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

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.

Prediction of individual weight loss using supervised learning: Findings from the CALERIE™ 2 study

BACKGROUND

Predicting individual weight loss 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 models to predict individual weight loss responses using only variables known before starting the intervention. In addition, we used machine learning to identify pre-intervention variables influencing the individual weight loss response.

METHODS

We used 12-month data from the Comprehensive Assessment of Long-term Effects of Reducing Intake of Energy (CALERIE™) phase 2 study, which aimed to analyze the long-term effects of caloric restriction on human longevity. Based on data from 130 subjects in the intervention group, we developed classification models to predict binary ("Success" and "No/low success") or multi-class ("High success," "Medium success," and "Low/no success") weight loss outcomes. Additionally, regression models were developed to predict individual weight change (percent). Models were evaluated based on accuracy, sensitivity, specificity (classification models), and root mean squared error (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 multi-class classification, accuracy (69%) and sensitivity (50%) tended to be lower. The best regression performance was obtained with 36 variables with a root mean squared error of 2.84%. Among the 21 variables predicting individual weight change most consistently, we identified two novel predictors, namely orgasm satisfaction and sexual behavior/experience. Other common predictors have previously been associated with weight loss (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.

TRIAL REGISTRATION

The CALERIE™ phase 2 study was registered at clinicaltrials.gov as NCT00427193.

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.

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).

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.

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.

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.

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.

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.

Constructing personalized characterizations of structural brain aberrations in patients with dementia using explainable artificial intelligence

Deep learning approaches for clinical predictions based on magnetic resonance imaging data have shown great promise as a translational technology for diagnosis and prognosis in neurological disorders, but its clinical impact has been limited. This is partially attributed to the opaqueness of deep learning models, causing insufficient understanding of what underlies their decisions. To overcome this, we trained convolutional neural networks on structural brain scans to differentiate dementia patients from healthy controls, and applied layerwise relevance propagation to procure individual-level explanations of the model predictions. Through extensive validations we demonstrate that deviations recognized by the model corroborate existing knowledge of structural brain aberrations in dementia. By employing the explainable dementia classifier in a longitudinal dataset of patients with mild cognitive impairment, we show that the spatially rich explanations complement the model prediction when forecasting transition to dementia and help characterize the biological manifestation of disease in the individual brain. Overall, our work exemplifies the clinical potential of explainable artificial intelligence in precision medicine.

Characterizing cognitive subtypes in schizophrenia using cortical curvature

Cognitive deficits are a core symptom of schizophrenia, but research on their neural underpinnings has been challenged by the heterogeneity in deficits' severity among patients. Here, we address this issue by combining logistic regression and random forest to classify two neuropsychological profiles of patients with high (HighCog) and low (LowCog) cognitive performance in two independent samples. We based our analysis on the cortical features grey matter volume (VOL), cortical thickness (CT), and mean curvature (MC) of N = 57 patients (discovery sample) and validated the classification in an independent sample (N = 52). We investigated which cortical feature would yield the best classification results and expected that the 10 most important features would include frontal and temporal brain regions. The model based on MC had the best performance with area under the curve (AUC) values of 76% and 73%, and identified fronto-temporal and occipital brain regions as the most important features for the classification. Moreover, subsequent comparison analyses could reveal significant differences in MC of single brain regions between the two cognitive profiles. The present study suggests MC as a promising neuroanatomical parameter for characterizing schizophrenia cognitive subtypes.

The use of automated and AI-driven algorithms for the detection of hippocampal sclerosis and focal cortical dysplasia

In drug-resistant epilepsy, magnetic resonance imaging (MRI) plays a central role in detecting lesions as it offers unmatched spatial resolution and whole-brain coverage. In addition, the last decade has witnessed continued developments in MRI-based computer-aided machine-learning techniques for improved diagnosis and prognosis. In this review, we focus on automated algorithms for the detection of hippocampal sclerosis and focal cortical dysplasia, particularly in cases deemed as MRI negative, with an emphasis on studies with histologically validated data. In addition, we discuss imaging-derived prognostic markers, including response to anti-seizure medication, post-surgical seizure outcome, and cognitive reserves. We also highlight the advantages and limitations of these approaches and discuss future directions toward person-centered care.

Can the neural representation of physical pain predict empathy for pain in others?

The question of whether physical pain and vicarious pain have some shared neural substrates is unresolved. Recent research has argued that physical and vicarious pain are represented by dissociable multivariate brain patterns by creating biomarkers for physical pain (Neurologic Pain Signature, NPS) and vicarious pain (Vicarious Pain Signature, VPS), respectively. In the current research, the NPS and two versions of the VPS were applied to three fMRI datasets (one new, two published) relating to vicarious pain which focused on between-subject differences in vicarious pain (Datasets 1 and 3) and within-subject manipulations of perspective taking (Dataset 2). Results show that (i) NPS can distinguish brain responses to images of pain vs no-pain and to a greater extent in vicarious pain responders who report experiencing pain when observing pain and (ii) neither version of the VPS mapped on to individual differences in vicarious pain and the two versions differed in their success in predicting vicarious pain overall. This study suggests that the NPS (created to detect physical pain) is, under some circumstances, sensitive to vicarious pain and there is significant variability in VPS measures (created to detect vicarious pain) to act as generalizable biomarkers of vicarious pain.

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.

Few-Shot Domain-Adaptive Anomaly Detection for Cross-Site Brain Images

Early screening is essential for effective intervention and treatment of individuals with mental disorders. Functional magnetic resonance imaging (fMRI) is a noninvasive tool for depicting neural activity and has demonstrated strong potential as a technique for identifying mental disorders. Due to the difficulty in data collection and diagnosis, imaging data from patients are rare at a single site, whereas abundant healthy control data are available from public datasets. However, joint use of these data from multiple sites for classification model training is hindered by cross-domain distribution discrepancy and diverse label spaces. Herein, we propose few-shot domain-adaptive anomaly detection (FAAD) to achieve cross-site anomaly detection of brain images based on only a few labeled samples. We introduce domain adaptation to mitigate cross-domain distribution discrepancy and jointly align the general and conditional feature distributions of imaging data across multiple sites. We utilize fMRI data of healthy subjects in the Human Connectome Project (HCP) as the source domain and fMRI images from six independent sites, including patients with mental disorders and demographically matched healthy controls, as target domains. Experiments showed the superiority of the proposed method compared with binary classification, traditional anomaly detection methods, and several recognized domain adaptation methods.

Unveiling the potential of machine learning in schizophrenia diagnosis: A meta-analytic study of task-based neuroimaging data

The emergence of machine learning (ML) techniques has opened up new avenues for identifying biomarkers associated with schizophrenia (SCZ) using task-related fMRI (t-fMRI) designs. To evaluate the effectiveness of this approach, we conducted a comprehensive meta-analysis of 31 t-fMRI studies using a bivariate model. Our findings revealed a high overall sensitivity of 0.83 and specificity of 0.82 for t-fMRI studies. Notably, neuropsychological domains modulated the classification performance, with selective attention demonstrating a significantly higher specificity than working memory (β = 0.98, z = 2.11, P = 0.04). Studies involving older, chronic patients with SCZ reported higher sensitivity (P <0.015) and specificity (P <0.001) than those involving younger, first-episode patients or high-risk individuals for psychosis. Additionally, we found that the severity of negative symptoms was positively associated with the specificity of the classification model (β = 7.19, z = 2.20, P = 0.03). Taken together, these results support the potential of using task-based fMRI data in combination with machine learning techniques to identify biomarkers related to symptom outcomes in SCZ, providing a promising avenue for improving diagnostic accuracy and treatment efficacy. Future attempts to deploy ML classification should consider the factors of algorithm choice, data quality and quantity, as well as issues related to generalization.

A Method to Estimate Longitudinal Change Patterns in Functional Network Connectivity of the Developing Brain Relevant to Psychiatric Problems, Cognition, and Age

Aim: To develop an approach to evaluate multiple overlapping brain functional change patterns (FCPs) in functional network connectivity (FNC) and apply to study developmental changes in brain function. Introduction: FNC, the network analog of functional connectivity (FC), is commonly used to capture the intrinsic functional relationships among brain networks. Ongoing research on longitudinal changes of intrinsic FC across whole-brain functional networks has proven useful for characterizing age-related changes, but to date, there has been little focus on capturing multivariate patterns of FNC change with brain development. Methods: In this article, we introduce a novel approach to evaluate multiple overlapping FCPs by utilizing FNC matrices. We computed FNC matrices from the large-scale Adolescent Brain Cognitive Development data using fully automated spatially constrained independent component analysis (ICA). We next evaluated changes in these patterns for a 2-year period using a second-level ICA on the FNC change maps. Results: Our proposed approach reveals several highly structured (modular) FCPs and significant results including strong brain FC between visual and sensorimotor domains that increase with age. We also find several FCPs that are associated with longitudinal changes of psychiatric problems, cognition, and age in the developing brain. Interestingly, FCP cross-covariation, reflecting coupling between maximally independent FCPs, also shows significant differences between upper and lower quartile loadings for longitudinal changes in age, psychiatric problems, and cognition scores, as well as baseline age in the developing brain. FCP patterns and results were also found to be highly reliable based on analysis of data collected in a separate scan session. Conclusion: In sum, our results show evidence of consistent multivariate patterns of functional change in emerging adolescents and the proposed approach provides a useful and general tool to evaluate covarying patterns of whole-brain functional changes in longitudinal data. Impact statement In this article, we introduce a novel approach utilizing functional network connectivity (FNC) matrices to estimate multiple overlapping brain functional change patterns (FCPs). The findings demonstrate several well-structured FCPs that exhibit significant changes for a 2-year period, particularly in the functional connectivity between the visual and sensorimotor domains. In addition, we discover several FCPs that are associated with psychopathology, cognition, and age. Finally, our proposed approach for studying age-related FCPs represents a pioneering method that provides a valuable tool for assessing interconnected patterns of whole-brain functional changes in longitudinal data and may be useful to study change over time with applicability to many other areas, including the study of longitudinal changes within diagnostic groups, treatment effects, aging effects, and more.

Automated diagnosis of autism with artificial intelligence: State of the art

Autism spectrum disorder (ASD) represents a panel of conditions that begin during the developmental period and result in impairments of personal, social, academic, or occupational functioning. Early diagnosis is directly related to a better prognosis. Unfortunately, the diagnosis of ASD requires a long and exhausting subjective process. We aimed to review the state of the art for automated autism diagnosis and recognition in this research. In February 2022, we searched multiple databases and sources of gray literature for eligible studies. We used an adapted version of the QUADAS-2 tool to assess the risk of bias in the studies. A brief report of the methods and results of each study is presented. Data were synthesized for each modality separately using the Split Component Synthesis (SCS) method. We assessed heterogeneity using the I 2 statistics and evaluated publication bias using trim and fill tests combined with ln DOR. Confidence in cumulative evidence was assessed using the GRADE approach for diagnostic studies. We included 344 studies from 186,020 participants (51,129 are estimated to be unique) for nine different modalities in this review, from which 232 reported sufficient data for meta-analysis. The area under the curve was in the range of 0.71-0.90 for all the modalities. The studies on EEG data provided the best accuracy, with the area under the curve ranging between 0.85 and 0.93. We found that the literature is rife with bias and methodological/reporting flaws. Recommendations are provided for future research to provide better studies and fill in the current knowledge gaps.

MRI economics: Balancing sample size and scan duration in brain wide association studies

A pervasive dilemma in neuroimaging is whether to prioritize sample size or scan duration given fixed resources. Here, we systematically investigate this trade-off in the context of brain-wide association studies (BWAS) using resting-state functional magnetic resonance imaging (fMRI). We find that total scan duration (sample size × scan duration per participant) robustly explains individual-level phenotypic prediction accuracy via a logarithmic model, suggesting that sample size and scan duration are broadly interchangeable. The returns of scan duration eventually diminish relative to sample size, which we explain with principled theoretical derivations. When accounting for fixed costs associated with each participant (e.g., recruitment, non-imaging measures), we find that prediction accuracy in small-scale BWAS might benefit from much longer scan durations (>50 min) than typically assumed. Most existing large-scale studies might also have benefited from smaller sample sizes with longer scan durations. Both logarithmic and theoretical models of the relationships among sample size, scan duration and prediction accuracy explain well-predicted phenotypes better than poorly-predicted phenotypes. The logarithmic and theoretical models are also undermined by individual differences in brain states. These results replicate across phenotypic domains (e.g., cognition and mental health) from two large-scale datasets with different algorithms and metrics. Overall, our study emphasizes the importance of scan time, which is ignored in standard power calculations. Standard power calculations inevitably maximize sample size at the expense of scan duration. The resulting prediction accuracies are likely lower than would be produced with alternate designs, thus impeding scientific discovery. Our empirically informed reference is available for future study design: WEB_APPLICATION_LINK.

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.

Functional magnetic resonance imaging in schizophrenia: current evidence, methodological advances, limitations and future directions

Functional neuroimaging emerged with great promise and has provided fundamental insights into the neurobiology of schizophrenia. However, it has faced challenges and criticisms, most notably a lack of clinical translation. This paper provides a comprehensive review and critical summary of the literature on functional neuroimaging, in particular functional magnetic resonance imaging (fMRI), in schizophrenia. We begin by reviewing research on fMRI biomarkers in schizophrenia and the clinical high risk phase through a historical lens, moving from case-control regional brain activation to global connectivity and advanced analytical approaches, and more recent machine learning algorithms to identify predictive neuroimaging features. Findings from fMRI studies of negative symptoms as well as of neurocognitive and social cognitive deficits are then reviewed. Functional neural markers of these symptoms and deficits may represent promising treatment targets in schizophrenia. Next, we summarize fMRI research related to antipsychotic medication, psychotherapy and psychosocial interventions, and neurostimulation, including treatment response and resistance, therapeutic mechanisms, and treatment targeting. We also review the utility of fMRI and data-driven approaches to dissect the heterogeneity of schizophrenia, moving beyond case-control comparisons, as well as methodological considerations and advances, including consortia and precision fMRI. Lastly, limitations and future directions of research in the field are discussed. Our comprehensive review suggests that, in order for fMRI to be clinically useful in the care of patients with schizophrenia, research should address potentially actionable clinical decisions that are routine in schizophrenia treatment, such as which antipsychotic should be prescribed or whether a given patient is likely to have persistent functional impairment. The potential clinical utility of fMRI is influenced by and must be weighed against cost and accessibility factors. Future evaluations of the utility of fMRI in prognostic and treatment response studies may consider including a health economics analysis.

A joint parcellation and boundary network with multi-rate-shared dilated graph attention for cortical surface parcellation

Cortical surface parcellation aims to segment the surface into anatomically and functionally significant regions, which are crucial for diagnosing and treating numerous neurological diseases. However, existing methods generally ignore the difficulty in learning labeling patterns of boundaries, hindering the performance of parcellation. To this end, this paper proposes a joint parcellation and boundary network (JPBNet) to promote the effectiveness of cortical surface parcellation. Its core is developing a multi-rate-shared dilated graph attention (MDGA) module and incorporating boundary learning into the parcellation process. The former, in particular, constructs a dilated graph attention strategy, extending the dilated convolution from regular data to irregular graph data. We fuse it with different dilated rates to extract context information in various scales by devising a shared graph attention layer. After that, a boundary enhancement module and a parcellation enhancement module based on graph attention mechanisms are built in each layer, forcing MDGA to capture informative and valuable features for boundary detection and parcellation tasks. Integrating MDGA, the boundary enhancement module, and the parcellation enhancement module at each layer to supervise boundary and parcellation information, an effective JPBNet is formed by stacking multiple layers. Experiments on the public dataset reveal that the proposed method outperforms comparison methods and performs well on boundaries for cortical surface parcellation.

Phototherapy for age-related brain diseases: Challenges, successes and future

Brain diseases present a significant obstacle to both global health and economic progress, owing to their elusive pathogenesis and the limited effectiveness of pharmaceutical interventions. Phototherapy has emerged as a promising non-invasive therapeutic modality for addressing age-related brain disorders, including stroke, Alzheimer's disease (AD), and Parkinson's disease (PD), among others. This review examines the recent progressions in phototherapeutic interventions. Firstly, the article elucidates the various wavelengths of visible light that possess the capability to penetrate the skin and skull, as well as the pathways of light stimulation, encompassing the eyes, skin, veins, and skull. Secondly, it deliberates on the molecular mechanisms of visible light on photosensitive proteins, within the context of brain disorders and other molecular pathways of light modulation. Lastly, the practical application of phototherapy in diverse clinical neurological disorders is indicated. Additionally, this review presents novel approaches that combine phototherapy and pharmacological interventions. Moreover, it outlines the limitations of phototherapeutics and proposes innovative strategies to improve the treatment of cerebral disorders.

Sex differences in brain-behavior relationships in the first two years of life

Background

Evidence for sex differences in cognition in childhood is established, but less is known about the underlying neural mechanisms for these differences. Recent findings suggest the existence of brain-behavior relationship heterogeneities during infancy; however, it remains unclear whether sex underlies these heterogeneities during this critical period when sex-related behavioral differences arise.

Methods

A sample of 316 infants was included with resting-state functional magnetic resonance imaging scans at neonate (3 weeks), 1, and 2 years of age. We used multiple linear regression to test interactions between sex and resting-state functional connectivity on behavioral scores of working memory, inhibitory self-control, intelligence, and anxiety collected at 4 years of age.

Results

We found six age-specific, intra-hemispheric connections showing significant and robust sex differences in functional connectivity-behavior relationships. All connections are either with the prefrontal cortex or the temporal pole, which has direct anatomical pathways to the prefrontal cortex. Sex differences in functional connectivity only emerge when associated with behavior, and not in functional connectivity alone. Furthermore, at neonate and 2 years of age, these age-specific connections displayed greater connectivity in males and lower connectivity in females in association with better behavioral scores.

Conclusions

Taken together, we critically capture robust and conserved brain mechanisms that are distinct to sex and are defined by their relationship to behavioral outcomes. Our results establish brain-behavior mechanisms as an important feature in the search for sex differences during development.

Prediction of cognitive performance differences in older age from multimodal neuroimaging data

Differences in brain structure and functional and structural network architecture have been found to partly explain cognitive performance differences in older ages. Thus, they may serve as potential markers for these differences. Initial unimodal studies, however, have reported mixed prediction results of selective cognitive variables based on these brain features using machine learning (ML). Thus, the aim of the current study was to investigate the general validity of cognitive performance prediction from imaging data in healthy older adults. In particular, the focus was with examining whether (1) multimodal information, i.e., region-wise grey matter volume (GMV), resting-state functional connectivity (RSFC), and structural connectivity (SC) estimates, may improve predictability of cognitive targets, (2) predictability differences arise for global cognition and distinct cognitive profiles, and (3) results generalize across different ML approaches in 594 healthy older adults (age range: 55-85 years) from the 1000BRAINS study. Prediction potential was examined for each modality and all multimodal combinations, with and without confound (i.e., age, education, and sex) regression across different analytic options, i.e., variations in algorithms, feature sets, and multimodal approaches (i.e., concatenation vs. stacking). Results showed that prediction performance differed considerably between deconfounding strategies. In the absence of demographic confounder control, successful prediction of cognitive performance could be observed across analytic choices. Combination of different modalities tended to marginally improve predictability of cognitive performance compared to single modalities. Importantly, all previously described effects vanished in the strict confounder control condition. Despite a small trend for a multimodal benefit, developing a biomarker for cognitive aging remains challenging.

Cortical atrophy in early-stage patients with anti-NMDA receptor encephalitis: a machine-learning MRI study with various feature extraction

Conventional brain magnetic resonance imaging (MRI) of anti-N-methyl-D-aspartate-receptor encephalitis (NMDARE) is non-specific, thus showing little differential diagnostic value, especially for MRI-negative patients. To characterize patterns of structural alterations and facilitate the diagnosis of MRI-negative NMDARE patients, we build two support vector machine models (NMDARE versus healthy controls [HC] model and NMDARE versus viral encephalitis [VE] model) based on radiomics features extracted from brain MRI. A total of 109 MRI-negative NMDARE patients in the acute phase, 108 HCs and 84 acute MRI-negative VE cases were included for training. Another 29 NMDARE patients, 28 HCs and 26 VE cases were included for validation. Eighty features discriminated NMDARE patients from HCs, with area under the receiver operating characteristic curve (AUC) of 0.963 in validation set. NMDARE patients presented with significantly lower thickness, area, and volume and higher mean curvature than HCs. Potential atrophy predominately presented in the frontal lobe (cumulative weight = 4.3725, contribution rate of 29.86%), and temporal lobe (cumulative weight = 2.573, contribution rate of 17.57%). The NMDARE versus VE model achieved certain diagnostic power, with AUC of 0.879 in validation set. Our research shows potential atrophy across the entire cerebral cortex in acute NMDARE patients, and MRI machine learning model has a potential to facilitate the diagnosis MRI-negative NMDARE.

Performance reserves in brain-imaging-based phenotype prediction

This study examines the impact of sample size on predicting cognitive and mental health phenotypes from brain imaging via machine learning. Our analysis shows a 3- to 9-fold improvement in prediction performance when sample size increases from 1,000 to 1 M participants. However, despite this increase, the data suggest that prediction accuracy remains worryingly low and far from fully exploiting the predictive potential of brain imaging data. Additionally, we find that integrating multiple imaging modalities boosts prediction accuracy, often equivalent to doubling the sample size. Interestingly, the most informative imaging modality often varied with increasing sample size, emphasizing the need to consider multiple modalities. Despite significant performance reserves for phenotype prediction, achieving substantial improvements may necessitate prohibitively large sample sizes, thus casting doubt on the practical or clinical utility of machine learning in some areas of neuroimaging.

Scaling behaviours of deep learning and linear algorithms for the prediction of stroke severity

Deep learning has allowed for remarkable progress in many medical scenarios. Deep learning prediction models often require 105-107 examples. It is currently unknown whether deep learning can also enhance predictions of symptoms post-stroke in real-world samples of stroke patients that are often several magnitudes smaller. Such stroke outcome predictions however could be particularly instrumental in guiding acute clinical and rehabilitation care decisions. We here compared the capacities of classically used linear and novel deep learning algorithms in their prediction of stroke severity. Our analyses relied on a total of 1430 patients assembled from the MRI-Genetics Interface Exploration collaboration and a Massachusetts General Hospital-based study. The outcome of interest was National Institutes of Health Stroke Scale-based stroke severity in the acute phase after ischaemic stroke onset, which we predict by means of MRI-derived lesion location. We automatically derived lesion segmentations from diffusion-weighted clinical MRI scans, performed spatial normalization and included a principal component analysis step, retaining 95% of the variance of the original data. We then repeatedly separated a train, validation and test set to investigate the effects of sample size; we subsampled the train set to 100, 300 and 900 and trained the algorithms to predict the stroke severity score for each sample size with regularized linear regression and an eight-layered neural network. We selected hyperparameters on the validation set. We evaluated model performance based on the explained variance (R2) in the test set. While linear regression performed significantly better for a sample size of 100 patients, deep learning started to significantly outperform linear regression when trained on 900 patients. Average prediction performance improved by ∼20% when increasing the sample size 9× [maximum for 100 patients: 0.279 ± 0.005 (R2, 95% confidence interval), 900 patients: 0.337 ± 0.006]. In summary, for sample sizes of 900 patients, deep learning showed a higher prediction performance than typically employed linear methods. These findings suggest the existence of non-linear relationships between lesion location and stroke severity that can be utilized for an improved prediction performance for larger sample sizes.

Gene-SGAN: discovering disease subtypes with imaging and genetic signatures via multi-view weakly-supervised deep clustering

Disease heterogeneity has been a critical challenge for precision diagnosis and treatment, especially in neurologic and neuropsychiatric diseases. Many diseases can display multiple distinct brain phenotypes across individuals, potentially reflecting disease subtypes that can be captured using MRI and machine learning methods. However, biological interpretability and treatment relevance are limited if the derived subtypes are not associated with genetic drivers or susceptibility factors. Herein, we describe Gene-SGAN - a multi-view, weakly-supervised deep clustering method - which dissects disease heterogeneity by jointly considering phenotypic and genetic data, thereby conferring genetic correlations to the disease subtypes and associated endophenotypic signatures. We first validate the generalizability, interpretability, and robustness of Gene-SGAN in semi-synthetic experiments. We then demonstrate its application to real multi-site datasets from 28,858 individuals, deriving subtypes of Alzheimer's disease and brain endophenotypes associated with hypertension, from MRI and single nucleotide polymorphism data. Derived brain phenotypes displayed significant differences in neuroanatomical patterns, genetic determinants, biological and clinical biomarkers, indicating potentially distinct underlying neuropathologic processes, genetic drivers, and susceptibility factors. Overall, Gene-SGAN is broadly applicable to disease subtyping and endophenotype discovery, and is herein tested on disease-related, genetically-associated neuroimaging phenotypes.

Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching

Individualized phenotypic prediction based on structural MRI is an important goal in neuroscience. Prediction performance increases with larger samples, but small-scale datasets with fewer than 200 participants are often unavoidable. We have previously proposed a "meta-matching" framework to translate models trained from large datasets to improve the prediction of new unseen phenotypes in small collection efforts. Meta-matching exploits correlations between phenotypes, yielding large improvement over classical machine learning when applied to prediction models using resting-state functional connectivity as input features. Here, we adapt the two best performing meta-matching variants ("meta-matching finetune" and "meta-matching stacking") from our previous study to work with T1-weighted MRI data by changing the base neural network architecture to a 3D convolution neural network. We compare the two meta-matching variants with elastic net and classical transfer learning using the UK Biobank (N = 36,461), Human Connectome Project Young Adults (HCP-YA) dataset (N = 1,017) and HCP-Aging dataset (N = 656). We find that meta-matching outperforms elastic net and classical transfer learning by a large margin, both when translating models within the same dataset, as well as translating models across datasets with different MRI scanners, acquisition protocols and demographics. For example, when translating a UK Biobank model to 100 HCP-YA participants, meta-matching finetune yielded a 136% improvement in variance explained over transfer learning, with an average absolute gain of 2.6% (minimum = -0.9%, maximum = 17.6%) across 35 phenotypes. Overall, our results highlight the versatility of the meta-matching framework.

Brain Disorder Detection and Diagnosis using Machine Learning and Deep Learning - A Bibliometric Analysis

BACKGROUND AND OBJECTIVE

Brain disorders are one of the major global mortality issues, and their early detection is crucial for healing. Machine learning, specifically deep learning, is a technology that is increasingly being used to detect and diagnose brain disorders. Our objective is to provide a quantitative bibliometric analysis of the field to inform researchers about trends that can inform their Research directions in the future.

METHODS

We carried out a bibliometric analysis to create an overview of brain disorder detection and diagnosis using machine learning and deep learning. Our bibliometric analysis includes 1550 articles gathered from the Scopus database on automated brain disorder detection and diagnosis using machine learning and deep learning published from 2015 to May 2023. A thorough bibliometric análisis is carried out with the help of Biblioshiny and the VOSviewer platform. Citation analysis and various measures of collaboration are analyzed in the study.

RESULTS

According to a study, maximum research is reported in 2022, with a consistent rise from preceding years. The majority of the authors referenced have concentrated on multiclass classification and innovative convolutional neural network models that are effective in this field. A keyword analysis revealed that among the several brain disorder types, Alzheimer's, autism, and Parkinson's disease had received the greatest attention. In terms of both authors and institutes, the USA, China, and India are among the most collaborating countries. We built a future research agenda based on our findings to help progress research on machine learning and deep learning for brain disorder detection and diagnosis.

CONCLUSION

In summary, our quantitative bibliometric analysis provides useful insights about trends in the field and points them to potential directions in applying machine learning and deep learning for brain disorder detection and diagnosis.

.

Neural networks from biological to artificial and vice versa

In this paper, we examine how deep learning can be utilized to investigate neural health and the difficulties in interpreting neurological analyses within algorithmic models. The key contribution of this paper is the investigation of the impact of a dead neuron on the performance of artificial neural networks (ANNs). Therefore, we conduct several tests using different training algorithms and activation functions to identify the precise influence of the training process on neighboring neurons and the overall performance of the ANN in such cases. The aim is to assess the potential application of the findings in the biological domain, the expected results may have significant implications for the development of effective treatment strategies for neurological disorders. Successive training phases that incorporate visual and acoustic data derived from past social and familial experiences could be suggested to achieve this goal. Finally, we explore the conceptual analogy between the Adam optimizer and the learning process of the brain by delving into the specifics of both systems while acknowledging their fundamental differences.

Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer's disease: Inter-cohort validation of Shanghai Memory Study and ADNI

Mild cognitive impairment (MCI) is a critical prodromal stage of Alzheimer's disease (AD), and the mechanism underlying the conversion is not fully explored. Construction and inter-cohort validation of imaging biomarkers for predicting MCI conversion is of great challenge at present, due to lack of longitudinal cohorts and poor reproducibility of various study-specific imaging indices. We proposed a novel framework for inter-cohort MCI conversion prediction, involving comparison of structural, static, and dynamic functional brain features from structural magnetic resonance imaging (sMRI) and resting-state functional MRI (fMRI) between MCI converters (MCI_C) and non-converters (MCI_NC), and support vector machine for construction of prediction models. A total of 218 MCI patients with 3-year follow-up outcome were selected from two independent cohorts: Shanghai Memory Study cohort for internal cross-validation, and Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort for external validation. In comparison with MCI_NC, MCI_C were mainly characterized by atrophy, regional hyperactivity and inter-network hypo-connectivity, and dynamic alterations characterized by regional and connectional instability, involving medial temporal lobe (MTL), posterior parietal cortex (PPC), and occipital cortex. All imaging-based prediction models achieved an area under the curve (AUC) > 0.7 in both cohorts, with the multi-modality MRI models as the best with excellent performances of AUC > 0.85. Notably, the combination of static and dynamic fMRI resulted in overall better performance as relative to static or dynamic fMRI solely, supporting the contribution of dynamic features. This inter-cohort validation study provides a new insight into the mechanisms of MCI conversion involving brain dynamics, and paves a way for clinical use of structural and functional MRI biomarkers in future.

CERAD-NAB and flexible battery based neuropsychological differentiation of Alzheimer's dementia and depression using machine learning approaches

Depression (DEP) and dementia of the Alzheimer's type (DAT) represent the most common neuropsychiatric disorders in elderly patients. Accurate differential diagnosis is indispensable to ensure appropriate treatment. However, DEP can yet mimic cognitive symptoms of DAT and patients with DAT often also present with depressive symptoms, impeding correct diagnosis. Machine learning (ML) approaches could eventually improve this discrimination using neuropsychological test data, but evidence is still missing. We therefore employed Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF) and conventional Logistic Regression (LR) to retrospectively predict the diagnoses of 189 elderly patients (68 DEP and 121 DAT) based on either the well-established Consortium to Establish a Registry for Alzheimer's Disease neuropsychological assessment battery (CERAD-NAB) or a flexible battery approach (FLEXBAT). The best performing combination consisted of FLEXBAT and NB, correctly classifying 87.0% of patients as either DAT or DEP. However, all accuracies were similar across algorithms and test batteries (83.0% - 87.0%). Accordingly, our study is the first to show that common ML algorithms with their default parameters can accurately differentiate between patients clinically diagnosed with DAT or DEP using neuropsychological test data, but do not necessarily outperform conventional LR.

Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method for MDD discrimination with rsfMRI

Major depressive disorder (MDD) is a serious and heterogeneous psychiatric disorder that needs accurate diagnosis. Resting-state functional MRI (rsfMRI), which captures multiple perspectives on brain structure, function, and connectivity, is increasingly applied in the diagnosis and pathological research of MDD. Different machine learning algorithms are then developed to exploit the rich information in rsfMRI and discriminate MDD patients from normal controls. Despite recent advances reported, the MDD discrimination accuracy has room for further improvement. The generalizability and interpretability of the discrimination method are not sufficiently addressed either. Here, we propose a machine learning method (MFMC) for MDD discrimination by concatenating multiple features and stacking multiple classifiers. MFMC is tested on the REST-meta-MDD data set that contains 2428 subjects collected from 25 different sites. MFMC yields 96.9% MDD discrimination accuracy, demonstrating a significant improvement over existing methods. In addition, the generalizability of MFMC is validated by the good performance when the training and testing subjects are from independent sites. The use of XGBoost as the meta classifier allows us to probe the decision process of MFMC. We identify 13 feature values related to 9 brain regions including the posterior cingulate gyrus, superior frontal gyrus orbital part, and angular gyrus, which contribute most to the classification and also demonstrate significant differences at the group level. The use of these 13 feature values alone can reach 87% of MFMC's full performance when taking all feature values. These features may serve as clinically useful diagnostic and prognostic biomarkers for MDD in the future.

Comparison of the diagnostic accuracy of resting-state fMRI driven machine learning algorithms in the detection of mild cognitive impairment

Mild cognitive impairment (MCI) is a potential therapeutic window in the prevention of dementia; however, automated detection of early cognitive deterioration is an unresolved issue. The aim of our study was to compare various classification approaches to differentiate MCI patients from healthy controls, based on rs-fMRI data, using machine learning (ML) algorithms. Own dataset (from two centers) and ADNI database were used during the analysis. Three fMRI parameters were applied in five feature selection algorithms: local correlation, intrinsic connectivity, and fractional amplitude of low frequency fluctuations. Support vector machine (SVM) and random forest (RF) methods were applied for classification. We achieved a relatively wide range of 78-87% accuracy for the various feature selection methods with SVM combining the three rs-fMRI parameters. In the ADNI datasets case we can also see even 90% accuracy scores. RF provided a more harmonized result among the feature selection algorithms in both datasets with 80-84% accuracy for our local and 74-82% for the ADNI database. Despite some lower performance metrics of some algorithms, most of the results were positive and could be seen in two unrelated datasets which increase the validity of our methods. Our results highlight the potential of ML-based fMRI applications for automated diagnostic techniques to recognize MCI patients.

Multilayer meta-matching: translating phenotypic prediction models from multiple datasets to small data

Resting-state functional connectivity (RSFC) is widely used to predict phenotypic traits in individuals. Large sample sizes can significantly improve prediction accuracies. However, for studies of certain clinical populations or focused neuroscience inquiries, small-scale datasets often remain a necessity. We have previously proposed a "meta-matching" approach to translate prediction models from large datasets to predict new phenotypes in small datasets. We demonstrated large improvement of meta-matching over classical kernel ridge regression (KRR) when translating models from a single source dataset (UK Biobank) to the Human Connectome Project Young Adults (HCP-YA) dataset. In the current study, we propose two meta-matching variants ("meta-matching with dataset stacking" and "multilayer meta-matching") to translate models from multiple source datasets across disparate sample sizes to predict new phenotypes in small target datasets. We evaluate both approaches by translating models trained from five source datasets (with sample sizes ranging from 862 participants to 36,834 participants) to predict phenotypes in the HCP-YA and HCP-Aging datasets. We find that multilayer meta-matching modestly outperforms meta-matching with dataset stacking. Both meta-matching variants perform better than the original "meta-matching with stacking" approach trained only on the UK Biobank. All meta-matching variants outperform classical KRR and transfer learning by a large margin. In fact, KRR is better than classical transfer learning when less than 50 participants are available for finetuning, suggesting the difficulty of classical transfer learning in the very small sample regime. The multilayer meta-matching model is publicly available at GITHUB_LINK.

A Causality-Driven Graph Convolutional Network for Postural Abnormality Diagnosis in Parkinsonians

Abnormal posture is a common movement disorder in the progress of Parkinson's disease (PD), and this abnormality can increase the risk of falls or even disabilities. The conventional assessment approach depends on the judgment of well-trained experts via canonical scales. However, this approach requires extensive clinical expertise and is highly subjective. Considering the potential of quantitative susceptibility mapping (QSM) in PD diagnosis, this study explored the QSM-based method for the automated classification between PD patients with and without postural abnormalities. Nevertheless, a major challenge is that unstable non-causal features typically lead to less reliable performance. Therefore, we propose a causality-driven graph-convolutional-network framework based on multi-instance learning, where performance stability is enhanced through the invariant prediction principle and causal interventions. Specifically, we adopt an intervention strategy that combines a non-causal intervenor with causal prediction. A stability constraint is proposed to ensure robust integrated prediction under different interventions. Moreover, an intra-class homogeneity constraint is enforced for each individually-learned causality scoring module to promote the extraction of group-level general features, and hence achieve a balance between subject-specific and group-level features. The proposed method demonstrated promising performance through extensive experiments on a real clinical dataset. Also, the features extracted by our method coincide with those reported in previous medical studies on PD posture abnormalities. In general, our work provides a clinically-valuable approach for automated, objective, and reliable diagnosis of postural abnormalities in Parkinsonians. Our source code is publicly available at https://github.com/SJTUBME-QianLab/CausalGCN-PDPA.

PFP-HOG: Pyramid and Fixed-Size Patch-Based HOG Technique for Automated Brain Abnormality Classification with MRI

Detecting neurological abnormalities such as brain tumors and Alzheimer's disease (AD) using magnetic resonance imaging (MRI) images is an important research topic in the literature. Numerous machine learning models have been used to detect brain abnormalities accurately. This study addresses the problem of detecting neurological abnormalities in MRI. The motivation behind this problem lies in the need for accurate and efficient methods to assist neurologists in the diagnosis of these disorders. In addition, many deep learning techniques have been applied to MRI to develop accurate brain abnormality detection models, but these networks have high time complexity. Hence, a novel hand-modeled feature-based learning network is presented to reduce the time complexity and obtain high classification performance. The model proposed in this work uses a new feature generation architecture named pyramid and fixed-size patch (PFP). The main aim of the proposed PFP structure is to attain high classification performance using essential feature extractors with both multilevel and local features. Furthermore, the PFP feature extractor generates low- and high-level features using a handcrafted extractor. To obtain the high discriminative feature extraction ability of the PFP, we have used histogram-oriented gradients (HOG); hence, it is named PFP-HOG. Furthermore, the iterative Chi2 (IChi2) is utilized to choose the clinically significant features. Finally, the k-nearest neighbors (kNN) with tenfold cross-validation is used for automated classification. Four MRI neurological databases (AD dataset, brain tumor dataset 1, brain tumor dataset 2, and merged dataset) have been utilized to develop our model. PFP-HOG and IChi2-based models attained 100%, 94.98%, 98.19%, and 97.80% using the AD dataset, brain tumor dataset1, brain tumor dataset 2, and merged brain MRI dataset, respectively. These findings not only provide an accurate and robust classification of various neurological disorders using MRI but also hold the potential to assist neurologists in validating manual MRI brain abnormality screening.

Gaussian Process-based prediction of memory performance and biomarker status in ageing and Alzheimer's disease-A systematic model evaluation

Neuroimaging markers based on Magnetic Resonance Imaging (MRI) combined with various other measures (such as genetic covariates, biomarkers, vascular risk factors, neuropsychological tests etc.) might provide useful predictions of clinical outcomes during the progression towards Alzheimer's disease (AD). The use of multiple features in predictive frameworks for clinical outcomes has become increasingly prevalent in AD research. However, many studies do not focus on systematically and accurately evaluating combinations of multiple input features. Hence, the aim of the present work is to explore and assess optimal combinations of various features for MR-based prediction of (1) cognitive status and (2) biomarker positivity with a multi-kernel learning Gaussian process framework. The explored features and parameters included (A) combinations of brain tissues, modulation, smoothing, and image resolution; (B) incorporating demographics & clinical covariates; (C) the impact of the size of the training data set; (D) the influence of dimensionality reduction and the choice of kernel types. The approach was tested in a large German cohort including 959 subjects from the multicentric longitudinal study of cognitive impairment and dementia (DELCODE). Our evaluation suggests the best prediction of memory performance was obtained for a combination of neuroimaging markers, demographics, genetic information (ApoE4) and CSF biomarkers explaining 57% of outcome variance in out-of-sample predictions. The highest performance for Aβ42/40 status classification was achieved for a combination of demographics, ApoE4, and a memory score while usage of structural MRI further improved the classification of individual patient's pTau status.