Multisite generalizability of schizophrenia diagnosis classification based on functional brain connectivity

Diagnosing schizophrenia using deep learning: Novel interpretation approaches and multi-site validation

Schizophrenia is a profound and enduring mental disorder that imposes significant negative impacts on individuals, their families, and society at large. The development of more accurate and objective diagnostic tools for schizophrenia can be expedited through the employment of deep learning (DL), that excels at deciphering complex hierarchical non-linear patterns. However, the limited interpretability of deep learning has eroded confidence in the model and restricted its clinical utility. At the same time, if the data source is only derived from a single center, the model's generalizability is difficult to test. To enhance the model's reliability and applicability, leave-one-center-out validation with a large and diverse sample from multiple centers is crucial. In this study, we utilized Nine different global centers to train and test the 3D Resnet model's generalizability, resulting in an 82% classification performance (area under the curve) on all datasets sourced from different countries, employing a leave-one-center-out-validation approach. Per our approximation of the feature significance of each region on the atlas, we identified marked differences in the thalamus, pallidum, and inferior frontal gyrus between individuals with schizophrenia and healthy controls, lending credence to prior research findings. At the same time, in order to translate the model's output into clinically applicable insights, the SHapley Additive exPlanations (SHAP) permutation explainer method with an anatomical atlas have been refined, thereby offering precise neuroanatomical and functional interpretations of different brain regions.

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

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

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

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

Assisting schizophrenia diagnosis using clinical electroencephalography and interpretable graph neural networks: a real-world and cross-site study

Schizophrenia (SCZ) is a chronic and serious mental disorder with a high mortality rate. At present, there is a lack of objective, cost-effective and widely disseminated diagnosis tools to address this mental health crisis globally. Clinical electroencephalogram (EEG) is a noninvasive technique to measure brain activity with high temporal resolution, and accumulating evidence demonstrates that clinical EEG is capable of capturing abnormal SCZ neuropathology. Although EEG-based automated diagnostic tools have obtained impressive performance on individual datasets, the transportability of potential EEG biomarkers in cross-site real-world application is still an open question. To address the challenges of small sample sizes and population heterogeneity, we develop an advanced interpretable deep learning model using multimodal clinical EEG features and demographic information as inputs to graph neural networks, and further propose different transfer learning strategies to adapt to different clinical scenarios. Taking the disease discrimination of health control (HC) and SCZ with 1030 participants as a use case, our model is trained on a small clinical dataset (N = 188, Chinese) and enhanced using a large-scale public dataset (N = 508, American) of adult participants. Cross-site validation from an independent dataset of adult participants (N = 157, Chinese) produced stable performance, with AUCs of 0.793-0.852 and accuracies of 0.786-0.858 for different SCZ prevalence, respectively. In addition, cross-site validation from another dataset of adolescent boys (N = 84, Russian) yielded an AUC of 0.702 and an accuracy of 0.690. Moreover, feature visualization further revealed that the ranking of feature importance varied significantly among different datasets, and that EEG theta and alpha band power appeared to be the most significant and translational biomarkers of SCZ pathology. Overall, our promising results demonstrate the feasibility of SCZ discrimination using EEG biomarkers in multiple clinical settings.

A neuromarker for deficit syndrome in schizophrenia from a combination of structural and functional magnetic resonance imaging

AIM

Deficit schizophrenia (DS), defined by primary and enduring negative symptoms, has been proposed as a promising homogeneous subtype of schizophrenia. It has been demonstrated that unimodal neuroimaging characteristics of DS were different from non-deficit schizophrenia (NDS), however, whether multimodal-based neuroimaging features could identify deficit syndrome remains to be determined.

METHODS

Functional and structural multimodal magnetic resonance imaging of DS, NDS and healthy controls were scanned. Voxel-based features of gray matter volume, fractional amplitude of low-frequency fluctuations, and regional homogeneity were extracted. The support vector machine classification models were constructed using these features separately and jointly. The most discriminative features were defined as the first 10% of features with the greatest weights. Moreover, relevance vector regression was applied to explore the predictive values of these top-weighted features in predicting negative symptoms.

RESULTS

The multimodal classifier achieved a higher accuracy (75.48%) compared with the single modal model in distinguishing DS from NDS. The most predictive brain regions were mainly located in the default mode and visual networks, exhibiting differences between functional and structural features. Further, the identified discriminative features significantly predicted scores of diminished expressivity factor in DS but not NDS.

CONCLUSIONS

The present study demonstrated that local properties of brain regions extracted from multimodal imaging data could distinguish DS from NDS with a machine learning-based approach and confirmed the relationship between distinctive features and the negative symptoms subdomain. These findings may improve the identification of potential neuroimaging signatures and improve the clinical assessment of the deficit syndrome.

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.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Neuroimaging biomarkers for detecting schizophrenia: A resting-state functional MRI-based radiomics analysis

Schizophrenia (SZ) is a common psychiatric disorder that is difficult to accurately diagnose in clinical practice. Quantifiable biomarkers are urgently required to explore the potential physiological mechanism of SZ and improve its diagnostic accuracy. Thus, this study aimed to identify biomarkers that classify SZ patients and healthy control subjects and investigate the potential neural mechanisms of SZ using degree centrality (DC)- and voxel-mirrored homotopic connectivity (VMHC)-based radiomics. Radiomics features were extracted from DC and VMHC metrics generated via resting-state functional magnetic resonance imaging, and significant features were selected and dimensionality was reduced using t-tests and least absolute shrinkage and selection operator. Subsequently, we built our model using a support vector machine classifier. We observed that our method obtained great classification performance (area under the curve, 0.808; accuracy, 74.02%), and it could be generalized to different brain atlases. The regions that we identified as discriminative features mainly included bilateral dorsal caudate and front-parietal, somatomotor, limbic, and default mode networks. Our findings showed that the radiomics-based machine learning method could facilitate us to understand the potential pathological mechanism of SZ more comprehensively and contribute to the accurate diagnosis of patients with SZ.

Predicting future cognitive decline from non-brain and multimodal brain imaging data in healthy and pathological aging

Previous literature has focused on predicting a diagnostic label from structural brain imaging. Since subtle changes in the brain precede a cognitive decline in healthy and pathological aging, our study predicts future decline as a continuous trajectory instead. Here, we tested whether baseline multimodal neuroimaging data improve the prediction of future cognitive decline in healthy and pathological aging. Nonbrain data (demographics, clinical, and neuropsychological scores), structural MRI, and functional connectivity data from OASIS-3 (N = 662; age = 46-96 years) were entered into cross-validated multitarget random forest models to predict future cognitive decline (measured by CDR and MMSE), on average 5.8 years into the future. The analysis was preregistered, and all analysis code is publicly available. Combining non-brain with structural data improved the continuous prediction of future cognitive decline (best test-set performance: R2 = 0.42). Cognitive performance, daily functioning, and subcortical volume drove the performance of our model. Including functional connectivity did not improve predictive accuracy. In the future, the prognosis of age-related cognitive decline may enable earlier and more effective individualized cognitive, pharmacological, and behavioral interventions.

Exploring neurometabolic alterations in bipolar disorder with suicidal ideation based on proton magnetic resonance spectroscopy and machine learning technology

Bipolar disorder (BD) is associated with a high risk of suicide. We used proton magnetic resonance spectroscopy (1H-MRS) to detect biochemical metabolite ratios in the bilateral prefrontal white matter (PWM) and hippocampus in 32 BD patients with suicidal ideation (SI) and 18 BD patients without SI, identified potential brain biochemical differences and used abnormal metabolite ratios to predict the severity of suicide risk based on the support vector machine (SVM) algorithm. Furthermore, we analyzed the correlations between biochemical metabolites and clinical variables in BD patients with SI. There were three main findings: (1) the highest classification accuracy of 88% and an area under the curve of 0.9 were achieved in distinguishing BD patients with and without SI, with N-acetyl aspartate (NAA)/creatine (Cr), myo-inositol (mI)/Cr values in the bilateral PWM, NAA/Cr and choline (Cho)/Cr values in the left hippocampus, and Cho/Cr values in the right hippocampus being the features contributing the most; (2) the above seven features could be used to predict Self-rating Idea of Suicide Scale scores (r = 0.4261, p = 0.0302); and (3) the level of neuronal function in the left hippocampus may be related to the duration of illness, the level of membrane phospholipid catabolism in the left hippocampus may be related to the severity of depression, and the level of inositol metabolism in the left PWM may be related to the age of onset in BD patients with SI. Our results showed that the combination of multiple brain biochemical metabolites could better predict the risk and severity of suicide in patients with BD and that there was a significant correlation between biochemical metabolic values and clinical variables in BD patients with SI.

Evaluating the Performance of Machine Learning Models for Automatic Diagnosis of Patients with Schizophrenia Based on a Single Site Dataset of 440 Participants

Background

Methods

Results

Conclusions

Large, open datasets for human connectomics research: Considerations for reproducible and responsible data use

Large, open datasets have emerged as important resources in the field of human connectomics. In this review, the evolution of data sharing involving magnetic resonance imaging is described. A summary of the challenges and progress in conducting reproducible data analyses is provided, including description of recent progress made in the development of community guidelines and recommendations, software and data management tools, and initiatives to enhance training and education. Finally, this review concludes with a discussion of ethical conduct relevant to analyses of large, open datasets and a researcher's responsibility to prevent further stigmatization of historically marginalized racial and ethnic groups. Moving forward, future work should include an enhanced emphasis on the social determinants of health, which may further contextualize findings among diverse population-based samples. Leveraging the progress to date and guided by interdisciplinary collaborations, the future of connectomics promises to be an impressive era of innovative research, yielding a more inclusive understanding of brain structure and function.

Machine Learning of Schizophrenia Detection with Structural and Functional Neuroimaging

Schizophrenia (SZ) is a severe psychiatric illness, and it affects around 1% of the general population; however, its reliable diagnosis is challenging. Functional MRI (fMRI) and structural MRI (sMRI) are useful techniques for investigating the functional and structural abnormalities of the human brain, and a growing number of studies have reported that multimodal brain data can improve diagnostic accuracy. Machine learning (ML) is widely used in the diagnosis of neuroscience and neuropsychiatry diseases, and it can obtain high accuracy. However, the conventional ML which concatenated the features into a longer feature vector could not be sufficiently effective to combine different features from different modalities. There are considerable controversies over the use of global signal regression (GSR), and few studies have explored the role of GSR in ML in diagnosing neurological diseases. The current study utilized fMRI and sMRI data to implement a new method named multimodal imaging and multilevel characterization with multiclassifier (M3) to classify SZs and healthy controls (HCs) and investigate the influence of GSR in SZ classification. We found that when we used Brainnetome 246 atlas and without performed GSR, our method obtained a classification accuracy of 83.49%, with a sensitivity of 68.69%, a specificity of 93.75%, and an AUC of 0.8491, respectively. We also got great classification performances with different processing methods (with/without GSR and different brain parcellation schemes). We found that the accuracy and specificity of the models without GSR were higher than that of the models with GSR. Our findings indicate that the M3 method is an effective tool to distinguish SZs from HCs, and it can identify discriminative regions to detect SZ to explore the neural mechanisms underlying SZ. The global signal may contain important neuronal information; it can improve the accuracy and specificity of SZ detection.

Functional Connectivity Alterations of the Temporal Lobe and Hippocampus in Semantic Dementia and Alzheimer's Disease

BACKGROUND

Semantic memory impairments in semantic dementia are attributed to atrophy and functional disruption of the anterior temporal lobes. In contrast, the posterior medial temporal neurodegeneration found in Alzheimer's disease is associated with episodic memory disturbance. The two dementia subtypes share hippocampal deterioration, despite a relatively spared episodic memory in semantic dementia.

OBJECTIVE

To unravel mutual and divergent functional alterations in Alzheimer's disease and semantic dementia, we assessed functional connectivity between temporal lobe regions in Alzheimer's disease (n = 16), semantic dementia (n = 23), and healthy controls (n = 17).

METHODS

In an exploratory study, we used a functional parcellation of the temporal cortex to extract time series from 66 regions for correlation analysis.

RESULTS

Apart from differing connections between Alzheimer's disease and semantic dementia that yielded reduced functional connectivity, we identified a common pathway between the right anterior temporal lobe and the right orbitofrontal cortex in both dementia subtypes. This disconnectivity might be related to social knowledge deficits as part of semantic memory decline. However, such interpretations are preferably made in a holistic context of disease-specific semantic impairments and functional connectivity changes.

CONCLUSION

Despite a major limitation owed to unbalanced databases between study groups, this study provides a preliminary picture of the brain's functional disconnectivity in Alzheimer's disease and semantic dementia. Future studies are needed to replicate findings of a common pathway with consistent diagnostic criteria and neuropsychological evaluation, balanced designs, and matched data MRI acquisition procedures.

Reducing Inter-Site Variability for Fluctuation Amplitude Metrics in Multisite Resting State BOLD-fMRI Data

It has been reported that resting state fluctuation amplitude (RSFA) exhibits extremely large inter-site variability, which limits its application in multisite studies. Although global normalization (GN) based approaches are efficient in reducing the site effects, they may cause spurious results. In this study, our purpose was to find alternative strategies to minimize the substantial site effects for RSFA, without the risk of introducing artificial findings. We firstly modified the ALFF algorithm so that it is conceptually validated and insensitive to data length, then found that (a) global mean amplitude of low-frequency fluctuation (ALFF) covaried only with BOLD signal intensity, while global mean fractional ALFF (fALFF) was significantly correlated with TRs across different sites; (b) The inter-site variations in raw RSFA values were significant across the entire brain and exhibited similar trends between gray matter and white matter; (c) For ALFF, signal intensity rescaling could dramatically reduce inter-site variability by several orders, but could not fully removed the globally distributed inter-site variability. For fALFF, the global site effects could be completely removed by TR controlling; (d) Meanwhile, the magnitude of the inter-site variability of fALFF could also be reduced to an acceptable level, as indicated by the detection power of fALFF in multisite data quite close to that in monosite data. Thus our findings suggest GN based harmonization methods could be replaced with only controlling for confounding factors including signal scaling, TR and full-band power.

A multiomics approach to heterogeneity in Alzheimer's disease: focused review and roadmap

Aetiological and clinical heterogeneity is increasingly recognized as a common characteristic of Alzheimer's disease and related dementias. This heterogeneity complicates diagnosis, treatment, and the design and testing of new drugs. An important line of research is discovery of multimodal biomarkers that will facilitate the targeting of subpopulations with homogeneous pathophysiological signatures. High-throughput 'omics' are unbiased data-driven techniques that probe the complex aetiology of Alzheimer's disease from multiple levels (e.g. network, cellular, and molecular) and thereby account for pathophysiological heterogeneity in clinical populations. This review focuses on data reduction analyses that identify complementary disease-relevant perturbations for three omics techniques: neuroimaging-based subtypes, metabolomics-derived metabolite panels, and genomics-related polygenic risk scores. Neuroimaging can track accrued neurodegeneration and other sources of network impairments, metabolomics provides a global small-molecule snapshot that is sensitive to ongoing pathological processes, and genomics characterizes relatively invariant genetic risk factors representing key pathways associated with Alzheimer's disease. Following this focused review, we present a roadmap for assembling these multiomics measurements into a diagnostic tool highly predictive of individual clinical trajectories, to further the goal of personalized medicine in Alzheimer's disease.

Gut microbiome-mediated epigenetic regulation of brain disorder and application of machine learning for multi-omics data analysis

The gut-brain axis (GBA) is a biochemical link that connects the central nervous system (CNS) and enteric nervous system (ENS). Clinical and experimental evidence suggests gut microbiota as a key regulator of the GBA. Microbes living in the gut not only interact locally with intestinal cells and the ENS but have also been found to modulate the CNS through neuroendocrine and metabolic pathways. Studies have also explored the involvement of gut microbiota dysbiosis in depression, anxiety, autism, stroke, and pathophysiology of other neurodegenerative diseases. Recent reports suggest that microbe-derived metabolites can influence host metabolism by acting as epigenetic regulators. Butyrate, an intestinal bacterial metabolite, is a known histone deacetylase inhibitor that has shown to improve learning and memory in animal models. Due to high disease variability amongst the population, a multi-omics approach that utilizes artificial intelligence and machine learning to analyze and integrate omics data is necessary to better understand the role of the GBA in pathogenesis of neurological disorders, to generate predictive models, and to develop precise and personalized therapeutics. This review examines our current understanding of epigenetic regulation of the GBA and proposes a framework to integrate multi-omics data for prediction, prevention, and development of precision health approaches to treat brain disorders.

Overlapping but Asymmetrical Relationships Between Schizophrenia and Autism Revealed by Brain Connectivity

Although the relationship between schizophrenia spectrum disorder (SSD) and autism spectrum disorder (ASD) has long been debated, it has not yet been fully elucidated. The authors quantified and visualized the relationship between ASD and SSD using dual classifiers that discriminate patients from healthy controls (HCs) based on resting-state functional connectivity magnetic resonance imaging. To develop a reliable SSD classifier, sophisticated machine-learning algorithms that automatically selected SSD-specific functional connections were applied to Japanese datasets from Kyoto University Hospital (N = 170) including patients with chronic-stage SSD. The generalizability of the SSD classifier was tested by 2 independent validation cohorts, and 1 cohort including first-episode schizophrenia. The specificity of the SSD classifier was tested by 2 Japanese cohorts of ASD and major depressive disorder. The weighted linear summation of the classifier's functional connections constituted the biological dimensions representing neural classification certainty for the disorders. Our previously developed ASD classifier was used as ASD dimension. Distributions of individuals with SSD, ASD, and HCs s were examined on the SSD and ASD biological dimensions. We found that the SSD and ASD populations exhibited overlapping but asymmetrical patterns in the 2 biological dimensions. That is, the SSD population showed increased classification certainty for the ASD dimension but not vice versa. Furthermore, the 2 dimensions were correlated within the ASD population but not the SSD population. In conclusion, using the 2 biological dimensions based on resting-state functional connectivity enabled us to discover the quantified relationships between SSD and ASD.

Disrupted pathways from limbic areas to thalamus in schizophrenia highlighted by whole-brain resting-state effective connectivity analysis

BACKGROUND

Numerous neuroimaging studies have revealed that schizophrenia was characterized by wide-spread dysconnection among brain regions during rest measured by functional connectivity (FC). In contrast with FC, effective connectivity (EC) provides information about directionality of brain connections and is thus valuable in mechanistic investigation of schizophrenic brain. However, a systematic characterization of whole-brain resting-state EC (rsEC) and how it captures different information compared with resting-state FC (rsFC) in schizophrenia are still lacking.

AIMS

To systematically characterize the abnormalities of rsEC, compared with rsFC, in schizophrenia, and to test its discriminative power as a neuroimaging marker for schizophrenia diagnosis.

METHOD

Whole-brain rsEC and rsFC networks were constructed using resting-state fMRI data and compared between 103 patients with schizophrenia and 110 healthy participants. Pattern classifications between patients and controls based on whole-brain rsEC and rsFC were further performed using multivariate pattern analysis.

RESULTS

We identified 17 rsEC significantly disrupted (mostly decreased) in patients, among which all were associated with the thalamus and 15 were from limbic areas (including hippocampus, parahippocampus and cingulate cortex) to the thalamus. In contrast, abnormal rsFC were widely distributed in the whole brain. The classification accuracies for distinguishing patients and controls using whole-brain rsEC and rsFC patterns were 78.6% and 82.7%, respectively, and was further improved to 84.5% when combining rsEC and rsFC.

CONCLUSIONS

Schizophrenia is featured by disrupted 'limbic areas-to-thalamus' rsEC, in contrast with diffusively altered rsFC. Moreover, both rsEC and rsFC contain valuable and complementary information which may be used as diagnostic markers for schizophrenia.

Neurobiological Divergence of the Positive and Negative Schizophrenia Subtypes Identified on a New Factor Structure of Psychopathology Using Non-negative Factorization: An International Machine Learning Study

BACKGROUND

Disentangling psychopathological heterogeneity in schizophrenia is challenging, and previous results remain inconclusive. We employed advanced machine learning to identify a stable and generalizable factorization of the Positive and Negative Syndrome Scale and used it to identify psychopathological subtypes as well as their neurobiological differentiations.

METHODS

Positive and Negative Syndrome Scale data from the Pharmacotherapy Monitoring and Outcome Survey cohort (1545 patients; 586 followed up after 1.35 ± 0.70 years) were used for learning the factor structure by an orthonormal projective non-negative factorization. An international sample, pooled from 9 medical centers across Europe, the United States, and Asia (490 patients), was used for validation. Patients were clustered into psychopathological subtypes based on the identified factor structure, and the neurobiological divergence between the subtypes was assessed by classification analysis on functional magnetic resonance imaging connectivity patterns.

RESULTS

A 4-factor structure representing negative, positive, affective, and cognitive symptoms was identified as the most stable and generalizable representation of psychopathology. It showed higher internal consistency than the original Positive and Negative Syndrome Scale subscales and previously proposed factor models. Based on this representation, the positive-negative dichotomy was confirmed as the (only) robust psychopathological subtypes, and these subtypes were longitudinally stable in about 80% of the repeatedly assessed patients. Finally, the individual subtype could be predicted with good accuracy from functional connectivity profiles of the ventromedial frontal cortex, temporoparietal junction, and precuneus.

CONCLUSIONS

Machine learning applied to multisite data with cross-validation yielded a factorization generalizable across populations and medical systems. Together with subtyping and the demonstrated ability to predict subtype membership from neuroimaging data, this work further disentangles the heterogeneity in schizophrenia.

Application of Support Vector Machine on fMRI Data as Biomarkers in Schizophrenia Diagnosis: A Systematic Review

Non-invasive measurements of brain function and structure as neuroimaging in patients with mental illnesses are useful and powerful tools for studying discriminatory biomarkers. To date, functional MRI (fMRI), structural MRI (sMRI) represent the most used techniques to provide multiple perspectives on brain function, structure, and their connectivity. Recently, there has been rising attention in using machine-learning (ML) techniques, pattern recognition methods, applied to neuroimaging data to characterize disease-related alterations in brain structure and function and to identify phenotypes, for example, for translation into clinical and early diagnosis. Our aim was to provide a systematic review according to the PRISMA statement of Support Vector Machine (SVM) techniques in making diagnostic discrimination between SCZ patients from healthy controls using neuroimaging data from functional MRI as input. We included studies using SVM as ML techniques with patients diagnosed with Schizophrenia. From an initial sample of 660 papers, at the end of the screening process, 22 articles were selected, and included in our review. This technique can be a valid, inexpensive, and non-invasive support to recognize and detect patients at an early stage, compared to any currently available assessment or clinical diagnostic methods in order to save crucial time. The higher accuracy of SVM models and the new integrated methods of ML techniques could play a decisive role to detect patients with SCZ or other major psychiatric disorders in the early stages of the disease or to potentially determine their neuroimaging risk factors in the near future.

Generalizability of machine learning for classification of schizophrenia based on resting-state functional MRI data

Machine learning has increasingly been applied to classification of schizophrenia in neuroimaging research. However, direct replication studies and studies seeking to investigate generalizability are scarce. To address these issues, we assessed within-site and between-site generalizability of a machine learning classification framework which achieved excellent performance in a previous study using two independent resting-state functional magnetic resonance imaging data sets collected from different sites and scanners. We established within-site generalizability of the classification framework in the main data set using cross-validation. Then, we trained a model in the main data set and investigated between-site generalization in the validated data set using external validation. Finally, recognizing the poor between-site generalization performance, we updated the unsupervised algorithm to investigate if transfer learning using additional unlabeled data were able to improve between-site classification performance. Cross-validation showed that the published classification procedure achieved an accuracy of 0.73 using majority voting across all selected components. External validation found a classification accuracy of 0.55 (not significant) and 0.70 (significant) using the direct and transfer learning procedures, respectively. The failure of direct generalization from one site to another demonstrates the limitation of within-site cross-validation and points toward the need to incorporate efforts to facilitate application of machine learning across multiple data sets. The improvement in performance with transfer learning highlights the importance of taking into account the properties of data when constructing predictive models across samples and sites. Our findings suggest that machine learning classification result based on a single study should be interpreted cautiously.

The Functional Brain Organization of an Individual Allows Prediction of Measures of Social Abilities Transdiagnostically in Autism and Attention-Deficit/Hyperactivity Disorder

BACKGROUND

Autism spectrum disorder and attention-deficit/hyperactivity disorder (ADHD) are associated with complex changes as revealed by functional magnetic resonance imaging. To date, neuroimaging-based models are not able to characterize individuals with sufficient sensitivity and specificity. Further, although evidence shows that ADHD traits occur in individuals with autism spectrum disorder, and autism spectrum disorder traits in individuals with ADHD, the neurofunctional basis of the overlap is undefined.

METHODS

Using individuals from the Autism Brain Imaging Data Exchange and ADHD-200, we apply a data-driven, subject-level approach, connectome-based predictive modeling, to resting-state functional magnetic resonance imaging data to identify brain-behavior associations that are predictive of symptom severity. We examine cross-diagnostic commonalities and differences.

RESULTS

Using leave-one-subject-out and split-half analyses, we define networks that predict Social Responsiveness Scale, Autism Diagnostic Observation Schedule, and ADHD Rating Scale scores and confirm that these networks generalize to novel subjects. Networks share minimal overlap of edges (<2%) but some common regions of high hubness (Brodmann areas 10, 11, and 21, cerebellum, and thalamus). Further, predicted Social Responsiveness Scale scores for individuals with ADHD are linked to ADHD symptoms, supporting the hypothesis that brain organization relevant to autism spectrum disorder severity shares a component associated with attention in ADHD. Predictive connections and high-hubness regions are found within a wide range of brain areas and across conventional networks.

CONCLUSIONS

An individual's functional connectivity profile contains information that supports dimensional, nonbinary classification in autism spectrum disorder and ADHD. Furthermore, we can determine disorder-specific and shared neurofunctional pathology using our method.

Harmonization of resting-state functional MRI data across multiple imaging sites via the separation of site differences into sampling bias and measurement bias

When collecting large amounts of neuroimaging data associated with psychiatric disorders, images must be acquired from multiple sites because of the limited capacity of a single site. However, site differences represent a barrier when acquiring multisite neuroimaging data. We utilized a traveling-subject dataset in conjunction with a multisite, multidisorder dataset to demonstrate that site differences are composed of biological sampling bias and engineering measurement bias. The effects on resting-state functional MRI connectivity based on pairwise correlations because of both bias types were greater than or equal to psychiatric disorder differences. Furthermore, our findings indicated that each site can sample only from a subpopulation of participants. This result suggests that it is essential to collect large amounts of neuroimaging data from as many sites as possible to appropriately estimate the distribution of the grand population. Finally, we developed a novel harmonization method that removed only the measurement bias by using a traveling-subject dataset and achieved the reduction of the measurement bias by 29% and improvement of the signal-to-noise ratios by 40%. Our results provide fundamental knowledge regarding site effects, which is important for future research using multisite, multidisorder resting-state functional MRI data.

Ten simple rules for predictive modeling of individual differences in neuroimaging

Establishing brain-behavior associations that map brain organization to phenotypic measures and generalize to novel individuals remains a challenge in neuroimaging. Predictive modeling approaches that define and validate models with independent datasets offer a solution to this problem. While these methods can detect novel and generalizable brain-behavior associations, they can be daunting, which has limited their use by the wider connectivity community. Here, we offer practical advice and examples based on functional magnetic resonance imaging (fMRI) functional connectivity data for implementing these approaches. We hope these ten rules will increase the use of predictive models with neuroimaging data.

Machine learning techniques in a structural and functional MRI diagnostic approach in schizophrenia: a systematic review

BACKGROUND

Diagnosis of schizophrenia (SCZ) is made exclusively clinically, since specific biomarkers that can predict the disease accurately remain unknown. Machine learning (ML) represents a promising approach that could support clinicians in the diagnosis of mental disorders.

OBJECTIVES

A systematic review, according to the PRISMA statement, was conducted to evaluate its accuracy to distinguish SCZ patients from healthy controls.

METHODS

We systematically searched PubMed, Embase, MEDLINE, PsychINFO and the Cochrane Library through December 2018 using generic terms for ML techniques and SCZ without language or time restriction. Thirty-five studies were included in this review: eight of them used structural neuroimaging, twenty-six used functional neuroimaging and one both, with a minimum accuracy >60% (most of them 75-90%). Sensitivity, Specificity and accuracy were extracted from each publication or obtained directly from authors.

RESULTS

Support vector machine, the most frequent technique, if associated with other ML techniques achieved accuracy close to 100%. The prefrontal and temporal cortices appeared to be the most useful brain regions for the diagnosis of SCZ. ML analysis can efficiently detect significantly altered brain connectivity in patients with SCZ (eg, default mode network, visual network, sensorimotor network, frontoparietal network and salience network).

CONCLUSION

The greater accuracy demonstrated by these predictive models and the new models resulting from the integration of multiple ML techniques will be increasingly decisive for early diagnosis and evaluation of the treatment response and to establish the prognosis of patients with SCZ. To achieve a real benefit for patients, the future challenge is to reach an accurate diagnosis not only through clinical evaluation but also with the aid of ML algorithms.

Cross-Validation of Functional MRI and Paranoid-Depressive Scale: Results From Multivariate Analysis

Introduction: There exists over the past decades a constant debate driven by controversies in the validity of psychiatric diagnosis. This debate is grounded in queries about both the validity and evidence strength of clinical measures. Materials and Methods: The objective of the study is to construct a bottom-up unsupervised machine learning approach, where the brain signatures identified by three principal components based on activations yielded from the three kinds of diagnostically relevant stimuli are used in order to produce cross-validation markers which may effectively predict the variance on the level of clinical populations and eventually delineate diagnostic and classification groups. The stimuli represent items from a paranoid-depressive self-evaluation scale, administered simultaneously with functional magnetic resonance imaging (fMRI). Results: We have been able to separate the two investigated clinical entities - schizophrenia and recurrent depression by use of multivariate linear model and principal component analysis. Following the individual and group MLM, we identified the three brain patterns that summarized all the individual variabilities of the individual brain patterns. Discussion: This is a confirmation of the possibility to achieve bottom-up classification of mental disorders, by use of the brain signatures relevant to clinical evaluation tests.

Identifying a neuroanatomical signature of schizophrenia, reproducible across sites and stages, using machine learning with structured sparsity

OBJECTIVE

Structural MRI (sMRI) increasingly offers insight into abnormalities inherent to schizophrenia. Previous machine learning applications suggest that individual classification is feasible and reliable and, however, is focused on the predictive performance of the clinical status in cross-sectional designs, which has limited biological perspectives. Moreover, most studies depend on relatively small cohorts or single recruiting site. Finally, no study controlled for disease stage or medication's effect. These elements cast doubt on previous findings' reproducibility.

METHOD

We propose a machine learning algorithm that provides an interpretable brain signature. Using large datasets collected from 4 sites (276 schizophrenia patients, 330 controls), we assessed cross-site prediction reproducibility and associated predictive signature. For the first time, we evaluated the predictive signature regarding medication and illness duration using an independent dataset of first-episode patients.

RESULTS

Machine learning classifiers based on neuroanatomical features yield significant intersite prediction accuracies (72%) together with an excellent predictive signature stability. This signature provides a neural score significantly correlated with symptom severity and the extent of cognitive impairments. Moreover, this signature demonstrates its efficiency on first-episode psychosis patients (73% accuracy).

CONCLUSION

These results highlight the existence of a common neuroanatomical signature for schizophrenia, shared by a majority of patients even from an early stage of the disorder.

Exploring the reproducibility of functional connectivity alterations in Parkinson's disease

Since anatomic MRI is presently not able to directly discern neuronal loss in Parkinson's Disease (PD), studying the associated functional connectivity (FC) changes seems a promising approach toward developing non-invasive and non-radioactive neuroimaging markers for this disease. While several groups have reported such FC changes in PD, there are also significant discrepancies between studies. Investigating the reproducibility of PD-related FC changes on independent datasets is therefore of crucial importance. We acquired resting-state fMRI scans for 43 subjects (27 patients and 16 normal controls, with 2 replicate scans per subject) and compared the observed FC changes with those obtained in two independent datasets, one made available by the PPMI consortium (91 patients, 18 controls) and a second one by the group of Tao Wu (20 patients, 20 controls). Unfortunately, PD-related functional connectivity changes turned out to be non-reproducible across datasets. This could be due to disease heterogeneity, but also to technical differences. To distinguish between the two, we devised a method to directly check for disease heterogeneity using random splits of a single dataset. Since we still observe non-reproducibility in a large fraction of random splits of the same dataset, we conclude that functional heterogeneity may be a dominating factor behind the lack of reproducibility of FC alterations in different rs-fMRI studies of PD. While global PD-related functional connectivity changes were non-reproducible across datasets, we identified a few individual brain region pairs with marginally consistent FC changes across all three datasets. However, training classifiers on each one of the three datasets to discriminate PD scans from controls produced only low accuracies on the remaining two test datasets. Moreover, classifiers trained and tested on random splits of the same dataset (which are technically homogeneous) also had low test accuracies, directly substantiating disease heterogeneity.