Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

Meta-Analysis Informed Functional Connectomes Representations for Depression Identification

BACKGROUND

Meta-analyses in neuroimaging have gained popularity. However, their clinical utility remains uncertain. Convergent masks, containing repeated clusters from publications, are often focal and small, and voxel-wise features can lead to the curse of dimensionality, limiting discriminative ability in clinical diagnosis.

PURPOSE

To develop a functional connectome representation (FCR) by integrating meta-analytic neuroimaging data and to evaluate its performance in identifying depression.

STUDY TYPE

Retrospective.

SUBJECTS

The principal data set included 151 patients with depression (male/female, 72/79) and 105 healthy controls (male/female, 48/57). An external test data set comprised 109 patients (male/female, 44/65) and 54 healthy controls (male/female, 15/39).

FIELD STRENGTH/SEQUENCE

3.0 T T1-weighted imaging, resting-state functional MRI with echo-planar sequence.

ASSESSMENT

We performed the community detection algorithm and principal component analysis to develop the FCR. The model's performance based on the FCR was evaluated in terms of accuracy, specificity, and sensitivity. Effect sizes (Cohen's d) for FCR components were calculated between patients and healthy controls. Model robustness was assessed by analyzing the association between accuracy and the degree of shuffled features in the permutation test.

STATISTICAL TESTS

Chi-squared test, two-sample t-test, effect sizes (Cohen's d), permutation tests for accuracy validation, and correlation analysis. Significance was determined at p < 0.05.

RESULTS

Effect sizes (Cohen's d) for each of the 39 principal components to quantify the magnitude of differences between depressed patients and healthy controls, ranged from d = -0.22 to d = 0.84. The FCR-based diagnostic model achieved an accuracy of 89.42% (principal data set) and 83.35% (external data set). Permutation tests (n = 1000) indicated that the model's accuracy was significantly higher than chance level. A significant negative correlation was observed between random noise and accuracy (r = -0.093).

DATA CONCLUSION

The FCR effectively discriminates between depressed patients and healthy controls, exhibiting strong diagnostic performance, generalization, and robustness, supporting its potential utility in clinical depression identification.

EVIDENCE LEVEL

Level 3.

TECHNICAL EFFICACY

Stage 2.

Key biomarkers in Alzheimer's disease: Insights for diagnosis and treatment strategies

Alzheimer's disease (AD) remains a significant global health challenge, characterized by its progressive neurodegeneration and cognitive decline. The urgent need for early diagnosis and effective treatment necessitates the identification of reliable biomarkers that can illuminate the underlying pathophysiology of AD. This review provides a comprehensive overview of the latest advancements in biomarker research, focusing on their applications in diagnosis, prognosis, and therapeutic development. We delve into the multifaceted landscape of AD biomarkers, encompassing molecular, imaging, and fluid-based markers. The integration of these biomarkers, including amyloid-β and tau proteins, neuroimaging modalities, cerebrospinal fluid analysis, and genetic risk factors, offers a more nuanced understanding of AD's complex etiology. By leveraging the power of precision medicine, biomarker-driven approaches can enable personalized treatment strategies and enhance diagnostic accuracy. Moreover, this review highlights the potential of biomarker research to accelerate drug discovery and development. By identifying novel therapeutic targets and monitoring disease progression, biomarkers can facilitate the evaluation of experimental treatments and ultimately improve patient outcomes. In conclusion, this review underscores the critical role of biomarkers in advancing our comprehension of AD and driving the development of effective interventions. By providing a comprehensive overview of the current state-of-the-art, this work aims to inspire future research and contribute to the goal of conquering AD.

Using machine learning and electronic health record (EHR) data for the early prediction of Alzheimer's Disease and Related Dementias

BACKGROUND

Over 6 million patients in the United States are affected by Alzheimer's Disease and Related Dementias (ADRD). Early detection of ADRD can significantly improve patient outcomes through timely treatment.

OBJECTIVE

To develop and validate machine learning (ML) models for early ADRD diagnosis and prediction using de-identified EHR data from the University of Missouri (MU) Healthcare.

DESIGN

Retrospective case-control study.

SETTING

The study used de-identified EHR data provided by the MU NextGen Biomedical Informatics, modeled with the PCORnet Common Data Model (CDM).

PARTICIPANTS

An initial cohort of 380,269 patients aged 40 or older with at least two healthcare encounters was narrowed to a final dataset of 4,012 ADRD cases and 119,723 controls.

METHODS

Six ML classifier models: Gradient-Boosted Trees (GBT), Light Gradient-Boosting Machine (LightGBM), Random Forest (RF), eXtreme Gradient-Boosting (XGBoost), Logistic Regression (LR), and Adaptive Boosting (AdaBoost) were evaluated using Area Under the Receiver Operating Characteristic Curve (AUC-ROC), accuracy, sensitivity, specificity, and F1 score. SHAP (SHapley Additive exPlanations) analysis was applied to interpret predictions.

RESULTS

The GBT model achieved the best AUC-ROC scores of 0.809-0.833 across 1- to 5-year prediction windows. SHAP analysis identified depressive disorder, age groups 80-90 yrs and 70-80 yrs, heart disease, anxiety, and the novel risk factors of sleep apnea, and headache.

CONCLUSION

This study underscores the potential of ML models for leveraging EHR data to enable early ADRD prediction, supporting timely interventions, and improving patient outcomes. By identifying both established and novel risk factors, these findings offer new opportunities for personalized screening and management strategies, advancing both clinical and informatics science.

Classification of schizophrenia spectrum disorder using machine learning and functional connectivity: reconsidering the clinical application

BACKGROUND

Early identification of Schizophrenia Spectrum Disorder (SSD) is crucial for effective intervention and prognosis improvement. Previous neuroimaging-based classifications have primarily focused on chronic, medicated SSD cohorts. However, the question remains whether brain metrics identified in these populations can serve as trait biomarkers for early-stage SSD. This study investigates whether functional connectivity features identified in chronic, medicated SSD patients could be generalized to early-stage SSD.

METHODS

Data were collected from 502 SSD patients and 575 healthy controls (HCs) across four medical institutions. Resting-state functional connectivity (FC) features were used to train a Support Vector Machine (SVM) classifier on individuals with medicated chronic SSD and HCs from three sites. The remaining site, comprising both chronic medicated and first-episode unmedicated SSD patients, was used for independent validation. A univariable analysis examined the association between medication dosage or illness duration and FC.

RESULTS

The classifier achieved 69% accuracy (p = 0.002), 63% sensitivity, 75% specificity, 0.75 area under the receiver operating characteristic curve, 69% F1-score, 72% positive predictive rate, and 67% negative predictive rate, when tested on an independent dataset. Subgroup analysis showed 71% sensitivity (p = 0.04) for chronic medicated SSD, but poor generalization to first-episode unmedicated SSD (sensitivity = 48%, p = 0.44). Univariable analysis revealed a significant association between FC and medication usage, but not disease duration.

CONCLUSIONS

Classifiers developed on chronic medicated SSD may predominantly capture state features of chronicity and medication, overshadowing potential SSD traits. This partially explains the current classifiers' non-generalizability across SSD patients with different clinical states, underscoring the need for models that can enhance the early detection of schizophrenia neural pathology.

Unraveling overoptimism and publication bias in ML-driven science

Machine learning (ML) is increasingly used across many disciplines with impressive reported results. However, recent studies suggest that the published performances of ML models are often overoptimistic. Validity concerns are underscored by findings of an inverse relationship between sample size and reported accuracy in published ML models, contrasting with the theory of learning curves where accuracy should improve or remain stable with increasing sample size. This paper investigates factors contributing to overoptimism in ML-driven science, focusing on overfitting and publication bias. We introduce a stochastic model for observed accuracy, integrating parametric learning curves and the aforementioned biases. We construct an estimator that corrects for these biases in observed data. Theoretical and empirical results show that our framework can estimate the underlying learning curve, providing realistic performance assessments from published results. By applying the model to meta-analyses of classifications of neurological conditions, we estimate the inherent limits of ML-driven prediction in each domain.

Leveraging artificial intelligence for diagnosis of children autism through facial expressions

The global population contains a substantial number of individuals who experience autism spectrum disorder, thus requiring immediate identification to enable successful intervention approaches. The authors assess the detection of autism-related learning difficulties in children by evaluating deep learning models that use transfer learning methods along with fine-tuning methods. Using autism spectrum disorder (ASD) diagnosed child RGB images data, researchers evaluated six prevalent deep learning structures: DenseNet201, ResNet152, VGG16, VGG19, MobileNetV2, and EfficientNet-B0. ResNet152 reached the highest accuracy rate of 89% when functioning independently. This paper develops a hybrid deep-learning model by integrating ResNet152 with Vision Transformers (ViT) to achieve better classification performance. The ViT-ResNet152 model's convolutional and transformer processing elements worked together to improve the accuracy of the diagnosis to 91.33% and make it better at finding different cases of autism spectrum disorder (ASD).The research outcomes demonstrate that AI tools show promise for delivering highly precise and standardized methods to detect ASD at an early stage. Future research needs to include multiple data types as well as extend dataset variability while optimizing hybrid architecture systems to elevate diagnostic forecasting. The incorporation of artificial intelligence in ASD evaluation services holds promise to transform early therapy approaches, which leads to better results for autistic children all around the globe.

Classification of Irritable Bowel Syndrome Using Brain Functional Connectivity Strength and Machine Learning

BACKGROUND

Irritable Bowel Syndrome (IBS) is a prevalent condition characterized by dysregulated brain-gut interactions. Despite its widespread impact, the brain mechanism of IBS remains incompletely understood, and there is a lack of objective diagnostic criteria and biomarkers. This study aims to investigate brain network alterations in IBS patients using the functional connectivity strength (FCS) method and to develop a support vector machine (SVM) classifier for distinguishing IBS patients from healthy controls (HCs).

METHODS

Thirty-one patients with IBS and thirty age and sex-matched HCs were enrolled in this study and underwent resting-state functional magnetic resonance imaging (fMRI) scans. We applied FCS to assess global brain functional connectivity changes in IBS patients. An SVM-based machine - learning approach was then used to evaluate whether the altered FCS regions could serve as fMRI-based markers for classifying IBS patients and HCs.

RESULTS

Compared to the HCs, patients with IBS showed significantly increased FCS in the left medial orbitofrontal cortex (mOFC) and decreased FCS in the bilateral cingulate cortex/precuneus (PCC/Pcu) and middle cingulate cortex (MCC). The machine-learning model achieved a classification accuracy of 91.9% in differentiating IBS patients from HCs.

CONCLUSION

These findings reveal a unique pattern of FCS alterations in brain areas governing pain regulation and emotional processing in IBS patients. The identified abnormal FCS features have the potential to serve as effective biomarkers for IBS classification. This study may contribute to a deeper understanding of the neural mechanisms of IBS and aid in its diagnosis in clinical practice.

A lightweight generative model for interpretable subject-level prediction

Recent years have seen a growing interest in methods for predicting an unknown variable of interest, such as a subject's diagnosis, from medical images depicting its anatomical-functional effects. Methods based on discriminative modeling excel at making accurate predictions, but are challenged in their ability to explain their decisions in anatomically meaningful terms. In this paper, we propose a simple technique for single-subject prediction that is inherently interpretable. It augments the generative models used in classical human brain mapping techniques, in which the underlying cause-effect relations can be encoded, with a multivariate noise model that captures dominant spatial correlations. Experiments demonstrate that the resulting model can be efficiently inverted to make accurate subject-level predictions, while at the same time offering intuitive visual explanations of its inner workings. The method is easy to use: training is fast for typical training set sizes, and only a single hyperparameter needs to be set by the user. Our code is available at https://github.com/chiara-mauri/Interpretable-subject-level-prediction.

An interpretable deep-learning approach to detect biomarkers in anxious-depressed symptoms from prefrontal fNIRS signals during an autobiographical memory test

BACKGROUND

Individuals with anxious-depressed (AD) symptoms have more severe mood disorders and cognitive impairment than those with non-anxious depression (NAD) symptoms. Therefore, it is important to clarify the underlying neurophysiology of these two symptom groups to optimize treatment.

METHODS

We developed an interpretable deep-learning framework based on two convolutional neural networks (CNN) to diagnose depression from functional near-infrared spectroscopy (fNIRS) neuroimaging data recorded during an autobiographical memory test (AMT) from 824 participants. This system was designed to discriminate between individuals with depressed symptoms (N = 127) and healthy controls (N = 697) and identify AD (N = 72) and NAD (N = 55). Besides, we employed the SHapley Additive exPlanations (SHAP) method to discover discriminative biomarkers for AD symptoms.

RESULTS

Positive episode recall features effectively distinguished depressed symptoms with the highest accuracy of 0.89, sensitivity of 0.84, specificity of 0.90, and area under the receiver operator characteristic curve (AUC) of 0.84. Conversely, negative episode recall features achieved the highest accuracy of 0.91, sensitivity of 0.80, specificity of 0.85, and an AUC of 0.91 for identifying AD symptoms. These performances were based on a five-fold cross-validation procedure. Based on the SHAP-derived analyses, the most influential channels contributing to AD symptom prediction were located within the right hemisphere.

CONCLUSION

This study revealed that the hemodynamic hypo-activation of negative emotional valence in the right frontal pole area (rFPA) may contribute to AD symptom prediction.

Longer scans boost prediction and cut costs in brain-wide association studies

A pervasive dilemma in brain-wide association studies (BWAS) is whether to prioritize functional MRI (fMRI) scan time or sample size. We derive a theoretical model showing that individual-level phenotypic prediction accuracy increases with sample size and total scan duration (sample size × scan time per participant). The model explains empirical prediction accuracies extremely well across 76 phenotypes from nine resting-fMRI and task-fMRI datasets (R2 = 0.89), spanning a wide range of scanners, acquisitions, racial groups, disorders and ages. For scans ≤20 mins, prediction accuracy increases linearly with the logarithm of total scan duration, suggesting interchangeability of sample size and scan time. However, sample size is ultimately more important than scan time in determining prediction accuracy. Nevertheless, when accounting for overhead costs associated with each participant (e.g., recruitment costs), to boost prediction accuracy, longer scans can yield substantial cost savings over larger sample size. To achieve high prediction performance, 10-min scans are highly cost inefficient. In most scenarios, the optimal scan time is ≥20 mins. On average, 30-min scans are the most cost-effective, yielding 22% cost savings over 10-min scans. Overshooting is cheaper than undershooting the optimal scan time, so we recommend aiming for ≥30 mins. Compared with resting-state whole-brain BWAS, the most cost-effective scan time is shorter for task-fMRI and longer for subcortical-cortical BWAS. Standard power calculations maximize sample size at the expense of scan time. Our study demonstrates that optimizing both sample size and scan time can boost prediction power while cutting costs. Our empirically informed reference is available for future study planning: WEB_APPLICATION_LINK.

Connectome architecture for gray matter atrophy and surgical outcomes in temporal lobe epilepsy

OBJECTIVE

Temporal lobe epilepsy (TLE) has been recognized as a network disorder with widespread gray matter atrophy. However, the role of connectome architecture in shaping morphological alterations and identifying atrophy epicenters remains unclear. Furthermore, individualized modeling of atrophy epicenters and their potential clinical applications have not been well established. This study aims to explore how gray matter atrophy correlates with normal connectome architecture, identify potential atrophy epicenters, and employ individualized modeling approach to evaluate the impact of different epicenter patterns on surgical outcomes in patients with TLE.

METHODS

This study utilized anatomic MRI data from 126 refractory TLE patients who underwent anterior temporal lobectomy and 60 healthy controls (HCs), along with normative functional and structural connectome data, to investigate the relationship between gray matter volume (GMV) changes and functional or structural connectivity. Two models were employed to identify atrophy epicenters: a data-driven approach evaluating nodal and neighbor atrophy rankings, and a network diffusion model (NDM) simulating the spread of pathology from different seed regions. K-means clustering was applied in patient-tailored modeling to uncover distinct epicenter subtypes.

RESULTS

Our findings indicate that the pattern of gray matter atrophy in TLE is constrained primarily by structural connectivity rather than by functional connectivity. Using the structural connectome, we pinpointed the hippocampus and adjacent temporo-limbic regions as key atrophy epicenters. The patient-tailored modeling revealed significant variability in epicenter distribution, allowing us to categorize them into two distinct subtypes. Notably, patients in subtype 2, with epicenters localized to the ipsilateral temporal pole and medial temporal lobe, exhibited significantly higher seizure-free rates compared to patients in subtype 1, whose epicenters situated in frontocentral regions.

SIGNIFICANCE

These findings highlight the central role of structural connectivity in shaping TLE-related morphological changes. Individualized epicenter modeling may enhance surgical decisions and improve prognostic stratification in TLE management.

Structural Cerebellar and Lateral Frontoparietal Networks are altered in CUD: An SBM Analysis

Repetitive drug use results in enduring structural and functional changes in the brain. Addiction research has consistently revealed significant modifications in key brain networks related to reward, habit, salience, executive function, memory and self-regulation. Techniques like Voxel-based Morphometry have highlighted large-scale structural differences in grey matter across distinct groups. Source-based Morphometry (SBM) takes this a step further by incorporating the Independent Component Analysis to detect shared patterns of grey matter variation, all without requiring prior selection of regions of interest. However, SBM has yet to be employed in the study of structural alteration patterns related to cocaine addiction. Therefore, we performed this analysis to explore alterations in structural covariance specific to cocaine addiction. Our study involved 40 individuals diagnosed with Cocaine Use Disorder (CUD) and 40 matched healthy controls. Participants with CUD completed clinical questionnaires assessing the severity of their dependence and other relevant clinical variables. Following the adjustment for age-related effects, we observed notable disparities between groups in two structural independent components, which we identified as the structural cerebellar network and the structural lateral frontoparietal network, which display opposing trends. Specifically, the individuals with CUD exhibited a heightened contribution to the cerebellar network but simultaneously demonstrated a reduced contribution to the lateral frontoparietal network compared to the healthy controls. These findings unveil distinctive covariance patterns of neuroregulation linked with cocaine addiction, which indicates an interruption in the typical structural development in an affected lateral frontoparietal network, while suggesting an extended pattern of neuroregulation within the cerebellar network in individuals with CUD.

Cognitive performance classification of older patients using machine learning and electronic medical records

Dementia rates are projected to increase significantly by 2050, posing considerable challenges for healthcare systems worldwide. Developing efficient diagnostic tools is critical, and machine learning (ML) algorithms have shown potential for improving the accuracy of cognitive impairment classification. This study aims to address challenges in current systems by leveraging readily available electronic medical record (EMR) data to simplify and enhance the classification of cognitive impairment. The analysis includes 283 older adults, categorized into three groups: 144 individuals with mild cognitive impairment (MCI), 38 with dementia, and 101 healthy controls. Various ML techniques are evaluated to classify cognitive performance levels based on input features such as sociodemographic variables, lab results, comorbidities, Body Mass Index (BMI), and functional scales. Key predictors for distinguishing healthy controls from individuals with MCI are identified. These are history of myocardial infarction, vitamin D3 levels, the Instrumental Activities of Daily Living (IADL) scale, age, and sodium levels. The nonlinear Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel achieve the best performance for MCI classification, with an accuracy of 69%, an AUC of 0.75, and a Matthews Correlation Coefficient (MCC) of 0.43. For distinguishing healthy controls from those with dementia, the most influential factors include the IADL scale, the Activities of Daily Living (ADL) scale, education, vitamin D3 levels, and age. Here, the Random Forest algorithm demonstrates superior performance, achieving 84% accuracy, an AUC of 0.96, and an MCC of 0.71. These two models consistently outperform other ML techniques, such as K-Nearest Neighbors, Multi-Layer Perceptron, linear SVM, Naive Bayes, Quadratic Discriminant Analysis, Linear Discriminant Analysis, AdaBoost, and Gaussian Process Classifiers. The findings suggest that EMR data can be an effective resource for the initial classification of cognitive impairments. Integrating these ML-driven approaches into primary care settings may facilitate the early identification of older patients who could benefit from further cognitive assessments.

Brain structural connectomic topology predicts medication response in youth with bipolar disorder: A randomized clinical trial

BACKGROUND

Response to pharmacotherapy varies considerably among youths with bipolar disorder (BD) and is poorly predicted by clinical or demographic features. It can take several weeks to determine whether medication for BD is clinically effective. Although neuroimaging biomarkers are promising predictors, few studies examined the predictive value of the brain connectomic topology.

METHODS

BD-I youth (N = 121) with no prior psychopharmacotherapy were randomized to 6-weeks of double-blind quetiapine or lithium. Structural magnetic resonance imaging (MRI) was performed before medication and at one week after medication initiation. Brain structural connectome was established from the MRI scans, and topological metrics were calculated for each patient. Deep learning-based prediction model was built using baseline and one-week connectome topology to predict medication response at week 6.

RESULTS

Both baseline topological metrics and one-week topological changes could predict treatment response with significant accuracy (73.8 % - 86.8 %). A longitudinally joint model combining baseline and one-week topology provided the highest accuracy (91.3 %). The transferability between models for quetiapine and lithium was relatively poor. In addition, predictions for the two drugs were driven by similar baseline but distinct one-week salient topological patterns.

LIMITATIONS

Independent replication is needed to validate our preliminary findings.

CONCLUSION

Brain structural connectomic topology at baseline and its acute changes within the first week enable accurate BD medication response prediction. The most contributive brain regions differed between prediction models for quetiapine and lithium after one week. These findings provide preliminary evidence for the development of neuroimaging-based biomarkers for guiding therapeutic interventions in youth with BD.

Applications of MRI in Schizophrenia: Current Progress in Establishing Clinical Utility

Schizophrenia is a severe mental illness that significantly impacts the lives of affected individuals and with increasing mortality rates. Early detection and intervention are crucial for improving outcomes but the lack of validated biomarkers poses great challenges in such efforts. The use of magnetic resonance imaging (MRI) in schizophrenia enables the investigation of the disorder's etiological and neuropathological substrates in vivo. After decades of research, promising findings of MRI have been shown to aid in screening high-risk individuals and predicting illness onset, and predicting symptoms and treatment outcomes of schizophrenia. The integration of machine learning and deep learning techniques makes it possible to develop intelligent diagnostic and prognostic tools with extracted or selected imaging features. In this review, we aimed to provide an overview of current progress and prospects in establishing clinical utility of MRI in schizophrenia. We first provided an overview of MRI findings of brain abnormalities that might underpin the symptoms or treatment response process in schizophrenia patients. Then, we summarized the ongoing efforts in the computer-aided utility of MRI in schizophrenia and discussed the gap between MRI research findings and real-world applications. Finally, promising pathways to promote clinical translation were provided. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 3.

Multimodal predictive modeling: Scalable imaging informed approaches to predict future brain health

BACKGROUND

Predicting future brain health is a complex endeavor that often requires integrating diverse data sources. The neural patterns and interactions identified through neuroimaging serve as the fundamental basis and early indicators that precede the manifestation of observable behaviors or psychological states.

NEW METHOD

In this work, we introduce a multimodal predictive modeling approach that leverages an imaging-informed methodology to gain insights into future behavioral outcomes. We employed three methodologies for evaluation: an assessment-only approach using support vector regression (SVR), a neuroimaging-only approach using random forest (RF), and an image-assisted method integrating the static functional network connectivity (sFNC) matrix from resting-state functional magnetic resonance imaging (rs-fMRI) alongside assessments. The image-assisted approach utilized a partially conditional variational autoencoder (PCVAE) to predict brain health constructs in future visits from the behavioral data alone.

RESULTS

Our performance evaluation indicates that the image-assisted method excels in handling conditional information to predict brain health constructs in subsequent visits and their longitudinal changes. These results suggest that during the training stage, the PCVAE model effectively captures relevant information from neuroimaging data, thereby potentially improving accuracy in making future predictions using only assessment data.

COMPARISON WITH EXISTING METHODS

The proposed image-assisted method outperforms traditional assessment-only and neuroimaging-only approaches by effectively integrating neuroimaging data with assessment factors.

CONCLUSION

This study underscores the potential of neuroimaging-informed predictive modeling to advance our comprehension of the complex relationships between cognitive performance and neural connectivity.

Mapping the neurodevelopmental predictors of psychopathology

Neuroimaging research has uncovered a multitude of neural abnormalities associated with psychopathology, but few prediction-based studies have been conducted during adolescence, and even fewer used neurobiological features that were extracted across multiple neuroimaging modalities. This gap in the literature is critical, as deriving accurate brain-based models of psychopathology is an essential step towards understanding key neural mechanisms and identifying high-risk individuals. As such, we trained adaptive tree-boosting algorithms on multimodal neuroimaging features from the Lifespan Human Connectome Developmental (HCP-D) sample that contained 956 participants between the ages of 8 to 22 years old. Our feature space consisted of 1037 anatomical, 1090 functional, and 192 diffusion MRI features, which were used to derive models that separately predicted internalizing symptoms, externalizing symptoms, and the general psychopathology factor. We found that multimodal models were the most accurate, but all brain-based models of psychopathology yielded out-of-sample predictions that were weakly correlated with actual symptoms (r2 < 0.15). White matter microstructural properties, including orientation dispersion indices and intracellular volume fractions, were the most predictive of general psychopathology, followed by cortical thickness and functional connectivity. Spatially, the most predictive features of general psychopathology were primarily localized within the default mode and dorsal attention networks. These results were mostly consistent across all dimensions of psychopathology, except orientation dispersion indices and the default mode network were not as heavily weighted in the prediction of internalizing and externalizing symptoms. Taken with prior literature, it appears that neurobiological features are an important part of the equation for predicting psychopathology but relying exclusively on neural markers is clearly not sufficient, especially among adolescent samples with subclinical symptoms. Consequently, risk factor models of psychopathology may benefit from incorporating additional sources of information that have also been shown to explain individual differences, such as psychosocial factors, environmental stressors, and genetic vulnerabilities.

Machine learning-based assessment of morphometric abnormalities distinguishes bipolar disorder and major depressive disorder

INTRODUCTION

Bipolar disorder (BD) and major depressive disorder (MDD) have overlapping clinical presentations which may make it difficult for clinicians to distinguish them potentially resulting in misdiagnosis. This study combined structural MRI and machine learning techniques to determine whether regional morphological differences could distinguish patients with BD and MDD.

METHODS

A total of 123 participants, including BD (n = 31), MDD (n = 48), and healthy controls (HC, n = 44), underwent high-resolution 3D T1-weighted imaging. Cortical thickness, surface area, and subcortical volumes were measured using FreeSurfer software. Common and classic machine learning models were utilized to identify distinct morphometric alterations between BD and MDD.

RESULTS

Significant morphological differences were observed in both common and distinct brain regions between BD, MDD, and HC. Specifically, abnormalities in the amygdala, thalamus, medial orbitofrontal cortex and fusiform were observed in both BD and MDD compared with HC. Relative to HC, unique differences in BD were identified in the lateral occipital and inferior/middle temporal regions, whereas MDD exhibited differences in nucleus accumbens and middle temporal regions. BD exhibited larger surface area in right middle temporal gyrus and greater right nucleus accumbens volume compared to MDD. The integration of two-stage models, including deep neural network (DNN) and support vector machine (SVM), achieved an accuracy rate of 91.2% in discriminating individuals with BD from MDD.

CONCLUSION

These findings demonstrate that structural MRI combined with machine learning techniques can accurately discriminate individuals with BD from MDD, and provide a foundation supporting the potential of this approach to improve diagnostic accuracy.

Differential gray matter correlates and machine learning prediction of abuse and internalizing psychopathology in adolescent females

Childhood abuse represents one of the most potent risk factors for the development of psychopathology during childhood, accounting for 30-60% of the risk for onset. While previous studies have separately associated reductions in gray matter volume (GMV) with childhood abuse and internalizing psychopathology (IP), it is unclear whether abuse and IP differ in their structural abnormalities, and which GMV features are related to abuse and IP at the individual level. In a pooled multisite, multi-investigator sample, 246 child and adolescent females between the ages of 8-18 were recruited into studies of interpersonal violence (IPV) and/or IP (i.e. posttraumatic stress disorder (PTSD), depression, and/or anxiety). Youth completed assessments for IP, childhood abuse history, and underwent high resolution T1 structural MRI. First, we characterized how differences in GMV associated with childhood abuse exposure depend on the presence or absence of IP using voxel-based morphometry (VBM). Next, we trained convolutional neural networks to predict individual psychopathology and abuse experience and estimated the strength and direction of importance of each structural feature in making individual-level predictions using Shapley values. Shapley values were aggregated across the entire cohort, and the top 1% of feature clusters with the highest importance are reported. At a group-level, VBM analyses identified widespread decreases in GMV across the prefrontal cortex, insula, and hippocampus in youth with IP, while abuse experience was specifically associated with increased GMV in the cingulate cortex and supramarginal gyrus. Further, interactions between IP and severity of abuse were identified in the ventral and dorsal prefrontal cortex, anterior cingulate cortex, and thalamus. After extensive training, model tuning, and model evaluation, the neural networks performed above chance when predicting IP (63% accuracy) and abuse experiences (71% accuracy) at the level of the individual. Interestingly, structural regions with the highest importance in making individual IP predictions had a high degree of overlap with group-level patterns. We have identified unique structural correlates of childhood abuse and IP on both the group and individual level with a high degree of overlap, providing evidence that IP and trauma exposure may uniquely and jointly impact child and adolescent structural neurodevelopment. Feature learning may offer power and novelty above and beyond traditional group-level approaches to the identification of biomarkers and a movement towards individualized diagnosis and treatment.

Hippocampal Subregions Volume and Texture for the Diagnosis of Mild Cognitive Impairment

The aim was to examine the diagnostic efficacy of hippocampal subregions volume and texture in differentiating amnestic mild cognitive impairment (MCI) from normal aging changes. Ninety MCI subjects and eighty-eight well-matched healthy controls (HCs) were selected. Twelve hippocampal subregions volume and texture features were extracted using Freesurfer and MaZda based on T1 weighted MRI. Then, two-sample t-test and Least Absolute Shrinkage and Selection Operator (LASSO) regression were developed to select a subset of the original features. Support vector machine (SVM) was used to perform the classification task and the area under the curve (AUC), sensitivity, specificity and accuracy were calculated to evaluate the diagnostic efficacy of the model. The volume features with high discriminative power were mainly located in the bilateral CA1 and CA4, while texture feature were gray-level non-uniformity, run length non-uniformity and fraction. Our model based on hippocampal subregions volume and texture features achieved better classification performance with an AUC of 0.90. The volume and texture of hippocampal subregions can be utilized for the diagnosis of MCI. Moreover, we found that the features that contributed most to the model were mainly textural features, followed by volume. These results may guide future studies using structural scans to classify patients with MCI.

Artificial Intelligence-Based Methodologies for Early Diagnostic Precision and Personalized Therapeutic Strategies in Neuro-Ophthalmic and Neurodegenerative Pathologies

Advancements in neuroimaging, particularly diffusion magnetic resonance imaging (MRI) techniques and molecular imaging with positron emission tomography (PET), have significantly enhanced the early detection of biomarkers in neurodegenerative and neuro-ophthalmic disorders. These include Alzheimer's disease, Parkinson's disease, multiple sclerosis, neuromyelitis optica, and myelin oligodendrocyte glycoprotein antibody disease. This review highlights the transformative role of advanced diffusion MRI techniques-Neurite Orientation Dispersion and Density Imaging and Diffusion Kurtosis Imaging-in identifying subtle microstructural changes in the brain and visual pathways that precede clinical symptoms. When integrated with artificial intelligence (AI) algorithms, these techniques achieve unprecedented diagnostic precision, facilitating early detection of neurodegeneration and inflammation. Additionally, next-generation PET tracers targeting misfolded proteins, such as tau and alpha-synuclein, along with inflammatory markers, enhance the visualization and quantification of pathological processes in vivo. Deep learning models, including convolutional neural networks and multimodal transformers, further improve diagnostic accuracy by integrating multimodal imaging data and predicting disease progression. Despite challenges such as technical variability, data privacy concerns, and regulatory barriers, the potential of AI-enhanced neuroimaging to revolutionize early diagnosis and personalized treatment in neurodegenerative and neuro-ophthalmic disorders is immense. This review underscores the importance of ongoing efforts to validate, standardize, and implement these technologies to maximize their clinical impact.

Resting-state functional connectome predicts sleep quality two months after the first negative COVID-19 antigen test

BACKGROUND

The COVID-19 pandemic has led to long-term neurological and psychological effects, including sleep disturbances. While prior studies have identified altered brain function post-COVID-19, specific functional connectivity (FC) patterns predicting sleep quality after recovery remain unclear. This study aims to identify FC patterns associated with sleep quality two months after the first negative COVID-19 antigen test.

METHODS

Using a connectome-based predictive modeling (CPM) approach, we identified the functional connectome regulating sleep quality based on a 164-region parcellation. Significant connections were analyzed using mediation models to examine their role in the relationship between anxiety, depression, and sleep.

RESULTS

FC between the right cerebellar peduncle and the left VIII of the cerebellum, and between the left middle temporal pole (MTP) and left ventral tegmental area (VTA), significantly predicted Pittsburgh Sleep Quality Index (PSQI) scores for sleep disturbances two months post-recovery (q2 = 0.059, MSE = 0.154, p = 0.017, r = 0.350). Mediation analysis showed a significant indirect effect of FC between the left MTP and VTA on the relationship between generalized anxiety and sleep disturbances (indirect effect = 0.013, 95% CI = [0.002, 0.03], pfdr <0.05). FC between the right dorsal raphe nucleus and ipsilateral regions-including occipital, parietal, and temporal areas-predicted PSQI scores for daytime dysfunction (q2 = 0.092, MSE = 0.678, p = 0.025, r = 0.342).

CONCLUSION

Post-COVID-19 brain connectivity and anxiety predict sleep quality. These findings highlight the potential for targeted therapeutic strategies to improve sleep and identify patients at risk for prolonged disturbances through FC biomarkers.

Magnetic resonance imaging-based machine learning classification of schizophrenia spectrum disorders: a meta-analysis

BACKGROUND

Recent advances in multivariate pattern recognition have fostered the search for reliable neuroimaging-based biomarkers in psychiatric conditions, including schizophrenia. These approaches consider the complex pattern of alterations in brain function and structure, overcoming the limitations of traditional univariate methods. To assess the reliability of neuroimaging-based biomarkers and the contribution of study characteristics in distinguishing individuals with schizophrenia spectrum disorder (SSD) from healthy controls (HCs), we conducted a systematic review of the studies that used multivariate pattern recognition for this objective.

METHODS

We systematically searched PubMed, Scopus, and Web of Science for studies on SSD classification using multivariate pattern analysis on magnetic resonance imaging data. We employed a bivariate random-effects meta-analytic model to explore the classification of sensitivity (SE) and specificity (SP) across studies while also evaluating the moderator effects of clinical and non-clinical variables.

RESULTS

A total of 119 studies (with 12,723 patients with SSD and 13,196 HCs) were identified. The meta-analysis estimated a SE of 79.1% (95% confidence interval [CI], 77.1%-81.0%) and a SP of 80.0% (95% CI, 77.8%-82.0%). In particular, the Positive and Negative Syndrome Scale and the Global Assessment of Functioning scores, age, age of onset, duration of untreated psychosis, deep learning, algorithm type, features selection, and validation methods had significant effects on classification performance.

CONCLUSIONS

Multivariate pattern analysis reliably identifies neuroimaging-based biomarkers of SSD, achieving ∼80% SE and SP. Despite clinical heterogeneity, discernible brain modifications effectively differentiate SSD from HCs. Classification performance depends on patient-related and methodological factors crucial for the development, validation, and application of prospective models in clinical settings.

Classification of mindfulness experiences from gamma-band effective connectivity: Application of machine-learning algorithms on resting, breathing, and body scan

BACKGROUND AND OBJECTIVE

Practicing mindfulness is a mental process toward interoceptive awareness, achieving stress reduction and emotion regulation through brain-function alteration. Literature has shown that electroencephalography (EEG)-derived connectivity possesses the potential to differentiate brain functions between mindfulness naïve and mindfulness experienced, where such quantitative differentiation could benefit telediagnosis for mental health. However, there is no prior guidance in model selection targeting on the mindfulness-experience prediction. Here we hypothesized that the EEG effective connectivity could reach a good prediction performance in mindfulness experiences with brain interpretability.

METHODS

We aimed at probing direct Directed Transfer Function (dDTF) to classify the participants' history of mindfulness-based stress reduction (MBSR), and aimed at optimizing the prediction accuracy by comparing multiple machine learning (ML) algorithms. Targeting the gamma-band effective connectivity, we evaluated the EEG-based prediction of the mindfulness experiences across 7 machine learning (ML) algorithms and 3 sessions (i.e., resting, focus-breathing, and body-scan).

RESULTS

The support vector machine and naïve Bayes classifiers exhibited significant accuracies above the chance level across all three sessions, and the decision tree algorithm reached the highest prediction accuracy of 91.7 % with the resting state, compared to the classification accuracies with the other two mindful states. We further conducted the analysis on essential EEG channels to preserve the classification accuracy, revealing that preserving just four channels (F7, F8, T7, and P7) out of 19 yielded the accuracy of 83.3 %. Delving into the contribution of connectivity features, specific connectivity features predominantly located in the frontal lobe contributed more to classifier construction, which aligned well with the existing mindfulness literature.

CONCLUSION

In the present study, we initiated a milestone of developing an EEG-based classifier to detect a person's mindfulness experience objectively. The prediction accuracy of the decision tree was optimal to differentiate the mindfulness experiences using the local resting-state EEG data. The suggested algorithm and key channels on the mindfulness-experience prediction may provide guidance for predicting mindfulness experiences using the EEG-based classification embedded in future wearable neurofeedback systems or plausible digital therapeutics.

Machine Learning Approaches to Identify Affected Brain Regions in Movement Disorders Using MRI Data: A Systematic Review and Diagnostic Meta-analysis

BACKGROUND

Movement disorders such as Parkinson's disease are associated with structural and functional changes in specific brain regions. Advanced magnetic resonance imaging (MRI) techniques combined with machine learning (ML) are promising tools for identifying imaging biomarkers and patterns associated with these disorders.

PURPOSE/HYPOTHESIS

We aimed to systematically identify the brain regions most commonly affected in movement disorders using ML approaches applied to structural and functional MRI data. We searched the PubMed and Scopus databases using relevant keywords up to June 2023 for studies that used ML approaches to detect brain regions associated with movement disorders using MRI data.

STUDY TYPE

A systematic review and diagnostic meta-analysis.

POPULATION/SUBJECTS

Sixty-seven studies with 6,285 patients were included.

FIELD STRENGTH/SEQUENCE

Studies utilizing 1.5T or 3T MR scanners and the acquisition of diffusion tensor imaging (DTI), structural MRI (sMRI), functional MRI (fMRI), or a combination of these were included.

ASSESSMENT

The authors independently assessed the study quality using the CLAIM and QUADAS-2 criteria and extracted data on diagnostic accuracy measures.

STATISTICAL TESTS

Sensitivity, specificity, accuracy, and area under the curve were pooled using random-effects models. Q statistics and the I2 index were used to evaluate heterogeneity, and Begg's funnel plot was used to identify publication bias.

RESULTS

sMRI showed the highest sensitivity (93%) and mixed modalities had the highest specificity (90%) for detecting regional abnormalities. sMRI had a 94% sensitivity for identifying subcortical changes. The support vector machine (93%) and logistic regression (91%) models exhibited high diagnostic accuracies.

DATA CONCLUSION

The combination of advanced MR neuroimaging techniques and ML is a promising approach for identifying brain biomarkers and affected regions in movement disorders with subcortical structures frequently implicated. Structural MRI, in particular, showed strong performance.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

Schizophrenia Detection and Classification: A Systematic Review of the Last Decade

BACKGROUND/OBJECTIVES

Artificial Intelligence (AI) in healthcare employs advanced algorithms to analyze complex and large-scale datasets, mimicking aspects of human cognition. By automating decision-making processes based on predefined thresholds, AI enhances the accuracy and reliability of healthcare data analysis, reducing the need for human intervention. Schizophrenia (SZ), a chronic mental health disorder affecting millions globally, is characterized by symptoms such as auditory hallucinations, paranoia, and disruptions in thought, behavior, and perception. The SZ symptoms can significantly impair daily functioning, underscoring the need for advanced diagnostic tools.

METHODS

This systematic review has been conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines and examines peer-reviewed studies from the last decade (2015-2024) on AI applications in SZ detection as well as classification. The review protocol has been registered in the International Prospective Register of Systematic Reviews (PROSPERO) under registration number: CRD42024612364. Research has been sourced from multiple databases and screened using predefined inclusion criteria. The review evaluates the use of both Machine Learning (ML) and Deep Learning (DL) methods across multiple modalities, including Electroencephalography (EEG), Structural Magnetic Resonance Imaging (sMRI), and Functional Magnetic Resonance Imaging (fMRI). The key aspects reviewed include datasets, preprocessing techniques, and AI models.

RESULTS

The review identifies significant advancements in AI methods for SZ diagnosis, particularly in the efficacy of ML and DL models for feature extraction, classification, and multi-modal data integration. It highlights state-of-the-art AI techniques and synthesizes insights into their potential to improve diagnostic outcomes. Additionally, the analysis underscores common challenges, including dataset limitations, variability in preprocessing approaches, and the need for more interpretable models.

CONCLUSIONS

This study provides a comprehensive evaluation of AI-based methods in SZ prognosis, emphasizing the strengths and limitations of current approaches. By identifying unresolved gaps, it offers valuable directions for future research in the application of AI for SZ detection and diagnosis.

Prediction of individual weight loss using supervised learning: findings from the CALERIETM 2 study

BACKGROUND

Predicting individual weight loss (WL) responses to lifestyle interventions is challenging but might help practitioners and clinicians select the most promising approach for each individual.

OBJECTIVE

The primary aim of this study was to develop machine learning (ML) models to predict individual WL responses using only variables known before starting the intervention. In addition, we used ML to identify pre-intervention variables influencing the individual WL response.

METHODS

We used 12-mo data from the comprehensive assessment of long-term effects of reducing intake of energy (CALERIETM) phase 2 study, which aimed to analyze the long-term effects of caloric restriction on human longevity. On the basis of the data from 130 subjects in the intervention group, we developed classification models to predict binary ("Success" and "No/low success") or multiclass ("High success," "Medium success," and "Low/no success") WL outcomes. Additionally, regression models were developed to predict individual weight change (percent). Models were evaluated on the basis of accuracy, sensitivity, specificity (classification models), and root mean squared error (RMSE; regression models).

RESULTS

Best classification models used 20-40 predictors and achieved 89%-97% accuracy, 91%-100% sensitivity, and 56%-86% specificity for binary classification. For multiclass classification, accuracy (69%) and sensitivity (50%) tended to be lower. The best regression performance was obtained with 36 variables with an RMSE of 2.84%. Among the 21 variables predicting individual weight change most consistently, we identified 2 novel predictors, namely orgasm satisfaction and sexual behavior/experience. Other common predictors have previously been associated with WL (16) or are already used in traditional prediction models (3).

CONCLUSIONS

The prediction models could be implemented by practitioners and clinicians to support the decision of whether lifestyle interventions are sufficient or more aggressive interventions are needed for a given individual, thereby supporting better, faster, data-driven, and unbiased decisions. The CALERIETM phase 2 study was registered at clinicaltrials.gov as NCT00427193.

Neural decoding and feature selection methods for closed-loop control of avoidance behavior

Objective.Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local field potentials (LFPs) could serve as the foundational technology for closed-loop control of such disorders. A significant challenge is identifying the LFP features that encode these defensive behaviors.Approach.We analyzed LFP signals from the infralimbic cortex and basolateral amygdala of rats undergoing tone-shock conditioning and extinction, standard for investigating defensive behaviors. We utilized a comprehensive set of neuro-markers across spectral, temporal, and connectivity domains, employing SHapley Additive exPlanations for feature importance evaluation within Light Gradient-Boosting Machine models. Our goal was to decode three commonly studied avoidance/defensive behaviors: freezing, bar-press suppression, and motion (accelerometry), examining the impact of different features on decoding performance.Main results.Band power and band power ratio between channels emerged as optimal features across sessions. High-gamma (80-150 Hz) power, power ratios, and inter-regional correlations were more informative than other bands that are more classically linked to defensive behaviors. Focusing on highly informative features enhanced performance. Across 4 recording sessions with 16 subjects, we achieved an average coefficient of determination of 0.5357 and 0.3476, and Pearson correlation coefficients of 0.7579 and 0.6092 for accelerometry jerk and bar press rate, respectively. Utilizing only the most informative features revealed differential encoding between accelerometry and bar press rate, with the former primarily through local spectral power and the latter via inter-regional connectivity. Our methodology demonstrated remarkably low training/inference time and memory usage, requiring<310 ms for training,<0.051 ms for inference, and 16.6 kB of memory, using a single core of AMD Ryzen Threadripper PRO 5995WX CPU.Significance.Our results demonstrate the feasibility of accurately decoding defensive behaviors with minimal latency, using LFP features from neural circuits strongly linked to these behaviors. This methodology holds promise for real-time decoding to identify physiological targets in closed-loop psychiatric neuromodulation.

Exploring the most discriminative brain structural abnormalities in ASD with multi-stage progressive feature refinement approach

Objective

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by increasing prevalence, diverse impairments, and unclear origins and mechanisms. To gain a better grasp of the origins of ASD, it is essential to identify the most distinctive structural brain abnormalities in individuals with ASD.

Methods

A Multi-Stage Progressive Feature Refinement Approach was employed to identify the most pivotal structural magnetic resonance imaging (MRI) features that distinguish individuals with ASD from typically developing (TD) individuals. The study included 175 individuals with ASD and 69 TD individuals, all aged between 7 and 18 years, matched in terms of age and gender. Both cortical and subcortical features were integrated, with a particular focus on hippocampal subfields.

Results

Out of 317 features, 9 had the most significant impact on distinguishing ASD from TD individuals. These structural features, which include a specific hippocampal subfield, are closely related to the brain areas associated with the reward system.

Conclusion

Structural irregularities in the reward system may play a crucial role in the pathophysiology of ASD, and specific hippocampal subfields may also contribute uniquely, warranting further investigation.

Multiclass classification of Autism Spectrum Disorder, attention deficit hyperactivity disorder, and typically developed individuals using fMRI functional connectivity analysis

Neurodevelopmental conditions, such as Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD), present unique challenges due to overlapping symptoms, making an accurate diagnosis and targeted intervention difficult. Our study employs advanced machine learning techniques to analyze functional magnetic resonance imaging (fMRI) data from individuals with ASD, ADHD, and typically developed (TD) controls, totaling 120 subjects in the study. Leveraging multiclass classification (ML) algorithms, we achieve superior accuracy in distinguishing between ASD, ADHD, and TD groups, surpassing existing benchmarks with an area under the ROC curve near 98%. Our analysis reveals distinct neural signatures associated with ASD and ADHD: individuals with ADHD exhibit altered connectivity patterns of regions involved in attention and impulse control, whereas those with ASD show disruptions in brain regions critical for social and cognitive functions. The observed connectivity patterns, on which the ML classification rests, agree with established diagnostic approaches based on clinical symptoms. Furthermore, complex network analyses highlight differences in brain network integration and segregation among the three groups. Our findings pave the way for refined, ML-enhanced diagnostics in accordance with established practices, offering a promising avenue for developing trustworthy clinical decision-support systems.

Bayesian Tensor Modeling for Image-based Classification of Alzheimer's Disease

Tensor-based representations are being increasingly used to represent complex data types such as imaging data, due to their appealing properties such as dimension reduction and the preservation of spatial information. Recently, there is a growing literature on using Bayesian scalar-on-tensor regression techniques that use tensor-based representations for high-dimensional and spatially distributed covariates to predict continuous outcomes. However surprisingly, there is limited development on corresponding Bayesian classification methods relying on tensor-valued covariates. Standard approaches that vectorize the image are not desirable due to the loss of spatial structure, and alternate methods that use extracted features from the image in the predictive model may suffer from information loss. We propose a novel data augmentation-based Bayesian classification approach relying on tensor-valued covariates, with a focus on imaging predictors. We propose two data augmentation schemes, one resulting in a support vector machine (SVM) type of classifier, and another yielding a logistic regression classifier. While both types of classifiers have been proposed independently in literature, our contribution is to extend such existing methodology to accommodate high-dimensional tensor valued predictors that involve low rank decompositions of the coefficient matrix while preserving the spatial information in the image. An efficient Markov chain Monte Carlo (MCMC) algorithm is developed for implementing these methods. Simulation studies show significant improvements in classification accuracy and parameter estimation compared to routinely used classification methods. We further illustrate our method in a neuroimaging application using cortical thickness MRI data from Alzheimer's Disease Neuroimaging Initiative, with results displaying better classification accuracy throughout several classification tasks, including classification on pairs of the three diagnostic groups: normal control, AD patients, and MCI patients; gender classification (males vs females); and cognitive performance based on high and low levels of MMSE scores.

Network-level enrichment provides a framework for biological interpretation of machine learning results

Machine learning algorithms are increasingly being utilized to identify brain connectivity biomarkers linked to behavioral and clinical outcomes. However, research often prioritizes prediction accuracy at the expense of biological interpretability, and inconsistent implementation of ML methods may hinder model accuracy. To address this, our paper introduces a network-level enrichment approach, which integrates brain system organization in the context of connectome-wide statistical analysis to reveal network-level links between brain connectivity and behavior. To demonstrate the efficacy of this approach, we used linear support vector regression (LSVR) models to examine the relationship between resting-state functional connectivity networks and chronological age. We compared network-level associations based on raw LSVR weights to those produced from the forward and inverse models. Results indicated that not accounting for shared family variance inflated prediction performance, the k-best feature selection via Pearson correlation reduced accuracy and reliability, and raw LSVR model weights produced network-level associations that deviated from the significant brain systems identified by forward and inverse models. Our findings offer crucial insights for applying machine learning to neuroimaging data, emphasizing the value of network enrichment for biological interpretation.

Neurodevelopmental subtypes of functional brain organization in the ABCD study using a rigorous analytic framework

The current study demonstrates that an individual's resting-state functional connectivity (RSFC) is a dependable biomarker for identifying differential patterns of cognitive and emotional functioning during late childhood. Using baseline RSFC data from the Adolescent Brain Cognitive Development (ABCD) study, which includes children aged 9-11, we identified four distinct RSFC subtypes. We introduce an integrated methodological pipeline for testing the reliability and importance of these subtypes. In the Identification phase, Leiden Community Detection defined RSFC subtypes, with their reproducibility confirmed through a split-sample technique in the Validation stage. The Evaluation phase showed that distinct cognitive and mental health profiles are associated with each subtype, with the Predictive phase indicating that subtypes better predict various cognitive and mental health characteristics than individual RSFC connections. The Replication stage employed bootstrapping and down-sampling methods to substantiate the reproducibility of these subtypes further. This work allows future explorations of developmental trajectories of these RSFC subtypes.

Individualized multi-modal MRI biomarkers predict 1-year clinical outcome in first-episode drug-naïve schizophrenia patients

Background

Antipsychotic medications offer limited long-term benefit to about 30% of patients with schizophrenia. We aimed to explore the individual-specific imaging markers to predict 1-year treatment response of schizophrenia.

Methods

Structural morphology and functional topological features related to treatment response were identified using an individualized parcellation analysis in conjunction with machine learning (ML). We performed dimensionality reductions using the Pearson correlation coefficient and three feature selection analyses and classifications using 10 ML classifiers. The results were assessed through a 5-fold cross-validation (training and validation cohorts, n = 51) and validated using the external test cohort (n = 17).

Results

ML algorithms based on individual-specific brain network proved more effective than those based on group-level brain network in predicting outcomes. The most predictive features based on individual-specific parcellation involved the GMV of the default network and the degree of the control, limbic, and default networks. The AUCs for the training, validation, and test cohorts were 0.947, 0.939, and 0.883, respectively. Additionally, the prediction performance of the models constructed by the different feature selection methods and classifiers showed no significant differences.

Conclusion

Our study highlighted the potential of individual-specific network parcellation in treatment resistant schizophrenia prediction and underscored the crucial role of feature attributes in predictive model accuracy.

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.

Abnormal structure and function of white matter in obsessive-compulsive disorder

BACKGROUND

Abnormal structure and function of gray matter (GM) have been discovered in the cortico-striatal-thalamic-cortical (CSTC) circuit in obsessive-compulsive disorder (OCD). The GM structure and function may be influenced by the structure and function of the white matter (WM). Therefore, it is crucial to explore the characteristics of WM in OCD.

METHODS

Diffusion tensor imaging and resting-state functional magnetic resonance imaging data of 52 patients with OCD and 39 healthy controls (HCs) were collected. The tract-based spatial statistics, amplitude of low-frequency fluctuations (ALFF), and structural-functional coupling approaches were utilized to explore the WM structure and function. Furthermore, the relationship between the abnormal WM structure and function and clinical symptoms of OCD was investigated using Pearson's correlation. Support vector machine was performed to evaluate whether patients with OCD could be identified with the changed WM structure and function.

RESULTS

Compared to HCs, the lower fractional anisotropy (FA) values of four clusters including the superior corona radiata, anterior corona radiata, right superior longitudinal fasciculus, corpus callosum, left posterior corona radiata, fornix, and the right anterior limb of internal capsule, reduced ALFF/FA ratio in the left anterior thalamic radiation (ATR), and the decreased functional connectivity between the left ATR and the left dorsal lateral prefrontal cortex within CSTC circuit at rest were observed in OCD. The decreased ALFF/FA ratio in the left ATR negatively correlated with Yale-Brown Obsessive-Compulsive Scale obsessive thinking scores and Hamilton Anxiety Rating Scale scores in OCD. Furthermore, the features that combined the abnormal WM structure and function performed best in distinguishing OCD from HCs with the appropriate accuracy (0.80), sensitivity (0.82), as well as specificity (0.80).

CONCLUSION

Current research discovered changed WM structure and function in OCD. Furthermore, abnormal WM structural-functional coupling may lead to aberrant GM connectivity within the CSTC circuit at rest in OCD.

TRIAL REGISTRATION

Study on the mechanism of brain network in obsessive-compulsive disorder with multi-model magnetic resonance imaging (ChiCTR-COC-17013301).

Classifying Unconscious, Psychedelic, and Neuropsychiatric Brain States with Functional Connectivity, Graph Theory, and Cortical Gradient Analysis

Accurate and generalizable classification of brain states is essential for understanding their neural underpinnings and improving clinical diagnostics. Traditionally, functional connectivity patterns and graph-theoretic metrics have been utilized. However, cortical gradient features, which reflect global brain organization, offer a complementary approach. We hypothesized that a machine learning model integrating these three feature sets would effectively discriminate between baseline and atypical brain states across a wide spectrum of conditions, even though the underlying neural mechanisms vary. To test this, we extracted features from brain states associated with three meta-conditions including unconsciousness (NREM2 sleep, propofol deep sedation, and propofol general anesthesia), psychedelic states induced by hallucinogens (subanesthetic ketamine, lysergic acid diethylamide, and nitrous oxide), and neuropsychiatric disorders (attention-deficit hyperactivity disorder, bipolar disorder, and schizophrenia). We used support vector machine with nested cross-validation to construct our models. The soft voting ensemble model marked the average balanced accuracy (average of specificity and sensitivity) of 79% (62-98% across all conditions), outperforming individual base models (70-76%). Notably, our models exhibited varying degrees of transferability across different datasets, with performance being dependent on the specific brain states and feature sets used. Feature importance analysis across meta-conditions suggests that the underlying neural mechanisms vary significantly, necessitating tailored approaches for accurate classification of specific brain states. This finding underscores the value of our feature-integrated ensemble models, which leverage the strengths of multiple feature types to achieve robust performance across a broader range of brain states. While our approach offers valuable insights into the neural signatures of different brain states, future work is needed to develop and validate even more generalizable models that can accurately classify brain states across a wider array of conditions.

Pitfalls in using ML to predict cognitive function performance

Machine learning analyses are widely used for predicting cognitive abilities, yet there are pitfalls that need to be considered during their implementation and interpretation of the results. Hence, the present study aimed at drawing attention to the risks of erroneous conclusions incurred by confounding variables illustrated by a case example predicting executive function performance by prosodic features. Healthy participants (n = 231) performed speech tasks and EF tests. From 264 prosodic features, we predicted EF performance using 66 variables, controlling for confounding effects of age, sex, and education. A reasonable model fit was apparently achieved for EF variables of the Trail Making Test. However, in-depth analyses revealed indications of confound leakage, leading to inflated prediction accuracies, due to a strong relationship between confounds and targets. These findings highlight the need to control confounding variables in ML pipelines and caution against potential pitfalls in ML predictions.

Predicting changes in brain metabolism and progression from mild cognitive impairment to dementia using multitask Deep Learning models and explainable AI

BACKGROUND

The prediction of Alzheimer's disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI).

METHODS

We analyzed data from 1,617 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had undergone at least one FDG-PET scan. We identified the brain regions with the most significant hypometabolism in AD and used Deep Learning (DL) models to predict future changes in brain metabolism. The best-performing model was then adapted under a multi-task learning framework to identify pMCI individuals. Finally, this model underwent further analysis using eXplainable AI (XAI) techniques.

RESULTS

Our results confirm a strong association between hypometabolism, disease progression, and cognitive decline. Furthermore, we demonstrated that integrating data on changes in brain metabolism during training enhanced the models' ability to detect pMCI individuals (sensitivity=88.4%, specificity=86.9%). Lastly, the application of XAI techniques enabled us to delve into the brain regions with the most significant impact on model predictions, highlighting the importance of the hippocampus, cingulate cortex, and some subcortical structures.

CONCLUSION

This study introduces a novel dimension to predictive modeling in AD, emphasizing the importance of projecting variations in brain metabolism under a multi-task learning paradigm.

Machine Learning Techniques to Predict Mental Health Diagnoses: A Systematic Literature Review

Introduction

This study aims to investigate the potential of machine learning in predicting mental health conditions among college students by analyzing existing literature on mental health diagnoses using various machine learning algorithms.

Methods

The research employed a systematic literature review methodology to investigate the application of deep learning techniques in predicting mental health diagnoses among students from 2011 to 2024. The search strategy involved key terms, such as "deep learning," "mental health," and related terms, conducted on reputable repositories like IEEE, Xplore, ScienceDirect, SpringerLink, PLOS, and Elsevier. Papers published between January, 2011, and May, 2024, specifically focusing on deep learning models for mental health diagnoses, were considered. The selection process adhered to PRISMA guidelines and resulted in 30 relevant studies.

Results

The study highlights Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine (SVM), Deep Neural Networks, and Extreme Learning Machine (ELM) as prominent models for predicting mental health conditions. Among these, CNN demonstrated exceptional accuracy compared to other models in diagnosing bipolar disorder. However, challenges persist, including the need for more extensive and diverse datasets, consideration of heterogeneity in mental health condition, and inclusion of longitudinal data to capture temporal dynamics.

Conclusion

This study offers valuable insights into the potential and challenges of machine learning in predicting mental health conditions among college students. While deep learning models like CNN show promise, addressing data limitations and incorporating temporal dynamics are crucial for further advancements.

Toward AI-driven neuroepigenetic imaging biomarker for alcohol use disorder: A proof-of-concept study

Alcohol use disorder (AUD) is a disorder of clinical and public health significance requiring novel and improved therapeutic solutions. Both environmental and genetic factors play a significant role in its pathophysiology. However, the underlying epigenetic molecular mechanisms that link the gene-environment interaction in AUD remain largely unknown. In this proof-of-concept study, we showed, for the first time, the neuroepigenetic biomarker capability of non-invasive imaging of class I histone deacetylase (HDAC) epigenetic enzymes in the in vivo brain for classifying AUD patients from healthy controls using a machine learning approach in the context of precision diagnosis. Eleven AUD patients and 16 age- and sex-matched healthy controls completed a simultaneous positron emission tomography-magnetic resonance (PET/MR) scan with the HDAC-binding radiotracer [11C]Martinostat. Our results showed lower HDAC expression in the anterior cingulate region in AUD. Furthermore, by applying a genetic algorithm feature selection, we identified five particular brain regions whose combined [11C]Martinostat relative standard uptake value (SUVR) features could reliably classify AUD vs. controls. We validate their promising classification reliability using a support vector machine classifier. These findings inform the potential of in vivo HDAC imaging biomarkers coupled with machine learning tools in the objective diagnosis and molecular translation of AUD that could complement the current diagnostic and statistical manual of mental disorders (DSM)-based intervention to propel precision medicine forward.

Diagnosis of mental disorders using machine learning: Literature review and bibliometric mapping from 2012 to 2023

Background

Mental disorders (MDs) are becoming a leading burden in non-communicable diseases (NCDs). As per the World Health Organization's 2022 assessment report, there was a steep increase of 25 % in MDs during the COVID-19 pandemic. Early diagnosis of MDs can significantly improve treatment outcome and save disability-adjusted life years (DALYs). In recent times, the application of machine learning (ML) and deep learning (DL)) has shown promising results in the diagnosis of MDs, and the field has witnessed a huge research output in the form of research publications. Therefore, a bibliometric mapping along with a review of recent advancements is required.

Methods

This study presents a bibliometric analysis and review of the research, published over the last 10 years. Literature searches were conducted in the Scopus database for the period from January 1, 2012, to June 9, 2023. The data was filtered and screened to include only relevant and reliable publications. A total of 2811 journal articles were found. The data was exported to a comma-separated value (CSV) format for further analysis. Furthermore, a review of 40 selected studies was performed.

Results

The popularity of ML techniques in diagnosing MDs has been growing, with an annual research growth rate of 17.05 %. The Journal of Affective Disorders published the most documents (n = 97), while Wang Y. (n = 64) has published the most articles. Lotka's law is observed, with a minority of authors contributing the majority of publications. The top affiliating institutes are the West China Hospital of Sichuan University followed by the University of California, with China and the US dominating the top 10 institutes. While China has more publications, papers affiliated with the US receive more citations. Depression and schizophrenia are the primary focuses of ML and deep learning (DL) in mental disease detection. Co-occurrence network analysis reveals that ML is associated with depression, schizophrenia, autism, anxiety, ADHD, obsessive-compulsive disorder, and PTSD. Popular algorithms include support vector machine (SVM) classifier, decision tree classifier, and random forest classifier. Furthermore, DL is linked to neuroimaging techniques such as MRI, fMRI, and EEG, as well as bipolar disorder. Current research trends encompass DL, LSTM, generalized anxiety disorder, feature fusion, and convolutional neural networks.

Predicting creative behavior using resting-state electroencephalography

Neuroscience research has shown that specific brain patterns can relate to creativity during multiple tasks but also at rest. Nevertheless, the electrophysiological correlates of a highly creative brain remain largely unexplored. This study aims to uncover resting-state networks related to creative behavior using high-density electroencephalography (HD-EEG) and to test whether the strength of functional connectivity within these networks could predict individual creativity in novel subjects. We acquired resting state HD-EEG data from 90 healthy participants who completed a creative behavior inventory. We then employed connectome-based predictive modeling; a machine-learning technique that predicts behavioral measures from brain connectivity features. Using a support vector regression, our results reveal functional connectivity patterns related to high and low creativity, in the gamma frequency band (30-45 Hz). In leave-one-out cross-validation, the combined model of high and low networks predicts individual creativity with very good accuracy (r = 0.36, p = 0.00045). Furthermore, the model's predictive power is established through external validation on an independent dataset (N = 41), showing a statistically significant correlation between observed and predicted creativity scores (r = 0.35, p = 0.02). These findings reveal large-scale networks that could predict creative behavior at rest, providing a crucial foundation for developing HD-EEG-network-based markers of creativity.

Neural Decoding and Feature Selection Techniques for Closed-Loop Control of Defensive Behavior

Objective

Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local field potentials (LFPs) could serve as foundational technology for closed-loop control of such disorders. A significant challenge is identifying the LFP features that encode these defensive behaviors.

Approach

We analyzed LFP signals from the infralimbic cortex and basolateral amygdala of rats undergoing tone-shock conditioning and extinction, standard for investigating defensive behaviors. We utilized a comprehensive set of neuro-markers across spectral, temporal, and connectivity domains, employing SHapley Additive exPlanations for feature importance evaluation within Light Gradient-Boosting Machine models. Our goal was to decode three commonly studied avoidance/defensive behaviors: freezing, bar-press suppression, and motion (accelerometry), examining the impact of different features on decoding performance.

Main results

Band power and band power ratio between channels emerged as optimal features across sessions. High-gamma (80-150 Hz) power, power ratios, and inter-regional correlations were more informative than other bands that are more classically linked to defensive behaviors. Focusing on highly informative features enhanced performance. Across 4 recording sessions with 16 subjects, we achieved an average coefficient of determination of 0.5357 and 0.3476, and Pearson correlation coefficients of 0.7579 and 0.6092 for accelerometry jerk and bar press rate, respectively. Utilizing only the most informative features revealed differential encoding between accelerometry and bar press rate, with the former primarily through local spectral power and the latter via inter-regional connectivity. Our methodology demonstrated remarkably low time complexity, requiring <110 ms for training and <1 ms for inference.

Significance

Our results demonstrate the feasibility of accurately decoding defensive behaviors with minimal latency, using LFP features from neural circuits strongly linked to these behaviors. This methodology holds promise for real-time decoding to identify physiological targets in closed-loop psychiatric neuromodulation.

Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review

Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n = 12), attention deficit and hyperactivity disorder (n = 7), and autism spectrum disorder (n = 6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM = 20) (DL = 10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n = 11) and ΔHbO-based functional connections (n = 11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

Identification of male schizophrenia patients using brain morphology based on machine learning algorithms

BACKGROUND

Schizophrenia is a severe psychiatric disease, and its prevalence is higher. However, diagnosis of early-stage schizophrenia is still considered a challenging task.

AIM

To employ brain morphological features and machine learning method to differentiate male individuals with schizophrenia from healthy controls.

METHODS

The least absolute shrinkage and selection operator and t tests were applied to select important features from structural magnetic resonance images as input features for classification. Four commonly used machine learning algorithms, the general linear model, random forest (RF), k-nearest neighbors, and support vector machine algorithms, were used to develop the classification models. The performance of the classification models was evaluated according to the area under the receiver operating characteristic curve (AUC).

RESULTS

A total of 8 important features with significant differences between groups were considered as input features for the establishment of classification models based on the four machine learning algorithms. Compared to other machine learning algorithms, RF yielded better performance in the discrimination of male schizophrenic individuals from healthy controls, with an AUC of 0.886.

CONCLUSION

Our research suggests that brain morphological features can be used to improve the early diagnosis of schizophrenia in male patients.

Evidence from comprehensive independent validation studies for smooth pursuit dysfunction as a sensorimotor biomarker for psychosis

Smooth pursuit eye movements are considered a well-established and quantifiable biomarker of sensorimotor function in psychosis research. Identifying psychotic syndromes on an individual level based on neurobiological markers is limited by heterogeneity and requires comprehensive external validation to avoid overestimation of prediction models. Here, we studied quantifiable sensorimotor measures derived from smooth pursuit eye movements in a large sample of psychosis probands (N = 674) and healthy controls (N = 305) using multivariate pattern analysis. Balanced accuracies of 64% for the prediction of psychosis status are in line with recent results from other large heterogenous psychiatric samples. They are confirmed by external validation in independent large samples including probands with (1) psychosis (N = 727) versus healthy controls (N = 292), (2) psychotic (N = 49) and non-psychotic bipolar disorder (N = 36), and (3) non-psychotic affective disorders (N = 119) and psychosis (N = 51) yielding accuracies of 65%, 66% and 58%, respectively, albeit slightly different psychosis syndromes. Our findings make a significant contribution to the identification of biologically defined profiles of heterogeneous psychosis syndromes on an individual level underlining the impact of sensorimotor dysfunction in psychosis.

Multivariate brain-behaviour associations in psychiatric disorders

Mapping brain-behaviour associations is paramount to understand and treat psychiatric disorders. Standard approaches involve investigating the association between one brain and one behavioural variable (univariate) or multiple variables against one brain/behaviour feature ('single' multivariate). Recently, large multimodal datasets have propelled a new wave of studies that leverage on 'doubly' multivariate approaches capable of parsing the multifaceted nature of both brain and behaviour simultaneously. Within this movement, canonical correlation analysis (CCA) and partial least squares (PLS) emerge as the most popular techniques. Both seek to capture shared information between brain and behaviour in the form of latent variables. We provide an overview of these methods, review the literature in psychiatric disorders, and discuss the main challenges from a predictive modelling perspective. We identified 39 studies across four diagnostic groups: attention deficit and hyperactive disorder (ADHD, k = 4, N = 569), autism spectrum disorders (ASD, k = 6, N = 1731), major depressive disorder (MDD, k = 5, N = 938), psychosis spectrum disorders (PSD, k = 13, N = 1150) and one transdiagnostic group (TD, k = 11, N = 5731). Most studies (67%) used CCA and focused on the association between either brain morphology, resting-state functional connectivity or fractional anisotropy against symptoms and/or cognition. There were three main findings. First, most diagnoses shared a link between clinical/cognitive symptoms and two brain measures, namely frontal morphology/brain activity and white matter association fibres (tracts between cortical areas in the same hemisphere). Second, typically less investigated behavioural variables in multivariate models such as physical health (e.g., BMI, drug use) and clinical history (e.g., childhood trauma) were identified as important features. Finally, most studies were at risk of bias due to low sample size/feature ratio and/or in-sample testing only. We highlight the importance of carefully mitigating these sources of bias with an exemplar application of CCA.

Large Individual Differences in Functional Connectivity in the Context of Major Depression and Antidepressant Pharmacotherapy

Clinical studies of major depression (MD) generally focus on group effects, yet interindividual differences in brain function are increasingly recognized as important and may even impact effect sizes related to group effects. Here, we examine the magnitude of individual differences in relation to group differences that are commonly investigated (e.g., related to MD diagnosis and treatment response). Functional MRI data from 107 participants (63 female, 44 male) were collected at baseline, 2, and 8 weeks during which patients received pharmacotherapy (escitalopram, N = 68) and controls (N = 39) received no intervention. The unique contributions of different sources of variation were examined by calculating how much variance in functional connectivity was shared across all participants and sessions, within/across groups (patients vs controls, responders vs nonresponders, female vs male participants), recording sessions, and individuals. Individual differences and common connectivity across groups, sessions, and participants contributed most to the explained variance (>95% across analyses). Group differences related to MD diagnosis, treatment response, and biological sex made significant but small contributions (0.3-1.2%). High individual variation was present in cognitive control and attention areas, while low individual variation characterized primary sensorimotor regions. Group differences were much smaller than individual differences in the context of MD and its treatment. These results could be linked to the variable findings and difficulty translating research on MD to clinical practice. Future research should examine brain features with low and high individual variation in relation to psychiatric symptoms and treatment trajectories to explore the clinical relevance of the individual differences identified here.

The power of many brains: Catalyzing neuropsychiatric discovery through open neuroimaging data and large-scale collaboration

Recent advances in open neuroimaging data are enhancing our comprehension of neuropsychiatric disorders. By pooling images from various cohorts, statistical power has increased, enabling the detection of subtle abnormalities and robust associations, and fostering new research methods. Global collaborations in imaging have furthered our knowledge of the neurobiological foundations of brain disorders and aided in imaging-based prediction for more targeted treatment. Large-scale magnetic resonance imaging initiatives are driving innovation in analytics and supporting generalizable psychiatric studies. We also emphasize the significant role of big data in understanding neural mechanisms and in the early identification and precise treatment of neuropsychiatric disorders. However, challenges such as data harmonization across different sites, privacy protection, and effective data sharing must be addressed. With proper governance and open science practices, we conclude with a projection of how large-scale imaging resources and collaborations could revolutionize diagnosis, treatment selection, and outcome prediction, contributing to optimal brain health.