Making Individual Prognoses in Psychiatry Using Neuroimaging and Machine Learning

Predicting Antidepressant Treatment Response From Cortical Structure on MRI: A Mega-Analysis From the ENIGMA-MDD Working Group

Accurately predicting individual antidepressant treatment response could expedite the lengthy trial-and-error process of finding an effective treatment for major depressive disorder (MDD). We tested and compared machine learning-based methods that predict individual-level pharmacotherapeutic treatment response using cortical morphometry from multisite longitudinal cohorts. We conducted an international analysis of pooled data from six sites of the ENIGMA-MDD consortium (n = 262 MDD patients; age = 36.5 ± 15.3 years; 154 (59%) female; mean response rate = 57%). Treatment response was defined as a ≥ 50% reduction in symptom severity score after 4-12 weeks post-initiation of antidepressant treatment. Structural MRI was acquired before, or < 14 days after, treatment initiation. The cortex was parcellated using FreeSurfer, from which cortical thickness and surface area were measured. We tested several machine learning pipeline configurations, which varied in (i) the way we presented the cortical data (i.e., average values per region of interest, as a vector containing voxel-wise cortical thickness and surface area measures, and as cortical thickness and surface area projections), (ii) whether we included clinical data, and the (iii) machine learning model (i.e., gradient boosting, support vector machine, and neural network classifiers) and (iv) cross-validation methods (i.e., k-fold and leave-one-site-out) we used. First, we tested if the overall predictive performance of the pipelines was better than chance, with a corrected 10-fold cross-validation permutation test. Second, we compared if some machine learning pipeline configurations outperformed others. In an exploratory analysis, we repeated our first analysis in three subpopulations, namely patients (i) from a single site, (ii) with comparable response rates, and (iii) showing the least (first quartile) and the most (fourth quartile) treatment response, which we call the extreme (non-)responders subpopulation. Finally, we explored the effect of including subcortical volumetric data on model performance. Overall, performance predicting antidepressant treatment response was not significantly better than chance (balanced accuracy = 50.5%; p = 0.66) and did not vary with alternative pipeline configurations. Exploratory analyses revealed that performance across models was only significantly better than chance in the extreme (non-)responders subpopulation (balanced accuracy = 63.9%, p = 0.001). Including subcortical data did not alter the observed model performance. Cortical structural MRI alone could not reliably predict individual pharmacotherapeutic treatment response in MDD. None of the used machine learning pipeline configurations outperformed the others. In exploratory analyses, we found that predicting response in the extreme (non-)responders subpopulation was feasible on both cortical data alone and combined with subcortical data, which suggests that specific MDD subpopulations may exhibit response-related patterns in structural data. Future work may use multimodal data to predict treatment response in MDD.

Decoding Schizophrenia: How AI-Enhanced fMRI Unlocks New Pathways for Precision Psychiatry

Schizophrenia, a highly complex psychiatric disorder, presents significant challenges in diagnosis and treatment due to its multifaceted neurobiological underpinnings. Recent advancements in functional magnetic resonance imaging (fMRI) and artificial intelligence (AI) have revolutionized the understanding and management of this condition. This manuscript explores how the integration of these technologies has unveiled key insights into schizophrenia's structural and functional neural anomalies. fMRI research highlights disruptions in crucial brain regions like the prefrontal cortex and hippocampus, alongside impaired connectivity within networks such as the default mode network (DMN). These alterations correlate with the cognitive deficits and emotional dysregulation characteristic of schizophrenia. AI techniques, including machine learning (ML) and deep learning (DL), have enhanced the detection and analysis of these complex patterns, surpassing traditional methods in precision. Algorithms such as support vector machines (SVMs) and Vision Transformers (ViTs) have proven particularly effective in identifying biomarkers and aiding early diagnosis. Despite these advancements, challenges such as variability in methodologies and the disorder's heterogeneity persist, necessitating large-scale, collaborative studies for clinical translation. Moreover, ethical considerations surrounding data integrity, algorithmic transparency, and patient individuality must guide AI's integration into psychiatry. Looking ahead, AI-augmented fMRI holds promise for tailoring personalized interventions, addressing unique neural dysfunctions, and improving therapeutic outcomes for individuals with schizophrenia. This convergence of neuroimaging and computational innovation heralds a transformative era in precision psychiatry.

Dynamic Real-Time Biosensing Enabled Biorhythm Tracking for Psychiatric Disorders

This review article explores the transformative potential of dynamic, real-time biosensing in biorhythm tracking for psychiatric disorders. Psychiatric diseases, characterized by a complex, heterogeneous, and multifactorial pathophysiology, pose challenges in both diagnosis and treatment. Common denominators in the pathophysiology of psychiatric diseases include disruptions in the stress response, sleep-wake cycle, energy metabolism, and immune response: all of these are characterized by a strong biorhythmic regulation (e.g., circadian), leading to dynamic changes in the levels of biomarkers involved. Technological and practical limitations have hindered the analysis of such dynamic processes to date. The integration of biosensors marks a paradigm shift in psychiatric research. These advanced technologies enable multiplex, non-invasive, and near-continuous analysis of biorhythmic biomarkers in real time, overcoming the constraints of conventional approaches. Focusing on the regulation of the stress response, sleep/wake cycle, energy metabolism, and immune response, biosensing allows for a deeper understanding of the heterogeneous and multifactorial pathophysiology of psychiatric diseases. The potential applications of nanobiosensing in biorhythm tracking, however, extend beyond observation. Continuous monitoring of biomarkers can provide a foundation for personalized medicine in Psychiatry, and allow for the transition from syndromal diagnostic entities to pathophysiology-based psychiatric diagnoses. This evolution promises enhanced disease tracking, early relapse prediction, and tailored disease management and treatment strategies. As non-invasive biosensing continues to advance, its integration into biorhythm tracking holds promise not only to unravel the intricate etiology of psychiatric disorders but also for ushering in a new era of precision medicine, ultimately improving the outcomes and quality of life for individuals grappling with these challenging conditions.

Sex classification from functional brain connectivity: Generalization to multiple datasets

Machine learning (ML) approaches are increasingly being applied to neuroimaging data. Studies in neuroscience typically have to rely on a limited set of training data which may impair the generalizability of ML models. However, it is still unclear which kind of training sample is best suited to optimize generalization performance. In the present study, we systematically investigated the generalization performance of sex classification models trained on the parcelwise connectivity profile of either single samples or compound samples of two different sizes. Generalization performance was quantified in terms of mean across-sample classification accuracy and spatial consistency of accurately classifying parcels. Our results indicate that the generalization performance of parcelwise classifiers (pwCs) trained on single dataset samples is dependent on the specific test samples. Certain datasets seem to "match" in the sense that classifiers trained on a sample from one dataset achieved a high accuracy when tested on the respected other one and vice versa. The pwCs trained on the compound samples demonstrated overall highest generalization performance for all test samples, including one derived from a dataset not included in building the training samples. Thus, our results indicate that both a large sample size and a heterogeneous data composition of a training sample have a central role in achieving generalizable results.

Sex classification from functional brain connectivity: Generalization to multiple datasets Generalizability of sex classifiers

Machine learning (ML) approaches are increasingly being applied to neuroimaging data. Studies in neuroscience typically have to rely on a limited set of training data which may impair the generalizability of ML models. However, it is still unclear which kind of training sample is best suited to optimize generalization performance. In the present study, we systematically investigated the generalization performance of sex classification models trained on the parcelwise connectivity profile of either single samples or a compound sample containing data from four different datasets. Generalization performance was quantified in terms of mean across-sample classification accuracy and spatial consistency of accurately classifying parcels. Our results indicate that generalization performance of pwCs trained on single dataset samples is dependent on the specific test samples. Certain datasets seem to "match" in the sense that classifiers trained on a sample from one dataset achieved a high accuracy when tested on the respected other one and vice versa. The pwC trained on the compound sample demonstrated overall highest generalization performance for all test samples, including one derived from a dataset not included in building the training samples. Thus, our results indicate that a big and heterogenous training sample comprising data of multiple datasets is best suited to achieve generalizable results.

oFVSD: a Python package of optimized forward variable selection decoder for high-dimensional neuroimaging data

The complexity and high dimensionality of neuroimaging data pose problems for decoding information with machine learning (ML) models because the number of features is often much larger than the number of observations. Feature selection is one of the crucial steps for determining meaningful target features in decoding; however, optimizing the feature selection from such high-dimensional neuroimaging data has been challenging using conventional ML models. Here, we introduce an efficient and high-performance decoding package incorporating a forward variable selection (FVS) algorithm and hyper-parameter optimization that automatically identifies the best feature pairs for both classification and regression models, where a total of 18 ML models are implemented by default. First, the FVS algorithm evaluates the goodness-of-fit across different models using the k-fold cross-validation step that identifies the best subset of features based on a predefined criterion for each model. Next, the hyperparameters of each ML model are optimized at each forward iteration. Final outputs highlight an optimized number of selected features (brain regions of interest) for each model with its accuracy. Furthermore, the toolbox can be executed in a parallel environment for efficient computation on a typical personal computer. With the optimized forward variable selection decoder (oFVSD) pipeline, we verified the effectiveness of decoding sex classification and age range regression on 1,113 structural magnetic resonance imaging (MRI) datasets. Compared to ML models without the FVS algorithm and with the Boruta algorithm as a variable selection counterpart, we demonstrate that the oFVSD significantly outperformed across all of the ML models over the counterpart models without FVS (approximately 0.20 increase in correlation coefficient, r, with regression models and 8% increase in classification models on average) and with Boruta variable selection algorithm (approximately 0.07 improvement in regression and 4% in classification models). Furthermore, we confirmed the use of parallel computation considerably reduced the computational burden for the high-dimensional MRI data. Altogether, the oFVSD toolbox efficiently and effectively improves the performance of both classification and regression ML models, providing a use case example on MRI datasets. With its flexibility, oFVSD has the potential for many other modalities in neuroimaging. This open-source and freely available Python package makes it a valuable toolbox for research communities seeking improved decoding accuracy.

Single-label machine learning classification revealed some hidden but inter-related causes of five psychotic disorder diseases

Psychotic disorder diseases (PDD) or mental illnesses are group of illnesses that affect the minds and impair the cognitive ability, retard emotional ability and obstruct the process of communication and relationship with others and are characterized by delusions, hallucinations and disoriented or disordered pattern of thinking. Prognosis of PDD is not sufficient because of the nature of the diseases and as such adequate form of diagnosis is required to detect, manage and treat the illness. This paper applied the single-label classification (SLC) machine learning approach in mining of electronic health records of people with PDD in Nigeria using eleven independent (demographic) variables and five PDD as target variables. The five PDDs are Insomnia, Schizophrenia, Minimal Brain dysfunction (MBD), which is also known as Attention-Deficit/Hyperactivity Disorder (ADHD), Vascular Dementia (VD) and Bipolar Disorder (BD). The aim of using SLC is that it would be easier to detect some PDDs that are related to each other without the loss of information, which is a plus over multi-label classification (MLC). ReliefF algorithm was used at each experiment to precipitate the order of importance of the independent variables and redundant variables were excluded from the analysis. The order of the variables in feature selection was matched with feature importance after the classifications and quantified using the Spearman rank correlation coefficient. The data was divided into: 70% for training and 30% for testing. Four new performance metrics adapted from the root mean square (RMSE) were proposed and used to measure the differences between the performance results of the 10 Machine learning models in terms of the training and testing and secondly, feature and without feature selection. The new metrics are close to zero which is an indication that the use of feature selection and cross validation may not greatly affects the accuracy of the SLC. When the PDDs are included as predictors for classifying others, there was a tremendous improvement as revealed by the four new metrics for classification accuracy (CA), precision and recall. Analysis of variance showed the four different metrics differs significantly for classification accuracy (CA) and precision. However, there were no significant difference between the CA and precision when the duo are compared together across the four evaluation metrics at p value less than 0.05.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Restoring the missing person to personalized medicine and precision psychiatry

Precision psychiatry has emerged as part of the shift to personalized medicine and builds on frameworks such as the U.S. National Institute of Mental Health Research Domain Criteria (RDoC), multilevel biological "omics" data and, most recently, computational psychiatry. The shift is prompted by the realization that a one-size-fits all approach is inadequate to guide clinical care because people differ in ways that are not captured by broad diagnostic categories. One of the first steps in developing this personalized approach to treatment was the use of genetic markers to guide pharmacotherapeutics based on predictions of pharmacological response or non-response, and the potential risk of adverse drug reactions. Advances in technology have made a greater degree of specificity or precision potentially more attainable. To date, however, the search for precision has largely focused on biological parameters. Psychiatric disorders involve multi-level dynamics that require measures of phenomenological, psychological, behavioral, social structural, and cultural dimensions. This points to the need to develop more fine-grained analyses of experience, self-construal, illness narratives, interpersonal interactional dynamics, and social contexts and determinants of health. In this paper, we review the limitations of precision psychiatry arguing that it cannot reach its goal if it does not include core elements of the processes that give rise to psychopathological states, which include the agency and experience of the person. Drawing from contemporary systems biology, social epidemiology, developmental psychology, and cognitive science, we propose a cultural-ecosocial approach to integrating precision psychiatry with person-centered care.

Threats to external validity in the neuroprediction of substance use treatment outcomes

Background: Tools predicting individual relapse risk would invaluably inform clinical decision-making (e.g. level-of-care) in substance use treatment. Studies of neuroprediction - use of neuromarkers to predict individual outcomes - have the dual potential to create such tools and inform etiological models leading to new treatments. However, financial limitations, statistical power demands, and related factors encourage restrictive selection criteria, yielding samples that do not fully represent the target population. This problem may be further compounded by a lack of statistical optimism correction in neuroprediction research, resulting in predictive models that are overfit to already-restricted samples.Objectives: This systematic review aims to identify potential threats to external validity related to restrictive selection criteria and underutilization of optimism correction in the existing neuroprediction literature targeting substance use treatment outcomes.Methods: Sixty-seven studies of neuroprediction in substance use treatment were identified and details of sample selection criteria and statistical optimism correction were extracted.Results: Most publications were found to report restrictive selection criteria (e.g. excluding psychiatric (94% of publications) and substance use comorbidities (69% of publications)) that would rule-out a considerable portion of the treatment population. Furthermore, only 21% of publications reported optimism correction.Conclusion: Restrictive selection criteria and underutilization of optimism correction are common in the existing literature and may limit the generalizability of identified neural predictors to the target population whose treatment they would ultimately inform. Greater attention to the inclusivity and generalizability of addiction neuroprediction research, as well as new opportunities provided through open science initiatives, have the potential to address this issue.

Current opinions on the present and future use of functional near-infrared spectroscopy in psychiatry

Functional near-infrared spectroscopy (fNIRS) is an optical imaging technique for assessing human brain activity by noninvasively measuring the fluctuation of cerebral oxygenated- and deoxygenated-hemoglobin concentrations associated with neuronal activity. Owing to its superior mobility, low cost, and good tolerance for motion, the past few decades have witnessed a rapid increase in the research and clinical use of fNIRS in a variety of psychiatric disorders. In this perspective article, we first briefly summarize the state-of-the-art concerning fNIRS research in psychiatry. In particular, we highlight the diverse applications of fNIRS in psychiatric research, the advanced development of fNIRS instruments, and novel fNIRS study designs for exploring brain activity associated with psychiatric disorders. We then discuss some of the open challenges and share our perspectives on the future of fNIRS in psychiatric research and clinical practice. We conclude that fNIRS holds promise for becoming a useful tool in clinical psychiatric settings with respect to developing closed-loop systems and improving individualized treatments and diagnostics.

Classification and prediction of cognitive performance differences in older age based on brain network patterns using a machine learning approach

Age-related cognitive decline varies greatly in healthy older adults, which may partly be explained by differences in the functional architecture of brain networks. Resting-state functional connectivity (RSFC) derived network parameters as widely used markers describing this architecture have even been successfully used to support diagnosis of neurodegenerative diseases. The current study aimed at examining whether these parameters may also be useful in classifying and predicting cognitive performance differences in the normally aging brain by using machine learning (ML). Classifiability and predictability of global and domain-specific cognitive performance differences from nodal and network-level RSFC strength measures were examined in healthy older adults from the 1000BRAINS study (age range: 55-85 years). ML performance was systematically evaluated across different analytic choices in a robust cross-validation scheme. Across these analyses, classification performance did not exceed 60% accuracy for global and domain-specific cognition. Prediction performance was equally low with high mean absolute errors (MAEs ≥ 0.75) and low to none explained variance (R2 ≤ 0.07) for different cognitive targets, feature sets, and pipeline configurations. Current results highlight limited potential of functional network parameters to serve as sole biomarker for cognitive aging and emphasize that predicting cognition from functional network patterns may be challenging.

Deriving psychiatric symptom-based biomarkers from multivariate relationships between psychophysiological and biochemical measures

Identification of biomarkers for psychiatric disorders remains very challenging due to substantial symptom heterogeneity and diagnostic comorbidity, limiting the ability to map symptoms to underlying neurobiology. Dimensional symptom clusters, such as anhedonia, hyperarousal, etc., are complex and arise due to interactions of a multitude of complex biological relationships. The primary aim of the current investigation was to use multi-set canonical correlation analysis (mCCA) to derive biomarkers (biochemical, physiological) linked to dimensional symptoms across the anxiety and depressive spectrum. Active-duty service members (N = 2,592) completed standardized depression, anxiety and posttraumatic stress questionnaires and several psychophysiological and biochemical assays. Using this approach, we identified two phenotype associations between distinct physiological and biological phenotypes. One was characterized by symptoms of dysphoric arousal (anhedonia, anxiety, hypervigilance) which was associated with low blood pressure and startle reactivity. This finding is in line with previous studies suggesting blunted physiological reactivity is associated with subpopulations endorsing anxiety with comorbid depressive features. A second phenotype of anxious fatigue (high anxiety and reexperiencing/avoidance symptoms coupled with fatigue) was associated with elevated blood levels of norepinephrine and the inflammatory marker C-reactive protein in conjunction with high blood pressure. This second phenotype may describe populations in which inflammation and high sympathetic outflow might contribute to anxious fatigue. Overall, these findings support the growing consensus that distinct neuropsychiatric symptom patterns are associated with differential physiological and blood-based biological profiles and highlight the potential of mCCA to reveal important psychiatric symptom biomarkers from several psychophysiological and biochemical measures.

Model Building in Forensic Psychiatry: A Machine Learning Approach to Screening Offender Patients with SSD

Today’s extensive availability of medical data enables the development of predictive models, but this requires suitable statistical methods, such as machine learning (ML). Especially in forensic psychiatry, a complex and cost-intensive field with risk assessments and predictions of treatment outcomes as central tasks, there is a need for such predictive tools, for example, to anticipate complex treatment courses and to be able to offer appropriate therapy on an individualized basis. This study aimed to develop a first basic model for the anticipation of adverse treatment courses based on prior compulsory admission and/or conviction as simple and easily objectifiable parameters in offender patients with a schizophrenia spectrum disorder (SSD). With a balanced accuracy of 67% and an AUC of 0.72, gradient boosting proved to be the optimal ML algorithm. Antisocial behavior, physical violence against staff, rule breaking, hyperactivity, delusions of grandeur, fewer feelings of guilt, the need for compulsory isolation, cannabis abuse/dependence, a higher dose of antipsychotics (measured by the olanzapine half-life) and an unfavorable legal prognosis emerged as the ten most influential variables out of a dataset with 209 parameters. Our findings could demonstrate an example of the use of ML in the development of an easy-to-use predictive model based on few objectifiable factors.

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.

Multimodal magnetic resonance neuroimaging measures characteristic of early cART-treated pediatric HIV: A feature selection approach

Children with perinatally acquired HIV (CPHIV) have poor cognitive outcomes despite early combination antiretroviral therapy (cART). While CPHIV-related brain alterations can be investigated separately using proton magnetic resonance spectroscopy (1 H-MRS), structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and functional MRI (fMRI), a set of multimodal MRI measures characteristic of children on cART has not been previously identified. We used the embedded feature selection of a logistic elastic-net (EN) regularization to select neuroimaging measures that distinguish CPHIV from controls and measured their classification performance via the area under the receiver operating characteristic curve (AUC) using repeated cross validation. We also wished to establish whether combining MRI modalities improved the models. In single modality analysis, sMRI volumes performed best followed by DTI, whereas individual EN models on spectroscopic, gyrification, and cortical thickness measures showed no class discrimination capability. Adding DTI and 1 H-MRS in basal measures to sMRI volumes produced the highest classification performancevalidation accuracy = 85 % AUC = 0.80 . The best multimodal MRI set consisted of 22 DTI and sMRI volume features, which included reduced volumes of the bilateral globus pallidus and amygdala, as well as increased mean diffusivity (MD) and radial diffusivity (RD) in the right corticospinal tract in cART-treated CPHIV. Consistent with previous studies of CPHIV, select subcortical volumes obtained from sMRI provide reasonable discrimination between CPHIV and controls. This may give insight into neuroimaging measures that are relevant in understanding the effects of HIV on the brain, thereby providing a starting point for evaluating their link with cognitive performance in CPHIV.

Can cognition help predict suicide risk in patients with major depressive disorder? A machine learning study

BACKGROUND

Previous studies suggest that deficits in cognition may increase the risk of suicide. Our study aims to develop a machine learning (ML) algorithm-based suicide risk prediction model using cognition in patients with major depressive disorder (MDD).

METHODS

Participants comprised 52 depressed suicide attempters (DSA) and 61 depressed non-suicide attempters (DNS), and 98 healthy controls (HC). All participants were required to complete a series of questionnaires, the Suicide Stroop Task (SST) and the Iowa Gambling Task (IGT). The performance in IGT was analyzed using repeated measures ANOVA. ML with extreme gradient boosting (XGBoost) classification algorithm and locally explanatory techniques assessed performance and relative importance of characteristics for predicting suicide attempts. Prediction performances were compared with the area under the curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI).

RESULTS

DSA and DNS preferred to select the card from disadvantageous decks (decks "A" + "B") under risky situation (p = 0.023) and showed a significantly poorer learning effect during the IGT (F = 2.331, p = 0.019) compared with HC. Performance of XGBoost model based on demographic and clinical characteristics was compared with that of the model created after adding cognition data (AUC, 0.779 vs. 0.819, p > 0.05). The net benefit of model was improved and cognition resulted in continuous reclassification improvement with NRI of 5.3%. Several clinical dimensions were significant predictors in the XGBoost classification algorithm.

LIMITATIONS

A limited sample size and failure to include sufficient suicide risk factors in the predictive model.

CONCLUSION

This study demonstrate that cognitive deficits may serve as an important risk factor to predict suicide attempts in patients with MDD. Combined with other demographic characteristics and attributes drawn from clinical questionnaires, cognitive function can improve the predictive effectiveness of the ML model. Additionally, explanatory ML models can help clinicians detect specific risk factors for each suicide attempter within MDD patients. These findings may be helpful for clinicians to detect those at high risk of suicide attempts quickly and accurately, and help them make proactive treatment decisions.

Quantifying Deviations of Brain Structure and Function in Major Depressive Disorder Across Neuroimaging Modalities

Importance

Identifying neurobiological differences between patients with major depressive disorder (MDD) and healthy individuals has been a mainstay of clinical neuroscience for decades. However, recent meta-analyses have raised concerns regarding the replicability and clinical relevance of brain alterations in depression.

Objective

To quantify the upper bounds of univariate effect sizes, estimated predictive utility, and distributional dissimilarity of healthy individuals and those with depression across structural magnetic resonance imaging (MRI), diffusion-tensor imaging, and functional task-based as well as resting-state MRI, and to compare results with an MDD polygenic risk score (PRS) and environmental variables.

Design, Setting, and Participants

This was a cross-sectional, case-control clinical neuroimaging study. Data were part of the Marburg-Münster Affective Disorders Cohort Study. Patients with depression and healthy controls were recruited from primary care and the general population in Münster and Marburg, Germany. Study recruitment was performed from September 11, 2014, to September 26, 2018. The sample comprised patients with acute and chronic MDD as well as healthy controls in the age range of 18 to 65 years. Data were analyzed from October 29, 2020, to April 7, 2022.

Main Outcomes and Measures

Primary analyses included univariate partial effect size (η2), classification accuracy, and distributional overlapping coefficient for healthy individuals and those with depression across neuroimaging modalities, controlling for age, sex, and additional modality-specific confounding variables. Secondary analyses included patient subgroups for acute or chronic depressive status.

Results

A total of 1809 individuals (861 patients [47.6%] and 948 controls [52.4%]) were included in the analysis (mean [SD] age, 35.6 [13.2] years; 1165 female patients [64.4%]). The upper bound of the effect sizes of the single univariate measures displaying the largest group difference ranged from partial η2 of 0.004 to 0.017, and distributions overlapped between 87% and 95%, with classification accuracies ranging between 54% and 56% across neuroimaging modalities. This pattern remained virtually unchanged when considering either only patients with acute or chronic depression. Differences were comparable with those found for PRS but substantially smaller than for environmental variables.

Conclusions and Relevance

Results of this case-control study suggest that even for maximum univariate biological differences, deviations between patients with MDD and healthy controls were remarkably small, single-participant prediction was not possible, and similarity between study groups dominated. Biological psychiatry should facilitate meaningful outcome measures or predictive approaches to increase the potential for a personalization of the clinical practice.

Personalized Diagnosis and Treatment for Neuroimaging in Depressive Disorders

Depressive disorders are highly heterogeneous in nature. Previous studies have not been useful for the clinical diagnosis and prediction of outcomes of major depressive disorder (MDD) at the individual level, although they provide many meaningful insights. To make inferences beyond group-level analyses, machine learning (ML) techniques can be used for the diagnosis of subtypes of MDD and the prediction of treatment responses. We searched PubMed for relevant studies published until December 2021 that included depressive disorders and applied ML algorithms in neuroimaging fields for depressive disorders. We divided these studies into two sections, namely diagnosis and treatment outcomes, for the application of prediction using ML. Structural and functional magnetic resonance imaging studies using ML algorithms were included. Thirty studies were summarized for the prediction of an MDD diagnosis. In addition, 19 studies on the prediction of treatment outcomes for MDD were reviewed. We summarized and discussed the results of previous studies. For future research results to be useful in clinical practice, ML enabling individual inferences is important. At the same time, there are important challenges to be addressed in the future.

Alcohol dependence inpatients classification with GLM and hierarchical clustering integration using fMRI data of alcohol multiple scenario cues

Alterations in brain reactions to alcohol-related cues are a neurobiological characteristic of alcohol dependence (AD) and a prospective target for achieving substantial treatment effects. However, a robust prediction of the differences in inpatients' brain responses to alcohol cues during the treatment process is still required. This study offers a data-driven approach for classifying AD inpatients undertaking alcohol treatment protocols based on their brain responses to alcohol imagery with and without drinking actions. The brain activity of thirty inpatients with AD undergoing treatment was scanned using functional magnetic resonance imaging (fMRI) while seeing alcohol and matched non-alcohol images. The mean values of brain regions of interest (ROI) for alcohol-related brain responses were obtained using general linear modeling (GLM) and subjected to hierarchical clustering analysis. The proposed classification technique identified two distinct subgroups of inpatients. For the two types of cues, subgroup one exhibited significant activation in a wide range of brain regions, while subgroup two showed mainly decreased activation. The proposed technique may aid in detecting the vulnerability of the classified inpatient subgroups, which can suggest allocating the inpatients in the classified subgroups to more effective therapies and developing prognostic future relapse markers in AD.

Predicting the future of neuroimaging predictive models in mental health

Predictive modeling using neuroimaging data has the potential to improve our understanding of the neurobiology underlying psychiatric disorders and putatively information interventions. Accordingly, there is a plethora of literature reviewing published studies, the mathematics underlying machine learning, and the best practices for using these approaches. As our knowledge of mental health and machine learning continue to evolve, we instead aim to look forward and "predict" topics that we believe will be important in current and future studies. Some of the most discussed topics in machine learning, such as bias and fairness, the handling of dirty data, and interpretable models, may be less familiar to the broader community using neuroimaging-based predictive modeling in psychiatry. In a similar vein, transdiagnostic research and targeting brain-based features for psychiatric intervention are modern topics in psychiatry that predictive models are well-suited to tackle. In this work, we target an audience who is a researcher familiar with the fundamental procedures of machine learning and who wishes to increase their knowledge of ongoing topics in the field. We aim to accelerate the utility and applications of neuroimaging-based predictive models for psychiatric research by highlighting and considering these topics. Furthermore, though not a focus, these ideas generalize to neuroimaging-based predictive modeling in other clinical neurosciences and predictive modeling with different data types (e.g., digital health data).

Machine learning detects predictors of symptom severity and impulsivity after dialectical behavior therapy skills training group in borderline personality disorder

Only 50% of the patients with Borderline Personality Disorder (BPD) respond to psychotherapies, such as Dialectical Behavioral Therapy (DBT), this might be increased by identifying baseline predictors of clinical change. We use machine learning to detect clinical features that could predict improvement/worsening for severity and impulsivity of BPD after DBT skills training group. To predict illness severity, we analyzed data from 125 patients with BPD divided into 17 DBT psychotherapy groups, and for impulsiveness we analyzed 89 patients distributed into 12 DBT groups. All patients were evaluated at baseline using widely self-report tests; ∼70% of the sample were randomly selected and two machine learning models (lasso and Random forest [Rf]) were trained using 10-fold cross-validation and compared to predict the post-treatment response. Models' generalization was assessed in ∼30% of the remaining sample. Relevant variables for DBT (i.e. the mindfulness ability "non-judging", or "non-planning" impulsiveness) measured at baseline, were robust predictors of clinical change after six months of weekly DBT sessions. Using 10-fold cross-validation, the Rf model had significantly lower prediction error than lasso for the BPD severity variable, Mean Absolute Error (MAE) lasso - Rf = 1.55 (95% CI, 0.63-2.48) as well as for impulsivity, MAE lasso - Rf = 1.97 (95% CI, 0.57-3.35). According to Rf and the permutations method, 34/613 significant predictors for severity and 17/613 for impulsivity were identified. Using machine learning to identify the most important variables before starting DBT could be fundamental for personalized treatment and disease prognosis.

Brain Mechanism of Acupuncture Treatment of Chronic Pain: An Individual-Level Positron Emission Tomography Study

Objective

Acupuncture has been shown to be effective in the treatment of chronic pain. However, their neural mechanism underlying the effective acupuncture response to chronic pain is still unclear. We investigated whether metabolic patterns in the pain matrix network might predict acupuncture therapy responses in patients with primary dysmenorrhea (PDM) using a machine-learning-based multivariate pattern analysis (MVPA) on positron emission tomography data (PET).

Methods

Forty-two patients with PDM were selected and randomized into two groups: real acupuncture and sham acupuncture (three menstrual cycles). Brain metabolic data from the three special brain networks (the sensorimotor network (SMN), default mode network (DMN), and salience network (SN)) were extracted at the individual level by using PETSurfer in fluorine-18 fluorodeoxyglucose positron emission tomography (18F-FDG-PET) data. MVPA analysis based on metabolic network features was employed to predict the pain relief after treatment in the pooled group and real acupuncture treatment, separately.

Results

Paired t-tests revealed significant alterations in pain intensity after real but not sham acupuncture treatment. Traditional mass-univariate correlations between brain metabolic and alterations in pain intensity were not significant. The MVPA results showed that the brain metabolic pattern in the DMN and SMN did predict the pain relief in the pooled group of patients with PDM (R2 = 0.25, p = 0.005). In addition, the metabolic pattern in the DMN could predict the pain relief after treatment in the real acupuncture treatment group (R2 = 0.40, p = 0.01).

Conclusion

This study indicates that the individual-level metabolic patterns in DMN is associated with real acupuncture treatment response in chronic pain. The present findings advanced the knowledge of the brain mechanism of the acupuncture treatment in chronic pain.

Implementing Critical Machine Learning (ML) Approaches for Generating Robust Discriminative Neuroimaging Representations Using Structural Equation Model (SEM)

Critical ML or CML is a critical approach development of the standard ML (SML) procedure. Conventional ML (ML) is being used in radiology departments where complex neuroimages are discriminated using ML technology. Radiologists and researchers found that sole decision by the ML algorithms is not accurate enough to implement the treatment procedure. Thus, an intelligent decision is required further by the radiologists after evaluating the ML outcomes. The current research is based on the critical ML, where radiologists' critical thinking ability, IQ (intelligence quotient), and experience in radiology have been examined to understand how these factors affect the accuracy of neuroimaging discrimination. A primary quantitative survey has been carried out, and the data were analysed in IBM SPSS. The results showed that experience in works has a positive impact on neuroimaging discrimination accuracy. IQ and trained ML are also responsible for improving the accuracy as well. Thus, radiologists with more experience in that field are able to improve the discriminative and diagnostic capability of CML.

Predicting Treatment Response in Schizophrenia With Magnetic Resonance Imaging and Polygenic Risk Score

Background: Prior studies have separately demonstrated that magnetic resonance imaging (MRI) and schizophrenia polygenic risk score (PRS) are predictive of antipsychotic medication treatment outcomes in schizophrenia. However, it remains unclear whether MRI combined with PRS can provide superior prognostic performance. Besides, the relative importance of these measures in predictions is not investigated.

Methods: We collected 57 patients with schizophrenia, all of which had baseline MRI and genotype data. All these patients received approximately 6 weeks of antipsychotic medication treatment. Psychotic symptom severity was assessed using the Positive and Negative Syndrome Scale (PANSS) at baseline and follow-up. We divided these patients into responders (N = 20) or non-responders (N = 37) based on whether their percentages of PANSS total reduction were above or below 50%. Nine categories of MRI measures and PRSs with 145 different p-value thresholding ranges were calculated. We trained machine learning classifiers with these baseline predictors to identify whether a patient was a responder or non-responder.

Results: The extreme gradient boosting (XGBoost) technique was applied to build binary classifiers. Using a leave-one-out cross-validation scheme, we achieved an accuracy of 86% with all MRI and PRS features. Other metrics were also estimated, including sensitivity (85%), specificity (86%), F1-score (81%), and area under the receiver operating characteristic curve (0.86). We found excluding a single feature category of gray matter volume (GMV), amplitude of low-frequency fluctuation (ALFF), and surface curvature could lead to a maximum accuracy drop of 10.5%. These three categories contributed more than half of the top 10 important features. Besides, removing PRS features caused a modest accuracy drop (8.8%), which was not the least decrease (1.8%) among all feature categories.

Conclusions: Our classifier using both MRI and PRS features was stable and not biased to predicting either responder or non-responder. Combining with MRI measures, PRS could provide certain extra predictive power of antipsychotic medication treatment outcomes in schizophrenia. PRS exhibited medium importance in predictions, lower than GMV, ALFF, and surface curvature, but higher than measures of cortical thickness, cortical volume, and surface sulcal depth. Our findings inform the contributions of PRS in predictions of treatment outcomes in schizophrenia.

Viability Study of Machine Learning-Based Prediction of COVID-19 Pandemic Impact in Obsessive-Compulsive Disorder Patients

BACKGROUND

Machine learning modeling can provide valuable support in different areas of mental health, because it enables to make rapid predictions and therefore support the decision making, based on valuable data. However, few studies have applied this method to predict symptoms' worsening, based on sociodemographic, contextual, and clinical data. Thus, we applied machine learning techniques to identify predictors of symptomatologic changes in a Spanish cohort of OCD patients during the initial phase of the COVID-19 pandemic.

METHODS

127 OCD patients were assessed using the Yale-Brown Obsessive-Compulsive Scale (Y-BOCS) and a structured clinical interview during the COVID-19 pandemic. Machine learning models for classification (LDA and SVM) and regression (linear regression and SVR) were constructed to predict each symptom based on patient's sociodemographic, clinical and contextual information.

RESULTS

A Y-BOCS score prediction model was generated with 100% reliability at a score threshold of ± 6. Reliability of 100% was reached for obsessions and/or compulsions related to COVID-19. Symptoms of anxiety and depression were predicted with less reliability (correlation R of 0.58 and 0.68, respectively). The suicidal thoughts are predicted with a sensitivity of 79% and specificity of 88%. The best results are achieved by SVM and SVR.

CONCLUSION

Our findings reveal that sociodemographic and clinical data can be used to predict changes in OCD symptomatology. Machine learning may be valuable tool for helping clinicians to rapidly identify patients at higher risk and therefore provide optimized care, especially in future pandemics. However, further validation of these models is required to ensure greater reliability of the algorithms for clinical implementation to specific objectives of interest.

Advantages of Machine Learning in Forensic Psychiatric Research—Uncovering the Complexities of Aggressive Behavior in Schizophrenia

Linear statistical methods may not be suited to the understanding of psychiatric phenomena such as aggression due to their complexity and multifactorial origins. Here, the application of machine learning (ML) algorithms offers the possibility of analyzing a large number of influencing factors and their interactions. This study aimed to explore inpatient aggression in offender patients with schizophrenia spectrum disorders (SSDs) using a suitable ML model on a dataset of 370 patients. With a balanced accuracy of 77.6% and an AUC of 0.87, support vector machines (SVM) outperformed all the other ML algorithms. Negative behavior toward other patients, the breaking of ward rules, the PANSS score at admission as well as poor impulse control and impulsivity emerged as the most predictive variables in distinguishing aggressive from non-aggressive patients. The present study serves as an example of the practical use of ML in forensic psychiatric research regarding the complex interplay between the factors contributing to aggressive behavior in SSD. Through its application, it could be shown that mental illness and the antisocial behavior associated with it outweighed other predictors. The fact that SSD is also highly associated with antisocial behavior emphasizes the importance of early detection and sufficient treatment.

Machine learning approaches for parsing comorbidity/heterogeneity in antisociality and substance use disorders: A primer

By some accounts, as many as 93% of individuals diagnosed with antisocial personality disorder (ASPD) or psychopathy also meet criteria for some form of substance use disorder (SUD). This high level of comorbidity, combined with an overlapping biopsychosocial profile, and potentially interacting features, has made it difficult to delineate the shared/unique characteristics of each disorder. Moreover, while rarely acknowledged, both SUD and antisociality exist as highly heterogeneous disorders in need of more targeted parcellation. While emerging data-driven nosology for psychiatric disorders (e.g., Research Domain Criteria (RDoC), Hierarchical Taxonomy of Psychopathology (HiTOP)) offers the opportunity for a more systematic delineation of the externalizing spectrum, the interrogation of large, complex neuroimaging-based datasets may require data-driven approaches that are not yet widely employed in psychiatric neuroscience. With this in mind, the proposed article sets out to provide an introduction into machine learning methods for neuroimaging that can help parse comorbid, heterogeneous externalizing samples. The modest machine learning work conducted to date within the externalizing domain demonstrates the potential utility of the approach but remains highly nascent. Within the paper, we make suggestions for how future work can make use of machine learning methods, in combination with emerging psychiatric nosology systems, to further diagnostic and etiological understandings of the externalizing spectrum. Finally, we briefly consider some challenges that will need to be overcome to encourage further progress in the field.

Searching for Imaging Biomarkers of Psychotic Dysconnectivity

BACKGROUND

Progress in precision psychiatry is predicated on identifying reliable individual-level diagnostic biomarkers. For psychosis, measures of structural and functional connectivity could be promising biomarkers given consistent reports of dysconnectivity across psychotic disorders using magnetic resonance imaging.

METHODS

We leveraged data from four independent cohorts of patients with psychosis and control subjects with observations from approximately 800 individuals. We used group-level analyses and two supervised machine learning algorithms (support vector machines and ridge regression) to test within-, between-, and across-sample classification performance of white matter and resting-state connectivity metrics.

RESULTS

Although we replicated group-level differences in brain connectivity, individual-level classification was suboptimal. Classification performance within samples was variable across folds (highest area under the curve [AUC] range = 0.30) and across datasets (average support vector machine AUC range = 0.50; average ridge regression AUC range = 0.18). Classification performance between samples was similarly variable or resulted in AUC values of approximately 0.65, indicating a lack of model generalizability. Furthermore, collapsing across samples (resting-state functional magnetic resonance imaging, N = 888; diffusion tensor imaging, N = 860) did not improve model performance (maximal AUC = 0.67). Ridge regression models generally outperformed support vector machine models, although classification performance was still suboptimal in terms of clinical relevance. Adjusting for demographic covariates did not greatly affect results.

CONCLUSIONS

Connectivity measures were not suitable as diagnostic biomarkers for psychosis as assessed in this study. Our results do not negate that other approaches may be more successful, although it is clear that a systematic approach to individual-level classification with large independent validation samples is necessary to properly vet neuroimaging features as diagnostic biomarkers.

Machine Learning and Deep Learning for the Pharmacogenomics of Antidepressant Treatments

A growing body of evidence now proposes that machine learning and deep learning techniques can serve as a vital foundation for the pharmacogenomics of antidepressant treatments in patients with major depressive disorder (MDD). In this review, we focus on the latest developments for pharmacogenomics research using machine learning and deep learning approaches together with neuroimaging and multi-omics data. First, we review relevant pharmacogenomics studies that leverage numerous machine learning and deep learning techniques to determine treatment prediction and potential biomarkers for antidepressant treatments in MDD. In addition, we depict some neuroimaging pharmacogenomics studies that utilize various machine learning approaches to predict antidepressant treatment outcomes in MDD based on the integration of research on pharmacogenomics and neuroimaging. Moreover, we summarize the limitations in regard to the past pharmacogenomics studies of antidepressant treatments in MDD. Finally, we outline a discussion of challenges and directions for future research. In light of latest advancements in neuroimaging and multi-omics, various genomic variants and biomarkers associated with antidepressant treatments in MDD are being identified in pharmacogenomics research by employing machine learning and deep learning algorithms.

Prediction of tuberous sclerosis-associated neurocognitive disorders and seizures via machine learning of structural magnetic resonance imaging

PURPOSE

Tuberous sclerosis complex (TSC) is a genetic disorder characterized by multiorgan hamartomas, including cerebral lesions, with seizures as a common presentation. Most TSC patients will also experience neurocognitive comorbidities. Our objective was to use machine learning techniques incorporating clinical and imaging data to predict the occurrence of major neurocognitive disorders and seizures in TSC patients.

METHODS

A cohort of TSC patients were enrolled in this retrospective study. Clinical data included genetic, demographic, and seizure characteristics. Imaging parameters included the number, characteristics, and location of cortical tubers and the presence of subependymal nodules, SEGAs, and cerebellar tubers. A random forest machine learning scheme was used to predict seizures and neurodevelopmental delay or intellectual developmental disability. Prediction ability was assessed by the area-under-the-curve of receiver-operating-characteristics (AUC-ROC) of ten-fold cross-validation training set and an independent validation set.

RESULTS

The study population included 77 patients, 55% male (17.1 ± 11.7 years old). The model achieved AUC-ROC of 0.72 ± 0.1 and 0.68 in the training and internal validation datasets, respectively, for predicting neurocognitive comorbidity. Performance was limited in predicting seizures (AUC-ROC of 0.54 ± 0.19 and 0.71 in the training and internal validation datasets, respectively). The integration of seizure characteristics into the model improved the prediction of neurocognitive comorbidity with AUC-ROC of 0.84 ± 0.07 and 0.75 in the training and internal validation datasets, respectively.

CONCLUSIONS

This proof of concept study shows that it is possible to achieve a reasonable prediction of major neurocognitive morbidity in TSC patients using structural brain imaging and machine learning techniques. These tools can help clinicians identify subgroups of TSC patients with an increased risk of developing neurocognitive comorbidities.

Artificial Intelligence for Mental Health Care: Clinical Applications, Barriers, Facilitators, and Artificial Wisdom

Artificial intelligence (AI) is increasingly employed in health care fields such as oncology, radiology, and dermatology. However, the use of AI in mental health care and neurobiological research has been modest. Given the high morbidity and mortality in people with psychiatric disorders, coupled with a worsening shortage of mental health care providers, there is an urgent need for AI to help identify high-risk individuals and provide interventions to prevent and treat mental illnesses. While published research on AI in neuropsychiatry is rather limited, there is a growing number of successful examples of AI's use with electronic health records, brain imaging, sensor-based monitoring systems, and social media platforms to predict, classify, or subgroup mental illnesses as well as problems such as suicidality. This article is the product of a study group held at the American College of Neuropsychopharmacology conference in 2019. It provides an overview of AI approaches in mental health care, seeking to help with clinical diagnosis, prognosis, and treatment, as well as clinical and technological challenges, focusing on multiple illustrative publications. Although AI could help redefine mental illnesses more objectively, identify them at a prodromal stage, personalize treatments, and empower patients in their own care, it must address issues of bias, privacy, transparency, and other ethical concerns. These aspirations reflect human wisdom, which is more strongly associated than intelligence with individual and societal well-being. Thus, the future AI or artificial wisdom could provide technology that enables more compassionate and ethically sound care to diverse groups of people.

Large-scale collaboration in ENIGMA-EEG: A perspective on the meta-analytic approach to link neurological and psychiatric liability genes to electrophysiological brain activity

BACKGROUND AND PURPOSE

The ENIGMA-EEG working group was established to enable large-scale international collaborations among cohorts that investigate the genetics of brain function measured with electroencephalography (EEG). In this perspective, we will discuss why analyzing the genetics of functional brain activity may be crucial for understanding how neurological and psychiatric liability genes affect the brain.

METHODS

We summarize how we have performed our currently largest genome-wide association study of oscillatory brain activity in EEG recordings by meta-analyzing the results across five participating cohorts, resulting in the first genome-wide significant hits for oscillatory brain function located in/near genes that were previously associated with psychiatric disorders. We describe how we have tackled methodological issues surrounding genetic meta-analysis of EEG features. We discuss the importance of harmonizing EEG signal processing, cleaning, and feature extraction. Finally, we explain our selection of EEG features currently being investigated, including the temporal dynamics of oscillations and the connectivity network based on synchronization of oscillations.

RESULTS

We present data that show how to perform systematic quality control and evaluate how choices in reference electrode and montage affect individual differences in EEG parameters.

CONCLUSION

The long list of potential challenges to our large-scale meta-analytic approach requires extensive effort and organization between participating cohorts; however, our perspective shows that these challenges are surmountable. Our perspective argues that elucidating the genetic of EEG oscillatory activity is a worthwhile effort in order to elucidate the pathway from gene to disease liability.

White matter degeneration in remote brain areas of stroke patients with motor impairment due to basal ganglia lesions

Diffusion tensor imaging (DTI) studies have revealed distinct white matter (WM) characteristics of the brain following diseases. Beyond the lesion‐symptom maps, stroke is characterized by extensive structural and functional alterations of brain areas remote to local lesions. Here, we further investigated the structural changes over a global level by using DTI data of 10 ischemic stroke patients showing motor impairment due to basal ganglia lesions and 11 healthy controls. DTI data were processed to obtain fractional anisotropy (FA) maps, and multivariate pattern analysis was used to explore brain regions that play an important role in classification based on FA maps. The WM structural network was constructed by the deterministic fiber‐tracking approach. In comparison with the controls, the stroke patients showed FA reductions in the perilesional basal ganglia, brainstem, and bilateral frontal lobes. Using network‐based statistics, we found a significant reduction in the WM subnetwork in stroke patients. We identified the patterns of WM degeneration affecting brain areas remote to the lesions, revealing the abnormal organization of the structural network in stroke patients, which may be helpful in understanding of the neural mechanisms underlying hemiplegia.

Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach

Schizophrenia and related disorders have heterogeneous outcomes. Individualized prediction of long-term outcomes may be helpful in improving treatment decisions. Utilizing extensive baseline data of 523 patients with a psychotic disorder and variable illness duration, we predicted symptomatic and global outcomes at 3-year and 6-year follow-ups. We classified outcomes as (1) symptomatic: in remission or not in remission, and (2) global outcome, using the Global Assessment of Functioning (GAF) scale, divided into good (GAF ≥ 65) and poor (GAF < 65). Aiming for a robust and interpretable prediction model, we employed a linear support vector machine and recursive feature elimination within a nested cross-validation design to obtain a lean set of predictors. Generalization to out-of-study samples was estimated using leave-one-site-out cross-validation. Prediction accuracies were above chance and ranged from 62.2% to 64.7% (symptomatic outcome), and 63.5-67.6% (global outcome). Leave-one-site-out cross-validation demonstrated the robustness of our models, with a minor drop in predictive accuracies of 2.3% on average. Important predictors included GAF scores, psychotic symptoms, quality of life, antipsychotics use, psychosocial needs, and depressive symptoms. These robust, albeit modestly accurate, long-term prognostic predictions based on lean predictor sets indicate the potential of machine learning models complementing clinical judgment and decision-making. Future model development may benefit from studies scoping patient's and clinicians' needs in prognostication.

Concerns in the Blurred Divisions between Medical and Consumer Neurotechnology

Neurotechnology has traditionally been central to the diagnosis and treatment of neurological disorders. While these devices have initially been utilized in clinical and research settings, recent advancements in neurotechnology have yielded devices that are more portable, user-friendly, and less expensive. These improvements allow laypeople to monitor their brain waves and interface their brains with external devices. Such improvements have led to the rise of wearable neurotechnology that is marketed to the consumer. While many of the consumer devices are marketed for innocuous applications, such as use in video games, there is potential for them to be repurposed for medical use. How do we manage neurotechnologies that skirt the line between medical and consumer applications and what can be done to ensure consumer safety? Here, we characterize neurotechnology based on medical and consumer applications and summarize currently marketed uses of consumer-grade wearable headsets. We lay out concerns that may arise due to the similar claims associated with both medical and consumer devices, the possibility of consumer devices being repurposed for medical uses, and the potential for medical uses of neurotechnology to influence commercial markets related to employment and self-enhancement.

Multimodal prognosis of negative symptom severity in individuals at increased risk of developing psychosis

Negative symptoms occur frequently in individuals at clinical high risk (CHR) for psychosis and contribute to functional impairments. The aim of this study was to predict negative symptom severity in CHR after 9 months. Predictive models either included baseline negative symptoms measured with the Structured Interview for Psychosis-Risk Syndromes (SIPS-N), whole-brain gyrification, or both to forecast negative symptoms of at least moderate severity in 94 CHR. We also conducted sequential risk stratification to stratify CHR into different risk groups based on the SIPS-N and gyrification model. Additionally, we assessed the models' ability to predict functional outcomes in CHR and their transdiagnostic generalizability to predict negative symptoms in 96 patients with recent-onset psychosis (ROP) and 97 patients with recent-onset depression (ROD). Baseline SIPS-N and gyrification predicted moderate/severe negative symptoms with significant balanced accuracies of 68 and 62%, while the combined model achieved 73% accuracy. Sequential risk stratification stratified CHR into a high (83%), medium (40-64%), and low (19%) risk group regarding their risk of having moderate/severe negative symptoms at 9 months follow-up. The baseline SIPS-N model was also able to predict social (61%), but not role functioning (59%) at above-chance accuracies, whereas the gyrification model achieved significant accuracies in predicting both social (76%) and role (74%) functioning in CHR. Finally, only the baseline SIPS-N model showed transdiagnostic generalization to ROP (63%). This study delivers a multimodal prognostic model to identify those CHR with a clinically relevant negative symptom severity and functional impairments, potentially requiring further therapeutic consideration.

Computational approaches and machine learning for individual-level treatment predictions

RATIONALE

The impact of neuroscience-based approaches for psychiatry on pragmatic clinical decision-making has been limited. Although neuroscience has provided insights into basic mechanisms of neural function, these insights have not improved the ability to generate better assessments, prognoses, diagnoses, or treatment of psychiatric conditions.

OBJECTIVES

To integrate the emerging findings in machine learning and computational psychiatry to address the question: what measures that are not derived from the patient's self-assessment or the assessment by a trained professional can be used to make more precise predictions about the individual's current state, the individual's future disease trajectory, or the probability to respond to a particular intervention?

RESULTS

Currently, the ability to use individual differences to predict differential outcomes is very modest possibly related to the fact that the effect sizes of interventions are small. There is emerging evidence of genetic and neuroimaging-based heterogeneity of psychiatric disorders, which contributes to imprecise predictions. Although the use of machine learning tools to generate clinically actionable predictions is still in its infancy, these approaches may identify subgroups enabling more precise predictions. In addition, computational psychiatry might provide explanatory disease models based on faulty updating of internal values or beliefs.

CONCLUSIONS

There is a need for larger studies, clinical trials using machine learning, or computational psychiatry model parameters predictions as actionable outcomes, comparing alternative explanatory computational models, and using translational approaches that apply similar paradigms and models in humans and animals.

Identification of attention-deficit hyperactivity disorder based on the complexity and symmetricity of pupil diameter

Adult attention-deficit/hyperactivity disorder (ADHD) frequently leads to psychological/social dysfunction if unaddressed. Identifying a reliable biomarker would assist the diagnosis of adult ADHD and ensure that adults with ADHD receive treatment. Pupil diameter can reflect inherent neural activity and deficits of attention or arousal characteristic of ADHD. Furthermore, distinct profiles of the complexity and symmetricity of neural activity are associated with some psychiatric disorders. We hypothesized that analysing the relationship between the size, complexity of temporal patterns, and asymmetricity of pupil diameters will help characterize the nervous systems of adults with ADHD and that an identification method combining these features would ease the diagnosis of adult ADHD. To validate this hypothesis, we evaluated the resting state hippus in adult participants with or without ADHD by examining the pupil diameter and its temporal complexity using sample entropy and the asymmetricity of the left and right pupils using transfer entropy. We found that large pupil diameters and low temporal complexity and symmetry were associated with ADHD. Moreover, the combination of these factors by the classifier enhanced the accuracy of ADHD identification. These findings may contribute to the development of tools to diagnose adult ADHD.

A Synthetic Literature Review on the Management of Emerging Treatment Resistance in First Episode Psychosis: Can We Move towards Precision Intervention and Individualised Care?

Treatment resistance is prevalent in early intervention in psychosis services, and causes a significant burden for the individual. A wide range of variables are shown to contribute to treatment resistance in first episode psychosis (FEP). Heterogeneity in illness course and the complex, multidimensional nature of the concept of recovery calls for an evidence base to better inform practice at an individual level. Current gold standard treatments, adopting a ‘one-size fits all’ approach, may not be addressing the needs of many individuals. This following review will provide an update and critical appraisal of current clinical practices and methodological approaches for understanding, identifying, and managing early treatment resistance in early psychosis. Potential new treatments along with new avenues for research will be discussed. Finally, we will discuss and critique the application and translation of machine learning approaches to aid progression in this area. The move towards ‘big data’ and machine learning holds some prospect for stratifying intervention-based subgroups of individuals. Moving forward, better recognition of early treatment resistance is needed, along with greater sophistication and precision in predicting outcomes, so that effective evidence-based treatments can be appropriately tailored to the individual. Understanding the antecedents and the early trajectory of one’s illness may also be key to understanding the factors that drive illness course.

Resting-State Functional Connectivity Patterns Predict Acupuncture Treatment Response in Primary Dysmenorrhea

Primary dysmenorrhea (PDM) is a common complaint in women throughout the menstrual years. Acupuncture has been shown to be effective in dysmenorrhea; however, there are large interindividual differences in patients’ responses to acupuncture treatment. Fifty-four patients with PDM were recruited and randomized into real or sham acupuncture treatment groups (over the course of three menstrual cycles). Pain-related functional connectivity (FC) matrices were constructed at baseline and post-treatment period. The different neural mechanisms altered by real and sham acupuncture were detected with multivariate analysis of variance. Multivariate pattern analysis (MVPA) based on a machine learning approach was used to explore whether the different FC patterns predicted the acupuncture treatment response in the PDM patients. The results showed that real but not sham acupuncture significantly relieved pain severity in PDM patients. Real and sham acupuncture displayed differences in FC alterations between the descending pain modulatory system (DPMS) and sensorimotor network (SMN), the salience network (SN) and SMN, and the SN and default mode network (DMN). Furthermore, MVPA found that these FC patterns at baseline could predict the acupuncture treatment response in PDM patients. The present study verified differentially altered brain mechanisms underlying real and sham acupuncture in PDM patients and supported the use of neuroimaging biomarkers for individual-based precise acupuncture treatment in patients with PDM.

Automated classification of depression from structural brain measures across two independent community-based cohorts

Major depressive disorder (MDD) has been the subject of many neuroimaging case-control classification studies. Although some studies report accuracies ≥80%, most have investigated relatively small samples of clinically-ascertained, currently symptomatic cases, and did not attempt replication in larger samples. We here first aimed to replicate previously reported classification accuracies in a small, well-phenotyped community-based group of current MDD cases with clinical interview-based diagnoses (from STratifying Resilience and Depression Longitudinally cohort, 'STRADL'). We performed a set of exploratory predictive classification analyses with measures related to brain morphometry and white matter integrity. We applied three classifier types-SVM, penalised logistic regression or decision tree-either with or without optimisation, and with or without feature selection. We then determined whether similar accuracies could be replicated in a larger independent population-based sample with self-reported current depression (UK Biobank cohort). Additional analyses extended to lifetime MDD diagnoses-remitted MDD in STRADL, and lifetime-experienced MDD in UK Biobank. The highest cross-validation accuracy (75%) was achieved in the initial current MDD sample with a decision tree classifier and cortical surface area features. The most frequently selected decision tree split variables included surface areas of bilateral caudal anterior cingulate, left lingual gyrus, left superior frontal, right precentral and paracentral regions. High accuracy was not achieved in the larger samples with self-reported current depression (53.73%), with remitted MDD (57.48%), or with lifetime-experienced MDD (52.68-60.29%). Our results indicate that high predictive classification accuracies may not immediately translate to larger samples with broader criteria for depression, and may not be robust across different classification approaches.

Multi-dimensional predictions of psychotic symptoms via machine learning

The diagnostic criteria for schizophrenia comprise a diverse range of heterogeneous symptoms. As a result, individuals each present a distinct set of symptoms despite having the same overall diagnosis. Whilst previous machine learning studies have primarily focused on dichotomous patient-control classification, we predict the severity of each individual symptom on a continuum. We applied machine learning regression within a multi-modal fusion framework to fMRI and behavioural data acquired during an auditory oddball task in 80 schizophrenia patients. Brain activity was highly predictive of some, but not all symptoms, namely hallucinations, avolition, anhedonia and attention. Critically, each of these symptoms was associated with specific functional alterations across different brain regions. We also found that modelling symptoms as an ensemble of subscales was more accurate, specific and informative than models which predict compound scores directly. In principle, this approach is transferrable to any psychiatric condition or multi-dimensional diagnosis.

Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up: Comparison of connectomic, structural, and clinical predictors

In a machine learning setting, this study aims to compare the prognostic utility of connectomic, brain structural, and clinical/demographic predictors of individual change in symptom severity in individuals with schizophrenia. Symptom severity at baseline and 1-year follow-up was assessed in 30 individuals with a schizophrenia-spectrum disorder using the Brief Psychiatric Rating Scale. Structural and functional neuroimaging was acquired in all individuals at baseline. Machine learning classifiers were trained to predict whether individuals improved or worsened with respect to positive, negative, and overall symptom severity. Classifiers were trained using various combinations of predictors, including regional cortical thickness and gray matter volume, static and dynamic resting-state connectivity, and/or baseline clinical and demographic variables. Relative change in overall symptom severity between baseline and 1-year follow-up varied markedly among individuals (interquartile range: 55%). Dynamic resting-state connectivity measured within the default-mode network was the most accurate single predictor of change in positive (accuracy: 87%), negative (83%), and overall symptom severity (77%) at follow-up. Incorporating predictors based on regional cortical thickness, gray matter volume, and baseline clinical variables did not markedly improve prediction accuracy and the prognostic utility of these predictors in isolation was moderate (<70%). Worsening negative symptoms at 1-year follow-up were predicted by hyper-connectivity and hypo-dynamism within the default-mode network at baseline assessment, while hypo-connectivity and hyper-dynamism predicted worsening positive symptoms. Given the modest sample size investigated, we recommend giving precedence to the relative ranking of the predictors investigated in this study, rather than the prediction accuracy estimates.

Translating research findings into clinical practice: a systematic and critical review of neuroimaging-based clinical tools for brain disorders

A pivotal aim of psychiatric and neurological research is to promote the translation of the findings into clinical practice to improve diagnostic and prognostic assessment of individual patients. Structural neuroimaging holds much promise, with neuroanatomical measures accounting for up to 40% of the variance in clinical outcome. Building on these findings, a number of imaging-based clinical tools have been developed to make diagnostic and prognostic inferences about individual patients from their structural Magnetic Resonance Imaging scans. This systematic review describes and compares the technical characteristics of the available tools, with the aim to assess their translational potential into real-world clinical settings. The results reveal that a total of eight tools. All of these were specifically developed for neurological disorders, and as such are not suitable for application to psychiatric disorders. Furthermore, most of the tools were trained and validated in a single dataset, which can result in poor generalizability, or using a small number of individuals, which can cause overoptimistic results. In addition, all of the tools rely on two strategies to detect brain abnormalities in single individuals, one based on univariate comparison, and the other based on multivariate machine-learning algorithms. We discuss current barriers to the adoption of these tools in clinical practice and propose a checklist of pivotal characteristics that should be included in an "ideal" neuroimaging-based clinical tool for brain disorders.

Your evidence? Machine learning algorithms for medical diagnosis and prediction

Computer systems for medical diagnosis based on machine learning are not mere science fiction. Despite undisputed potential benefits, such systems may also raise problems. Two (interconnected) issues are particularly significant from an ethical point of view: The first issue is that epistemic opacity is at odds with a common desire for understanding and potentially undermines information rights. The second (related) issue concerns the assignment of responsibility in cases of failure. The core of the two issues seems to be that understanding and responsibility are concepts that are intrinsically tied to the discursive practice of giving and asking for reasons. The challenge is to find ways to make the outcomes of machine learning algorithms compatible with our discursive practice. This comes down to the claim that we should try to integrate discursive elements into machine learning algorithms. Under the title of "explainable AI" initiatives heading in this direction are already under way. Extensive research in this field is needed for finding adequate solutions.