Leveraging Machine Learning for Gaining Neurobiological and Nosological Insights in Psychiatric Research

Enhancing drug discovery in schizophrenia: a deep learning approach for accurate drug-target interaction prediction - DrugSchizoNet

Drug discovery relies on the precise prognosis of drug-target interactions (DTI). Due to their ability to learn from raw data, deep learning (DL) methods have displayed outstanding performance over traditional approaches. However, challenges such as imbalanced data, noise, poor generalization, high cost, and time-consuming processes hinder progress in this field. To overcome the above challenges, we propose a DL-based model termed DrugSchizoNet for drug interaction (DI) prediction of Schizophrenia. Our model leverages drug-related data from the DrugBank and repoDB databases, employing three key preprocessing techniques. First, data cleaning eliminates duplicate or incomplete entries to ensure data integrity. Next, normalization is performed to enhance security and reduce costs associated with data acquisition. Finally, feature extraction is applied to improve the quality of input data. The three layers of the DrugSchizoNet model are the input, hidden and output layers. In the hidden layer, we employ dropout regularization to mitigate overfitting and improve generalization. The fully connected (FC) layer extracts relevant features, while the LSTM layer captures the sequential nature of DIs. In the output layer, our model provides confidence scores for potential DIs. To optimize the prediction accuracy, we utilize hyperparameter tuning through OB-MOA optimization. Experimental results demonstrate that DrugSchizoNet achieves a superior accuracy of 98.70%. The existing models, including CNN-RNN, DANN, CKA-MKL, DGAN, and CNN, across various evaluation metrics such as accuracy, recall, specificity, precision, F1 score, AUPR, and AUROC are compared with the proposed model. By effectively addressing the challenges of imbalanced data, noise, poor generalization, high cost and time-consuming processes, DrugSchizoNet offers a promising approach for accurate DTI prediction in Schizophrenia. Its superior performance demonstrates the potential of DL in advancing drug discovery and development processes.

Advances in Clustering and Classification of Tic Disorders: A Systematic Review

Purpose

Tic disorders (TD) are common neurodevelopmental disorders characterized by heterogeneous tic symptoms in children, making diagnostic classification difficult. This complexity requires accurate subtyping using data-driven computational methods to identify patterns within clinical data. This systematic review primarily summarizes the current evidence for the classification of TD using a data-driven approach.

Patients and Methods

We conducted a systematic literature search on PubMed and Web of Science up to December 2023 and identified 16 publications analyzing 14 unique samples, totaling approximately 6000 subjects.

Results

Nine studies classified different subtypes of TD based on symptoms and behavior. Seven studies identified novel factor structures based on TD and its complex comorbidity patterns. Seven studies highlighted associations between TD symptom patterns and genetics, reflecting the diversity of underlying genetic mechanisms underlying TD.

Conclusion

This systematic review reveals significant variability in research on the classification of TD, which limits the application of findings for accurate diagnosis and guiding treatment strategies in pediatric psychiatry. Further research incorporating multidimensional information (such as genetic, neuroimaging, and environmental and social factors) is essential to improve the understanding of TD subtypes.

Leveraging Stacked Classifiers for Multi-task Executive Function in Schizophrenia Yields Diagnostic and Prognostic Insights

Cognitive impairment is a central characteristic of schizophrenia. Executive functioning (EF) impairments are often seen in mental disorders, particularly schizophrenia, where they relate to adverse outcomes. As a heterogeneous construct, how specifically each dimension of EF to characterize the diagnostic and prognostic aspects of schizophrenia remains opaque. We used classification models with a stacking approach on systematically measured EFs to discriminate 195 patients with schizophrenia from healthy individuals. Baseline EF measurements were moreover employed to predict symptomatically remitted or non-remitted prognostic subgroups. EF feature importance was determined at the group-level and the ensuing individual importance scores were associated with four symptom dimensions. EF assessments of inhibitory control (interference and response inhibitions), followed by working memory, evidently predicted schizophrenia diagnosis (area under the curve [AUC]=0.87) and remission status (AUC=0.81). The models highlighted the importance of interference inhibition or working memory updating in accurately identifying individuals with schizophrenia or those in remission. These identified patients had high-level negative symptoms at baseline and those who remitted showed milder cognitive symptoms at follow-up, without differences in baseline EF or symptom severity compared to non-remitted patients. Our work indicates that impairments in specific EF dimensions in schizophrenia are differentially linked to individual symptom-load and prognostic outcomes. Thus, assessments and models based on EF may be a promising tool that can aid in the clinical evaluation of this disorder.

Research hotspots and trends of neuroimaging in social anxiety: a CiteSpace bibliometric analysis based on Web of Science and Scopus database

Background

This study focused on the research hotspots and development trends of the neuroimaging of social anxiety (SA) in the past 25 years.

Methods

We selected 1,305 studies on SA neuroimaging from the Web of Science and Scopus from January 1998 to December 2023. CiteSpace was used to analyze the number of published articles visually, cited references, cooperation among authors and institutions, co-occurrence of keywords, clustering of keywords, burst of keywords, and time zone of co-occurring keywords.

Results

A total of 1,305 articles were included, and the annual number of articles published over nearly 25 years showed the overall trend is on the rise. The analysis of author and institutional collaboration reveals that most authors collaborate closely. Among them, the team led by Pine, Daniel S published 59 articles, making it the most central team. Harvard University is identified as the most central institution in this network. The research hotspots can be categorized into four areas: research techniques, cognitive processing research areas, core brain regions and brain networks, and the neural predictors of treatment outcomes in SA. The most recent burst keywords are "cognitive behavioral therapy," "systematic review," "machine learning," "major clinical study," "transcranial direct current stimulation," "depression," and "outcome assessment," which provided clues on research frontiers. Based on the burst map and keyword time zone map, it appears that exploring the activity of brain regions involved in cognitive processing, such as face processing and attentional bias, as well as the comorbidity of SA and depression, through brain imaging technology, using brain signals as predictors of treatment outcomes in SA.

Conclusion

This study conducted a comprehensive, objective, and visual analysis of publications, and revealed hot topics and trends concerning the study of the brain mechanism of SA from 1998 to 2023. This work might assist researchers in identifying new insights on potential collaborators and institutions, hot topics, and research directions.

Are Psychiatric Nosologies Limiting the Success of Clinical Prediction Models?

This Viewpoint discusses the limitations of clinical prediction models in psychiatric research.

Irregularity of visual motion perception and negative symptoms in schizophrenia

Schizophrenia (SZ) is a severe psychiatric disorder characterized by perceptual, emotional, and behavioral abnormalities, with cognitive impairment being a prominent feature of the disorder. Recent studies demonstrate irregularity in SZ with increased variability on the neural level. Is there also irregularity on the psychophysics level like in visual perception? Here, we introduce a methodology to analyze the irregularity in a trial-by-trial way to compare the SZ and healthy control (HC) subjects. In addition, we use an unsupervised clustering algorithm K-means + + to identify SZ subgroups in the sample, followed by validation of the subgroups based on intraindividual visual perception variability and clinical symptomatology. The K-means + + method divided SZ patients into two subgroups by measuring durations across trials in the motion discrimination task, i.e., high, and low irregularity of SZ patients (HSZ, LSZ). We found that HSZ and LSZ subgroups are associated with more negative and positive symptoms respectively. Applying a mediation model in the HSZ subgroup, the enhanced irregularity mediates the relationship between visual perception and negative symptoms. Together, we demonstrate increased irregularity in visual perception of a HSZ subgroup, including its association with negative symptoms. This may serve as a promising marker for identifying and distinguishing SZ subgroups.

Translational Connectomics: overview of machine learning in macroscale Connectomics for clinical insights

Connectomics is a neuroscience paradigm focused on noninvasively mapping highly intricate and organized networks of neurons. The advent of neuroimaging has led to extensive mapping of the brain functional and structural connectome on a macroscale level through modalities such as functional and diffusion MRI. In parallel, the healthcare field has witnessed a surge in the application of machine learning and artificial intelligence for diagnostics, especially in imaging. While reviews covering machine learn ing and macroscale connectomics exist for specific disorders, none provide an overview that captures their evolving role, especially through the lens of clinical application and translation. The applications include understanding disorders, classification, identifying neuroimaging biomarkers, assessing severity, predicting outcomes and intervention response, identifying potential targets for brain stimulation, and evaluating the effects of stimulation intervention on the brain and connectome mapping in patients before neurosurgery. The covered studies span neurodegenerative, neurodevelopmental, neuropsychiatric, and neurological disorders. Along with applications, the review provides a brief of common ML methods to set context. Conjointly, limitations in ML studies within connectomics and strategies to mitigate them have been covered.

Seeing more than the Tip of the Iceberg: Approaches to Subthreshold Effects in Functional Magnetic Resonance Imaging of the Brain

Many functional magnetic resonance imaging (fMRI) studies and presurgical mapping applications rely on mass-univariate inference with subsequent multiple comparison correction. Statistical results are frequently visualized as thresholded statistical maps. This approach has inherent limitations including the risk of drawing overly-selective conclusions based only on selective results passing such thresholds. This article gives an overview of both established and newly emerging scientific approaches to supplement such conventional analyses by incorporating information about subthreshold effects with the aim to improve interpretation of findings or leverage a wider array of information. Topics covered include neuroimaging data visualization, p-value histogram analysis and the related Higher Criticism approach for detecting rare and weak effects. Further examples from multivariate analyses and dedicated Bayesian approaches are provided.

Resting-state EEG dynamic functional connectivity distinguishes non-psychotic major depression, psychotic major depression and schizophrenia

This study aims to identify dynamic patterns within the spatiotemporal feature space that are specific to nonpsychotic major depression (NPMD), psychotic major depression (PMD), and schizophrenia (SCZ). The study also evaluates the effectiveness of machine learning algorithms based on these network manifestations in differentiating individuals with NPMD, PMD, and SCZ. A total of 579 participants were recruited, including 152 patients with NPMD, 45 patients with PMD, 185 patients with SCZ, and 197 healthy controls (HCs). A dynamic functional connectivity (DFC) approach was employed to estimate the principal FC states within each diagnostic group. Incremental proportions of data (ranging from 10% to 100%) within each diagnostic group were used for variability testing. DFC metrics, such as proportion, mean duration, and transition number, were examined among the four diagnostic groups to identify disease-related neural activity patterns. These patterns were then used to train a two-layer classifier for the four groups (HC, NPMD, PMD, and SCZ). The four principal brain states (i.e., states 1,2,3, and 4) identified by the DFC approach were highly representative within and across diagnostic groups. Between-group comparisons revealed significant differences in network metrics of state 2 and state 3, within delta, theta, and gamma frequency bands, between healthy individuals and patients in each diagnostic group (p < 0.01, FDR corrected). Moreover, the identified key dynamic network metrics achieved an accuracy of 73.1 ± 2.8% in the four-way classification of HC, NPMD, PMD, and SCZ, outperforming the static functional connectivity (SFC) approach (p < 0.001). These findings suggest that the proposed DFC approach can identify dynamic network biomarkers at the single-subject level. These biomarkers have the potential to accurately differentiate individual subjects among various diagnostic groups of psychiatric disorders or healthy controls. This work may contribute to the development of a valuable EEG-based diagnostic tool with enhanced accuracy and assistive capabilities.

Differentiation between atypical anorexia nervosa and anorexia nervosa using machine learning

OBJECTIVE

Body mass index (BMI) is the primary criterion differentiating anorexia nervosa (AN) and atypical anorexia nervosa despite prior literature indicating few differences between disorders. Machine learning (ML) classification provides us an efficient means of accurately distinguishing between two meaningful classes given any number of features. The aim of the present study was to determine if ML algorithms can accurately distinguish AN and atypical AN given an ensemble of features excluding BMI, and if not, if the inclusion of BMI enables ML to accurately classify between the two.

METHODS

Using an aggregate sample from seven studies consisting of individuals with AN and atypical AN who completed baseline questionnaires (N = 448), we used logistic regression, decision tree, and random forest ML classification models each trained on two datasets, one containing demographic, eating disorder, and comorbid features without BMI, and one retaining all features and BMI.

RESULTS

Model performance for all algorithms trained with BMI as a feature was deemed acceptable (mean accuracy = 74.98%, mean area under the receiving operating characteristics curve [AUC] = 74.75%), whereas model performance diminished without BMI (mean accuracy = 59.37%, mean AUC = 59.98%).

DISCUSSION

Model performance was acceptable, but not strong, if BMI was included as a feature; no other features meaningfully improved classification. When BMI was excluded, ML algorithms performed poorly at classifying cases of AN and atypical AN when considering other demographic and clinical characteristics. Results suggest a reconceptualization of atypical AN should be considered.

PUBLIC SIGNIFICANCE

There is a growing debate about the differences between anorexia nervosa and atypical anorexia nervosa as their diagnostic differentiation relies on BMI despite being similar otherwise. We aimed to see if machine learning could distinguish between the two disorders and found accurate classification only if BMI was used as a feature. This finding calls into question the need to differentiate between the two disorders.

Functional connectomics in depression: insights into therapies

Depression is a common mental disorder characterized by heterogeneous cognitive and behavioral symptoms. The emerging research paradigm of functional connectomics has provided a quantitative theoretical framework and analytic tools for parsing variations in the organization and function of brain networks in depression. In this review, we first discuss recent progress in depression-associated functional connectome variations. We then discuss treatment-specific brain network outcomes in depression and propose a hypothetical model highlighting the advantages and uniqueness of each treatment in relation to the modulation of specific brain network connectivity and symptoms of depression. Finally, we look to the future promise of combining multiple treatment types in clinical practice, using multisite datasets and multimodal neuroimaging approaches, and identifying biological depression subtypes.

Out of their minds? Externalist challenges for using AI in forensic psychiatry

Harnessing the power of machine learning (ML) and other Artificial Intelligence (AI) techniques promises substantial improvements across forensic psychiatry, supposedly offering more objective evaluations and predictions. However, AI-based predictions about future violent behaviour and criminal recidivism pose ethical challenges that require careful deliberation due to their social and legal significance. In this paper, we shed light on these challenges by considering externalist accounts of psychiatric disorders which stress that the presentation and development of psychiatric disorders is intricately entangled with their outward environment and social circumstances. We argue that any use of predictive AI in forensic psychiatry should not be limited to neurobiology alone but must also consider social and environmental factors. This thesis has practical implications for the design of predictive AI systems, especially regarding the collection and processing of training data, the selection of ML methods, and the determination of their explainability requirements.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.