Optimizing prediction of response to antidepressant medications using machine learning and integrated genetic, clinical, and demographic data

Machine learning-driven risk prediction and feature identification for major depressive disorder and its progression: an exploratory study based on five years of longitudinal data from the US national health survey

BACKGROUND

Major depressive disorder (MDD) presents significant public health challenges due to its increasing prevalence and complex risk factors. This study systematically analyzed data from 2019 to 2023 to explore trends in MDD incidence, symptom progression, and multidimensional influencing factors.

OBJECTIVE

The study aimed to identify key risk factors and mechanisms of MDD progression through multidimensional variable analysis and machine learning model evaluation, optimizing predictive models to provide a scientific basis for early screening, targeted interventions, and public health policy formulation.

METHODS

Data from the U.S. National Health Interview Survey (NHIS) were analyzed using LASSO regression for feature selection and various machine learning models (e.g., AdaBoost, Gradient Boosting, Gaussian NB, Extra Trees) for risk prediction. SHAP value analysis was employed to interpret the models and identify key predictors across psychological, social, and biological domains.

RESULTS

Depression risk was closely associated with psychological health (e.g., PHQ82, ANXLEVEL), social support (e.g., DISCRIM1, PCNTADLT), and biological health (e.g., COGMEMDFF, DEPEV). AdaBoost, Gradient Boosting, Gaussian NB, and Extra Trees demonstrated superior performance in different tasks, with SHAP analysis highlighting the critical role of psychological health in risk prediction and the importance of social support and cognitive deficits in symptom progression.

CONCLUSIONS

This study provides a scientific foundation for early screening of MDD, personalized intervention strategies, and public health policy optimization. Future research should expand data coverage, optimize models, and incorporate causal inference methods to enhance the precision and applicability of depression risk prediction.

Individual patterns of activity predict the response to physical exercise as an intervention in mild to moderate depression

Physical exercise (PE) as antidepressive intervention is a promising alternative, as shown by multiple meta-analyses. However, there is no consensus regarding optimal intensity and duration of exercise, and there are no objective criteria available for personalized indication of treatment. The aims of this study were (1) to evaluate whether individual activity patterns before intervention can predict the response to treatment; and (2) to evaluate whether the patient outcome can be improved by using prior information on treatment efficacy at individual level. The study included subjects with mild to moderate depression randomized to three PE regimens as antidepressive intervention. Features extracted from actigraphy recordings were used for training linear regression ensembles to predict the response to treatment. The Bayesian analysis of coefficients yielded distinct signatures in enriched feature subsets for each PE regimen. Next, we used a counterfactual approach by virtually assigning each patient to the PE regimen predicted to yield best outcome. This procedure significantly increased the remission rates as compared to random assignment to treatment. Our data suggest that the analysis of individual patterns of activity can identify a PE regimen to yield the best results, and that assignment to PE regimen using this information would significantly increase remission rate.

Artificial Intelligence and Neuroscience: Transformative Synergies in Brain Research and Clinical Applications

The convergence of Artificial Intelligence (AI) and neuroscience is redefining our understanding of the brain, unlocking new possibilities in research, diagnosis, and therapy. This review explores how AI's cutting-edge algorithms-ranging from deep learning to neuromorphic computing-are revolutionizing neuroscience by enabling the analysis of complex neural datasets, from neuroimaging and electrophysiology to genomic profiling. These advancements are transforming the early detection of neurological disorders, enhancing brain-computer interfaces, and driving personalized medicine, paving the way for more precise and adaptive treatments. Beyond applications, neuroscience itself has inspired AI innovations, with neural architectures and brain-like processes shaping advances in learning algorithms and explainable models. This bidirectional exchange has fueled breakthroughs such as dynamic connectivity mapping, real-time neural decoding, and closed-loop brain-computer systems that adaptively respond to neural states. However, challenges persist, including issues of data integration, ethical considerations, and the "black-box" nature of many AI systems, underscoring the need for transparent, equitable, and interdisciplinary approaches. By synthesizing the latest breakthroughs and identifying future opportunities, this review charts a path forward for the integration of AI and neuroscience. From harnessing multimodal data to enabling cognitive augmentation, the fusion of these fields is not just transforming brain science, it is reimagining human potential. This partnership promises a future where the mysteries of the brain are unlocked, offering unprecedented advancements in healthcare, technology, and beyond.

The effect of repetitive and Deep Transcranial Magnetic Stimulation on quantitative electroencephalography in major depressive disorder

Background

F-8-coil repetitive transcranial magnetic stimulation (rTMS) and H-1-coil deep repetitive transcranial magnetic stimulation (dTMS) have been indicated for the treatment of major depressive disorder (MDD) in adult patients by applying different treatment protocols. Nevertheless, the evidence for long-term electrophysiological alterations in the cortex following prolonged TMS interventions, as assessed by quantitative electroencephalography (qEEG), remains insufficiently explored. This study aims to demonstrate the qEEG-based distinctions between rTMS and dTMS in the management of depression and to evaluate the potential correlation between the electrophysiological changes induced by these two distinct TMS interventions and the clinical improvement in depressive and anxiety symptoms.

Methods

A total of 60 patients diagnosed with treatment resistant depression received rTMS (n = 30) or dTMS (n = 30) along with their usual treatments in Kemal Arıkan Psychiatry Clinic. All the participants underwent resting-state qEEG recording before and at the end of 30 sessions of TMS treatment. The significant qEEG changes were then tested for their correlation with the improvement in depression and anxiety.

Results

After the course of rTMS and dTMS a considerable reduction is seen in the severity of depression and anxiety. Although improvements in depression and anxiety were observed in both TMS groups, specific neural activity patterns were associated with better outcomes in depression. Patients who exhibited lower alpha activity in the left fronto-central region and higher gamma activity in the right prefrontal region following rTMS showed more significant improvements in depression symptoms. Similarly, those whose beta activity increased in the left prefrontal region but decreased in the right prefrontal region after rTMS tended to have greater reductions in depression and anxiety severity. For patients in the dTMS group, those who demonstrated a decrease in left temporal theta activity after treatment were more likely to experience a substantial improvement in depression severity.

Conclusion

Following 30 sessions of rTMS with a F8 coil and dTMS with an H1 coil, notable alterations in qEEG activity with clinical significance were discerned. The persistence of these changes should be investigated in the subsequent follow-up period.

Comparison of Different Machine Learning Methodologies for Predicting the Non-Specific Treatment Response in Placebo Controlled Major Depressive Disorder Clinical Trials

Placebo effect represents a serious confounder for the assessment of treatment effect to the extent that it has become increasingly difficult to develop antidepressant medications appropriate for outperforming placebo. Treatment effect in randomized, placebo-controlled trials, is usually estimated by the mean baseline adjusted difference of treatment response in active and placebo arms and is function of treatment-specific and non-specific effects. The non-specific treatment effect varies subject by subject conditional to the individual propensity to respond to placebo. This effect is not estimable at an individual level using the conventional parallel-group study design, since each subject enrolled in the trial is assigned to receive either active treatment or placebo, but not both. The objective of this study was to conduct a comparative analysis of the machine learning methodologies to estimate the individual probability of a non-specific treatment effect. The estimated probability is expected to support novel methodological approaches for better controlling effect of excessively high placebo response. At this purpose, six machine learning methodologies (gradient boosting machine, lasso regression, logistic regression, support vector machines, k-nearest neighbors, and random forests) were compared to the multilayer perceptrons artificial neural network (ANN) methodology for predicting the probability of individual non-specific treatment response. ANN achieved the highest overall accuracy among all methods tested. A fivefold cross-validation was used to assess performances and risks of overfitting of the ANN model. The analysis conducted without subjects with non-specific effect indicated a significant increase of signal detection with significant increase in effect size.

The role of gut microbiota and metabolomic pathways in modulating the efficacy of SSRIs for major depressive disorder

This study aims to explore the mechanism by which gut microbiota influences the antidepressant effects of serotonin reuptake inhibitors (SSRIs) through metabolic pathways. A total of 126 patients were analyzed for their gut microbiota and metabolomics. Patients received SSRI treatment and were categorized into responder and non-responder groups based on changes in their Hamilton Depression Rating Scale (HAMD-17) scores before and after treatment. The association between gut microbiota composition and the efficacy of SSRIs was investigated through 16S rRNA gene sequencing and metabolomic analysis, and a predictive model was developed. As a result, the study found significant differences in gut microbiota composition between the responder and resistant groups. Specific taxa, such as Ruminococcus, Bifidobacterium, and Faecalibacterium, were more abundant in the responder group. Functional analysis revealed upregulation of acetate degradation and neurotransmitter synthesis pathways in the responder group. The machine learning model indicated that gut microbiota and metabolites are potential biomarkers for predicting SSRIs efficacy. In conclusion, gut microbiota influences the antidepressant effects of SSRIs through metabolic pathways. The diversity and function of gut microbiota can serve as biomarkers for predicting the treatment response, providing new insights for personalized treatment.

Drug metabolizing enzymes pharmacogenetic variation-informed antidepressant therapy approach for common mental disorders: A systematic review and meta-analysis

IMPORTANCE

Currently, 30-50 % of individuals with depression and 40 % with anxiety-collectively referred to as common mental disorders (CMDs), exhibit inadequate responses to antidepressant treatments.

OBJECTIVE

To assess the effectiveness and safety of drug-metabolizing enzyme pharmacogenetic variation informed treatment (PGxIT) versus usual antidepressant treatment (UT) in patients with CMDs.

DATA SOURCES

A literature search was conducted in the MEDLINE, Scopus, and Cochrane Library databases from inception until January 30, 2024.

STUDY SELECTION

Studies were selected based on CMD diagnoses, reporting on the genetic variations of drug-metabolizing enzyme (DME) genes in relation to antidepressants, involving PGxIT and UT groups with human subjects, and published in English.

DATA EXTRACTION AND SYNTHESIS

Data extraction and quality assessment were performed independently by two authors. A pooled risk ratio (RR) with 95 % CI was estimated using both random and fixed-effect models, and heterogeneity was assessed using Cochran's Q test and the I2 statistic. The publication bias of eligible studies was assessed using post hoc Doi plots and the LFK index.

RESULTS

This systematic review included 18 studies (n = 7021). The PGxIT demonstrated greater efficacy in the remission of symptoms of depressive disorder at 8 weeks (RR 1.523 [95 % CI: 1.255-1.843]; I2 = 48 %) and 12 weeks (RR 1.631 [95 % CI: 1.001-2.657]; I2 = 86 %; p < 0.01), and symptoms of anxiety disorder compared to UT. Additionally, the risk of adverse drug events (ADEs) was significantly lower in the PGxIT group (RR = 0.65 [95 % CI: 0.52-0.82]; I2 = 0 %) than in the UT group. The certainty of evidence for both outcomes was moderate.

CONCLUSIONS AND RELEVANCE

This systematic review and meta-analysis suggest that pharmacogenetically guided antidepressant treatment, based on genetic variation in drug-metabolizing enzymes, is associated with superior efficacy in the remission of symptoms for patients with depressive disorders and a reduction in ADEs compared to usual treatment and the findings of the systematic review for remission in anxiety disorders indicate that, PGx guided treatment is also associated with increased remission of symptoms in anxiety disorders compared to usual treatment.

Externally validated clinical prediction models for estimating treatment outcomes for patients with a mood, anxiety or psychotic disorder: systematic review and meta-analysis

BACKGROUND

Suboptimal treatment outcomes contribute to the high disease burden of mood, anxiety or psychotic disorders. Clinical prediction models could optimise treatment allocation, which may result in better outcomes. Whereas ample research on prediction models is performed, model performance in other clinical contexts (i.e. external validation) is rarely examined. This gap hampers generalisability and as such implementation in clinical practice.

AIMS

Systematically appraise studies on externally validated clinical prediction models for estimated treatment outcomes for mood, anxiety and psychotic disorders by (1) reviewing methodological quality and applicability of studies and (2) investigating how model properties relate to differences in model performance.

METHOD

The review and meta-analysis protocol was prospectively registered with PROSPERO (registration number CRD42022307987). A search was conducted on 8 November 2021 in the databases PubMED, PsycINFO and EMBASE. Random-effects meta-analysis and meta-regression were conducted to examine between-study heterogeneity in discriminative performance and its relevant influencing factors.

RESULTS

Twenty-eight studies were included. The majority of studies (n = 16) validated models for mood disorders. Clinical predictors (e.g. symptom severity) were most frequently included (n = 25). Low methodological and applicability concerns were found for two studies. The overall discrimination performance of the meta-analysis was fair with wide prediction intervals (0.72 [0.46; 0.89]). The between-study heterogeneity was not explained by number or type of predictors but by disorder diagnosis.

CONCLUSIONS

Few models seem ready for further implementation in clinical practice to aid treatment allocation. Besides the need for more external validation studies, we recommend close examination of the clinical setting before model implementation.

Antidepressant Treatment Response Prediction With Early Assessment of Functional Near-Infrared Spectroscopy and Micro-RNA

While functional near-infrared spectroscopy (fNIRS) had previously been suggested for major depressive disorder (MDD) diagnosis, the clinical application to predict antidepressant treatment response (ATR) is still unclear. To address this, the aim of the current study is to investigate MDD ATR at three response levels using fNIRS and micro-ribonucleic acids (miRNAs). Our proposed algorithm includes a custom inter-subject variability reduction based on the principal component analysis (PCA). The principal components of extracted features are first identified for non-responders' group. The first few components that sum up to 99% of explained variance are discarded to minimize inter-subject variability while the remaining projection vectors are applied on all response groups (24 non-responders, 15 partial-responders, 13 responders) to obtain their relative projections in feature space. The entire algorithm achieved a better performance through the radial basis function (RBF) support vector machine (SVM), with 82.70% accuracy, 78.44% sensitivity, 86.15% precision, and 91.02% specificity, respectively, when compared with conventional machine learning approaches that combine clinical, sociodemographic and genetic information as the predictor. The performance of the proposed custom algorithm suggests the prediction of ATR can be improved with multiple features sources, provided that the inter-subject variability is properly addressed, and can be an effective tool for clinical decision support system in MDD ATR prediction. Clinical and Translational Impact Statement-The fusion of neuroimaging fNIRS features and miRNA profiles significantly enhances the prediction accuracy of MDD ATR. The minimally required features also make the personalized medicine more practical and realizable.

Artificial intelligence, medications, pharmacogenomics, and ethics

Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing various scientific and clinical disciplines including pharmacogenomics (PGx) by enabling the analysis of complex datasets and the development of predictive models. The integration of AI and ML with PGx has the potential to provide more precise, data-driven insights into new drug targets, drug efficacy, drug selection, and risk of adverse events. While significant effort to develop and validate these tools remain, ongoing advancements in AI technologies, coupled with improvements in data quality and depth is anticipated to drive the transition of these tools into clinical practice and delivery of individualized treatments and improved patient outcomes. The successful development and integration of AI-assisted PGx tools will require careful consideration of ethical, legal, and social issues (ELSI) in research and clinical practice. This paper explores the intersection of PGx with AI, highlighting current research and potential clinical applications, and ELSI including privacy, oversight, patient and provider knowledge and acceptance, and the impact on patient-provider relationship and new roles.

A large-scale observational comparison of antidepressants and their effects

BACKGROUND

Selective Serotonin Reuptake Inhibitors (SSRIs) represent a diverse class of medications widely prescribed for depression and anxiety. Despite their common use, there is an absence of large-scale, real-world evidence capturing the heterogeneity in their effects on individuals. This study addresses this gap by utilizing naturalistic search data to explore the varied impact of six different SSRIs on user behavior.

METHODS

The study sample included ∼508 thousand Bing users with searches for one of six SSRIs (citalopram, escitalopram, fluoxetine, fluvoxamine, paroxetine, sertraline) from April-December 2022, comprising 510 million queries. Cox proportional hazard models were employed to examine 30 topics (e.g., shopping, tourism, health) and 195 health symptoms (e.g., anxiety, weight gain, impotence), using each SSRI as a reference. We assessed the relative hazard ratios between drugs and, where feasible, ranked the SSRIs based on their observed effects. We used Cox proportional hazard models in order to account for both the likelihood of users searching for a particular topic or symptom and the associated time to that search. The temporal aspect aided in distinguishing between potential symptoms of the disorder, short-term medication side effects, and later appearing side effects.

RESULTS

Differences were found in search behaviors associated with each SSRI. E.g., fluvoxamine was associated with a significantly higher likelihood of searching weight gain compared to all other SSRIs (HRs 1.85-2.93). Searches following citalopram were associated with significantly higher rates of later impotence queries compared to all other SSRIs (HRs 5.11-7.76), except fluvoxamine. Fluvoxamine was associated with a significantly higher rate of health related searches than all other SSRIs (HRs 2.11-2.36).

CONCLUSIONS

Our study reveals new insights into the varying SSRI impacts, suggesting distinct symptom profiles. This novel use of large-scale, naturalistic search data contributes to pharmacovigilance efforts, enhancing our understanding of intra-class variation among SSRIs, potentially uncovering previously unidentified drug effects.

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.

Building machine learning prediction models for well-being using predictors from the exposome and genome in a population cohort

Effective personalized well-being interventions require the ability to predict who will thrive or not, and the understanding of underlying mechanisms. Here, using longitudinal data of a large population cohort (the Netherlands Twin Register, collected 1991-2022), we aim to build machine learning prediction models for adult well-being from the exposome and genome, and identify the most predictive factors (N between 702 and 5874). The specific exposome was captured by parent and self-reports of psychosocial factors from childhood to adulthood, the genome was described by polygenic scores, and the general exposome was captured by linkage of participants' postal codes to objective, registry-based exposures. Not the genome (R 2 = -0.007 [-0.026-0.010]), but the general exposome (R 2 = 0.047 [0.015-0.076]) and especially the specific exposome (R 2 = 0.702 [0.637-0.753]) were predictive of well-being in an independent test set. Adding the genome (P = 0.334) and general exposome (P = 0.695) independently or jointly (P = 0.029) beyond the specific exposome did not improve prediction. Risk/protective factors such as optimism, personality, social support and neighborhood housing characteristics were most predictive. Our findings highlight the importance of longitudinal monitoring and promises of different data modalities for well-being prediction.

Cajaninstilbene acid ameliorates depression-like behaviors in mice by suppressing TLR4/NF-κB mediated neuroinflammation and promoting autophagy

Depression is a life-threatening neurodegenerative disease lacking a complete cure. Cajaninstilbene acid (CSA), a potent stilbene compound, has demonstrated neuroprotective effects, however, studies on its antidepressant mechanisms are still scarce. This study examined the effects of CSA on lipopolysaccharide (LPS)-induced and chronic unpredictable mild stress (CUMS)-induced depression in mice, investigating its mechanisms related to inflammation and autophagy. Mice were treated with CSA (7.5, 15, and 30 mg/kg) daily for 3 weeks before intraperitoneal LPS injection (0.8 mg/kg). Another cohort underwent the same doses of CSA (7.5-30 mg/kg) daily for 6 weeks in accompany with CUMS stimulation. Behavioral assessments were conducted, and cortical samples were collected for molecular analysis. Findings indicate that CSA ameliorated depressive behaviors induced by both LPS and CUMS. Notably, CSA (15 mg/kg) reversed despair behavior in mice more persistently than amitriptyline, indicating that optimal doses of CSA may effectively decelerate the procession of mood despair and yield a good compliance. CSA countered CUMS-induced activation of TLR4/NF-κB pathway and the reduction in autophagy levels. Furthermore, CSA attenuated the CUMS-induced decline in neuroplasticity. Collectively, these findings suggest that CSA mitigates depression-like behaviors in mice by inhibiting TLR4/NF-κB-mediated neuroinflammation and enhancing autophagy. This research provides further insights into CSA's mechanisms of action in ameliorating depressive behaviors, offering a scientific foundation for developing CSA-based antidepressants.

Machine learning for antidepressant treatment selection in depression

Finding the right antidepressant for the individual patient with major depressive disorder can be a difficult endeavor and is mostly based on trial-and-error. Machine learning (ML) is a promising tool to personalize antidepressant prescription. In this review, we summarize the current evidence of ML in the selection of antidepressants and conclude that its value for clinical practice is still limited. Apart from the current focus on effectiveness, several other factors should be taken into account to make ML-based prediction models useful for clinical application.

Exploring mood disorders and treatment options using human stem cells

Despite their global prevalence, the mechanisms for mood disorders like bipolar disorder and major depressive disorder remain largely misunderstood. Mood stabilizers and antidepressants, although useful and effective for some, do not have a high responsiveness rate across those with these conditions. One reason for low responsiveness to these drugs is patient heterogeneity, meaning there is diversity in patient characteristics relating to genetics, etiology, and environment affecting treatment. In the past two decades, novel induced pluripotent stem cell (iPSC) research and technology have enabled the use of human-derived brain cells as a new model to study human disease that can help account for patient variance. Human iPSC technology is an emerging tool to better understand the molecular mechanisms of these disorders as well as a platform to test novel treatments and existing pharmaceuticals. This literature review describes the use of iPSC technology to model bipolar and major depressive disorder, common medications used to treat these disorders, and novel patient-derived alternative treatment methods for non-responders stemming from past publications, as well as presenting new data derived from these models.

Common Mental Health Disorders and Their Current Prescription Patterns in Saudi Arabia's Primary Healthcare Settings

Background The mental healthcare program is widely implemented in primary healthcare settings in Saudi Arabia. It consisted of early screening and management of mental health disorders associated with chronic health conditions. Family physicians are authorized to prescribe selective serotonin reuptake inhibitors (SSRIs) for early management of mental health disorders in primary healthcare centers (PHCs). The aim of the study is exploring the prevalence of various types of mental health disorders and to assess the prescribing pattern of SSRIs in PHCs. Materials and methods A cross-sectional study based on the data from electronic health records, telephone interviews, and prescriptions of individuals administered SSRIs at PHCs. Results Among 219 patients visiting PHCs, 67.6% were female participants. Forty-four percent of the patients were 20-30 years old and 61.2% of them received SSRI medications. The most prevalent chronic condition was diabetes (22.5%) followed by hypertension (20.5%) and asthma (6.4%). The most prevalent mental disorder was major depressive disorder (MDD; 78.1%), followed by anxiety disorder (7.3%), panic disorder (6.4%), and MDD with anxiety disorders (5.5%). Conclusion Implementing mental healthcare programs in PHCs is believed to promote population health. MDD was the predominant mental health disorder among patients visiting PHCs, and SSRIs were the most prescribed medications in this setting. This suggests that mental healthcare programs in PHCs are effective in improving mental health outcomes.

Efficacy of Esketamine among patients with treatment resistant depression in a 'real world' health-care setting in Israel

One in five people will likely suffer from major depressive disorder (MDD) during their life. Thirty percent of those with MDD will experience Treatment Resistant Depression (TRD), which is characterized by a failure to respond to two adequately administered trials of antidepressants. Esketamine is a rapidly acting intranasal antidepressant. Present-day Esketamine research has limited data in real-world populations. This study aimed to assess Esketamine treatment in a real-world community-based population. This naturalistic retrospective study included 94 individuals age 18 and above diagnosed with TRD, treated with Esketamine in an outpatient setting. The treatment was given in a single clinic, from January 2021 to January 2023, following approval of the Institutional Internal Review Board. The treatment included an acute phase (biweekly treatment, continuing 4-8 weeks), followed by a maintenance phase (once a week to once a month, for 6-12 months). Dosing ranged from 28 mg to 84 mg. Demographic and clinical data were retrospectively gathered. Depressive symptoms were assessed using the Quick Inventory of Depressive Symptomatology, at baseline and during each treatment phase. All patients completed the acute phase. About 60% completed the maintenance phase. Linear improvement of depressive symptoms was revealed in both phases. A sub-analysis of patients with comorbid personality disorder revealed a similar improvement pattern in the acute phase with milder improvement during the maintenance phase, compared to the other patients. This study supports the use of Esketamine for TRD, including patients with comorbid personality disorder and previous electroconvulsive therapy.

Machine Learning-Based Prediction of Escitalopram and Sertraline Side Effects With Pharmacokinetic Data in Children and Adolescents

Selective serotonin reuptake inhibitors (SSRI) are the first-line pharmacologic treatment for anxiety and depressive disorders in children and adolescents. Many patients experience side effects that are difficult to predict, are associated with significant morbidity, and can lead to treatment discontinuation. Variation in SSRI pharmacokinetics could explain differences in treatment outcomes, but this is often overlooked as a contributing factor to SSRI tolerability. This study evaluated data from 288 escitalopram-treated and 255 sertraline-treated patients ≤ 18 years old to develop machine learning models to predict side effects using electronic health record data and Bayesian estimated pharmacokinetic parameters. Trained on a combined cohort of escitalopram- and sertraline-treated patients, a penalized logistic regression model achieved an area under the receiver operating characteristic curve (AUROC) of 0.77 (95% confidence interval (CI): 0.66-0.88), with 0.69 sensitivity (95% CI: 0.54-0.86), and 0.82 specificity (95% CI: 0.72-0.87). Medication exposure, clearance, and time since the last dose increase were among the top features. Individual escitalopram and sertraline models yielded an AUROC of 0.73 (95% CI: 0.65-0.81) and 0.64 (95% CI: 0.55-0.73), respectively. Post hoc analysis showed sertraline-treated patients with activation side effects had slower clearance (P = 0.01), which attenuated after accounting for age (P = 0.055). These findings raise the possibility that a machine learning approach leveraging pharmacokinetic data can predict escitalopram- and sertraline-related side effects. Clinicians may consider differences in medication pharmacokinetics, especially during dose titration and as opposed to relying on dose, when managing side effects. With further validation, application of this model to predict side effects may enhance SSRI precision dosing strategies in youth.

Multiomics and blood-based biomarkers of electroconvulsive therapy in severe and treatment-resistant depression: study protocol of the DetECT study

Electroconvulsive therapy (ECT) is commonly used to treat treatment-resistant depression (TRD). However, our knowledge of the ECT-induced molecular mechanisms causing clinical improvement is limited. To address this issue, we developed the single-center, prospective observational DetECT study ("Multimodal Biomarkers of ECT in TRD"; registered 18/07/2022, www.clinicalTrials.gov , NCT05463562). Its objective is to identify molecular, psychological, socioeconomic, and clinical biomarkers of ECT response in TRD. We aim to recruit n = 134 patients in 3 years. Over the course of 12 biweekly ECT sessions (± 7 weeks), participant blood is collected before and 1 h after the first and seventh ECT and within 1 week after the twelfth session. In pilot subjects (first n = 10), additional blood draws are performed 3 and 6 h after the first ECT session to determine the optimal post-ECT blood draw interval. In blood samples, multiomic analyses are performed focusing on genotyping, epigenetics, RNA sequencing, neuron-derived exosomes, purines, and immunometabolics. To determine clinical response and side effects, participants are asked weekly to complete four standardized self-rating questionnaires on depressive and somatic symptoms. Additionally, clinician ratings are obtained three times (weeks 1, 4, and 7) within structured clinical interviews. Medical and sociodemographic data are extracted from patient records. The multimodal data collected are used to perform the conventional statistics as well as mixed linear modeling to identify clusters that link biobehavioural measures to ECT response. The DetECT study can provide important insight into the complex mechanisms of ECT in TRD and a step toward biologically informed and data-driven-based ECT biomarkers.

Explainable multimodal prediction of treatment-resistance in patients with depression leveraging brain morphometry and natural language processing

Although 20 % of patients with depression receiving treatment do not achieve remission, predicting treatment-resistant depression (TRD) remains challenging. In this study, we aimed to develop an explainable multimodal prediction model for TRD using structured electronic medical record data, brain morphometry, and natural language processing. In total, 247 patients with a new depressive episode were included. TRD-predictive models were developed based on the combination of following parameters: selected tabular dataset features, independent components-map weightings from brain T1-weighted magnetic resonance imaging (MRI), and topic probabilities from clinical notes. All models applied the extreme gradient boosting (XGBoost) algorithm via five-fold cross-validation. The model using all data sources showed the highest area under the receiver operating characteristic of 0.794, followed by models that used combined brain MRI and structured data, brain MRI and clinical notes, clinical notes and structured data, brain MRI only, structured data only, and clinical notes only (0.770, 0.762, 0.728, 0.703, 0.684, and 0.569, respectively). Classifications of TRD were driven by several predictors, such as previous exposure to antidepressants and antihypertensive medications, sensorimotor network, default mode network, and somatic symptoms. Our findings suggest that a combination of clinical data with neuroimaging and natural language processing variables improves the prediction of TRD.

Examining factors related to low performance of predicting remission in participants with major depressive disorder using neuroimaging data and other clinical features

Major depressive disorder (MDD), a prevalent mental health issue, affects more than 8% of the US population, and almost 17% in the young group of 18-25 years old. Since Covid-19, its prevalence has become even more significant. However, the remission (being free of depression) rates of first-line antidepressant treatments on MDD are only about 30%. To improve treatment outcomes, researchers have built various predictive models for treatment responses and yet none of them have been adopted in clinical use. One reason is that most predictive models are based on data from subjective questionnaires, which are less reliable. Neuroimaging data are promising objective prognostic factors, but they are expensive to obtain and hence predictive models using neuroimaging data are limited and such studies were usually in small scale (N<100). In this paper, we proposed an advanced machine learning (ML) pipeline for small training dataset with large number of features. We implemented multiple imputation for missing data and repeated K-fold cross validation (CV) to robustly estimate predictive performances. Different feature selection methods and stacking methods using 6 general ML models including random forest, gradient boosting decision tree, XGBoost, penalized logistic regression, support vector machine (SVM), and neural network were examined to evaluate the model performances. All predictive models were compared using model performance metrics such as accuracy, balanced accuracy, area under ROC curve (AUC), sensitivity and specificity. Our proposed ML pipeline was applied to a training dataset and obtained an accuracy and AUC above 0.80. But such high performance failed while applying our ML pipeline using an external validation dataset from the EMBARC study which is a multi-center study. We further examined the possible reasons especially the site heterogeneity issue.

A genetic risk score to predict treatment nonresponse in psychotic depression

Psychotic depression is a severe and difficult-to-treat subtype of major depressive disorder for which higher rates of treatment-resistant depression were found. Studies have been performed aiming to predict treatment-resistant depression or treatment nonresponse. However, most of these studies excluded patients with psychotic depression. We created a genetic risk score (GRS) based on a large treatment-resistant depression genome-wide association study. We tested whether this GRS was associated with nonresponse, nonremission and the number of prior adequate antidepressant trials in patients with a psychotic depression. Using data from a randomized clinical trial with patients with a psychotic depression (n = 122), we created GRS deciles and calculated positive prediction values (PPV), negative predictive values (NPV) and odds ratios (OR). Nonresponse and nonremission were assessed after 7 weeks of treatment with venlafaxine, imipramine or venlafaxine plus quetiapine. The GRS was negatively correlated with treatment response (r = -0.32, p = 0.0023, n = 88) and remission (r = -0.31, p = 0.0037, n = 88), but was not correlated with the number of prior adequate antidepressant trials. For patients with a GRS in the top 10%, we observed a PPV of 100%, a NPV of 73.7% and an OR of 52.4 (p = 0.00072, n = 88) for nonresponse. For nonremission, a PPV of 100%, a NPV of 51.9% and an OR of 21.3 (p = 0.036, n = 88) was observed for patients with a GRS in the top 10%. Overall, an increased risk for nonresponse and nonremission was seen in patients with GRSs in the top 40%. Our results suggest that a treatment-resistant depression GRS is predictive of treatment nonresponse and nonremission in psychotic depression.

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

Prediction of depression treatment outcome from multimodal data: a CAN-BIND-1 report

BACKGROUND

Prediction of treatment outcomes is a key step in improving the treatment of major depressive disorder (MDD). The Canadian Biomarker Integration Network in Depression (CAN-BIND) aims to predict antidepressant treatment outcomes through analyses of clinical assessment, neuroimaging, and blood biomarkers.

METHODS

In the CAN-BIND-1 dataset of 192 adults with MDD and outcomes of treatment with escitalopram, we applied machine learning models in a nested cross-validation framework. Across 210 analyses, we examined combinations of predictive variables from three modalities, measured at baseline and after 2 weeks of treatment, and five machine learning methods with and without feature selection. To optimize the predictors-to-observations ratio, we followed a tiered approach with 134 and 1152 variables in tier 1 and tier 2 respectively.

RESULTS

A combination of baseline tier 1 clinical, neuroimaging, and molecular variables predicted response with a mean balanced accuracy of 0.57 (best model mean 0.62) compared to 0.54 (best model mean 0.61) in single modality models. Adding week 2 predictors improved the prediction of response to a mean balanced accuracy of 0.59 (best model mean 0.66). Adding tier 2 features did not improve prediction.

CONCLUSIONS

A combination of clinical, neuroimaging, and molecular data improves the prediction of treatment outcomes over single modality measurement. The addition of measurements from the early stages of treatment adds precision. Present results are limited by lack of external validation. To achieve clinically meaningful prediction, the multimodal measurement should be scaled up to larger samples and the robustness of prediction tested in an external validation dataset.

Perceived antidepressant efficacy associated with reduced negative and enhanced neutral mnemonic discrimination

Introduction

While antidepressants are one of the first-line treatments for depression, the mechanisms underlying antidepressant action are unclear. Furthermore, the extent to which antidepressants impact emotional and cognitive dysfunction in depression requires more fine-grained approaches toward measuring these impacts in humans. Depression is associated with emotion and mood dysregulation in addition to cognitive deficits. Depressed individuals experience general memory impairment as well as a negativity bias in episodic memory, where negative events are better remembered than positive or neutral events. One potential mechanism hypothesized to underlie the negativity bias in memory is dysfunctional hippocampal pattern separation, in which depressed individuals tend to show impaired general pattern separation but enhanced negative pattern separation. Mnemonic discrimination tasks have been designed to tax hippocampal pattern separation in humans and provide a powerful approach to develop a mechanistic account for cognitive dysfunction in depression. While antidepressants have been examined primarily in rodent models in the context of hippocampal pattern separation, this has yet to be examined in humans.

Methods

Here, we investigated how antidepressant usage and their perceived efficacy was associated with emotional mnemonic discrimination, given our prior work indicating a negativity bias for mnemonic discrimination in individuals with greater depressive symptoms.

Results

We found that individuals who reported a greater improvement in their depressive symptoms after taking antidepressants (responders) showed reduced negative and enhanced neutral mnemonic discrimination compared to those with little to no improvement (non-responders). Perceived antidepressant efficacy was the strongest predictor of a reduction in the negativity bias for mnemonic discrimination, even when controlling for current depressive symptoms, antidepressant type, and other relevant factors.

Discussion

These results suggest that antidepressants, when effective, can shift memory dynamics toward healthy function.

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.

Detection of Depression-Related Tweets in Mexico Using Crosslingual Schemes and Knowledge Distillation

Mental health problems are one of the various ills that afflict the world’s population. Early diagnosis and medical care are public health problems addressed from various perspectives. Among the mental illnesses that most afflict the population is depression; its early diagnosis is vitally important, as it can trigger more severe illnesses, such as suicidal ideation. Due to the lack of homogeneity in current diagnostic tools, the community has focused on using AI tools for opportune diagnosis. Unfortunately, there is a lack of data that allows the use of IA tools for the Spanish language. Our work has a cross-lingual scheme to address this issue, allowing us to identify Spanish and English texts. The experiments demonstrated the methodology’s effectiveness with an F1-score of 0.95. With this methodology, we propose a method to solve a classification problem for depression tweets (or short texts) by reusing English language databases with insufficient data to generate a classification model, such as in the Spanish language. We also validated the information obtained with public data to analyze the behavior of depression in Mexico during the COVID-19 pandemic. Our results show that the use of these methodologies can serve as support, not only in the diagnosis of depression, but also in the construction of different language databases that allow the creation of more efficient diagnostic tools.

Psychedelics: Science sabotaged by Social Media

The substantial challenges facing high and low dose psychedelic drug development to achieve regulatory approval have been documented in the scientific literature. These limitations have not deterred drug developers and social media from repeatedly misleading patients, the public and health professionals. Developing "micro doses" of psychedelics overcomes many of the scientific and regulatory challenges of high dose psychedelics. If micro-dosing could be shown to be efficacious and safe for long term use, it could be administered in the typical model for treatment of mental disorders. Such a model would be more cost effective than the high dose/intense psychotherapy model currently described and could be readily available to all individuals who need another medication option. Outpatient psychotherapeutic agents have a clear route for approval and would be unlikely to be burdened by the extensive Risks Evaluation and Mitigation Strategy needed for high dose use. There may be a different therapeutic role for both high and low dose psychedelic agents. This article is part of the Special Issue on "National Institutes of Health Psilocybin Research Speaker Series".

Role of the mesolimbic dopamine pathway in the antidepressant effects of ketamine

Depression is a complex and highly heterogeneous disorder which diagnosis is based on an exceedingly variable set of clinical symptoms. Current treatments focus almost exclusively on the manipulation of monoamine neurotransmitter systems, but despite considerable efforts, these remain inadequate for a significant proportion of those afflicted by the disorder. The emergence of racemic (R, S)-ketamine as a fast-acting antidepressant has provided an exciting new path for the study of major depressive disorder (MDD) and the search for better therapeutics for its treatment. Previous work suggested that ketamine's mechanism of action is primarily mediated via blockaded of N-methyl-d-aspartate (NMDA) receptors, however, this is an area of active research and clinical and preclinical evidence now indicate that ketamine acts on multiple systems. The last couple of decades have cemented the mesolimbic dopamine reward pathway's involvement in the pathogenesis of MDD and related mood disorders. Exposure to negative stress dysregulates dopamine neuronal activity disrupting reward and motivational processes resulting in anhedonia (lack of pleasure), a hallmark symptom of depression. Although the mechanism(s) underlying ketamine's antidepressant activity continue to be elucidated, current evidence indicate that its therapeutic effects are mediated, at least in part, via long-lasting synaptic changes and subsequent molecular adaptations in brain regions within the mesolimbic dopamine system. Notwithstanding, ketamine is a drug of abuse, and this liability may pose limitations for long term use as an antidepressant. This review outlines the current knowledge of ketamine's actions within the mesolimbic dopamine system and its abuse potential. This article is part of the Special Issue on 'Ketamine and its Metabolites'.

Temporal multi-step predictive modeling of remission in major depressive disorder using early stage treatment data; STAR*D based machine learning approach

BACKGROUND

Artificial intelligence is currently being used to facilitate early disease detection, better understand disease progression, optimize medication/treatment dosages, and uncover promising novel treatments and potential outcomes.

METHODS

Utilizing the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) dataset, we built a machine learning model to predict depression remission rates using same clinical data as features for each of the first three antidepressant treatment steps in STAR*D. We only used early treatment data (baseline and first follow up) in each STAR*D step to temporally analyze predictive features of remission at the end of the step.

RESULTS

Our model showed significant prediction performance across the three treatment steps, At step 1, Model accuracy was 66 %; sensitivity-65 %, specificity-67 %, positive predictive value (PPV)-65.5 %, and negative predictive value (NPV)-66.6 %. At step 2, model accuracy was 71.3 %, sensitivity-74.3 %, specificity-69 %, PPV-64.5 %, and NPV-77.9 %. At step 3, accuracy reached 84.6 %; sensitivity-69 %, specificity-88.8 %, PPV-67 %, and NPV-91.1 %. Across all three steps, the early Quick Inventory of Depressive Symptomatology-Self-Report (QIDS-SR) scores were key elements in predicting the final treatment outcome. The model also identified key sociodemographic factors that predicted treatment remission at different steps.

LIMITATIONS

The retrospective design, lack of replication in an independent dataset, and the use of "a complete case analysis" model in our analysis.

CONCLUSIONS

This proof-of-concept study showed that using early treatment data, multi-step temporal prediction of depressive symptom remission results in clinically useful accuracy rates. Whether these predictive models are generalizable deserves further study.

Machine Learning and Pharmacogenomics at the Time of Precision Psychiatry

Traditional medicine and biomedical sciences are reaching a turning point because of the constantly growing impact and volume of Big Data. Machine Learning (ML) techniques and related algorithms play a central role as diagnostic, prognostic, and decision-making tools in this field. Another promising area becoming part of everyday clinical practice is personalized therapy and pharmacogenomics. Applying ML to pharmacogenomics opens new frontiers to tailored therapeutical strategies to help clinicians choose drugs with the best response and fewer side effects, operating with genetic information and combining it with the clinical profile. This systematic review aims to draw up the state-of-the-art ML applied to pharmacogenomics in psychiatry. Our research yielded fourteen papers; most were published in the last three years. The sample comprises 9,180 patients diagnosed with mood disorders, psychoses, or autism spectrum disorders. Prediction of drug response and prediction of side effects are the most frequently considered domains with the supervised ML technique, which first requires training and then testing. The random forest is the most used algorithm; it comprises several decision trees, reduces the training set's overfitting, and makes precise predictions. ML proved effective and reliable, especially when genetic and biodemographic information were integrated into the algorithm. Even though ML and pharmacogenomics are not part of everyday clinical practice yet, they will gain a unique role in the next future in improving personalized treatments in psychiatry.

Mitochondrial Impairment: A Common Motif in Neuropsychiatric Presentation? The Link to the Tryptophan-Kynurenine Metabolic System

Nearly half a century has passed since the discovery of cytoplasmic inheritance of human chloramphenicol resistance. The inheritance was then revealed to take place maternally by mitochondrial DNA (mtDNA). Later, a number of mutations in mtDNA were identified as a cause of severe inheritable metabolic diseases with neurological manifestation, and the impairment of mitochondrial functions has been probed in the pathogenesis of a wide range of illnesses including neurodegenerative diseases. Recently, a growing number of preclinical studies have revealed that animal behaviors are influenced by the impairment of mitochondrial functions and possibly by the loss of mitochondrial stress resilience. Indeed, as high as 54% of patients with one of the most common primary mitochondrial diseases, mitochondrial encephalomyopathy with lactic acidosis and stroke-like episodes (MELAS) syndrome, present psychiatric symptoms including cognitive impairment, mood disorder, anxiety, and psychosis. Mitochondria are multifunctional organelles which produce cellular energy and play a major role in other cellular functions including homeostasis, cellular signaling, and gene expression, among others. Mitochondrial functions are observed to be compromised and to become less resilient under continuous stress. Meanwhile, stress and inflammation have been linked to the activation of the tryptophan (Trp)-kynurenine (KYN) metabolic system, which observably contributes to the development of pathological conditions including neurological and psychiatric disorders. This review discusses the functions of mitochondria and the Trp-KYN system, the interaction of the Trp-KYN system with mitochondria, and the current understanding of the involvement of mitochondria and the Trp-KYN system in preclinical and clinical studies of major neurological and psychiatric diseases.

Investigation of Psychoactive Medications: Challenges and a Practical and Scalable New Path

In the last two decades the validity of clinical trials in psychiatry has been subject to discussion. The most accepted clinical study method in the medical area, randomized controlled trial (RCT), faces significant problems when applied to the psychiatric world. One of the causes for this scenario is the strict participant inclusion and exclusion criteria that may not represent the real world. The inconsistency of the different endpoint parameters that are used in the field is another cause. We think that psychiatric RCTs' challenges, together with the underlying complexity of psychiatry, lead to a problematic clinical practice. Today, psychoactive drugs are routinely tested not in an official clinical trial setting. Off-label psychoactive drugs are commonly prescribed, and other substances, such as herbal remedies, are also regularly consumed. Learning from those real-life experiments can teach us useful lessons. Real-world data (RWD) includes information about heterogeneous patient populations, and it can be measured with standardized parameters. Collecting RWD can also address the need for systematically documenting and sharing case reports' outcomes. We suggest using digital tools to capture objective and continuous behavioral data from patients passively. New conclusions will be constantly drawn, possibly allowing more personalized treatment outcomes. The relevant next-generation decision support tools are already available.

Predicting the Treatment Outcomes of Antidepressants Using a Deep Neural Network of Deep Learning in Drug-Naïve Major Depressive Patients

Predicting the treatment response to antidepressants by pretreatment features would be useful, as up to 70–90% of patients with major depressive disorder (MDD) do not respond to treatment as expected. Therefore, we aim to establish a deep neural network (DNN) model of deep learning to predict the treatment outcomes of antidepressants in drug-naïve and first-diagnosis MDD patients during severe depressive stage using different domains of signature profiles of clinical features, peripheral biochemistry, psychosocial factors, and genetic polymorphisms. The multilayer feedforward neural network containing two hidden layers was applied to build models with tenfold cross-validation. The areas under the curve (AUC) of the receiver operating characteristic curves were used to evaluate the performance of the models. The results demonstrated that the AUCs of the model ranged between 0.7 and 0.8 using a combination of different domains of categorical variables. Moreover, models using the extracted variables demonstrated better performance, and the best performing model was characterized by an AUC of 0.825, using the levels of cortisol and oxytocin, scales of social support and quality of life, and polymorphisms of the OXTR gene. A complex interactions model developed through DNN could be useful at the clinical level for predicting the individualized outcomes of antidepressants.

Electrophysiological correlates and predictors of the antidepressant response to repeated ketamine infusions in treatment-resistant depression

BACKGROUND

Sub-anesthetic ketamine doses rapidly reduce depressive symptoms, although additional investigations of the underlying neural mechanisms and the prediction of response outcomes are needed. Electroencephalographic (EEG)-derived measures have shown promise in predicting antidepressant response to a variety of treatments, and are sensitive to ketamine administration. This study examined their utility in characterizing changes in depressive symptoms following single and repeated ketamine infusions.

METHODS

Recordings were obtained from patients with treatment-resistant major depressive disorder (MDD) (N = 24) enrolled in a multi-phase clinical ketamine trial. During the randomized, double-blind, crossover phase (Phase 1), patients received intravenous ketamine (0.5 mg/kg) and midazolam (30 μg/kg), at least 1 week apart. For each medication, three resting, eyes-closed recordings were obtained per session (pre-infusion, immediately post-infusion, 2 h post-infusion), and changes in power (delta, theta1/2/total, alpha1/2/total, beta, gamma), alpha asymmetry, theta cordance, and theta source-localized anterior cingulate cortex activity were quantified. The relationships between ketamine-induced changes with early (Phase 1) and sustained (Phases 2,3: open-label repeated infusions) decreases in depressive symptoms (Montgomery-Åsberg Depression Rating Score, MADRS) and suicidal ideation (MADRS item 10) were examined.

RESULTS

Both medications decreased alpha and theta immediately post-infusion, however, only midazolam increased delta (post-infusion), and only ketamine increased gamma (immediately post- and 2 h post-infusion). Regional- and frequency-specific ketamine-induced EEG changes were related to and predictive of decreases in depressive symptoms (theta, gamma) and suicidal ideation (alpha). Early and sustained treatment responders differed at baseline in surface-level and source-localized theta.

CONCLUSIONS

Ketamine exerts frequency-specific changes on EEG-derived measures, which are related to depressive symptom decreases in treatment-resistant MDD and provide information regarding early and sustained individual response to ketamine.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov: Action of Ketamine in Treatment-Resistant Depression, NCT01945047.

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.

Artificial intelligence: A powerful paradigm for scientific research

Artificial intelligence (AI) coupled with promising machine learning (ML) techniques well known from computer science is broadly affecting many aspects of various fields including science and technology, industry, and even our day-to-day life. The ML techniques have been developed to analyze high-throughput data with a view to obtaining useful insights, categorizing, predicting, and making evidence-based decisions in novel ways, which will promote the growth of novel applications and fuel the sustainable booming of AI. This paper undertakes a comprehensive survey on the development and application of AI in different aspects of fundamental sciences, including information science, mathematics, medical science, materials science, geoscience, life science, physics, and chemistry. The challenges that each discipline of science meets, and the potentials of AI techniques to handle these challenges, are discussed in detail. Moreover, we shed light on new research trends entailing the integration of AI into each scientific discipline. The aim of this paper is to provide a broad research guideline on fundamental sciences with potential infusion of AI, to help motivate researchers to deeply understand the state-of-the-art applications of AI-based fundamental sciences, and thereby to help promote the continuous development of these fundamental sciences.

A New Characterization of Mental Health Disorders Using Digital Behavioral Data: Evidence from Major Depressive Disorder

Mental health disorders are ambiguously defined and diagnosed. The established diagnosis technique, which is based on structured interviews, questionnaires and data subjectively reported by the patients themselves, leaves the mental health field behind other medical areas. We support these statements with examples from major depressive disorder (MDD). The National Institute of Mental Health (NIMH) launched the Research Domain Criteria (RDoC) project in 2009 as a new framework to investigate psychiatric pathologies from a multidisciplinary point of view. This is a good step in the right direction. Contemporary psychiatry considers mental illnesses as diseases that manifest in the mind and arise from the brain, expressed as a behavioral condition; therefore, we claim that these syndromes should be characterized primarily using behavioral characteristics. We suggest the use of smartphones and wearable devices to passively collect quantified behavioral data from patients by utilizing digital biomarkers of mental disorder symptoms. Various digital biomarkers of MDD symptoms have already been detected, and apps for collecting this longitudinal behavioral data have already been developed. This quantified data can be used to determine a patient’s diagnosis and personalized treatment, and thereby minimize the diagnosis rate of comorbidities. As there is a wide spectrum of human behavior, such a fluidic and personalized approach is essential.