEG data are collected for 4 main frequency bands (Δ, θ, α, and β, accompanying spatial resolution with location information by collecting data from 19 electrodes. Following the pre-processing step, different DL architectures were employed to underline discrimination performance by comparing classification accuracies. The classification performance of models based on location data, MobileNet architecture generated 89.33% and 92.66% classification accuracy. As to the frequency bands, delta frequency band outperformed compared to other bands with 90.22% predictive accuracy and area under curve (AUC) value of 0.9 for ResNet-50 architecture. The main contribution of the study is the delineation of distinctive spatial and temporal features using various DL architectures to dichotomize 46 MDD subjects from 46 healthy subjects. Exploring translational biomarkers of mood disorders based on DL perspective is the main focus of this study and, though it is challenging, with its promising potential to improve our understanding of the psychiatric disorders, computational methods are highly worthy for the diagnosis process and valuable in terms of both speed and accuracy compared with classical approaches.

Fatigue and brain arousal in patients with major depressive disorder

Fatigue is considered a key symptom of major depressive disorder (MDD), yet the term lacks specificity. It can denote a state of increased sleepiness and lack of drive (i.e., downregulated arousal) as well as a state of high inner tension and inhibition of drive with long sleep onset latencies (i.e., upregulated arousal), the latter typically found in depression. It has been proposed to differentiate fatigue along the dimension of brain arousal. We investigated whether such stratification within a group of MDD patients would reveal a subgroup with distinct clinical features. Using an automatic classification of EEG vigilance stages, an arousal stability score was calculated for 15-min resting EEGs of 102 MDD patients with fatigue. 23.5% of the patients showed signs of hypoarousal with EEG patterns indicating drowsiness or sleep; this hypoaroused subgroup was compared with remaining patients (non-hypoaroused subgroup) concerning self-rated measures of depressive symptoms, sleepiness, and sleep. The hypoaroused subgroup scored higher on the Beck Depression Inventory items "loss of energy" (Z = - 2.13, p = 0.033; ɳ² = 0.044, 90% CI 0.003-0.128) and "concentration difficulty" (Z = - 2.40, p = 0.017; ɳ² = 0.056, 90% CI 0.009-0.139), and reported higher trait and state sleepiness (p < 0.05) as compared to the non-hypoaroused group. The non-hypoaroused subgroup, in contrast, reported more frequently the presence of suicidal ideation (Chi² = 3.81, p = 0.051; ɳ² = 0.037, 90% CI 0.0008-0.126). In this study, we found some evidence that stratifying fatigued MDD patients by arousal may lead to subgroups that are pathophysiologically and clinically more homogeneous. Brain arousal may be a worth while target in clinical research for better understanding the mechanisms underlying suicidal tendencies and to improve treatment response.

A newly developed free software tool set for averaging electroencephalogram implemented in the Perl programming language

Background

Considering the need for daily activity analysis of older adults, development of easy-to-use, free electroencephalogram (EEG) analysis tools are desired in order to decrease barriers to accessing this technology and increase the entry of a wide range of new researchers.

New method

We describe a newly developed tool set for EEG analysis, enabling import, average, waveform display and iso-potential scalp topographies, utilizing the programming language Perl.

Results

The basic processing, including average, display waveforms, and isopotential scalp topography was implemented in the current system. The validation was examined by making difference waveforms between the results using the current analysis system and a commercial software.

Comparison with Existing Method(s): The current software tool set consists of free software. The scripts are easily editable by any user and there are no black boxes.

Conclusions

The currently reported procedures provide an easy-to-begin, flexible, readable, easy-to-modify basic tool set for EEG analysis and is expected to recruit new EEG researchers.

Classification of Depression Through Resting-State Electroencephalogram as a Novel Practice in Psychiatry: Review

Background

Machine learning applications in health care have increased considerably in the recent past, and this review focuses on an important application in psychiatry related to the detection of depression. Since the advent of computational psychiatry, research based on functional magnetic resonance imaging has yielded remarkable results, but these tools tend to be too expensive for everyday clinical use.

Objective

This review focuses on an affordable data-driven approach based on electroencephalographic recordings. Web-based applications via public or private cloud-based platforms would be a logical next step. We aim to compare several different approaches to the detection of depression from electroencephalographic recordings using various features and machine learning models.

Methods

To detect depression, we reviewed published detection studies based on resting-state electroencephalogram with final machine learning, and to predict therapy outcomes, we reviewed a set of interventional studies using some form of stimulation in their methodology.

Results

We reviewed 14 detection studies and 12 interventional studies published between 2008 and 2019. As direct comparison was not possible due to the large diversity of theoretical approaches and methods used, we compared them based on the steps in analysis and accuracies yielded. In addition, we compared possible drawbacks in terms of sample size, feature extraction, feature selection, classification, internal and external validation, and possible unwarranted optimism and reproducibility. In addition, we suggested desirable practices to avoid misinterpretation of results and optimism.

Conclusions

This review shows the need for larger data sets and more systematic procedures to improve the use of the solution for clinical diagnostics. Therefore, regulation of the pipeline and standard requirements for methodology used should become mandatory to increase the reliability and accuracy of the complete methodology for it to be translated to modern psychiatry.

Deep learning and feature based medication classifications from EEG in a large clinical data set

The amount of freely available human phenotypic data is increasing daily, and yet little is known about the types of inferences or identifying characteristics that could reasonably be drawn from that data using new statistical methods. One data type of particular interest is electroencephalographical (EEG) data, collected noninvasively from humans in various behavioral contexts. The Temple University EEG corpus associates thousands of hours of de-identified EEG records with contemporaneous physician reports that include metadata that might be expected to show a measurable correlation with characteristics of the recorded signal. Given that machine learning methods applied to neurological signals are being used in emerging diagnostic applications, we leveraged this data source to test the confidence with which algorithms could predict, using a patient’s EEG record(s) as input, which medications were noted on the matching physician report. We comparatively assessed deep learning and feature-based approaches on their ability to distinguish between the assumed presence of Dilantin (phenytoin), Keppra (levetiracetam), or neither. Our methods could successfully distinguish between patients taking either anticonvulsant and those taking no medications; as well as between the two anticonvulsants. Further, we found different approaches to be most effective for different groups of classifications.

Connectome-based models can predict early symptom improvement in major depressive disorder

BACKGROUND

Major depressive disorder (MDD) is a debilitating mental illness with more than 50% of patients not achieving an adequate response using first-line treatments. Reliable models that predict antidepressant treatment outcome are needed to guide clinical decision making. We aimed to build predictive models of treatment improvement for MDD patients using machine learning approaches based on fMRI resting-state functional connectivity patterns.

METHODS

Resting-state fMRI data were acquired from 192 untreated MDD patients at recruitment, and their severity of depression was assessed by Hamilton Rating Scale for Depression (HAMD) at baseline. Patients were given medication after the initial MR scan and their symptoms were monitored through HAMD for a period of six months. Connectome-based predictive modeling (CPM) algorithms were implemented to predict the improvement in HAMD score at one month from resting-state connectivity at baseline. Additionally, by selectively combining the features from all leave-one-out iterations in the model building stage, we created a consensus model that could be generalized to predict improvement in HAMD score in samples of non-overlapping subjects at different time points.

RESULTS

Using baseline functional connectivity, CPM successfully predicted symptom improvement of depression at one month. In addition, a consensus 'MDD improvement model' could predict symptom improvement for novel individuals at the two-week, one-month, two-month and three-month time points after antidepressant treatment.

CONCLUSIONS

Individual pre-treatment functional brain networks contain meaningful information that can be gleaned to build predictors of treatment outcome. The identified MDD improvement networks could be an appropriate biomarker for predicting individual therapeutic response of antidepressant treatment. Replication and validation using other large datasets will be a key next step before these models can be used in clinical practice.

Predicting antidepressant response through early improvement of individual symptoms of depression incorporating baseline characteristics of patients: An individual patient data meta-analysis

Overall early improvement in depression after commencement of antidepressant treatment could be associated with subsequent response or remission, but its predictive ability is not adequate. We aimed to investigate whether early improvement of individual depressive symptoms and important baseline characteristics of patients including the number of previous depressive episodes and the duration of index episode, better predicts response or remission. We requested pharmaceutical companies in Japan for individual patient data from randomized placebo-controlled trials focusing on the efficacy of second-generation antidepressants. Primary and secondary outcomes were response and remission at week 6, respectively. We compared models that only included improvement in the overall depression severity at week 2 with models that also included improvement in individual symptoms and baseline characteristics, by conducting an individual patient data meta-analysis. We obtained data from three trials comprising 997 participants. For the response outcome, the model incorporating individual symptoms and baseline characteristics demonstrated better predictive values than those in the model including early improvement in overall depression only. However, the area under the receiver operating characteristic curve, and positive and negative predictive values were 0.65, 0.70, and 0.64, respectively, suggesting that 30% and 36% of the participants still had false-negative and false-positive predictions, respectively. For the remission outcome, the corresponding values in the latter model were 0.72, 0.62, and 0.68, respectively. We suggest that clinical judgement on early discontinuation of antidepressant from non-early improvement at week 2 should be carefully made.

Evaluation of a Machine Learning Model Based on Pretreatment Symptoms and Electroencephalographic Features to Predict Outcomes of Antidepressant Treatment in Adults With Depression: A Prespecified Secondary Analysis of a Randomized Clinical Trial

IMPORTANCE

Despite the high prevalence and potential outcomes of major depressive disorder, whether and how patients will respond to antidepressant medications is not easily predicted.

OBJECTIVE

To identify the extent to which a machine learning approach, using gradient-boosted decision trees, can predict acute improvement for individual depressive symptoms with antidepressants based on pretreatment symptom scores and electroencephalographic (EEG) measures.

DESIGN, SETTING, AND PARTICIPANTS

This prognostic study analyzed data collected as part of the International Study to Predict Optimized Treatment in Depression, a randomized, prospective open-label trial to identify clinically useful predictors and moderators of response to commonly used first-line antidepressant medications. Data collection was conducted at 20 sites spanning 5 countries and including 518 adult outpatients (18-65 years of age) from primary care or specialty care practices who received a diagnosis of current major depressive disorder between December 1, 2008, and September 30, 2013. Patients were antidepressant medication naive or willing to undergo a 1-week washout period of any nonprotocol antidepressant medication. Statistical analysis was conducted from January 5 to June 30, 2019.

EXPOSURES

Participants with major depressive disorder were randomized in a 1:1:1 ratio to undergo 8 weeks of treatment with escitalopram oxalate (n = 162), sertraline hydrochloride (n = 176), or extended-release venlafaxine hydrochloride (n = 180).

MAIN OUTCOMES AND MEASURES

The primary objective was to predict improvement in individual symptoms, defined as the difference in score for each of the symptoms on the 21-item Hamilton Rating Scale for Depression from baseline to week 8, evaluated using the C index.

RESULTS

The resulting data set contained 518 patients (274 women; mean [SD] age, 39.0 [12.6] years; mean [SD] 21-item Hamilton Rating Scale for Depression score improvement, 13.0 [7.0]). With the use of 5-fold cross-validation for evaluation, the machine learning model achieved C index scores of 0.8 or higher on 12 of 21 clinician-rated symptoms, with the highest C index score of 0.963 (95% CI, 0.939-1.000) for loss of insight. The importance of any single EEG feature was higher than 5% for prediction of 7 symptoms, with the most important EEG features being the absolute delta band power at the occipital electrode sites (O1, 18.8%; Oz, 6.7%) for loss of insight. Over and above the use of baseline symptom scores alone, the use of both EEG and baseline symptom features was associated with a significant increase in the C index for improvement in 4 symptoms: loss of insight (C index increase, 0.012 [95% CI, 0.001-0.020]), energy loss (C index increase, 0.035 [95% CI, 0.011-0.059]), appetite changes (C index increase, 0.017 [95% CI, 0.003-0.030]), and psychomotor retardation (C index increase, 0.020 [95% CI, 0.008-0.032]).

CONCLUSIONS AND RELEVANCE

This study suggests that machine learning may be used to identify independent associations of symptoms and EEG features to predict antidepressant-associated improvements in specific symptoms of depression. The approach should next be prospectively validated in clinical trials and settings.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT00693849.

Prospective testing of a neurophysiologic biomarker for treatment decisions in major depressive disorder: The PRISE-MD trial

Management of Major Depressive Disorder (MDD) might be improved by a biomarker to predict whether a selected medication is likely to lead to remission. We previously reported on a quantitative electroencephalogram-based biomarker, the Antidepressant Treatment Response (ATR) index, that integrated recordings at baseline and after one week of treatment. The present study prospectively tested whether treatment directed by the biomarker increased the likelihood of remission; we hypothesized that continued treatment with a drug predicted to lead to remission (i.e., high ATR values) would be associated with better outcomes than if the drug was predicted not to lead to remission (i.e., low ATR values). We enrolled 180 adult outpatients with unipolar MDD from the community. After one week of escitalopram treatment to determine the biomarker, stratified randomization (high vs. low ATR) was used to assign subjects to either continued escitalopram or a switch to bupropion as a blinded control condition, for seven additional weeks. For the 73 evaluable subjects assigned to continued escitalopram treatment, the remission rate was significantly higher for those in whom ATR had predicted remission versus non-remission (60.4% vs. 30.0%, respectively, p = 0.01). Accuracy was enhanced by combining 1-week depressive symptom change with ATR (68.6% vs 28.9%). This prospective validation study supports further development of the ATR biomarker, alone or together with early symptom change, to improve care by identifying individuals unlikely to remit with their current treatment, and support the decision to change treatment after one week rather than after failing a full, prolonged course of medication.

An electroencephalographic signature predicts antidepressant response in major depression

Antidepressants are widely prescribed, but their efficacy relative to placebo is modest, in part because the clinical diagnosis of major depression encompasses biologically heterogeneous conditions. Here, we sought to identify a neurobiological signature of response to antidepressant treatment as compared to placebo. We designed a latent-space machine-learning algorithm tailored for resting-state electroencephalography (EEG) and applied it to data from the largest imaging-coupled, placebo-controlled antidepressant study (n = 309). Symptom improvement was robustly predicted in a manner both specific for the antidepressant sertraline (versus placebo) and generalizable across different study sites and EEG equipment. This sertraline-predictive EEG signature generalized to two depression samples, wherein it reflected general antidepressant medication responsivity and related differentially to a repetitive transcranial magnetic stimulation treatment outcome. Furthermore, we found that the sertraline resting-state EEG signature indexed prefrontal neural responsivity, as measured by concurrent transcranial magnetic stimulation and EEG. Our findings advance the neurobiological understanding of antidepressant treatment through an EEG-tailored computational model and provide a clinical avenue for personalized treatment of depression.

Neuroimaging Biomarkers for Predicting Treatment Response and Recurrence of Major Depressive Disorder

The acute treatment duration for major depressive disorder (MDD) is 8 weeks or more. Treatment of patients with MDD without predictors of treatment response and future recurrence presents challenges and clinical problems to patients and physicians. Recently, many neuroimaging studies have been published on biomarkers for treatment response and recurrence of MDD using various methods such as brain volumetric magnetic resonance imaging (MRI), functional MRI (resting-state and affective tasks), diffusion tensor imaging, magnetic resonance spectroscopy, near-infrared spectroscopy, and molecular imaging (i.e., positron emission tomography and single photon emission computed tomography). The results have been inconsistent, and we hypothesize that this could be due to small sample size; different study design, including eligibility criteria; and differences in the imaging and analysis techniques. In the future, we suggest a more sophisticated research design, larger sample size, and a more comprehensive integration including genetics to establish biomarkers for the prediction of treatment response and recurrence of MDD.

Frontal theta and posterior alpha in resting EEG: A critical examination of convergent and discriminant validity

Prior research has identified two resting EEG biomarkers with potential for predicting functional outcomes in depression: theta current density in frontal brain regions (especially rostral anterior cingulate cortex) and alpha power over posterior scalp regions. As little is known about the discriminant and convergent validity of these putative biomarkers, a thorough evaluation of these psychometric properties was conducted toward the goal of improving clinical utility of these markers. Resting 71-channel EEG recorded from 35 healthy adults at two sessions (1-week retest) were used to systematically compare different quantification techniques for theta and alpha sources at scalp (surface Laplacian or current source density [CSD]) and brain (distributed inverse; exact low resolution electromagnetic tomography [eLORETA]) level. Signal quality was evaluated with signal-to-noise ratio, participant-level spectra, and frequency PCA covariance decomposition. Convergent and discriminant validity were assessed within a multitrait-multimethod framework. Posterior alpha was reliably identified as two spectral components, each with unique spatial patterns and condition effects (eyes open/closed), high signal quality, and good convergent and discriminant validity. In contrast, frontal theta was characterized by one low-variance component, low signal quality, lack of a distinct spectral peak, and mixed validity. Correlations between candidate biomarkers suggest that posterior alpha components constitute reliable, convergent, and discriminant biometrics in healthy adults. Component-based identification of spectral activity (CSD/eLORETA-fPCA) was superior to fixed, a priori frequency bands. Improved quantification and conceptualization of frontal theta is necessary to determine clinical utility.