Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large-scale multi-sample study

Graph convolutional network with attention mechanism improve major depressive depression diagnosis based on plasma biomarkers and neuroimaging data

BACKGROUND

The absence of clinically-validated biomarkers or objective protocols hinders effective major depressive disorder (MDD) diagnosis. Compared to healthy control (HC), MDD exhibits anomalies in plasma protein levels and neuroimaging presentations. Despite extensive machine learning studies in psychiatric diagnosis, a reliable tool integrating multi-modality data is still lacking.

METHODS

In this study, blood samples from 100 MDD and 100 HC were analyzed, along with MRI images from 46 MDD and 49 HC. Here, we devised a novel algorithm, integrating graph neural networks and attention modules, for MDD diagnosis based on inflammatory cytokines, neurotrophic factors, and Orexin A levels in the blood samples. Model performance was assessed via accuracy and F1 value in 3-fold cross-validation, comparing with 9 traditional algorithms. We then applied our algorithm to a dataset containing both the aforementioned protein quantifications and neuroimages, evaluating if integrating neuroimages into the model improves performance.

RESULTS

Compared to HC, MDD showed significant alterations in plasma protein levels and gray matter volume revealed by MRI. Our new algorithm exhibited superior performance, achieving an F1 value and accuracy of 0.9436 and 94.08 %, respectively. Integration of neuroimaging data enhanced our novel algorithm's performance, resulting in an improved F1 value and accuracy, reaching 0.9543 and 95.06 %.

LIMITATIONS

This single-center study with a small sample size requires future evaluations on a larger test set for improved reliability.

CONCLUSIONS

In comparison to traditional machine learning models, our newly developed MDD diagnostic model exhibited superior performance and showed promising potential for inclusion in routine clinical diagnosis for MDD.

Nonlinear latent representations of high-dimensional task-fMRI data: Unveiling cognitive and behavioral insights in heterogeneous spatial maps

Finding an interpretable and compact representation of complex neuroimaging data is extremely useful for understanding brain behavioral mapping and hence for explaining the biological underpinnings of mental disorders. However, hand-crafted representations, as well as linear transformations, may inadequately capture the considerable variability across individuals. Here, we implemented a data-driven approach using a three-dimensional autoencoder on two large-scale datasets. This approach provides a latent representation of high-dimensional task-fMRI data which can account for demographic characteristics whilst also being readily interpretable both in the latent space learned by the autoencoder and in the original voxel space. This was achieved by addressing a joint optimization problem that simultaneously reconstructs the data and predicts clinical or demographic variables. We then applied normative modeling to the latent variables to define summary statistics ('latent indices') and establish a multivariate mapping to non-imaging measures. Our model, trained with multi-task fMRI data from the Human Connectome Project (HCP) and UK biobank task-fMRI data, demonstrated high performance in age and sex predictions and successfully captured complex behavioral characteristics while preserving individual variability through a latent representation. Our model also performed competitively with respect to various baseline models including several variants of principal components analysis, independent components analysis and classical regions of interest, both in terms of reconstruction accuracy and strength of association with behavioral variables.

Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers

INTRODUCTION

Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer Disease (AD) heterogeneity. We employed a deep learning-based multimodal normative framework to analyze individual-level variation across ATN (amyloid-tau-neurodegeneration) imaging biomarkers.

METHODS

We selected cross-sectional discovery (n = 665) and replication cohorts (n = 430) with available T1-weighted MRI, amyloid and tau PET. Normative modeling estimated individual-level abnormal deviations in amyloid-positive individuals compared to amyloid-negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra-group heterogeneity. An individual-level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN.

RESULTS

Greater intra-group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression.

DISCUSSION

Subject-specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain.

Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers

INTRODUCTION

Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer Disease (AD) heterogeneity. We employed a deep learning-based multimodal normative framework to analyze individual-level variation across ATN (amyloid-tau-neurodegeneration) imaging biomarkers.

METHODS

We selected cross-sectional discovery (n = 665) and replication cohorts (n = 430) with available T1-weighted MRI, amyloid and tau PET. Normative modeling estimated individual-level abnormal deviations in amyloid-positive individuals compared to amyloid-negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra-group heterogeneity. An individual-level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN.

RESULTS

Greater intra-group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression.

DISCUSSION

Subject-specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain.

Deep Canonical Correlation Fusion Algorithm Based on Denoising Autoencoder for ASD Diagnosis and Pathogenic Brain Region Identification

Autism Spectrum Disorder (ASD) is defined as a neurodevelopmental condition distinguished by unconventional neural activities. Early intervention is key to managing the progress of ASD, and current research primarily focuses on the use of structural magnetic resonance imaging (sMRI) or resting-state functional magnetic resonance imaging (rs-fMRI) for diagnosis. Moreover, the use of autoencoders for disease classification has not been sufficiently explored. In this study, we introduce a new framework based on autoencoder, the Deep Canonical Correlation Fusion algorithm based on Denoising Autoencoder (DCCF-DAE), which proves to be effective in handling high-dimensional data. This framework involves efficient feature extraction from different types of data with an advanced autoencoder, followed by the fusion of these features through the DCCF model. Then we utilize the fused features for disease classification. DCCF integrates functional and structural data to help accurately diagnose ASD and identify critical Regions of Interest (ROIs) in disease mechanisms. We compare the proposed framework with other methods by the Autism Brain Imaging Data Exchange (ABIDE) database and the results demonstrate its outstanding performance in ASD diagnosis. The superiority of DCCF-DAE highlights its potential as a crucial tool for early ASD diagnosis and monitoring.

Individual deviations from normative electroencephalographic connectivity predict antidepressant response

BACKGROUND

Antidepressant medications yield unsatisfactory treatment outcomes in patients with major depressive disorder (MDD) with modest advantages over the placebo, partly due to the elusive mechanisms of antidepressant responses and unexplained heterogeneity in patient's response to treatment. Here we develop a novel normative modeling framework to quantify individual deviations in psychopathological dimensions that offers a promising avenue for the personalized treatment for psychiatric disorders.

METHODS

We built a normative model with resting-state electroencephalography (EEG) connectivity data from healthy controls of three independent cohorts. We characterized the individual deviation of MDD patients from the healthy norms, based on which we trained sparse predictive models for treatment responses of MDD patients (102 sertraline-medicated and 119 placebo-medicated). Hamilton depression rating scale (HAMD-17) was assessed at both baseline and after the eight-week antidepressant treatment.

RESULTS

We successfully predicted treatment outcomes for patients receiving sertraline (r = 0.43, p < 0.001) and placebo (r = 0.33, p < 0.001). We also showed that the normative modeling framework successfully distinguished subclinical and diagnostic variabilities among subjects. From the predictive models, we identified key connectivity signatures in resting-state EEG for antidepressant treatment, suggesting differences in neural circuit involvement between sertraline and placebo responses.

CONCLUSIONS

Our findings and highly generalizable framework advance the neurobiological understanding in the potential pathways of antidepressant responses, enabling more targeted and effective personalized MDD treatment.

TRIAL REGISTRATION

Establishing Moderators and Biosignatures of Antidepressant Response for Clinical Care for Depression (EMBARC), NCT#01407094.

A primer on the use of machine learning to distil knowledge from data in biological psychiatry

Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium

BACKGROUND

Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group.

METHODS

We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality.

RESULTS

We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance.

CONCLUSION

These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

Using normative modeling and machine learning for detecting mild traumatic brain injury from magnetoencephalography data

New biomarkers are urgently needed for many brain disorders; for example, the diagnosis of mild traumatic brain injury (mTBI) is challenging as the clinical symptoms are diverse and nonspecific. EEG and MEG studies have demonstrated several population-level indicators of mTBI that could serve as objective markers of brain injury. However, deriving clinically useful biomarkers for mTBI and other brain disorders from EEG/MEG signals is hampered by the large inter-individual variability even across healthy people. Here, we used a multivariate machine-learning approach to detect mTBI from resting-state MEG measurements. To address the heterogeneity of the condition, we employed a normative modeling approach and modeled MEG signal features of individual mTBI patients as deviations with respect to the normal variation. To this end, a normative dataset comprising 621 healthy participants was used to determine the variation in power spectra across the cortex. In addition, we constructed normative datasets based on age-matched subsets of the full normative data. To discriminate patients from healthy control subjects, we trained support-vector-machine classifiers on the quantitative deviation maps for 25 mTBI patients and 20 controls not included in the normative dataset. The best performing classifier made use of the full normative data across the entire age and frequency ranges. This classifier was able to distinguish patients from controls with an accuracy of 79%. Inspection of the trained model revealed that low-frequency activity in the theta frequency band (4-8 Hz) is a significant indicator of mTBI, consistent with earlier studies. The results demonstrate the feasibility of using normative modeling of MEG data combined with machine learning to advance diagnosis of mTBI and identify patients that would benefit from treatment and rehabilitation. The current approach could be applied to a wide range of brain disorders, thus providing a basis for deriving MEG/EEG-based biomarkers.

Brain Status Transferring Generative Adversarial Network for Decoding Individualized Atrophy in Alzheimer's Disease

Deep learning has been widely investigated in brain image computational analysis for diagnosing brain diseases such as Alzheimer's disease (AD). Most of the existing methods built end-to-end models to learn discriminative features by group-wise analysis. However, these methods cannot detect pathological changes in each subject, which is essential for the individualized interpretation of disease variances and precision medicine. In this article, we propose a brain status transferring generative adversarial network (BrainStatTrans-GAN) to generate corresponding healthy images of patients, which are further used to decode individualized brain atrophy. The BrainStatTrans-GAN consists of generator, discriminator, and status discriminator. First, a normative GAN is built to generate healthy brain images from normal controls. However, it cannot generate healthy images from diseased ones due to the lack of paired healthy and diseased images. To address this problem, a status discriminator with adversarial learning is designed in the training process to produce healthy brain images for patients. Then, the residual between the generated and input images can be computed to quantify pathological brain changes. Finally, a residual-based multi-level fusion network (RMFN) is built for more accurate disease diagnosis. Compared to the existing methods, our method can model individualized brain atrophy for facilitating disease diagnosis and interpretation. Experimental results on T1-weighted magnetic resonance imaging (MRI) data of 1,739 subjects from three datasets demonstrate the effectiveness of our method.

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.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Individual Deviations from Normative Electroencephalographic Connectivity Predict Antidepressant Response

Antidepressant medications yield unsatisfactory treatment outcomes in patients with major depressive disorder (MDD) with modest advantages over the placebo. This modest efficacy is partly due to the elusive mechanisms of antidepressant responses and unexplained heterogeneity in patient's response to treatment - the approved antidepressants only benefit a portion of patients, calling for personalized psychiatry based on individual-level prediction of treatment responses. Normative modeling, a framework that quantifies individual deviations in psychopathological dimensions, offers a promising avenue for the personalized treatment for psychiatric disorders. In this study, we built a normative model with resting-state electroencephalography (EEG) connectivity data from healthy controls of three independent cohorts. We characterized the individual deviation of MDD patients from the healthy norms, based on which we trained sparse predictive models for treatment responses of MDD patients. We successfully predicted treatment outcomes for patients receiving sertraline (r = 0.43, p < 0.001) and placebo (r = 0.33, p < 0.001). We also showed that the normative modeling framework successfully distinguished subclinical and diagnostic variabilities among subjects. From the predictive models, we identified key connectivity signatures in resting-state EEG for antidepressant treatment, suggesting differences in neural circuit involvement between treatment responses. Our findings and highly generalizable framework advance the neurobiological understanding in the potential pathways of antidepressant responses, enabling more targeted and effective MDD treatment.

Generalizability of 3D CNN models for age estimation in diverse youth populations using structural MRI

Recently, several studies have investigated the neurodevelopment of psychiatric disorders using brain data acquired via structural magnetic resonance imaging (sMRI). These analyses have shown the potential of sMRI data to provide a relatively precise characterization of brain structural biomarkers. Despite these advances, a relatively unexplored question is how reliable and consistent a model is when assessing subjects from other independent datasets. In this study, we investigate the performance and generalizability of the same model architecture trained from distinct datasets comprising youths in diverse stages of neurodevelopment and with different mental health conditions. We employed models with the same 3D convolutional neural network (CNN) architecture to assess autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), brain age, and a measure of dimensional psychopathology, the Child Behavior Checklist (CBCL) total score. The investigated datasets include the Autism Brain Imaging Data Exchange II (ABIDE-II, N = 580), Attention Deficit Hyperactivity Disorder (ADHD-200, N = 922), Brazilian High-Risk Cohort Study (BHRCS, N = 737), and Adolescent Brain Cognitive Development (ABCD, N = 11,031). Models' performance and interpretability were assessed within each dataset (for diagnosis tasks) and inter-datasets (for age estimation). Despite the demographic and phenotypic differences of the subjects, all models presented significant estimations for age (p value < 0.001) within and between datasets. In addition, most models showed a moderate to high correlation in age estimation. The results, including the models' brain regions of interest (ROI), were analyzed and discussed in light of the youth neurodevelopmental structural changes. Among other interesting discoveries, we found that less confounded training datasets produce models with higher generalization capacity.

[Hippocampal Development Deviation and Its Relationship With Cognition in Major Psychiatric Disorders]

Objective

To investigate hippocampal development deviation and its association with cognition in patients with major psychiatric disorders (MPDs), including schizophrenia, bipolar disorder and major depressive disorder.

Methods

The T1-weighted MRI data of 174 first-episode drug-naïve schizophrenia (FES) atients, 169 bipolar disorder (BD) patients, 184 major depressive disorder (MDD) patients, and 321 healthy controls were collected and their hippocampal volume was extracted after preprocessing with Freesurfer 5.3. A normative neurodevelopment model was applied to calculate the hippocampal deviation scores. Data on cognitive functions, including visual memory, attention, spatial working memory, were collected. Comparison by different sexes was made to identify difference between the hippocampal development deviation scores of the control group and those of the disease groups. We also investigated the moderating effect of age on the deviation score and explored the association between the deviation score and cognitive function.

Results

The hippocampal development deviation scores of patients with MPDs were significantly lower than those of the healthy controls (false discovery rate [FDR]-P<0.05). Analysis of the moderating effect of age revealed lower deviation scores in young patients (<[25.83-28.56] yr.) and higher deviation scores in old patients (>[35.87-54.35] yr.) in comparison with those of the healthy controls. The right hippocampal deviation scores in male FES patients were positively correlated with the number of errors for tasks concerning spatial working memory ( r=0.32, FDR-P=0.04).

Conclusion

Our findings suggest abnormal hippocampal development in MPDs patients and its different distribution in MPDs patients of different age groups. The hippocampal development deviation score may provide a new perspective for further understanding of etiology in MPDs.

Morphological fingerprinting: Identifying patients with first-episode schizophrenia using auto-encoded morphological patterns

Although a large number of case-control statistical and machine learning studies have been conducted to investigate structural brain changes in schizophrenia, how best to measure and characterize structural abnormalities for use in classification algorithms remains an open question. In the current study, a convolutional 3D autoencoder specifically designed for discretized volumes was constructed and trained with segmented brains from 477 healthy individuals. A cohort containing 158 first-episode schizophrenia patients and 166 matched controls was fed into the trained autoencoder to generate auto-encoded morphological patterns. A classifier discriminating schizophrenia patients from healthy controls was built using 80% of the samples in this cohort by automated machine learning and validated on the remaining 20% of the samples, and this classifier was further validated on another independent cohort containing 77 first-episode schizophrenia patients and 58 matched controls acquired at a different resolution. This specially designed autoencoder allowed a satisfactory recovery of the input. With the same feature dimension, the classifier trained with autoencoded features outperformed the classifier trained with conventional morphological features by about 10% points, achieving 73.44% accuracy and 0.8 AUC on the internal validation set and 71.85% accuracy and 0.77 AUC on the external validation set. The use of features automatically learned from the segmented brain can better identify schizophrenia patients from healthy controls, but there is still a need for further improvements to establish a clinical diagnostic marker. However, with a limited sample size, the method proposed in the current study shed insight into the application of deep learning in psychiatric disorders.

Normative model detects abnormal functional connectivity in psychiatric disorders

INTRODUCTION

The diagnosis of psychiatric disorders is mostly based on the clinical evaluation of the patient's signs and symptoms. Deep learning binary-based classification models have been developed to improve the diagnosis but have not yet reached clinical practice, in part due to the heterogeneity of such disorders. Here, we propose a normative model based on autoencoders.

METHODS

We trained our autoencoder on resting-state functional magnetic resonance imaging (rs-fMRI) data from healthy controls. The model was then tested on schizophrenia (SCZ), bipolar disorder (BD), and attention-deficit hyperactivity disorder (ADHD) patients to estimate how each patient deviated from the norm and associate it with abnormal functional brain networks' (FBNs) connectivity. Rs-fMRI data processing was conducted within the FMRIB Software Library (FSL), which included independent component analysis and dual regression. Pearson's correlation coefficients between the extracted blood oxygen level-dependent (BOLD) time series of all FBNs were calculated, and a correlation matrix was generated for each subject.

RESULTS AND DISCUSSION

We found that the functional connectivity related to the basal ganglia network seems to play an important role in the neuropathology of BD and SCZ, whereas in ADHD, its role is less evident. Moreover, the abnormal connectivity between the basal ganglia network and the language network is more specific to BD. The connectivity between the higher visual network and the right executive control and the connectivity between the anterior salience network and the precuneus networks are the most relevant in SCZ and ADHD, respectively. The results demonstrate that the proposed model could identify functional connectivity patterns that characterize different psychiatric disorders, in agreement with the literature. The abnormal connectivity patterns from the two independent SCZ groups of patients were similar, demonstrating that the presented normative model was also generalizable. However, the group-level differences did not withstand individual-level analysis implying that psychiatric disorders are highly heterogeneous. These findings suggest that a precision-based medical approach, focusing on each patient's specific functional network changes may be more beneficial than the traditional group-based diagnostic classification.

Machine Learning and Non-Affective Psychosis: Identification, Differential Diagnosis, and Treatment

PURPOSE OF REVIEW

This review will cover the most relevant findings on the use of machine learning (ML) techniques in the field of non-affective psychosis, by summarizing the studies published in the last three years focusing on illness detection and treatment.

RECENT FINDINGS

Multiple ML tools that include mostly supervised approaches such as support vector machine, gradient boosting, and random forest showed promising results by applying these algorithms to various sources of data: socio-demographic information, EEG, language, digital content, blood biomarkers, neuroimaging, and electronic health records. However, the overall performance, in the binary classification case, varied from 0.49, which is to be considered very low (i.e., noise), to over 0.90. These results are fully justified by different factors, some of which may be attributable to the preprocessing of the data, the wide variety of the data, and the a-priori setting of hyperparameters. One of the main limitations of the field is the lack of stratification of results based on biological sex, given that psychosis presents differently in men and women; hence, the necessity to tailor identification tools and data analytic strategies. Timely identification and appropriate treatment are key factors in reducing the consequences of psychotic disorders. In recent years, the emergence of new analytical tools based on artificial intelligence such as supervised ML approaches showed promises as a potential breakthrough in this field. However, ML applications in everyday practice are still in its infancy.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.

Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects approximately 1% of the population and causes significant burdens. ASD's pathogenesis remains elusive; hence, diagnosis is based on a constellation of behaviors. Structural magnetic resonance imaging (sMRI) studies have shown several abnormalities in volumetric and geometric features of the autistic brain. However, inconsistent findings prevented most contributions from being translated into clinical practice. Establishing reliable biomarkers for ASD using sMRI is crucial for the correct diagnosis and treatment. In recent years, machine learning (ML) and specifically deep learning (DL) have quickly extended to almost every sector, notably in disease diagnosis. Thus, this has led to a shift and improvement in ASD diagnostic methods, fulfilling most clinical diagnostic requirements. However, ASD discovery remains difficult. This review examines the ML-based ASD diagnosis literature over the past 5 years. A literature-based taxonomy of the research landscape has been mapped, and the major aspects of this topic have been covered. First, we provide an overview of ML's general classification pipeline and the features of sMRI. Next, representative studies are highlighted and discussed in detail with respect to methods, and biomarkers. Finally, we highlight many common challenges and make recommendations for future directions. In short, the limited sample size was the main obstacle; Thus, comprehensive data sets and rigorous methods are necessary to check the generalizability of the results. ML technologies are expected to advance significantly in the coming years, contributing to the diagnosis of ASD and helping clinicians soon.

The performance of artificial intelligence-driven technologies in diagnosing mental disorders: an umbrella review

Artificial intelligence (AI) has been successfully exploited in diagnosing many mental disorders. Numerous systematic reviews summarize the evidence on the accuracy of AI models in diagnosing different mental disorders. This umbrella review aims to synthesize results of previous systematic reviews on the performance of AI models in diagnosing mental disorders. To identify relevant systematic reviews, we searched 11 electronic databases, checked the reference list of the included reviews, and checked the reviews that cited the included reviews. Two reviewers independently selected the relevant reviews, extracted the data from them, and appraised their quality. We synthesized the extracted data using the narrative approach. We included 15 systematic reviews of 852 citations identified. The included reviews assessed the performance of AI models in diagnosing Alzheimer's disease (n = 7), mild cognitive impairment (n = 6), schizophrenia (n = 3), bipolar disease (n = 2), autism spectrum disorder (n = 1), obsessive-compulsive disorder (n = 1), post-traumatic stress disorder (n = 1), and psychotic disorders (n = 1). The performance of the AI models in diagnosing these mental disorders ranged between 21% and 100%. AI technologies offer great promise in diagnosing mental health disorders. The reported performance metrics paint a vivid picture of a bright future for AI in this field. Healthcare professionals in the field should cautiously and consciously begin to explore the opportunities of AI-based tools for their daily routine. It would also be encouraging to see a greater number of meta-analyses and further systematic reviews on performance of AI models in diagnosing other common mental disorders such as depression and anxiety.

Going deep into schizophrenia with artificial intelligence

Despite years of research, the mechanisms governing the onset, relapse, symptomatology, and treatment of schizophrenia (SZ) remain elusive. The lack of appropriate analytic tools to deal with the heterogeneity and complexity of SZ may be one of the reasons behind this situation. Deep learning, a subfield of artificial intelligence (AI) inspired by the nervous system, has recently provided an accessible way of modeling and analyzing complex, high-dimensional, nonlinear systems. The unprecedented accuracy of deep learning algorithms in classification and prediction tasks has revolutionized a wide range of scientific fields and is rapidly permeating SZ research. Deep learning has the potential of becoming a valuable aid for clinicians in the prediction, diagnosis, and treatment of SZ, especially in combination with principles from Bayesian statistics. Furthermore, deep learning could become a powerful tool for uncovering the mechanisms underlying SZ thanks to a growing number of techniques designed for improving model interpretability and causal reasoning. The purpose of this article is to introduce SZ researchers to the field of deep learning and review its latest applications in SZ research. In general, existing studies have yielded impressive results in classification and outcome prediction tasks. However, methodological concerns related to the assessment of model performance in several studies, the widespread use of small training datasets, and the little clinical value of some models suggest that some of these results should be taken with caution.

Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques

Schizophrenia is a severe neuropsychiatric disease whose diagnosis, unfortunately, lacks an objective diagnostic tool supporting a thorough psychiatric examination of the patient. We took advantage of today’s computational abilities, structural magnetic resonance imaging, and modern machine learning methods, such as stacked autoencoders (SAE) and 3D convolutional neural networks (3D CNN), to teach them to classify 52 patients with schizophrenia and 52 healthy controls. The main aim of this study was to explore whether complex feature extraction methods can help improve the accuracy of deep learning-based classifiers compared to minimally preprocessed data. Our experiments employed three commonly used preprocessing steps to extract three different feature types. They included voxel-based morphometry, deformation-based morphometry, and simple spatial normalization of brain tissue. In addition to classifier models, features and their combination, other model parameters such as network depth, number of neurons, number of convolutional filters, and input data size were also investigated. Autoencoders were trained on feature pools of 1000 and 5000 voxels selected by Mann-Whitney tests, and 3D CNNs were trained on whole images. The most successful model architecture (autoencoders) achieved the highest average accuracy of 69.62% (sensitivity 68.85%, specificity 70.38%). The results of all experiments were statistically compared (the Mann-Whitney test). In conclusion, SAE outperformed 3D CNN, while preprocessing using VBM helped SAE improve the results.

Structural and diffusion MRI based schizophrenia classification using 2D pretrained and 3D naive Convolutional Neural Networks

The ability of automatic feature learning makes Convolutional Neural Network (CNN) potentially suitable to uncover the complex and widespread brain changes in schizophrenia. Despite that, limited studies have been done on schizophrenia identification using interpretable deep learning approaches on multimodal neuroimaging data. Here, we developed a deep feature approach based on pre-trained 2D CNN and naive 3D CNN models trained from scratch for schizophrenia classification by integrating 3D structural and diffusion magnetic resonance imaging (MRI) data. We found that the naive 3D CNN models outperformed the pretrained 2D CNN models and the handcrafted feature-based machine learning approach using support vector machine during both cross-validation and testing on an independent dataset. Multimodal neuroimaging-based models accomplished performance superior to models based on a single modality. Furthermore, we identified brain grey matter and white matter regions critical for illness classification at the individual- and group-level which supported the salience network and striatal dysfunction hypotheses in schizophrenia. Our findings underscore the potential of CNN not only to automatically uncover and integrate multimodal 3D brain imaging features for schizophrenia identification, but also to provide relevant neurobiological interpretations which are crucial for developing objective and interpretable imaging-based probes for prognosis and diagnosis in psychiatric disorders.

Outlier detection in multimodal MRI identifies rare individual phenotypes among more than 15,000 brains

Outliers in neuroimaging represent spurious data or the data of unusual phenotypes that deserve special attention such as clinical follow-up. Outliers have usually been detected in a supervised or semi-supervised manner for labeled neuroimaging cohorts. There has been much less work using unsupervised outlier detection on large unlabeled cohorts like the UK Biobank brain imaging dataset. Given its large sample size, rare imaging phenotypes within this unique cohort are of interest, as they are often clinically relevant and could be informative for discovering new processes. Here, we developed a two-level outlier detection and screening methodology to characterize individual outliers from the multimodal MRI dataset of more than 15,000 UK Biobank subjects. In primary screening, using brain ventricles, white matter, cortical thickness, and functional connectivity-based imaging phenotypes, every subject was parameterized with an outlier score per imaging phenotype. Outlier scores of these imaging phenotypes had good-to-excellent test-retest reliability, with the exception of resting-state functional connectivity (RSFC). Due to the low reliability of RSFC outlier scores, RSFC outliers were excluded from further individual-level outlier screening. In secondary screening, the extreme outliers (1,026 subjects) were examined individually, and those arising from data collection/processing errors were eliminated. A representative subgroup of 120 subjects from the remaining non-artifactual outliers were radiologically reviewed, and radiological findings were identified in 97.5% of them. This study establishes an unsupervised framework for investigating rare individual imaging phenotypes within a large neuroimaging cohort.

Applications of Unsupervised Machine Learning in Autism Spectrum Disorder Research: a Review

Large amounts of autism spectrum disorder (ASD) data is created through hospitals, therapy centers, and mobile applications; however, much of this rich data does not have pre-existing classes or labels. Large amounts of data—both genetic and behavioral—that are collected as part of scientific studies or a part of treatment can provide a deeper, more nuanced insight into both diagnosis and treatment of ASD. This paper reviews 43 papers using unsupervised machine learning in ASD, including k-means clustering, hierarchical clustering, model-based clustering, and self-organizing maps. The aim of this review is to provide a survey of the current uses of unsupervised machine learning in ASD research and provide insight into the types of questions being answered with these methods.

Mental Health Prediction Using Machine Learning: Taxonomy, Applications, and Challenges

The increase of mental health problems and the need for effective medical health care have led to an investigation of machine learning that can be applied in mental health problems. This paper presents a recent systematic review of machine learning approaches in predicting mental health problems. Furthermore, we will discuss the challenges, limitations, and future directions for the application of machine learning in the mental health field. We collect research articles and studies that are related to the machine learning approaches in predicting mental health problems by searching reliable databases. Moreover, we adhere to the PRISMA methodology in conducting this systematic review. We include a total of 30 research articles in this review after the screening and identification processes. Then, we categorize the collected research articles based on the mental health problems such as schizophrenia, bipolar disorder, anxiety and depression, posttraumatic stress disorder, and mental health problems among children. Discussing the findings, we reflect on the challenges and limitations faced by the researchers on machine learning in mental health problems. Additionally, we provide concrete recommendations on the potential future research and development of applying machine learning in the mental health field.

Deep learning for neuroimaging-based diagnosis and rehabilitation of Autism Spectrum Disorder: A review

Accurate diagnosis of Autism Spectrum Disorder (ASD) followed by effective rehabilitation is essential for the management of this disorder. Artificial intelligence (AI) techniques can aid physicians to apply automatic diagnosis and rehabilitation procedures. AI techniques comprise traditional machine learning (ML) approaches and deep learning (DL) techniques. Conventional ML methods employ various feature extraction and classification techniques, but in DL, the process of feature extraction and classification is accomplished intelligently and integrally. DL methods for diagnosis of ASD have been focused on neuroimaging-based approaches. Neuroimaging techniques are non-invasive disease markers potentially useful for ASD diagnosis. Structural and functional neuroimaging techniques provide physicians substantial information about the structure (anatomy and structural connectivity) and function (activity and functional connectivity) of the brain. Due to the intricate structure and function of the brain, proposing optimum procedures for ASD diagnosis with neuroimaging data without exploiting powerful AI techniques like DL may be challenging. In this paper, studies conducted with the aid of DL networks to distinguish ASD are investigated. Rehabilitation tools provided for supporting ASD patients utilizing DL networks are also assessed. Finally, we will present important challenges in the automated detection and rehabilitation of ASD and propose some future works.

Diagnosing autism spectrum disorder in children using conventional MRI and apparent diffusion coefficient based deep learning algorithms

OBJECTIVE

To develop and validate deep learning (DL) methods for diagnosing autism spectrum disorder (ASD) based on conventional MRI (cMRI) and apparent diffusion coefficient (ADC) images.

METHODS

A total of 151 ASD children and 151 age-matched typically developing (TD) controls were included in this study. The data from these subjects were assigned to training and validation datasets. An additional 20 ASD children and 25 TD controls were acquired, whose data were utilized in an independent test set. All subjects underwent cMRI and diffusion-weighted imaging examination of the brain. We developed a series of DL models to separate ASD from TD based on the cMRI and ADC data. The seven models used include five single-sequence models (SSMs), one dominant-sequence model (DSM), and one all-sequence model (ASM). To enhance the feature detection of the models, we embed an attention mechanism module.

RESULTS

The highest AUC (0.824 ~ 0.850) was achieved when applying the SSM based on either FLAIR or ADC to the validation and independent test sets. A DSM using the combination of FLAIR and ADC showed an improved AUC in the validation (0.873) and independent test sets (0.876). The ASM also showed better diagnostic value in the validation (AUC = 0.838) and independent test sets (AUC = 0.836) compared to the SSMs. Among the models with attention mechanism, the DSM achieved the highest diagnostic performance with an AUC, accuracy, sensitivity, and specificity of 0.898, 84.4%, 85.0%, and 84.0% respectively.

CONCLUSIONS

This study established the potential of DL models to distinguish ASD cases from TD controls based on cMRI and ADC images.

KEY POINTS

• Deep learning models based on conventional MRI and ADC can be used to diagnose ASD. • The model (DSM) based on the FLAIR and ADC sequence achieved the best diagnostic performance with an AUC of 0.836 in the independent test sets. • The attention mechanism further improved the diagnostic performance of the models.

Detecting microstructural deviations in individuals with deep diffusion MRI tractometry

Most diffusion magnetic resonance imaging studies of disease rely on statistical comparisons between large groups of patients and healthy participants to infer altered tissue states in the brain; however, clinical heterogeneity can greatly challenge their discriminative power. There is currently an unmet need to move away from the current approach of group-wise comparisons to methods with the sensitivity to detect altered tissue states at the individual level. This would ultimately enable the early detection and interpretation of microstructural abnormalities in individual patients, an important step towards personalized medicine in translational imaging. To this end, Detect was developed to advance diffusion magnetic resonance imaging tractometry towards single-patient analysis. By operating on the manifold of white-matter pathways and learning normative microstructural features, our framework captures idiosyncrasies in patterns along white-matter pathways. Our approach paves the way from traditional group-based comparisons to true personalized radiology, taking microstructural imaging from the bench to the bedside.

Application of Artificial Intelligence in the MRI Classification Task of Human Brain Neurological and Psychiatric Diseases: A Scoping Review

Artificial intelligence (AI) for medical imaging is a technology with great potential. An in-depth understanding of the principles and applications of magnetic resonance imaging (MRI), machine learning (ML), and deep learning (DL) is fundamental for developing AI-based algorithms that can meet the requirements of clinical diagnosis and have excellent quality and efficiency. Moreover, a more comprehensive understanding of applications and opportunities would help to implement AI-based methods in an ethical and sustainable manner. This review first summarizes recent research advances in ML and DL techniques for classifying human brain magnetic resonance images. Then, the application of ML and DL methods to six typical neurological and psychiatric diseases is summarized, including Alzheimer's disease (AD), Parkinson's disease (PD), major depressive disorder (MDD), schizophrenia (SCZ), attention-deficit/hyperactivity disorder (ADHD), and autism spectrum disorder (ASD). Finally, the limitations of the existing research are discussed, and possible future research directions are proposed.

Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer's disease in a cross-sectional multi-cohort study

Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed. In this study, we assessed normative models based on deep autoencoders using structural neuroimaging data from patients with Alzheimer's disease (n = 206) and mild cognitive impairment (n = 354). We first trained the autoencoder on an independent dataset (UK Biobank dataset) with 11,034 healthy controls. Then, we estimated how each patient deviated from this norm and established which brain regions were associated to this deviation. Finally, we compared the performance of our normative model against traditional classifiers. As expected, we found that patients exhibited deviations according to the severity of their clinical condition. The model identified medial temporal regions, including the hippocampus, and the ventricular system as critical regions for the calculation of the deviation score. Overall, the normative model had comparable cross-cohort generalizability to traditional classifiers. To promote open science, we are making all scripts and the trained models available to the wider research community.

Three-Dimensional Convolutional Autoencoder Extracts Features of Structural Brain Images With a "Diagnostic Label-Free" Approach: Application to Schizophrenia Datasets

There has been increasing interest in performing psychiatric brain imaging studies using deep learning. However, most studies in this field disregard three-dimensional (3D) spatial information and targeted disease discrimination, without considering the genetic and clinical heterogeneity of psychiatric disorders. The purpose of this study was to investigate the efficacy of a 3D convolutional autoencoder (3D-CAE) for extracting features related to psychiatric disorders without diagnostic labels. The network was trained using a Kyoto University dataset including 82 patients with schizophrenia (SZ) and 90 healthy subjects (HS) and was evaluated using Center for Biomedical Research Excellence (COBRE) datasets, including 71 SZ patients and 71 HS. We created 16 3D-CAE models with different channels and convolutions to explore the effective range of hyperparameters for psychiatric brain imaging. The number of blocks containing two convolutional layers and one pooling layer was set, ranging from 1 block to 4 blocks. The number of channels in the extraction layer varied from 1, 4, 16, and 32 channels. The proposed 3D-CAEs were successfully reproduced into 3D structural magnetic resonance imaging (MRI) scans with sufficiently low errors. In addition, the features extracted using 3D-CAE retained the relation to clinical information. We explored the appropriate hyperparameter range of 3D-CAE, and it was suggested that a model with 3 blocks may be related to extracting features for predicting the dose of medication and symptom severity in schizophrenia.

Brain imaging-based machine learning in autism spectrum disorder: methods and applications

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.

Estimating Gender and Age from Brain Structural MRI of Children and Adolescents: A 3D Convolutional Neural Network Multitask Learning Model

Despite recent advances, assessing biological measurements for neuropsychiatric disorders is still a challenge, where confounding variables such as gender and age (as a proxy for neurodevelopment) play an important role. This study explores brain structural magnetic resonance imaging (sMRI) from two public data sets (ABIDE-II and ADHD-200) with healthy control (HC, N = 894), autism spectrum disorder (ASD, N = 251), and attention deficit hyperactivity disorder (ADHD, N = 357) individuals. We used gray and white matter preprocessed via voxel-based morphometry (VBM) to train a 3D convolutional neural network with a multitask learning strategy to estimate gender, age, and mental health status from structural brain differences. Gradient-based methods were employed to generate attention maps, providing clinically relevant identification of most representative brain regions for models' decision-making. This approach resulted in satisfactory predictions for gender and age. ADHD-200-trained models, evaluated in 10-fold cross-validation procedures on test set, obtained a mean absolute error (MAE) of 1.43 years (±0.22 SD) for age prediction and an area under the curve (AUC) of 0.85 (±0.04 SD) for gender classification. In out-of-sample validation, the best-performing ADHD-200 models satisfactorily predicted age (MAE = 1.57 years) and gender (AUC = 0.89) in the ABIDE-II data set. The models' accuracy was in line with the current state-of-the-art machine learning applications in neuroimaging. Key regions for models' accuracy were presented as a meaningful graphical output. New implementations, such as the use of VBM along with a 3D convolutional neural network multitask learning model and a brain imaging graphical output, reinforce the relevance of the proposed workflow.

The performance of artificial intelligence-driven technologies in diagnosing mental disorders: An umbrella review (Preprint).. [DOI: 10.2196/preprints.29235] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Diagnosing mental disorders is usually not an easy task and requires a large amount of time and effort given the complex nature of mental disorders. Artificial intelligence (AI) has been successfully exploited in diagnosing many mental disorders. Numerous systematic reviews summarize the evidence on the accuracy of AI models in diagnosing different mental disorders.

OBJECTIVE

This umbrella review aims to synthesize results of previous systematic reviews on the performance of AI models in diagnosing mental disorders.

METHODS

To identify relevant systematic reviews, we searched 11 electronic databases, checked the reference list of the included reviews, and checked the reviews that cited the included reviews. Two reviewers independently selected the relevant reviews, extracted the data from them, and appraised their quality. We synthesized the extracted data using the narrative approach. Specifically, results of the included reviews were grouped based on the target mental disorders that the AI classifiers distinguish.

RESULTS

We included 15 systematic reviews of 852 citations identified by searching all databases. The included reviews assessed the performance of AI models in diagnosing Alzheimer’s disease (n=7), mild cognitive impairment (n=6), schizophrenia (n=3), bipolar disease (n=2), autism spectrum disorder (n=1), obsessive-compulsive disorder (n=1), post-traumatic stress disorder (n=1), and psychotic disorders (n=1). The performance of the AI models in diagnosing these mental disorders ranged between 21% and 100%.

CONCLUSIONS

AI technologies offer great promise in diagnosing mental health disorders. The reported performance metrics paint a vivid picture of a bright future for AI in this field. To expedite progress towards these technologies being incorporated into routine practice, we recommend that healthcare professionals in the field cautiously and consciously begin to explore the opportunities of AI-based tools for their daily routine. It would also be encouraging to see a greater number of meta-analyses and further systematic reviews on performance of AI models in diagnosing other common mental disorders such as depression and anxiety.

CLINICALTRIAL

CRD42021231558

Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis

Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n = 22), schizophrenia (SZ; n = 22) and attention-deficit/hyperactivity disorder (ADHD; n = 9). Thirty-two of the thirty-five studies that directly compared DL to SML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and SML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. Our results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. However, it is not yet used to its full potential: most studies use pre-engineered features, whereas one of the main advantages of DL is its ability to learn representations of minimally processed data. Our current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets. To truly uncover the added value of DL, we need carefully designed comparisons of SML and DL models which are yet rarely performed.

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.

Identification of autism spectrum disorder based on short-term spontaneous hemodynamic fluctuations using deep learning in a multi-layer neural network

OBJECTIVE

To classify children with autism spectrum disorder (ASD) and typical development (TD) using short-term spontaneous hemodynamic fluctuations and to explore the abnormality of inferior frontal gyrus and temporal lobe in ASD.

METHODS

25 ASD children and 22 TD children were measured with functional near-infrared spectroscopy located on the inferior frontal gyrus and temporal lobe. To extract features used to classify ASD and TD, a multi-layer neural network was applied, combining with a three-layer convolutional neural network, a layer of long and short-term memory network (LSTM) and a layer of LSTM with Attention mechanism. In order to shorten the time of data collection and get more information from limited samples, a sliding window with 3.5 s width was utilized after comparisons, and numerous short (3.5 s) fNIRS time series were then obtained and used as the input of the multi-layer neural network.

RESULTS

A good classification between ASD and TD was obtained with considerably high accuracy by using a multi-layer neural network in different brain regions, especially in the left temporal lobe, where sensitivity of 90.6% and specificity of 97.5% achieved.

CONCLUSIONS

The "CLAttention" multi-layer neural network has the potential to excavate more meaningful features to distinguish between ASD and TD. Moreover, the temporal lobe may be worth further study.

SIGNIFICANCE

The findings in this study may have implications for rapid diagnosis of children with ASD and provide a new perspective for future medical diagnosis.

Iranian Brain Imaging Database: A Neuropsychiatric Database of Healthy Brain

INTRODUCTION

The Iranian Brain Imaging Database (IBID) was initiated in 2017, with 5 major goals: provide researchers easy access to a neuroimaging database, provide normative quantitative measures of the brain for clinical research purposes, study the aging profile of the brain, examine the association of brain structure and function, and join the ENIGMA consortium. Many prestigious databases with similar goals are available. However, they were not done on an Iranian population, and the battery of their tests (e.g. cognitive tests) is selected based on their specific questions and needs.

METHODS

The IBID will include 300 participants (50% female) in the age range of 20 to 70 years old, with an equal number of participants (#60) in each age decade. It comprises a battery of cognitive, lifestyle, medical, and mental health tests, in addition to several Magnetic Resonance Imaging (MRI) protocols. Each participant completes the assessments on two referral days.

RESULTS

The study currently has a cross-sectional design, but longitudinal assessments are considered for the future phases of the study. Here, details of the methodology and the initial results of assessing the first 152 participants of the study are provided.

CONCLUSION

IBID is established to enable research into human brain function, to aid clinicians in disease diagnosis research, and also to unite the Iranian researchers with interests in the brain.

Deep learning for small and big data in psychiatry

Psychiatry today must gain a better understanding of the common and distinct pathophysiological mechanisms underlying psychiatric disorders in order to deliver more effective, person-tailored treatments. To this end, it appears that the analysis of 'small' experimental samples using conventional statistical approaches has largely failed to capture the heterogeneity underlying psychiatric phenotypes. Modern algorithms and approaches from machine learning, particularly deep learning, provide new hope to address these issues given their outstanding prediction performance in other disciplines. The strength of deep learning algorithms is that they can implement very complicated, and in principle arbitrary predictor-response mappings efficiently. This power comes at a cost, the need for large training (and test) samples to infer the (sometimes over millions of) model parameters. This appears to be at odds with the as yet rather 'small' samples available in psychiatric human research to date (n < 10,000), and the ambition of predicting treatment at the single subject level (n = 1). Here, we aim at giving a comprehensive overview on how we can yet use such models for prediction in psychiatry. We review how machine learning approaches compare to more traditional statistical hypothesis-driven approaches, how their complexity relates to the need of large sample sizes, and what we can do to optimally use these powerful techniques in psychiatric neuroscience.

A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Deep learning has recently been used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and it has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders. This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis. We first provide a comprehensive overview of deep learning techniques and popular network architectures by introducing various types of deep neural networks and recent developments. We then review deep learning methods for computer-aided analysis of four typical brain disorders, including Alzheimer's disease, Parkinson's disease, Autism spectrum disorder, and Schizophrenia, where the first two diseases are neurodegenerative disorders and the last two are neurodevelopmental and psychiatric disorders, respectively. More importantly, we discuss the limitations of existing studies and present possible future directions.

Brain MRI-based 3D Convolutional Neural Networks for Classification of Schizophrenia and Controls

Convolutional Neural Network (CNN) has been successfully applied on classification of both natural images and medical images but limited studies applied it to differentiate patients with schizophrenia from healthy controls. Given the subtle, mixed, and sparsely distributed brain atrophy patterns of schizophrenia, the capability of automatic feature learning makes CNN a powerful tool for classifying schizophrenia from controls as it removes the subjectivity in selecting relevant spatial features. To examine the feasibility of applying CNN to classification of schizophrenia and controls based on structural Magnetic Resonance Imaging (MRI), we built 3D CNN models with different architectures and compared their performance with a handcrafted feature-based machine learning approach. Support vector machine (SVM) was used as classifier and Voxel-based Morphometry (VBM) was used as feature for handcrafted feature-based machine learning. 3D CNN models with sequential architecture, inception module and residual module were trained from scratch. CNN models achieved higher cross-validation accuracy than handcrafted feature-based machine learning. Moreover, testing on an independent dataset, 3D CNN models greatly outperformed handcrafted feature-based machine learning. This study underscored the potential of CNN for identifying patients with schizophrenia using 3D brain MR images and paved the way for imaging-based individual-level diagnosis and prognosis in psychiatric disorders.

Heart Rate Variability in the Perinatal Period: A Critical and Conceptual Review

Neonatal intensive care units (NICUs) greatly expand the use of technology. There is a need to accurately diagnose discomfort, pain, and complications, such as sepsis, mainly before they occur. While specific treatments are possible, they are often time-consuming, invasive, or painful, with detrimental effects for the development of the infant. In the last 40 years, heart rate variability (HRV) has emerged as a non-invasive measurement to monitor newborns and infants, but it still is underused. Hence, the present paper aims to review the utility of HRV in neonatology and the instruments available to assess it, showing how HRV could be an innovative tool in the years to come. When continuously monitored, HRV could help assess the baby’s overall wellbeing and neurological development to detect stress-/pain-related behaviors or pathological conditions, such as respiratory distress syndrome and hyperbilirubinemia, to address when to perform procedures to reduce the baby’s stress/pain and interventions, such as therapeutic hypothermia, and to avoid severe complications, such as sepsis and necrotizing enterocolitis, thus reducing mortality. Based on literature and previous experiences, the first step to efficiently introduce HRV in the NICUs could consist in a monitoring system that uses photoplethysmography, which is low-cost and non-invasive, and displays one or a few metrics with good clinical utility. However, to fully harness HRV clinical potential and to greatly improve neonatal care, the monitoring systems will have to rely on modern bioinformatics (machine learning and artificial intelligence algorithms), which could easily integrate infant’s HRV metrics, vital signs, and especially past history, thus elaborating models capable to efficiently monitor and predict the infant’s clinical conditions. For this reason, hospitals and institutions will have to establish tight collaborations between the obstetric, neonatal, and pediatric departments: this way, healthcare would truly improve in every stage of the perinatal period (from conception to the first years of life), since information about patients’ health would flow freely among different professionals, and high-quality research could be performed integrating the data recorded in those departments.

Deep learning of brain magnetic resonance images: A brief review

Magnetic resonance imaging (MRI) is one of the most popular techniques in brain science and is important for understanding brain function and neuropsychiatric disorders. However, the processing and analysis of MRI is not a trivial task with lots of challenges. Recently, deep learning has shown superior performance over traditional machine learning approaches in image analysis. In this survey, we give a brief review of the recent popular deep learning approaches and their applications in brain MRI analysis. Furthermore, popular brain MRI databases and deep learning tools are also introduced. The strength and weaknesses of different approaches are addressed, and challenges as well as future directions are also discussed.

Autoencoder as a New Method for Maintaining Data Privacy While Analyzing Videos of Patients With Motor Dysfunction: Proof-of-Concept Study

Background

In chronic neurological diseases, especially in multiple sclerosis (MS), clinical assessment of motor dysfunction is crucial to monitor the disease in patients. Traditional scales are not sensitive enough to detect slight changes. Video recordings of patient performance are more accurate and increase the reliability of severity ratings. When these recordings are automated, quantitative disability assessments by machine learning algorithms can be created. Creation of these algorithms involves non–health care professionals, which is a challenge for maintaining data privacy. However, autoencoders can address this issue.

Objective

The aim of this proof-of-concept study was to test whether coded frame vectors of autoencoders contain relevant information for analyzing videos of the motor performance of patients with MS.

Methods

In this study, 20 pre-rated videos of patients performing the finger-to-nose test were recorded. An autoencoder created encoded frame vectors from the original videos and decoded the videos again. The original and decoded videos were shown to 10 neurologists at an academic MS center in Basel, Switzerland. The neurologists tested whether the 200 videos were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-Expanded Disability Status Scale definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between the original and decoded videos.

Results

In total, 172 of 200 (86.0%) videos were of sufficient quality to be ratable. The intrarater agreement between the original and decoded videos was 0.317 (Cohen weighted kappa). The average difference in the ratings between the original and decoded videos was 0.26, in which the original videos were rated as more severe. The interrater agreement between the original videos was 0.459 and that between the decoded videos was 0.302. The agreement was higher when no deficits or very severe deficits were present.

Conclusions

The vast majority of videos (172/200, 86.0%) decoded by the autoencoder contained clinically relevant information and had fair intrarater agreement with the original videos. Autoencoders are a potential method for enabling the use of patient videos while preserving data privacy, especially when non–health-care professionals are involved.