Can we accurately classify schizophrenia patients from healthy controls using magnetic resonance imaging and machine learning? A multi-method and multi-dataset study

Artificial intelligence in insanity evaluation. Potential opportunities and current challenges

The formulation of a scientific opinion on whether the individual who committed a crime should be held responsible for his/her actions or should be considered not responsible by reason of insanity is very difficult. Indeed, forensic psychopathological decision on insanity is highly prone to errors and is affected by human cognitive biases, resulting in low inter-rater reliability. In this context, artificial intelligence can be extremely useful to improve the inter-subjectivity of insanity evaluation. In this paper, we discuss the possible applications of artificial intelligence in this field as well as the challenges and pitfalls that hamper the effective implementation of AI in insanity evaluation. In particular, thus far, it is possible to apply only supervised algorithms without knowing which is the ground truth and which data should be used to train and test the algorithms. In addition, it is not known which percentage of accuracy of the algorithms is sufficient to support partial or total insanity, nor which are the boundaries between sanity and partial or total insanity. Finally, ethical aspects have not been sufficiently investigated. We conclude that these pitfalls should be resolved before AI can be safely and reliably applied in criminal trials.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Improved patient identification by incorporating symptom severity in deep learning using neuroanatomic images in first episode schizophrenia

Brain alterations associated with illness severity in schizophrenia remain poorly understood. Establishing linkages between imaging biomarkers and symptom expression may enhance mechanistic understanding of acute psychotic illness. Constructing models using MRI and clinical features together to maximize model validity may be particularly useful for these purposes. A multi-task deep learning model for standard case/control recognition incorporated with psychosis symptom severity regression was constructed with anatomic MRI collected from 286 patients with drug-naïve first-episode schizophrenia and 330 healthy controls from two datasets, and validated with an independent dataset including 40 first-episode schizophrenia. To evaluate the contribution of regression to the case/control recognition, a single-task classification model was constructed. Performance of unprocessed anatomical images and of predefined imaging features obtained using voxel-based morphometry (VBM) and surface-based morphometry (SBM), were examined and compared. Brain regions contributing to the symptom severity regression and illness identification were identified. Models developed with unprocessed images achieved greater group separation than either VBM or SBM measurements, differentiating schizophrenia patients from healthy controls with a balanced accuracy of 83.0% with sensitivity = 76.1% and specificity = 89.0%. The multi-task model also showed superior performance to single-task classification model without considering clinical symptoms. These findings showed high replication in the site-split validation and external validation analyses. Measurements in parietal, occipital and medial frontal cortex and bilateral cerebellum had the greatest contribution to the multi-task model. Incorporating illness severity regression in pattern recognition algorithms, our study developed an MRI-based model that was of high diagnostic value in acutely ill schizophrenia patients, highlighting clinical relevance of the model.

Consistent frontal-limbic-occipital connections in distinguishing treatment-resistant and non-treatment-resistant schizophrenia

BACKGROUND AND HYPOTHESIS

Treatment-resistant schizophrenia (TR-SZ) and non-treatment-resistant schizophrenia (NTR-SZ) lack specific biomarkers to distinguish from each other. This investigation aims to identify consistent dysfunctional brain connections with different atlases, multiple feature selection strategies, and several classifiers in distinguishing TR-SZ and NTR-SZ.

STUDY DESIGN

55 TR-SZs, 239 NTR-SZs, and 87 healthy controls (HCs) were recruited from the Affiliated Brain Hospital of Nanjing Medical University. Resting-state functional connection (FC) matrices were constructed from automated anatomical labeling (AAL), Yeo-Networks (YEO) and Brainnetome (BNA) atlases. Two feature selection methods (Select From Model and Recursive Feature Elimination) and four classifiers (Adaptive Boost, Bernoulli Naïve Bayes, Gradient Boosting and Random Forest) were combined to identify the consistent FCs in distinguishing TR-SZ and HC, NTR-SZ and HC, TR-SZ and NTR-SZ.

STUDY RESULTS

The whole brain FCs, except the temporal-occipital FC, were consistent in distinguishing SZ and HC. Abnormal frontal-limbic, frontal-parietal and occipital-temporal FCs were consistent in distinguishing TR-SZ and NTR-SZ, that were further correlated with disease progression, symptoms and medication dosage. Moreover, the frontal-limbic and frontal-parietal FCs were highly consistent for the diagnosis of SZ (TR-SZ vs. HC, NTR-SZ vs. HC and TR-SZ vs. NTR-SZ). The BNA atlas achieved the highest classification accuracy (>90 %) comparing with AAL and YEO in the most diagnostic tasks.

CONCLUSIONS

These results indicate that the frontal-limbic and the frontal-parietal FCs are the robust neural pathways in the diagnosis of SZ, whereas the frontal-limbic, frontal-parietal and occipital-temporal FCs may be informative in recognizing those TR-SZ in the clinical practice.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Aberrant inhibitory control as a transdiagnostic dimension of mental disorders - A meta-analysis of the antisaccade task in different psychiatric populations

This meta-analysis examined inhibitory control performance in the antisaccade task across mental disorders. Following PRISMA guidelines, we analyzed data from k = 146 studies (n = 13,807 participants) on antisaccade performance. Effect sizes were estimated using random-effects models and restricted maximum-likelihood estimation, with robustness tests for study heterogeneity and publication bias. Most disorders displayed elevated error rates, with schizophrenia showing the greatest impairments, followed by autism spectrum disorder, bipolar disorder and attention deficit hyperactivity disorder. Small to medium impairments were also found in eating disorders, major depressive disorder, obsessive-compulsive disorder and substance use disorder. Results were robust against corrections for publication bias and largely unaffected by confounding variables. Prolonged latencies were observed in schizophrenia, attention deficit hyperactivity disorder, bipolar disorder and obsessive compulsive disorder, with smaller and less robust effect sizes. Results indicate inhibitory control deficits in the antisaccade task across mental disorders, especially evident for error rates. While present in most disorders, results imply varying degrees of impairments, ranging from small to large in effect sizes, with largest impairments in schizophrenia.

Multi-Task Collaborative Pre-Training and Adaptive Token Selection: A Unified Framework for Brain Representation Learning

Structural magnetic resonance imaging (sMRI) reveals the structural organization of the brain. Learning general brain representations from sMRI is an enduring topic in neuroscience. Previous deep learning models neglect that the brain, as the core of cognition, is distinct from other organs whose primary attribute is anatomy. Capturing the high-level representation associated with inter-individual cognitive variability is key to appropriately represent the brain. Given that this cognition-related information is subtle, mixed, and distributed in the brain structure, sMRI-based models need to both capture fine-grained details and understand how they relate to the overall global structure. Additionally, it is also necessary to explicitly express the cognitive information that implicitly embedded in local-global image features. Therefore, we propose MCPATS, a brain representation learning framework that combines Multi-task Collaborative Pre-training (MCP) and Adaptive Token Selection (ATS). First, we develop MCP, including mask-reconstruction to understand global context, distort-restoration to capture fine-grained local details, adversarial learning to integrate features at different granularities, and age-prediction, using age as a surrogate for cognition to explicitly encode cognition-related information from local-global image features. This co-training allows progressive learning of implicit and explicit cognition-related representations. Then, we develop ATS based on mutual attention for downstream use of the learned representation. During fine-tuning, the ATS highlights discriminative features and reduces the impact of irrelevant information. MCPATS was validated on three different public datasets for brain disease diagnosis, outperforming competing methods and achieving accurate diagnosis. Further, we performed detailed analysis to confirm that the MCPATS-learned representation captures cognition-related information.

Unveiling Promising Neuroimaging Biomarkers for Schizophrenia Through Clinical and Genetic Perspectives

Schizophrenia is a complex and serious brain disorder. Neuroscientists have become increasingly interested in using magnetic resonance-based brain imaging-derived phenotypes (IDPs) to investigate the etiology of psychiatric disorders. IDPs capture valuable clinical advantages and hold biological significance in identifying brain abnormalities. In this review, we aim to discuss current and prospective approaches to identify potential biomarkers for schizophrenia using clinical multimodal neuroimaging and imaging genetics. We first described IDPs through their phenotypic classification and neuroimaging genomics. Secondly, we discussed the applications of multimodal neuroimaging by clinical evidence in observational studies and randomized controlled trials. Thirdly, considering the genetic evidence of IDPs, we discussed how can utilize neuroimaging data as an intermediate phenotype to make association inferences by polygenic risk scores and Mendelian randomization. Finally, we discussed machine learning as an optimum approach for validating biomarkers. Together, future research efforts focused on neuroimaging biomarkers aim to enhance our understanding of schizophrenia.

Schizophrenia diagnosis based on diverse epoch size resting-state EEG using machine learning

Schizophrenia is a severe mental disorder that impairs a person's mental, social, and emotional faculties gradually. Detection in the early stages with an accurate diagnosis is crucial to remedying the patients. This study proposed a new method to classify schizophrenia disease in the rest state based on neurologic signals achieved from the brain by electroencephalography (EEG). The datasets used consisted of 28 subjects, 14 for each group, which are schizophrenia and healthy control. The data was collected from the scalps with 19 EEG channels using a 250 Hz frequency. Due to the brain signal variation, we have decomposed the EEG signals into five sub-bands using a band-pass filter, ensuring the best signal clarity and eliminating artifacts. This work was performed with several scenarios: First, traditional techniques were applied. Secondly, augmented data (additive white Gaussian noise and stretched signals) were utilized. Additionally, we assessed Minimum Redundancy Maximum Relevance (MRMR) as the features reduction method. All these data scenarios are applied with three different window sizes (epochs): 1, 2, and 5 s, utilizing six algorithms to extract features: Fast Fourier Transform (FFT), Approximate Entropy (ApEn), Log Energy entropy (LogEn), Shannon Entropy (ShnEn), and kurtosis. The L2-normalization method was applied to the derived features, positively affecting the results. In terms of classification, we applied four algorithms: K-nearest neighbor (KNN), support vector machine (SVM), quadratic discriminant analysis (QDA), and ensemble classifier (EC). From all the scenarios, our evaluation showed that SVM had remarkable results in all evaluation metrics with LogEn features utilizing a 1-s window size, impacting the diagnosis of Schizophrenia disease. This indicates that an accurate diagnosis of schizophrenia can be achieved through the right features and classification model selection. Finally, we contrasted our results to recently published works using the same and a different dataset, where our method showed a notable improvement.

Distinguishing schizophrenia and bipolar disorder through a Multiclass Classification model based on multimodal neuroimaging data

This study aimed to identify neural biomarkers for schizophrenia (SZ) and bipolar disorder (BP) by analyzing multimodal neuroimaging. Utilizing data from structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and resting-state functional magnetic resonance imaging (rs-fMRI), multiclass classification models were created for SZ, BP, and healthy controls (HC). A total of 113 participants (BP: 31, SZ: 39, and HC: 43) were recruited under strict enrollment control, from which 272, 200, and 1875 features were extracted from sMRI, DTI, and rs-fMRI data, respectively. A support vector machine (SVM) with recursive feature elimination (RFE) was employed to build the models using a one-against-one approach and leave-one-out cross-validation, achieving a classification accuracy of 70.8%. The most discriminative features were primarily from rs-fMRI, along with significant findings in sMRI and DTI. Key biomarkers identified included the increased thickness of the left cuneus cortex and decreased regional functional connectivity strength (rFCS) in the left supramarginal gyrus as shared indicators for BP and SZ. Additionally, decreased fractional anisotropy in the left superior fronto-occipital fasciculus was suggested as specific to BP, while decreased rFCS in the left inferior parietal area might serve as a specific biomarker for SZ. These findings underscore the potential of multimodal neuroimaging in distinguishing between BP and SZ and contribute to the understanding of their neural underpinnings.

Detecting schizophrenia with 3D structural brain MRI using deep learning

Schizophrenia is a chronic neuropsychiatric disorder that causes distinct structural alterations within the brain. We hypothesize that deep learning applied to a structural neuroimaging dataset could detect disease-related alteration and improve classification and diagnostic accuracy. We tested this hypothesis using a single, widely available, and conventional T1-weighted MRI scan, from which we extracted the 3D whole-brain structure using standard post-processing methods. A deep learning model was then developed, optimized, and evaluated on three open datasets with T1-weighted MRI scans of patients with schizophrenia. Our proposed model outperformed the benchmark model, which was also trained with structural MR images using a 3D CNN architecture. Our model is capable of almost perfectly (area under the ROC curve = 0.987) distinguishing schizophrenia patients from healthy controls on unseen structural MRI scans. Regional analysis localized subcortical regions and ventricles as the most predictive brain regions. Subcortical structures serve a pivotal role in cognitive, affective, and social functions in humans, and structural abnormalities of these regions have been associated with schizophrenia. Our finding corroborates that schizophrenia is associated with widespread alterations in subcortical brain structure and the subcortical structural information provides prominent features in diagnostic classification. Together, these results further demonstrate the potential of deep learning to improve schizophrenia diagnosis and identify its structural neuroimaging signatures from a single, standard T1-weighted brain MRI.

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

Supervised machine learning classification of psychosis biotypes based on brain structure: findings from the Bipolar-Schizophrenia network for intermediate phenotypes (B-SNIP)

Traditional diagnostic formulations of psychotic disorders have low correspondence with underlying disease neurobiology. This has led to a growing interest in using brain-based biomarkers to capture biologically-informed psychosis constructs. Building upon our prior work on the B-SNIP Psychosis Biotypes, we aimed to examine whether structural MRI (an independent biomarker not used in the Biotype development) can effectively classify the Biotypes. Whole brain voxel-wise grey matter density (GMD) maps from T1-weighted images were used to train and test (using repeated randomized train/test splits) binary L2-penalized logistic regression models to discriminate psychosis cases (n = 557) from healthy controls (CON, n = 251). A total of six models were evaluated across two psychosis categorization schemes: (i) three Biotypes (B1, B2, B3) and (ii) three DSM diagnoses (schizophrenia (SZ), schizoaffective (SAD) and bipolar (BD) disorders). Above-chance classification accuracies were observed in all Biotype (B1 = 0.70, B2 = 0.65, and B3 = 0.56) and diagnosis (SZ = 0.64, SAD = 0.64, and BD = 0.59) models. However, the only model that showed evidence of specificity was B1, i.e., the model was able to discriminate B1 vs. CON and did not misclassify other psychosis cases (B2 or B3) as B1 at rates above nominal chance. The GMD-based classifier evidence for B1 showed a negative association with an estimate of premorbid general intellectual ability, regardless of group membership, i.e. psychosis or CON. Our findings indicate that, complimentary to clinical diagnoses, the B-SNIP Psychosis Biotypes may offer a promising approach to capture specific aspects of psychosis neurobiology.

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.

Predicting firm creation in rural Texas: A multi-model machine learning approach to a complex policy problem

Rural and urban America have becoming increasingly divided, both politically and economically. Entrepreneurship can help rural communities catch back up by jumpstarting economic growth, creating jobs, and building resilience to economic shocks. However, less is known about firm creation in rural areas compared to urban areas. To that end, in this paper we ask: What factors predict firm creation in rural America? Our analysis, based on a comparative framework involving multiple machine learning modeling techniques, helps addresses three gaps in academic literature on rural firm creation. First, entrepreneurship research stretches across disciplines, often using econometric methods to identify the effect of a specific variable, rather than comparing the predictive importance of multiple variables. Second, research on firm creation centers on high-tech, urban firms. Third, modern machine learning techniques have not yet been applied in an integrated way to address rural entrepreneurship, a complex economic and policy problem that defies simple, monocausal claims. In this paper, we apply four machine learning methods (subset selection, lasso, random forest, and extreme gradient boosting) to a novel dataset to examine what social and economic factors are predictive of firm growth in rural Texas counties from 2008-2018. Our results suggest that some factors commonly discussed as promoting entrepreneurship (e.g., access to broadband and patents) may not be as predictive as socioeconomic ones (age distribution, ethnic diversity, social capital, and immigration). We also find that the strength of specific industries (oil, wind, healthcare, and elder/childcare) predicts firm growth, as does the number of local banks. Most factors predictive of firm growth in rural counties are distinct from those in urban counties, supporting the argument that rural entrepreneurship is a distinct phenomenon worthy of distinct focus. More broadly, this multi-model approach can offer initial, focusing guidance to policymakers seeking to address similarly complex policy problems.

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.

Applications of Deep Learning to Neurodevelopment in Pediatric Imaging: Achievements and Challenges

Deep learning has achieved remarkable progress, particularly in neuroimaging analysis. Deep learning applications have also been extended from adult to pediatric medical images, and thus, this paper aims to present a systematic review of this recent research. We first introduce the commonly used deep learning methods and architectures in neuroimaging, such as convolutional neural networks, auto-encoders, and generative adversarial networks. A non-exhaustive list of commonly used publicly available pediatric neuroimaging datasets and repositories are included, followed by a categorical review of recent works in pediatric MRI-based deep learning studies in the past five years. These works are categorized into recognizing neurodevelopmental disorders, identifying brain and tissue structures, estimating brain age/maturity, predicting neurodevelopment outcomes, and optimizing MRI brain imaging and analysis. Finally, we also discuss the recent achievements and challenges on these applications of deep learning to pediatric neuroimaging.

Effects of randomness in the development of machine learning models in neuroimaging studies of schizophrenia

Numerous studies have used machine learning with neuroimaging data for identifying individuals with a schizophrenia diagnosis. However, inconsistent results have limited the ability of the psychiatric community to objectively judge and accept the value of this approach. One factor that has contributed to the inconsistency, but has long been ignored, is randomness in the practice of machine learning. This is manifest when executing the same machine learning pipeline multiple times on the same dataset but getting different results. In the current study, a dataset of anatomical MRI scans from 158 patients with first-episode medication-naïve schizophrenia and 166 matched controls was used to investigate the effect of randomness on classifier performance estimates under different algorithm complexity and data splitting ratios. The maximum discriminatory accuracy that could be reached was 62.6 % ± 4.7 % (43.5 %-79.3 %) obtained when using extra-trees classifiers without feature normalization. Regions contributing to discrimination were located at bilateral temporal lobes and right frontal lobe. The results show that randomness has a significant impact on the precision of model performance estimates, especially when the size of test set is small. Current neuroimaging feature engineering combined with machine learning still falls short of being able to make diagnoses in the clinical context, but has value in revealing patterns of regional brain alteration associated with the illness. The current results indicate that effects of randomness on model performance should be reported and considered in interpreting model utility and it is necessary to evaluate models on large test sets to obtain valid estimates of model performance.

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.

Application of machine learning methods in predicting schizophrenia and bipolar disorders: A systematic review

Background and Aim

Schizophrenia and bipolar disorder (BD) are critical and high-risk inherited mental disorders with debilitating symptoms. Worldwide, 3% of the population suffers from these disorders. The mortality rate of these patients is higher compared to other people. Current procedures cannot effectively diagnose these disorders because it takes an average of 10 years from the onset of the first symptoms to the definitive diagnosis of the disease. Machine learning (ML) techniques are used to meet this need. This study aimed to summarize information on the use of ML techniques for predicting schizophrenia and BD to help early and timely diagnosis of the disease.

Methods

A systematic literature search included articles published until January 19, 2020 in 3 databases. Two reviewers independently assessed original papers to determine eligibility for inclusion in this review. PRISMA guidelines were followed to conduct the study, and the Prediction Model Risk of Bias Assessment Tool (PROBAST) to assess included papers.

Results

In this review, 1243 papers were retrieved through database searches, of which 15 papers were included based on full-text assessment. ML techniques were used to predict schizophrenia and BDs. The main algorithms applied were support vector machine (SVM) (10 studies), random forests (RF) (5 studies), and gradient boosting (GB) (3 studies). Input and output characteristics were very diverse and have been kept to enable future research. RFs algorithms demonstrated significantly higher accuracy and sensitivity than SVM and GB. GB demonstrated significantly higher specificity than SVM and RF. We found no significant difference between RF and SVM in terms of specificity.

Conclusion

ML can precisely predict results and assist in making clinical decisions-concerning schizophrenia and BD. RF often performed better than other algorithms in supervised learning tasks. This study identified gaps in the literature and opportunities for future psychological ML research.

Could psychedelic drugs have a role in the treatment of schizophrenia? Rationale and strategy for safe implementation

Schizophrenia is a widespread psychiatric disorder that affects 0.5-1.0% of the world's population and induces significant, long-term disability that exacts high personal and societal cost. Negative symptoms, which respond poorly to available antipsychotic drugs, are the primary cause of this disability. Association of negative symptoms with cortical atrophy and cell loss is widely reported. Psychedelic drugs are undergoing a significant renaissance in psychiatric disorders with efficacy reported in several conditions including depression, in individuals facing terminal cancer, posttraumatic stress disorder, and addiction. There is considerable evidence from preclinical studies and some support from human studies that psychedelics enhance neuroplasticity. In this Perspective, we consider the possibility that psychedelic drugs could have a role in treating cortical atrophy and cell loss in schizophrenia, and ameliorating the negative symptoms associated with these pathological manifestations. The foremost concern in treating schizophrenia patients with psychedelic drugs is induction or exacerbation of psychosis. We consider several strategies that could be implemented to mitigate the danger of psychotogenic effects and allow treatment of schizophrenia patients with psychedelics to be implemented. These include use of non-hallucinogenic derivatives, which are currently the focus of intense study, implementation of sub-psychedelic or microdosing, harnessing of entourage effects in extracts of psychedelic mushrooms, and blocking 5-HT2A receptor-mediated hallucinogenic effects. Preclinical studies that employ appropriate animal models are a prerequisite and clinical studies will need to be carefully designed on the basis of preclinical and translational data. Careful research in this area could significantly impact the treatment of one of the most severe and socially debilitating psychiatric disorders and open an exciting new frontier in psychopharmacology.

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.

Striatal glutamate, subcortical structure and clinical response to first-line treatment in first-episode psychosis patients

INTRODUCTION

Recent studies have observed that patients with treatment-resistant schizophrenia as well as patients with schizophrenia who do not respond within a medication trial exhibit excess activity of the glutamate system. In this study we sought to replicate the within-trial glutamate abnormality and to investigate the potential for structural differences and treatment-induced changes to improve identification of medication responders and non-responders.

METHODS

We enrolled 48 medication-naïve patients in a 4-week trial of risperidone and classified them retrospectively into responders and non-responders using clinical criteria. Proton magnetic resonance spectroscopy and T1-weighted structural MRI were acquired pre- and post-treatment to quantify striatal glutamate levels and several measures of subcortical brain structure.

RESULTS

Patients were classified as 29 responders and 19 non-responders. Striatal glutamate was higher in the non-responders than responders both pre- and post-treatment (F1,39 = 7.15, p = .01). Volumetric measures showed a significant group x time interaction (t = 5.163, <1%FDR), and group x time x glutamate interaction (t = 4.23, <15%FDR) were seen in several brain regions. Striatal volumes increased at trend level with treatment in both groups, and a positive association of striatal volumes with glutamate levels was seen in the non-responders.

CONCLUSIONS

Combining anatomic measures with glutamate levels offers the potential to enhance classification of responders and non-responders to antipsychotic medications as well as to provide mechanistic understanding of the interplay between neuroanatomical and neurochemical changes induced by these medications. Ethical statement The study was approved by the Ethics and Scientific committees of the Instituto Nacional de Neurología y Neurocirugía in Mexico City. All participants over 18 years fully understood and signed the informed consent; in case the patient was under 18 years, informed consent was obtained from both parents. Participants did not receive a stipend.

Discriminative Analysis of Schizophrenia Patients Using Topological Properties of Structural and Functional Brain Networks: A Multimodal Magnetic Resonance Imaging Study

Interest in the application of machine learning (ML) techniques to multimodal magnetic resonance imaging (MRI) data for the diagnosis of schizophrenia (SZ) at the individual level is growing. However, a few studies have applied the features of structural and functional brain networks derived from multimodal MRI data to the discriminative analysis of SZ patients at different clinical stages. In this study, 205 normal controls (NCs), 61 first-episode drug-naive SZ (FESZ) patients, and 79 chronic SZ (CSZ) patients were recruited. We acquired their structural MRI, diffusion tensor imaging, and resting-state functional MRI data and constructed brain networks for each participant, including the gray matter network (GMN), white matter network (WMN), and functional brain network (FBN). We then calculated 3 nodal properties for each brain network, including degree centrality, nodal efficiency, and betweenness centrality. Two classifications (SZ vs. NC and FESZ vs. CSZ) were performed using five ML algorithms. We found that the SVM classifier with the input features of the combination of nodal properties of both the GMN and FBN achieved the best performance to discriminate SZ patients from NCs [accuracy, 81.2%; area under the receiver operating characteristic curve (AUC), 85.2%; p &lt; 0.05]. Moreover, the SVM classifier with the input features of the combination of the nodal properties of both the GMN and WMN achieved the best performance to discriminate FESZ from CSZ patients (accuracy, 86.2%; AUC, 92.3%; p &lt; 0.05). Furthermore, the brain areas in the subcortical/cerebellum network and the frontoparietal network showed significant importance in both classifications. Together, our findings provide new insights to understand the neuropathology of SZ and further highlight the potential advantages of multimodal network properties for identifying SZ patients at different clinical stages.

A Comprehensive Review of Computer-Aided Diagnosis of Major Mental and Neurological Disorders and Suicide: A Biostatistical Perspective on Data Mining

The World Health Organization (WHO) suggests that mental disorders, neurological disorders, and suicide are growing causes of morbidity. Depressive disorders, schizophrenia, bipolar disorder, Alzheimer's disease, and other dementias account for 1.84%, 0.60%, 0.33%, and 1.00% of total Disability Adjusted Life Years (DALYs). Furthermore, suicide, the 15th leading cause of death worldwide, could be linked to mental disorders. More than 68 computer-aided diagnosis (CAD) methods published in peer-reviewed journals from 2016 to 2021 were analyzed, among which 75% were published in the year 2018 or later. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol was adopted to select the relevant studies. In addition to the gold standard, the sample size, neuroimaging techniques or biomarkers, validation frameworks, the classifiers, and the performance indices were analyzed. We further discussed how various performance indices are essential based on the biostatistical and data mining perspective. Moreover, critical information related to the Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines was analyzed. We discussed how balancing the dataset and not using external validation could hinder the generalization of the CAD methods. We provided the list of the critical issues to consider in such studies.

Spectral features based convolutional neural network for accurate and prompt identification of schizophrenic patients

Schizophrenia is a fatal mental disorder, which affects millions of people globally by the disturbance in their thinking, feeling and behaviour. In the age of the internet of things assisted with cloud computing and machine learning techniques, the computer-aided diagnosis of schizophrenia is essentially required to provide its patients with an opportunity to own a better quality of life. In this context, the present paper proposes a spectral features based convolutional neural network (CNN) model for accurate identification of schizophrenic patients using spectral analysis of multichannel EEG signals in real-time. This model processes acquired EEG signals with filtering, segmentation and conversion into frequency domain. Then, given frequency domain segments are divided into six distinct spectral bands like delta, theta-1, theta-2, alpha, beta and gamma. The spectral features including mean spectral amplitude, spectral power and Hjorth descriptors (Activity, Mobility and Complexity) are extracted from each band. These features are independently fed to the proposed spectral features-based CNN and long short-term memory network (LSTM) models for classification. This work also makes use of raw time-domain and frequency-domain EEG segments for classification using temporal CNN and spectral CNN models of same architectures respectively. The overall analysis of simulation results of all models exhibits that the proposed spectral features based CNN model is an efficient technique for accurate and prompt identification of schizophrenic patients among healthy individuals with average classification accuracies of 94.08% and 98.56% for two different datasets with optimally small classification time.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

A machine-learning framework for robust and reliable prediction of short- and long-term treatment response in initially antipsychotic-naïve schizophrenia patients based on multimodal neuropsychiatric data

The reproducibility of machine-learning analyses in computational psychiatry is a growing concern. In a multimodal neuropsychiatric dataset of antipsychotic-naïve, first-episode schizophrenia patients, we discuss a workflow aimed at reducing bias and overfitting by invoking simulated data in the design process and analysis in two independent machine-learning approaches, one based on a single algorithm and the other incorporating an ensemble of algorithms. We aimed to (1) classify patients from controls to establish the framework, (2) predict short- and long-term treatment response, and (3) validate the methodological framework. We included 138 antipsychotic-naïve, first-episode schizophrenia patients with data on psychopathology, cognition, electrophysiology, and structural magnetic resonance imaging (MRI). Perinatal data and long-term outcome measures were obtained from Danish registers. Short-term treatment response was defined as change in Positive And Negative Syndrome Score (PANSS) after the initial antipsychotic treatment period. Baseline diagnostic classification algorithms also included data from 151 matched controls. Both approaches significantly classified patients from healthy controls with a balanced accuracy of 63.8% and 64.2%, respectively. Post-hoc analyses showed that the classification primarily was driven by the cognitive data. Neither approach predicted short- nor long-term treatment response. Validation of the framework showed that choice of algorithm and parameter settings in the real data was successfully guided by results from the simulated data. In conclusion, this novel approach holds promise as an important step to minimize bias and obtain reliable results with modest sample sizes when independent replication samples are not available.

Functional Magnetic Resonance Imaging Connectivity Accurately Distinguishes Cases With Psychotic Disorders From Healthy Controls, Based on Cortical Features Associated With Brain Network Development

BACKGROUND

Machine learning (ML) can distinguish cases with psychotic disorder from healthy controls based on magnetic resonance imaging (MRI) data, but it is not yet clear which MRI metrics are the most informative for case-control ML, or how ML algorithms relate to the underlying biology.

METHODS

We analyzed multimodal MRI data from 2 independent case-control studies of psychotic disorders (cases, n = 65, 28; controls, n = 59, 80) and compared ML accuracy across 5 selected MRI metrics from 3 modalities. Cortical thickness, mean diffusivity, and fractional anisotropy were estimated at each of 308 cortical regions, as well as functional and structural connectivity between each pair of regions. Functional connectivity data were also used to classify nonpsychotic siblings of cases (n = 64) and to distinguish cases from controls in a third independent study (cases, n = 67; controls, n = 81).

RESULTS

In both principal studies, the most informative metric was functional MRI connectivity: The areas under the receiver operating characteristic curve were 88% and 76%, respectively. The cortical map of diagnostic connectivity features (ML weights) was replicable between studies (r = .27, p < .001); correlated with replicable case-control differences in functional MRI degree centrality and with a prior cortical map of adolescent development of functional connectivity; predicted intermediate probabilities of psychosis in siblings; and was replicated in the third case-control study.

CONCLUSIONS

ML most accurately distinguished cases from controls by a replicable pattern of functional MRI connectivity features, highlighting abnormal hubness of cortical nodes in an anatomical pattern consistent with the concept of psychosis as a disorder of network development.

A Systematic Characterization of Structural Brain Changes in Schizophrenia

A systematic characterization of the similarities and differences among different methods for detecting structural brain abnormalities in schizophrenia, such as voxel-based morphometry (VBM), tensor-based morphometry (TBM), and projection-based thickness (PBT), is important for understanding the brain pathology in schizophrenia and for developing effective biomarkers for a diagnosis of schizophrenia. However, such studies are still lacking. Here, we performed VBM, TBM, and PBT analyses on T1-weighted brain MR images acquired from 116 patients with schizophrenia and 116 healthy controls. We found that, although all methods detected wide-spread structural changes, different methods captured different information - only 10.35% of the grey matter changes in cortex were detected by all three methods, and VBM only detected 11.36% of the white matter changes detected by TBM. Further, pattern classification between patients and controls revealed that combining different measures improved the classification accuracy (81.9%), indicating that fusion of different structural measures serves as a better neuroimaging marker for the objective diagnosis of schizophrenia.

Diagnosing schizophrenia with network analysis and a machine learning method

OBJECTIVE

Schizophrenia is a chronic and debilitating neuropsychiatric disorder. It has been suggested that impaired brain connectivity underlies the pathophysiology of schizophrenia. Network analysis has thus recently emerged in the field of schizophrenia research.

METHODS

We investigated 48 schizophrenia patients and 24 healthy controls using network analysis and a machine learning method. A number of global and nodal network properties were estimated from graphs that were reconstructed using probabilistic brain tractography. These network properties were then compared between groups and used for machine learning to classify schizophrenia patients and healthy controls.

RESULTS

In classifying schizophrenia patients and healthy controls via network properties, the support vector machine, random forest, naïve Bayes, and gradient boosting machine learning models showed an encouraging level of performance. The overall connectivity was revealed as the most significant contributing feature to this classification among the global network properties. Among the nodal network properties, although the relative importance of each region of interest was not identical, there were still some patterns.

CONCLUSION

In conclusion, the possibility exists to classify schizophrenia patients and healthy controls using network properties, and we have found that there is a provisional pattern of involved brain regions among patients with schizophrenia.

Using Machine Learning and Structural Neuroimaging to Detect First Episode Psychosis: Reconsidering the Evidence

Despite the high level of interest in the use of machine learning (ML) and neuroimaging to detect psychosis at the individual level, the reliability of the findings is unclear due to potential methodological issues that may have inflated the existing literature. This study aimed to elucidate the extent to which the application of ML to neuroanatomical data allows detection of first episode psychosis (FEP), while putting in place methodological precautions to avoid overoptimistic results. We tested both traditional ML and an emerging approach known as deep learning (DL) using 3 feature sets of interest: (1) surface-based regional volumes and cortical thickness, (2) voxel-based gray matter volume (GMV) and (3) voxel-based cortical thickness (VBCT). To assess the reliability of the findings, we repeated all analyses in 5 independent datasets, totaling 956 participants (514 FEP and 444 within-site matched controls). The performance was assessed via nested cross-validation (CV) and cross-site CV. Accuracies ranged from 50% to 70% for surfaced-based features; from 50% to 63% for GMV; and from 51% to 68% for VBCT. The best accuracies (70%) were achieved when DL was applied to surface-based features; however, these models generalized poorly to other sites. Findings from this study suggest that, when methodological precautions are adopted to avoid overoptimistic results, detection of individuals in the early stages of psychosis is more challenging than originally thought. In light of this, we argue that the current evidence for the diagnostic value of ML and structural neuroimaging should be reconsidered toward a more cautious interpretation.

Development of an Al-Based Web Diagnostic System for Phenotyping Psychiatric Disorders

Background: Artificial intelligence (AI)-based medical diagnostic applications are on the rise. Our recent study has suggested an explainable deep neural network (EDNN) framework for identifying key structural deficits related to the pathology of schizophrenia. Here, we presented an AI-based web diagnostic system for schizophrenia under the EDNN framework with three-dimensional (3D) visualization of subjects' neuroimaging dataset. Methods: This AI-based web diagnostic system consisted of a web server and a neuroimaging diagnostic database. The web server deployed the EDNN algorithm under the Node.js environment. Feature selection and network model building were performed on the dataset obtained from two hundred schizophrenic patients and healthy controls in the Taiwan Aging and Mental Illness (TAMI) cohort. We included an independent cohort with 88 schizophrenic patients and 44 healthy controls recruited at Tri-Service General Hospital Beitou Branch for validation purposes. Results: Our AI-based web diagnostic system achieved 84.00% accuracy (89.47% sensitivity, 80.62% specificity) for gray matter (GM) and 90.22% accuracy (89.21% sensitivity, 91.23% specificity) for white matter (WM) on the TAMI cohort. For the Beitou cohort as an unseen test set, the model achieved 77.27 and 70.45% accuracy for GM and WM. Furthermore, it achieved 85.50 and 88.20% accuracy after model retraining to mitigate the effects of drift on the predictive capability. Moreover, our system visualized the identified voxels in brain atrophy in a 3D manner with patients' structural image, optimizing the evaluation process of the diagnostic results. Discussion: Together, our approach under the EDNN framework demonstrated the potential future direction of making a schizophrenia diagnosis based on structural brain imaging data. Our deep learning model is explainable, arguing for the accuracy of the key information related to the pathology of schizophrenia when using the AI-based web assessment platform. The rationale of this approach is in accordance with the Research Domain Criteria suggested by the National Institute of Mental Health.

Accuracy of diagnostic classification algorithms using cognitive-, electrophysiological-, and neuroanatomical data in antipsychotic-naïve schizophrenia patients

BACKGROUND

A wealth of clinical studies have identified objective biomarkers, which separate schizophrenia patients from healthy controls on a group level, but current diagnostic systems solely include clinical symptoms. In this study, we investigate if machine learning algorithms on multimodal data can serve as a framework for clinical translation.

METHODS

Forty-six antipsychotic-naïve, first-episode schizophrenia patients and 58 controls underwent neurocognitive tests, electrophysiology, and magnetic resonance imaging (MRI). Patients underwent clinical assessments before and after 6 weeks of antipsychotic monotherapy with amisulpride. Nine configurations of different supervised machine learning algorithms were applied to first estimate the unimodal diagnostic accuracy, and next to estimate the multimodal diagnostic accuracy. Finally, we explored the predictability of symptom remission.

RESULTS

Cognitive data significantly classified patients from controls (accuracies = 60-69%; p values = 0.0001-0.009). Accuracies of electrophysiology, structural MRI, and diffusion tensor imaging did not exceed chance level. Multimodal analyses with cognition plus any combination of one or more of the remaining three modalities did not outperform cognition alone. None of the modalities predicted symptom remission.

CONCLUSIONS

In this multivariate and multimodal study in antipsychotic-naïve patients, only cognition significantly discriminated patients from controls, and no modality appeared to predict short-term symptom remission. Overall, these findings add to the increasing call for cognition to be included in the definition of schizophrenia. To bring about the full potential of machine learning algorithms in first-episode, antipsychotic-naïve schizophrenia patients, careful a priori variable selection based on independent data as well as inclusion of other modalities may be required.

Using machine learning to explain the heterogeneity of schizophrenia. Realizing the promise and avoiding the hype

Despite extensive research and prodigious advances in neuroscience, our comprehension of the nature of schizophrenia remains rudimentary. Our failure to make progress is attributed to the extreme heterogeneity of this condition, enormous complexity of the human brain, limitations of extant research paradigms, and inadequacy of traditional statistical methods to integrate or interpret increasingly large amounts of multidimensional information relevant to unravelling brain function. Fortunately, the rapidly developing science of machine learning appears to provide tools capable of addressing each of these impediments. Enthusiasm about the potential of machine learning methods to break the current impasse is reflected in the steep increase in the number of scientific publication about the application of machine learning to the study of schizophrenia. Machine learning approaches are, however, poorly understood by schizophrenia researchers and clinicians alike. In this paper, we provide a simple description of the nature and techniques of machine learning and their application to the study of schizophrenia. We then summarize its potential and constraints with illustrations from six studies of machine learning in schizophrenia and address some common misconceptions about machine learning. We suggest some guidelines for researchers, readers, science editors and reviewers of the burgeoning machine learning literature in schizophrenia. In order to realize its enormous promise, we suggest the need for the disciplined application of machine learning methods to the study of schizophrenia with a clear recognition of its capability and challenges accompanied by a concurrent effort to improve machine learning literacy among neuroscientists and mental health professionals.

Diffusion kurtosis imaging of gray matter in schizophrenia

Prior postmortem studies have shown gray matter (GM) microstructural abnormalities in schizophrenia. However, few studies to date have examined GM microstructural integrity in schizophrenia in vivo. Here, we employed diffusion kurtosis imaging (DKI) to test for differences in GM microstructure in eighteen schizophrenia (SZ) patients versus nineteen healthy controls (HC). GM microstructure was characterized in each participant using DKI-derived metrics of mean kurtosis (MK) and mean diffusivity (MD). Individual T1-weighted images were used to create subject-specific cortically-labelled regions of interest (ROIs) of the four cortical lobes and sixty-eight cortical GM regions delineated by the Desikan-Killiany atlas, and to derive the associated cortical thickness and area measures. The derived ROIs were also registered to the diffusion space of each subject and used to generate region-specific mean MK and MD values. We additionally administered the Wisconsin Card Sorting Test (WCST), Stroop test, and Trail Making Test part B (Trails-B) to test the relationship between GM metrics and executive function in SZ. We found significantly increased MK and MD in SZ compared to HC participants in the temporal lobe, sub-lobar temporal cortical regions (fusiform, inferior temporal, middle temporal and temporal pole), and posterior cingulate cortex after correcting for multiple comparisons. Correlational analyses revealed significant associations of MK and MD with executive function scores derived from the WCST, Stroop, and Trails-B tests, along with an inverse relationship between MK and MD and cortical thickness and area. A hierarchical multiple linear regression analysis showed that up to 85% of the inter-subject variability in cognitive function in schizophrenia measured by the WCST could be explained by MK in combination with either GM thickness or area. MK and MD appear to be sensitive to GM microstructural pathology in schizophrenia and may provide useful biomarkers of abnormal cortical microstructure in this disorder.

Identifying psychosis spectrum disorder from experience sampling data using machine learning approaches

The ubiquity of smartphones opened up the possibility of widespread use of the Experience Sampling Method (ESM). The method is used to collect longitudinal data of participants' daily life experiences and is ideal to capture fluctuations in emotions (momentary mental states) as an indicator for later mental ill-health. In this study, ESM data of patients with psychosis spectrum disorder and controls were used to examine daily life emotions and higher order patterns thereof. We attempted to determine whether aggregated ESM data, in which statistical measures represent the distribution and dynamics of the original data, were able to distinguish patients from controls in a predictive modeling framework. Variable importance, recursive feature elimination, and ReliefF methods were used for feature selection. Model training, tuning, and testing were performed in nested cross-validation, based on algorithms such as Random Forests, Support Vector Machines, Gaussian Processes, Logistic Regression, and Neural Networks. ROC analysis was used to post-process these models. Stability of model performance was studied using Monte Carlo simulations. The results provide evidence that patterns in emotion changes can be captured by applying a combination of these techniques. Acceleration in the variables anxious and insecure was particularly successful in adding further predictive power to the models. The best results were achieved by Support Vector Machines with radial kernel (accuracy = 82% and sensitivity = 82%). This proof-of-concept work demonstrates that synergistic machine learning and statistical modeling may be used to harness the power of ESM data in the future.