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

Longitudinal reduction in brain volume in patients with schizophrenia and its association with cognitive function

Establishing a brain biomarker for schizophrenia is strongly desirable not only to support diagnosis by psychiatrists but also to help track the progressive changes in the brain over the course of the illness. A brain morphological signature of schizophrenia was reported in a recent study and is defined by clusters of brain regions with reduced volume in schizophrenia patients compared to healthy individuals. This signature was proven to be effective at differentiating patients with schizophrenia from healthy individuals, suggesting that it is a good candidate brain biomarker of schizophrenia. However, the longitudinal characteristics of this signature have remained unclear. In this study, we examined whether these changes occurred over time and whether they were associated with clinical outcomes. We found a significant change in the brain morphological signature in schizophrenia patients with more brain volume loss than the natural, age-related reduction in healthy individuals, suggesting that this change can capture a progressive morphological change in the brain. We further found a significant association between changes in the brain morphological signature and changes in the full-scale intelligence quotient (IQ). The patients with IQ improvement showed preserved brain morphological signatures, whereas the patients without IQ improvement showed progressive changes in the brain morphological signature, suggesting a link between potential recovery of intellectual abilities and the speed of brain pathology progression. We conclude that the brain morphological signature is a brain biomarker that can be used to evaluate progressive changes in the brain that are associated with cognitive impairment due to schizophrenia.

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

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

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.

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.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

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.

A morphological study of schizophrenia with magnetic resonance imaging, advanced analytics, and machine learning

We have performed a morphological analysis of patients with schizophrenia and compared them with healthy controls. Our analysis includes the use of publicly available automated extraction tools to assess regional cortical thickness (inclusive of within region cortical thickness variability) from structural magnetic resonance imaging (MRI), to characterize group-wise abnormalities associated with schizophrenia based on a publicly available dataset. We have also performed a correlation analysis between the automatically extracted biomarkers and a variety of patient clinical variables available. Finally, we also present the results of a machine learning analysis. Results demonstrate regional cortical thickness abnormalities in schizophrenia. We observed a correlation (rho = 0.474) between patients’ depression and the average cortical thickness of the right medial orbitofrontal cortex. Our leading machine learning technology evaluated was the support vector machine with stepwise feature selection, yielding a sensitivity of 92% and a specificity of 74%, based on regional brain measurements, including from the insula, superior frontal, caudate, calcarine sulcus, gyrus rectus, and rostral middle frontal regions. These results imply that advanced analytic techniques combining MRI with automated biomarker extraction can be helpful in characterizing patients with schizophrenia.

The progression of disorder-specific brain pattern expression in schizophrenia over 9 years

Age plays a crucial role in the performance of schizophrenia vs. controls (SZ-HC) neuroimaging-based machine learning (ML) models as the accuracy of identifying first-episode psychosis from controls is poor compared to chronic patients. Resolving whether this finding reflects longitudinal progression in a disorder-specific brain pattern or a systematic but non-disorder-specific deviation from a normal brain aging (BA) trajectory in schizophrenia would help the clinical translation of diagnostic ML models. We trained two ML models on structural MRI data: an SZ-HC model based on 70 schizophrenia patients and 74 controls and a BA model (based on 561 healthy individuals, age range = 66 years). We then investigated the two models’ predictions in the naturalistic longitudinal Northern Finland Birth Cohort 1966 (NFBC1966) following 29 schizophrenia and 61 controls for nine years. The SZ-HC model’s schizophrenia-specificity was further assessed by utilizing independent validation (62 schizophrenia, 95 controls) and depression samples (203 depression, 203 controls). We found better performance at the NFBC1966 follow-up (sensitivity = 75.9%, specificity = 83.6%) compared to the baseline (sensitivity = 58.6%, specificity = 86.9%). This finding resulted from progression in disorder-specific pattern expression in schizophrenia and was not explained by concomitant acceleration of brain aging. The disorder-specific pattern’s progression reflected longitudinal changes in cognition, outcomes, and local brain changes, while BA captured treatment-related and global brain alterations. The SZ-HC model was also generalizable to independent schizophrenia validation samples but classified depression as control subjects. Our research underlines the importance of taking account of longitudinal progression in a disorder-specific pattern in schizophrenia when developing ML classifiers for different age groups.

In schizophrenia, non-remitters and partial remitters to treatment with antipsychotics are qualitatively distinct classes with respect to neurocognitive deficits and neuro-immune biomarkers: results of soft independent modeling of class analogy

Around one third of schizophrenia patients are non-responders to antipsychotic therapy. The present study aimed to delineate the pathway-phenotypes of non-remitters (NRTT) and partial remitters (PRTT) to treatment with antipsychotics as defined using the Global Clinical Impression scales. We recruited 60 NRTT, 50 PRTT and 43 healthy controls and measured schizophrenia symptoms, neurocognitive tests, plasma CCL11, interleukin-(IL)-6, IL-10, Dickkopf protein 1 (DKK1), high mobility group box-1 protein (HMGB1), κ- and μ-opioid receptors (KOR and MOR, respectively), endomorphin-2 (EM-2), and β-endorphin. Soft independent modeling of class analogy (SIMCA) showed that NRTT and PRTT are significantly discriminated with a cross-validated accuracy of 94.7% and are qualitatively distinct classes using symptomatome, and neuro-immune-opioid-cognitome (NIOC) features as modeling variables. Moreover, a NIOC pathway phenotype discriminated PRTT from healthy controls with an accuracy of 100% indicating that PRTT and controls are two qualitative distinct classes. Using NIOC features as discriminatory variables in SIMCA showed that all PRTT were rejected as belonging to the normal control class and authenticated as belonging to their target class. In conclusion, a non-response to treatment can best be profiled using a SIMCA model constructed using symptomatome and NIOC features. A partial response should be delineated using SIMCA by authenticating patients as controls or PRTT instead of using scale-derived cut-off values or a number of scale items being rated mild or better. The results show that PRTT is characterized by an active NIOC pathway phenotype and that both NRTT and PRTT should be treated by targeting neuro-immune and opioid pathways.

Multi-modal neuroimaging feature fusion via 3D Convolutional Neural Network architecture for schizophrenia diagnosis

Early and precise diagnosis of schizophrenia disorder (SZ) has an essential role in the quality of a patient’s life and future treatments. Structural and functional neuroimaging provides robust biomarkers for understanding the anatomical and functional changes associated with SZ. Each of the neuroimaging techniques shows only a different perspective on the functional or structural of the brain, while multi-modal fusion can reveal latent connections in the brain. In this paper, we propose an approach for the fusion of structural and functional brain data with a deep learning-based model to take advantage of data fusion and increase the accuracy of schizophrenia disorder diagnosis. The proposed method consists of an architecture of 3D convolutional neural networks (CNNs) that applied to magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and diffusion tensor imaging (DTI) extracted features. We use 3D MRI patches, fMRI spatial independent component analysis (ICA) map, and DTI fractional anisotropy (FA) as model inputs. Our method is validated on the COBRE dataset, and an average accuracy of 99.35% is obtained. The proposed method demonstrates promising classification performance and can be applied to real data.

Influencing Factors and Machine Learning-Based Prediction of Side Effects in Psychotherapy

Background: Side effects in psychotherapy are a common phenomenon, but due to insufficient understanding of the relevant predictors of side effects in psychotherapy, many psychotherapists or clinicians fail to identify and manage these side effects. The purpose of this study was to predict whether clients or patients would experience side effects in psychotherapy by machine learning and to analyze the related influencing factors. Methods: A self-compiled "Psychotherapy Side Effects Questionnaire (PSEQ)" was delivered online by a WeChat official account. Three hundred and seventy participants were included in the cross-sectional analysis. Psychotherapy outcomes were classified as participants with side effects and without side effects. A number of features were selected to distinguish participants with different psychotherapy outcomes. Six machine learning-based algorithms were then chosen and trained by our dataset to build outcome prediction classifiers. Results: Our study showed that: (1) the most common side effects were negative emotions in psychotherapy, such as anxiety, tension, sadness, and anger, etc. (24.6%, 91/370); (2) the mental state of the psychotherapist, as perceived by the participant during psychotherapy, was the most relevant feature to predict whether clients would experience side effects in psychotherapy; (3) a Random Forest-based machine learning classifier offered the best prediction performance of the psychotherapy outcomes, with an F1-score of 0.797 and an AUC value of 0.804. These numbers indicate a high prediction performance, which allowed our approach to be used in practice. Conclusions: Our Random Forest-based machine learning classifier could accurately predict the possible outcome of a client in psychotherapy. Our study sheds light on the influencing factors of the side effects of psychotherapy and could help psychotherapists better predict the outcomes of psychotherapy.

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.

From the microscope to the magnet: Disconnection in schizophrenia and bipolar disorder

White matter (WM) abnormalities have implicated schizophrenia (SZ) and bipolar disorder (BD) as disconnection syndromes, yet the extent to which these abnormalities are shared versus distinct remains unclear. Diffusion tensor imaging (DTI) studies yield a putative measure of WM integrity while neuropathological studies provide more specific microstructural information. We therefore systematically reviewed all neuropathological (n = 12) and DTI (n = 11) studies directly comparing patients with SZ and BD. Most studies (18/23) reported no difference between patient groups. Changes in oligodendrocyte density, myelin staining and gene, protein and mRNA expression were found in SZ and/or BD patients as compared to healthy individuals, while DTI studies showed common alterations in thalamic radiations, uncinate fasciculus, corpus callosum, longitudinal fasciculus and corona radiata. Altogether, findings suggest shared disconnectivity in SZ and BD, which are likely related to their considerable overlap. Above all, neuroimaging findings corroborated neuropathological findings in the prefrontal cortex, demonstrating the utility of integrating multiple methodologies. Focusing on clinical dimensions over disease entities will advance our understanding of disconnectivity and help inform preventive medicine.