Insights from an autism imaging biomarker challenge: Promises and threats to biomarker discovery

Generalizable and transportable resting-state neural signatures characterized by functional networks, neurotransmitters, and clinical symptoms in autism

Autism spectrum disorder (ASD) is a lifelong condition with elusive biological mechanisms. The complexity of factors, including inter-site and developmental differences, hinders the development of a generalizable neuroimaging classifier for ASD. Here, we developed a classifier for ASD using a large-scale, multisite resting-state fMRI dataset of 730 Japanese adults, aiming to capture neural signatures that reflect pathophysiology at the functional network level, neurotransmitters, and clinical symptoms of the autistic brain. Our adult ASD classifier was successfully generalized to adults in the United States, Belgium, and Japan. The classifier further demonstrated its successful transportability to children and adolescents. The classifier contained 141 functional connections (FCs) that were important for discriminating individuals with ASD from typically developing controls. These FCs and their terminal brain regions were associated with difficulties in social interaction and dopamine and serotonin, respectively. Finally, we mapped attention-deficit/hyperactivity disorder (ADHD), schizophrenia (SCZ), and major depressive disorder (MDD) onto the biological axis defined by the ASD classifier. ADHD and SCZ, but not MDD, were located proximate to ASD on the biological dimensions. Our results revealed functional signatures of the ASD brain, grounded in molecular characteristics and clinical symptoms, achieving generalizability and transportability applicable to the evaluation of the biological continuity of related diseases.

Replicability and generalizability in population psychiatric neuroimaging

Studies linking mental health with brain function in cross-sectional population-based association studies have historically relied on small, underpowered samples. Given the small effect sizes typical of such brain-wide associations, studies require samples into the thousands to achieve the statistical power necessary for replicability. Here, we detail how small sample sizes have hampered replicability and provide sample size targets given established association strength benchmarks. Critically, while replicability will improve with larger samples, it is not guaranteed that observed effects will meaningfully apply to target populations of interest (i.e., be generalizable). We discuss important considerations related to generalizability in psychiatric neuroimaging and provide an example of generalizability failure due to "shortcut learning" in brain-based predictions of mental health phenotypes. Shortcut learning is a phenomenon whereby machine learning models learn an association between the brain and an unmeasured construct (the shortcut), rather than the intended target of mental health. Given the complex nature of brain-behavior interactions, the future of epidemiological approaches to brain-based studies of mental health will require large, diverse samples with comprehensive assessment.

Psychiatric neuroimaging designs for individualised, cohort, and population studies

Psychiatric neuroimaging faces challenges to rigour and reproducibility that prompt reconsideration of the relative strengths and limitations of study designs. Owing to high resource demands and varying inferential goals, current designs differentially emphasise sample size, measurement breadth, and longitudinal assessments. In this overview and perspective, we provide a guide to the current landscape of psychiatric neuroimaging study designs with respect to this balance of scientific goals and resource constraints. Through a heuristic data cube contrasting key design features, we discuss a resulting trade-off among small sample, precision longitudinal studies (e.g., individualised studies and cohorts) and large sample, minimally longitudinal, population studies. Precision studies support tests of within-person mechanisms, via intervention and tracking of longitudinal course. Population studies support tests of generalisation across multifaceted individual differences. A proposed reciprocal validation model (RVM) aims to recursively leverage these complementary designs in sequence to accumulate evidence, optimise relative strengths, and build towards improved long-term clinical utility.

Extracting interpretable signatures of whole-brain dynamics through systematic comparison

The brain's complex distributed dynamics are typically quantified using a limited set of manually selected statistical properties, leaving the possibility that alternative dynamical properties may outperform those reported for a given application. Here, we address this limitation by systematically comparing diverse, interpretable features of both intra-regional activity and inter-regional functional coupling from resting-state functional magnetic resonance imaging (rs-fMRI) data, demonstrating our method using case-control comparisons of four neuropsychiatric disorders. Our findings generally support the use of linear time-series analysis techniques for rs-fMRI case-control analyses, while also identifying new ways to quantify informative dynamical fMRI structures. While simple statistical representations of fMRI dynamics performed surprisingly well (e.g., properties within a single brain region), combining intra-regional properties with inter-regional coupling generally improved performance, underscoring the distributed, multifaceted changes to fMRI dynamics in neuropsychiatric disorders. The comprehensive, data-driven method introduced here enables systematic identification and interpretation of quantitative dynamical signatures of multivariate time-series data, with applicability beyond neuroimaging to diverse scientific problems involving complex time-varying systems.

Specialization of anterior and posterior hippocampal functional connectivity differs in autism

Structural and functional differences in the hippocampus have been related to the episodic memory and social impairments observed in autism spectrum disorder (ASD). In neurotypical individuals, hippocampal-cortical functional connectivity systematically varies between anterior and posterior hippocampus, with changes observed during typical development. It remains unknown whether this specialization of anterior-posterior hippocampal connectivity is disrupted in ASD, and whether age-related differences in this specialization exist in ASD. We examined connectivity of the anterior and posterior hippocampus in an ASD (N = 139) and non-autistic comparison group (N = 133) aged 5-21 using resting-state functional magnetic resonance imaging (MRI) data from the Healthy Brain Network (HBN). Consistent with previous results, we observed lower connectivity between the whole hippocampus and medial prefrontal cortex in ASD. Moreover, preferential connectivity of the posterior relative to the anterior hippocampus for memory-sensitive regions in posterior parietal cortex was reduced in ASD, demonstrating a weaker anterior-posterior specialization of hippocampal-cortical connectivity. Finally, connectivity between the posterior hippocampus and precuneus negatively correlated with age in the ASD group but remained stable in the comparison group, suggesting an altered developmental specialization. Together, these differences in hippocampal-cortical connectivity may help us understand the neurobiological basis of the memory and social impairments found in ASD.

Exome functional risk score and brain connectivity can predict social adaptability outcome of children with autism spectrum disorder in 4 years' follow up

Introduction

Autism Spectrum Disorder (ASD) is a common neurodevelopmental disorder emerging in early childhood, with heterogeneous clinical outcomes across individuals. This study aims to recognize neuroimaging genetic factors associated with outcomes of ASD after a 4-year follow-up.

Methods

A total of 104 ASD children were included in this study; they underwent clinical assessments, MRI data acquisition, and the whole exome sequencing (WES). Exome functional risk score (EFRS) was calculated based on WES; and two modalities of brain connectivity were constructed based on MRI data, that is functional connectivity (FC) for functional MRI (fMRI), and individual differential structural covariance network (IDSCN) for structural MRI (sMRI), to explore the neuroimaging genetic biomarker of outcomes of ASD children.

Results

Regression analysis found EFRS predicts social adaptability at the 4-year follow-up (Y = -0.013X + 9.29, p = 0.003). We identified 19 pairs of FC associated with autism symptoms severity at follow-up, 10 pairs of FC and 4 pairs of IDSCN associated with social adaptability at follow-up, and 10 pairs of FC associated with ASD EFRS by support vector regression (SVR). Related brain regions with prognostic predictive effects are mainly distributed in superior frontal gyrus, occipital cortex, temporal cortex, parietal cortex, paracentral lobule, pallidum, and amygdala for FC, and temporal cortex, thalamus, and hippocampus for IDSCN. Mediation model showed that ASD EFRS affects the social communication of ASD children through the mediation of FC between left middle occipital gyrus and left pallidum (RMSEA=0.126, CMIN=80.66, DF=42, p< 0.001, CFI=0.867, AIC=152).

Discussion

Our findings underscore that both EFRS and brain connectivity can predict social adaptability, and that brain connectivity serving as mediator in the relationship of EFRS and behaviors of ASD, suggesting the intervention targets in the future clinical application.

Seeing beyond words: Visualizing autism spectrum disorder biomarker insights

Objective

This study employs bibliometric and visual analysis to elucidate global research trends in Autism Spectrum Disorder (ASD) biomarkers, identify critical research focal points, and discuss the potential integration of diverse biomarker modalities for precise ASD assessment.

Methods

A comprehensive bibliometric analysis was conducted using data from the Web of Science Core Collection database until December 31, 2022. Visualization tools, including R, VOSviewer, CiteSpace, and gCLUTO, were utilized to examine collaborative networks, co-citation patterns, and keyword associations among countries, institutions, authors, journals, documents, and keywords.

Results

ASD biomarker research emerged in 2004, accumulating a corpus of 4348 documents by December 31, 2022. The United States, with 1574 publications and an H-index of 213, emerged as the most prolific and influential country. The University of California, Davis, contributed significantly with 346 publications and an H-index of 69, making it the leading institution. Concerning journals, the Journal of Autism and Developmental Disorders, Autism Research, and PLOS ONE were the top three publishers of ASD biomarker-related articles among a total of 1140 academic journals. Co-citation and keyword analyses revealed research hotspots in genetics, imaging, oxidative stress, neuroinflammation, gut microbiota, and eye tracking. Emerging topics included "DNA methylation," "eye tracking," "metabolomics," and "resting-state fMRI."

Conclusion

The field of ASD biomarker research is dynamically evolving. Future endeavors should prioritize individual stratification, methodological standardization, the harmonious integration of biomarker modalities, and longitudinal studies to advance the precision of ASD diagnosis and treatment.

The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification

Functional connectivity (FC) obtained from resting-state functional magnetic resonance imaging has been integrated with machine learning algorithms to deliver consistent and reliable brain disease classification outcomes. However, in classical learning procedures, custom-built specialized feature selection techniques are typically used to filter out uninformative features from FC patterns to generalize efficiently on the datasets. The ability of convolutional neural networks (CNN) and other deep learning models to extract informative features from data with grid structure (such as images) has led to the surge in popularity of these techniques. However, the designs of many existing CNN models still fail to exploit the relationships between entities of graph-structure data (such as networks). Therefore, graph convolution network (GCN) has been suggested as a means for uncovering the intricate structure of brain network data, which has the potential to substantially improve classification accuracy. Furthermore, overfitting in classifiers can be largely attributed to the limited number of available training samples. Recently, the generative adversarial network (GAN) has been widely used in the medical field for its generative aspect that can generate synthesis images to cope with the problems of data scarcity and patient privacy. In our previous work, GCN and GAN have been designed to investigate FC patterns to perform diagnosis tasks, and their effectiveness has been tested on the ABIDE-I dataset. In this paper, the models will be further applied to FC data derived from more public datasets (ADHD, ABIDE-II, and ADNI) and our in-house dataset (PTSD) to justify their generalization on all types of data. The results of a number of experiments show the powerful characteristic of GAN to mimic FC data to achieve high performance in disease prediction. When employing GAN for data augmentation, the diagnostic accuracy across ADHD-200, ABIDE-II, and ADNI datasets surpasses that of other machine learning models, including results achieved with BrainNetCNN. Specifically, in ADHD, the accuracy increased from 67.74% to 73.96% with GAN, in ABIDE-II from 70.36% to 77.40%, and in ADNI, reaching 52.84% and 88.56% for multiclass and binary classification, respectively. GCN also obtains decent results, with the best accuracy in ADHD datasets at 71.38% for multinomial and 75% for binary classification, respectively, and the second-best accuracy in the ABIDE-II dataset (72.28% and 75.16%, respectively). Both GAN and GCN achieved the highest accuracy for the PTSD dataset, reaching 97.76%. However, there are still some limitations that can be improved. Both methods have many opportunities for the prediction and diagnosis of diseases.

Cumulative Effects of Resting-State Connectivity Across All Brain Networks Significantly Correlate with Attention-Deficit Hyperactivity Disorder Symptoms

Identification of replicable neuroimaging correlates of attention-deficit hyperactivity disorder (ADHD) has been hindered by small sample sizes, small effects, and heterogeneity of methods. Given evidence that ADHD is associated with alterations in widely distributed brain networks and the small effects of individual brain features, a whole-brain perspective focusing on cumulative effects is warranted. The use of large, multisite samples is crucial for improving reproducibility and clinical utility of brain-wide MRI association studies. To address this, a polyneuro risk score (PNRS) representing cumulative, brain-wide, ADHD-associated resting-state functional connectivity was constructed and validated using data from the Adolescent Brain Cognitive Development (ABCD, N = 5,543, 51.5% female) study, and was further tested in the independent Oregon-ADHD-1000 case-control cohort (N = 553, 37.4% female). The ADHD PNRS was significantly associated with ADHD symptoms in both cohorts after accounting for relevant covariates (p < 0.001). The most predictive PNRS involved all brain networks, though the strongest effects were concentrated among the default mode and cingulo-opercular networks. In the longitudinal Oregon-ADHD-1000, non-ADHD youth had significantly lower PNRS (Cohen's d = -0.318, robust p = 5.5 × 10-4) than those with persistent ADHD (age 7-19). The PNRS, however, did not mediate polygenic risk for ADHD. Brain-wide connectivity was robustly associated with ADHD symptoms in two independent cohorts, providing further evidence of widespread dysconnectivity in ADHD. Evaluation in enriched samples demonstrates the promise of the PNRS approach for improving reproducibility in neuroimaging studies and unraveling the complex relationships between brain connectivity and behavioral disorders.

Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting State Functional MRI Images

This study aims to increase the accuracy of autism spectrum disorder (ASD) diagnosis based on cognitive and behavioral phenotypes through multiple neuroimaging modalities. We apply machine learning (ML) algorithms to classify ASD patients and healthy control (HC) participants using structural magnetic resonance imaging (s-MRI) together with resting state functional MRI (rs-f-MRI and f-MRI) data from the large multisite data repository ABIDE (autism brain imaging data exchange) and identify important brain connectivity features. The 2D f-MRI images were converted into 3D s-MRI images, and datasets were preprocessed using the Montreal Neurological Institute (MNI) atlas. The data were then denoised to remove any confounding factors. We show, by using three fusion strategies such as early fusion, late fusion, and cross fusion, that, in this implementation, hybrid convolutional recurrent neural networks achieve better performance in comparison to either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). The proposed model classifies subjects as autistic or not according to how functional and anatomical connectivity metrics provide an overall diagnosis based on the autism diagnostic observation schedule (ADOS) standard. Our hybrid network achieved an accuracy of 96% by fusing s-MRI and f-MRI together, which outperforms the methods used in previous studies.

Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Autism-spectrum disorders (ASDs) are developmental disabilities that manifest in early childhood and are characterized by qualitative abnormalities in social behaviors, communication skills, and restrictive or repetitive behaviors. To explore the neurobiological mechanisms in ASD, extensive research has been done to identify potential diagnostic biomarkers through a neuroimaging genetics approach. Neuroimaging genetics helps to identify ASD-risk genes that contribute to structural and functional variations in brain circuitry and validate biological changes by elucidating the mechanisms and pathways that confer genetic risk. Integrating artificial intelligence models with neuroimaging data lays the groundwork for accurate diagnosis and facilitates the identification of early diagnostic biomarkers for ASD. This review discusses the significance of neuroimaging genetics approaches to gaining a better understanding of the perturbed neurochemical system and molecular pathways in ASD and how these approaches can detect structural, functional, and metabolic changes and lead to the discovery of novel biomarkers for the early diagnosis of ASD.

The Neurogenetics of Functional Connectivity Alterations in Autism: Insights From Subtyping in 657 Individuals

BACKGROUND

There is little consensus and controversial evidence on anatomical alterations in the brains of people with autism spectrum disorder (ASD), due in part to the large heterogeneity present in ASD, which in turn is a major drawback for developing therapies. One strategy to characterize this heterogeneity in ASD is to cluster large-scale functional brain connectivity profiles.

METHODS

A subtyping approach based on consensus clustering of functional brain connectivity patterns was applied to a population of 657 autistic individuals with quality-assured neuroimaging data. We then used high-resolution gene transcriptomic data to characterize the molecular mechanism behind each subtype by performing enrichment analysis of the set of genes showing a high spatial similarity with the profiles of functional connectivity alterations between each subtype and a group of typically developing control participants.

RESULTS

Two major stable subtypes were found: subtype 1 exhibited hypoconnectivity (less average connectivity than typically developing control participants) and subtype 2, hyperconnectivity. The 2 subtypes did not differ in structural imaging metrics in any of the analyzed regions (68 cortical and 14 subcortical) or in any of the behavioral scores (including IQ, Autism Diagnostic Interview, and Autism Diagnostic Observation Schedule). Finally, only subtype 2, comprising about 43% of ASD participants, led to significant enrichments after multiple testing corrections. Notably, the dominant enrichment corresponded to excitation/inhibition imbalance, a leading well-known primary mechanism in the pathophysiology of ASD.

CONCLUSIONS

Our results support a link between excitation/inhibition imbalance and functional connectivity alterations, but only in one ASD subtype, overall characterized by brain hyperconnectivity and major alterations in somatomotor and default mode networks.

Modularity-Constrained Dynamic Representation Learning for Interpretable Brain Disorder Analysis with Functional MRI

Resting-state functional MRI (rs-fMRI) is increasingly used to detect altered functional connectivity patterns caused by brain disorders, thereby facilitating objective quantification of brain pathology. Existing studies typically extract fMRI features using various machine/deep learning methods, but the generated imaging biomarkers are often challenging to interpret. Besides, the brain operates as a modular system with many cognitive/topological modules, where each module contains subsets of densely inter-connected regions-of-interest (ROIs) that are sparsely connected to ROIs in other modules. However, current methods cannot effectively characterize brain modularity. This paper proposes a modularity-constrained dynamic representation learning (MDRL) framework for interpretable brain disorder analysis with rs-fMRI. The MDRL consists of 3 parts: (1) dynamic graph construction, (2) modularity-constrained spatiotemporal graph neural network (MSGNN) for dynamic feature learning, and (3) prediction and biomarker detection. In particular, the MSGNN is designed to learn spatiotemporal dynamic representations of fMRI, constrained by 3 functional modules (i.e., central executive network, salience network, and default mode network). To enhance discriminative ability of learned features, we encourage the MSGNN to reconstruct network topology of input graphs. Experimental results on two public and one private datasets with a total of 1,155 subjects validate that our MDRL outperforms several state-of-the-art methods in fMRI-based brain disorder analysis. The detected fMRI biomarkers have good explainability and can be potentially used to improve clinical diagnosis.

Retinal electrophysiology in central nervous system disorders. A review of human and mouse studies

The retina and brain share similar neurochemistry and neurodevelopmental origins, with the retina, often viewed as a "window to the brain." With retinal measures of structure and function becoming easier to obtain in clinical populations there is a growing interest in using retinal findings as potential biomarkers for disorders affecting the central nervous system. Functional retinal biomarkers, such as the electroretinogram, show promise in neurological disorders, despite having limitations imposed by the existence of overlapping genetic markers, clinical traits or the effects of medications that may reduce their specificity in some conditions. This narrative review summarizes the principal functional retinal findings in central nervous system disorders and related mouse models and provides a background to the main excitatory and inhibitory retinal neurotransmitters that have been implicated to explain the visual electrophysiological findings. These changes in retinal neurochemistry may contribute to our understanding of these conditions based on the findings of retinal electrophysiological tests such as the flash, pattern, multifocal electroretinograms, and electro-oculogram. It is likely that future applications of signal analysis and machine learning algorithms will offer new insights into the pathophysiology, classification, and progression of these clinical disorders including autism, attention deficit/hyperactivity disorder, bipolar disorder, schizophrenia, depression, Parkinson's, and Alzheimer's disease. New clinical applications of visual electrophysiology to this field may lead to earlier, more accurate diagnoses and better targeted therapeutic interventions benefiting individual patients and clinicians managing these individuals and their families.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

Few-Shot Classification of Autism Spectrum Disorder using Site-Agnostic Meta-Learning and Brain MRI

For machine learning applications in medical imaging, the availability of training data is often limited, which hampers the design of radiological classifiers for subtle conditions such as autism spectrum disorder (ASD). Transfer learning is one method to counter this problem of low training data regimes. Here we explore the use of meta-learning for very low data regimes in the context of having prior data from multiple sites - an approach we term site-agnostic meta-learning. Inspired by the effectiveness of meta-learning for optimizing a model across multiple tasks, here we propose a framework to adapt it to learn across multiple sites. We tested our meta-learning model for classifying ASD versus typically developing controls in 2,201 T1-weighted (T1-w) MRI scans collected from 38 imaging sites as part of Autism Brain Imaging Data Exchange (ABIDE) [age: 5.2 -64.0 years]. The method was trained to find a good initialization state for our model that can quickly adapt to data from new unseen sites by fine-tuning on the limited data that is available. The proposed method achieved an area under the receiver operating characteristic curve (ROC-AUC)=0.857 on 370 scans from 7 unseen sites in ABIDE using a few-shot setting of 2-way 20-shot i.e., 20 training samples per site. Our results outperformed a transfer learning baseline by generalizing across a wider range of sites as well as other related prior work. We also tested our model in a zero-shot setting on an independent test site without any additional fine-tuning. Our experiments show the promise of the proposed site-agnostic meta-learning framework for challenging neuroimaging tasks involving multi-site heterogeneity with limited availability of training data.Clinical Relevance- We propose a learning framework that accommodates multi-site heterogeneity and limited data to assist in challenging neuroimaging tasks.

Candidate biomarkers in psychiatric disorders: state of the field

The field of psychiatry is hampered by a lack of robust, reliable and valid biomarkers that can aid in objectively diagnosing patients and providing individualized treatment recommendations. Here we review and critically evaluate the evidence for the most promising biomarkers in the psychiatric neuroscience literature for autism spectrum disorder, schizophrenia, anxiety disorders and post-traumatic stress disorder, major depression and bipolar disorder, and substance use disorders. Candidate biomarkers reviewed include various neuroimaging, genetic, molecular and peripheral assays, for the purposes of determining susceptibility or presence of illness, and predicting treatment response or safety. This review highlights a critical gap in the biomarker validation process. An enormous societal investment over the past 50 years has identified numerous candidate biomarkers. However, to date, the overwhelming majority of these measures have not been proven sufficiently reliable, valid and useful to be adopted clinically. It is time to consider whether strategic investments might break this impasse, focusing on a limited number of promising candidates to advance through a process of definitive testing for a specific indication. Some promising candidates for definitive testing include the N170 signal, an event-related brain potential measured using electroencephalography, for subgroup identification within autism spectrum disorder; striatal resting-state functional magnetic resonance imaging (fMRI) measures, such as the striatal connectivity index (SCI) and the functional striatal abnormalities (FSA) index, for prediction of treatment response in schizophrenia; error-related negativity (ERN), an electrophysiological index, for prediction of first onset of generalized anxiety disorder, and resting-state and structural brain connectomic measures for prediction of treatment response in social anxiety disorder. Alternate forms of classification may be useful for conceptualizing and testing potential biomarkers. Collaborative efforts allowing the inclusion of biosystems beyond genetics and neuroimaging are needed, and online remote acquisition of selected measures in a naturalistic setting using mobile health tools may significantly advance the field. Setting specific benchmarks for well-defined target application, along with development of appropriate funding and partnership mechanisms, would also be crucial. Finally, it should never be forgotten that, for a biomarker to be actionable, it will need to be clinically predictive at the individual level and viable in clinical settings.

One Size Does Not Fit All: Methodological Considerations for Brain-Based Predictive Modeling in Psychiatry

Psychiatric illnesses are heterogeneous in nature. No illness manifests in the same way across individuals, and no two patients with a shared diagnosis exhibit identical symptom profiles. Over the last several decades, group-level analyses of in vivo neuroimaging data have led to fundamental advances in our understanding of the neurobiology of psychiatric illnesses. More recently, access to computational resources and large, publicly available datasets alongside the rise of predictive modeling and precision medicine approaches have facilitated the study of psychiatric illnesses at an individual level. Data-driven machine learning analyses can be applied to identify disease-relevant biological subtypes, predict individual symptom profiles, and recommend personalized therapeutic interventions. However, when developing these predictive models, methodological choices must be carefully considered to ensure accurate, robust, and interpretable results. Choices pertaining to algorithms, neuroimaging modalities and states, data transformation, phenotypes, parcellations, sample sizes, and populations we are specifically studying can influence model performance. Here, we review applications of neuroimaging-based machine learning models to study psychiatric illnesses and discuss the effects of different methodological choices on model performance. An understanding of these effects is crucial for the proper implementation of predictive models in psychiatry and will facilitate more accurate diagnoses, prognoses, and therapeutics.

Generalizable neuromarker for autism spectrum disorder across imaging sites and developmental stages: A multi-site study

Autism spectrum disorder (ASD) is a lifelong condition, and its underlying biological mechanisms remain elusive. The complexity of various factors, including inter-site and development-related differences, makes it challenging to develop generalizable neuroimaging-based biomarkers for ASD. This study used a large-scale, multi-site dataset of 730 Japanese adults to develop a generalizable neuromarker for ASD across independent sites (U.S., Belgium, and Japan) and different developmental stages (children and adolescents). Our adult ASD neuromarker achieved successful generalization for the US and Belgium adults (area under the curve [AUC] = 0.70) and Japanese adults (AUC = 0.81). The neuromarker demonstrated significant generalization for children (AUC = 0.66) and adolescents (AUC = 0.71; all P < 0.05 , family-wise-error corrected). We identified 141 functional connections (FCs) important for discriminating individuals with ASD from TDCs. These FCs largely centered on social brain regions such as the amygdala, hippocampus, dorsomedial and ventromedial prefrontal cortices, and temporal cortices. Finally, we mapped schizophrenia (SCZ) and major depressive disorder (MDD) onto the biological axis defined by the neuromarker and explored the biological continuity of ASD with SCZ and MDD. We observed that SCZ, but not MDD, was located proximate to ASD on the biological dimension defined by the ASD neuromarker. The successful generalization in multifarious datasets and the observed relations of ASD with SCZ on the biological dimensions provide new insights for a deeper understanding of ASD.

Has Machine Learning Enhanced the Diagnosis of Autism Spectrum Disorder?

Autism spectrum disorder (ASD) is a complex neurological condition that limits an individual's capacity for communication and learning throughout their life. Although symptoms of Autism can be diagnosed in individuals of different ages, it is labeled as a developmental disorder because symptoms typically start to show up in the initial 2 years of childhood. Autism has no single known cause but multiple factors contribute to its etiology in children. Because symptoms and severity of ASD vary in every individual, there could be many causes. Detection of ASD in the early stages is crucial for providing a path for rehabilitation that enhances the quality of life and integrates the ASD person into the social, family, and professional spheres. Assessment of ASD includes experienced observers in neutral environments, which brings constraints and biases to a lack of credibility and fails to accurately reflect performance in terms of real-world scenarios. To get around these limitations, the conducted review offers a thorough analysis of the impact on the individual and the ones living around them and most recent research on how these techniques are implemented in the diagnosis of ASD. As a result of improvements in technology, assessments now include processing unconventional data than can be collected from measurements arising out of laboratory chemistry or of electrophysiological origin. Examples of these technologies include virtual reality and sensors including eye-tracking imaging. Studies have been conducted towards recognition of emotion and brain networks to identify functional connectivity and discriminate between people with ASD and people who are thought to be typically developing. Diagnosis of Autism has recently made substantial use of long short term memory (LSTM), convolutional neural network (CNN) and its variants, the random forest (RF) and naive Bayes (NB) machine learning techniques. It is hoped that researchers will develop methodologies that increase the probability of identification of ASD in its varied forms and contribute towards improved lifestyle for patients with ASD and those affected by the pathology.

Interpreting mental state decoding with deep learning models

In mental state decoding, researchers aim to identify the set of mental states (e.g., experiencing happiness or fear) that can be reliably identified from the activity patterns of a brain region (or network). Deep learning (DL) models are highly promising for mental state decoding because of their unmatched ability to learn versatile representations of complex data. However, their widespread application in mental state decoding is hindered by their lack of interpretability, difficulties in applying them to small datasets, and in ensuring their reproducibility and robustness. We recommend approaching these challenges by leveraging recent advances in explainable artificial intelligence (XAI) and transfer learning, and also provide recommendations on how to improve the reproducibility and robustness of DL models in mental state decoding.