Will Machine Learning Enable Us to Finally Cut the Gordian Knot of Schizophrenia

Inference of social cognition in schizophrenia patients with neurocognitive domains and neurocognitive tests using automated machine learning

AIM

It has been suggested that single neurocognitive domain or neurocognitive test can be used to determine the overall cognitive function in schizophrenia using machine learning algorithms. It is unknown whether social cognition in schizophrenia patients can be estimated with machine learning based on neurocognitive domains or neurocognitive tests.

METHODS

To predict social cognition in schizophrenia, we applied an automated machine learning (AutoML) framework resulting from the analysis of predictive factors such as six neurocognitive domain scores and nine neurocognitive test scores of 380 schizophrenia patients in the Taiwanese population. Four clinical parameters (i.e., age, gender, subgroup, and education) were also used as predictive factors. We utilized an AutoML framework called Tree-based Pipeline Optimization Tool (TPOT) to generate predictive pipelines automatically.

RESULTS

The analysis revealed that all neurocognitive domains and tests except the reasoning and problem solving domain/test showed significant associations with social cognition. In addition, a TPOT-generated pipeline can best predict social cognition in schizophrenia using seven predictive factors, including five neurocognitive domains (i.e., speed of processing, sustained attention, working memory, verbal learning and memory, and visual learning and memory) and two clinical parameters (i.e., age and gender). This predictive pipeline consists of machine learning algorithms such as function transformers, an approximate feature map, independent component analysis, and linear regression.

CONCLUSION

The study indicates that an AutoML framework such as TPOT may provide a promising way to produce truly effective machine learning pipelines for predicting social cognition in schizophrenia using neurocognitive domains and/or neurocognitive tests.

Computing schizophrenia: ethical challenges for machine learning in psychiatry

Recent advances in machine learning (ML) promise far-reaching improvements across medical care, not least within psychiatry. While to date no psychiatric application of ML constitutes standard clinical practice, it seems crucial to get ahead of these developments and address their ethical challenges early on. Following a short general introduction concerning ML in psychiatry, we do so by focusing on schizophrenia as a paradigmatic case. Based on recent research employing ML to further the diagnosis, treatment, and prediction of schizophrenia, we discuss three hypothetical case studies of ML applications with view to their ethical dimensions. Throughout this discussion, we follow the principlist framework by Tom Beauchamp and James Childress to analyse potential problems in detail. In particular, we structure our analysis around their principles of beneficence, non-maleficence, respect for autonomy, and justice. We conclude with a call for cautious optimism concerning the implementation of ML in psychiatry if close attention is paid to the particular intricacies of psychiatric disorders and its success evaluated based on tangible clinical benefit for patients.

Accelerated aging signatures in subjects with schizophrenia and their unaffected siblings

Schizophrenia (SZ) is a chronic debilitating disease. Subjects with SZ have significant shorter life expectancy. Growing evidence suggests that a process of pathological accelerated aging occurs in SZ, leading to early development of severe clinical diseases and worse morbimortality. Furthermore, unaffected relatives can share certain endophenotypes with subjects with SZ. We aim to characterize accelerated aging as a possible endophenotype of schizophrenia by using a machine learning (ML) model of peripheral biomarkers to accurately differentiate subjects with SZ (n = 35), their unaffected siblings (SB, n = 36) and healthy controls (HC, n = 47). We used a random forest algorithm that included biomarkers related to aging: eotaxins CCL-11 and CCL-24; the oxidative stress markers thiobarbituric acid-reactive substances (TBARS), protein carbonyl content (PCC), glutathione peroxidase (GPx); and telomere length (TL). The ML algorithm of biomarkers was able to distinguish individuals with SZ from HC with prediction accuracy of 79.7%, SZ from SB with 62.5% accuracy and SB from HC with 75.5% accuracy. These results support the hypothesis that a pathological accelerated aging might occur in SZ, and this pathological aging could be an endophenotype of the disease, once this profile was also observed in SB, suggesting that SB might suffer from an accelerated aging in some level.

Schizophrenia: A Survey of Artificial Intelligence Techniques Applied to Detection and Classification

Artificial Intelligence in healthcare employs machine learning algorithms to emulate human cognition in the analysis of complicated or large sets of data. Specifically, artificial intelligence taps on the ability of computer algorithms and software with allowable thresholds to make deterministic approximate conclusions. In comparison to traditional technologies in healthcare, artificial intelligence enhances the process of data analysis without the need for human input, producing nearly equally reliable, well defined output. Schizophrenia is a chronic mental health condition that affects millions worldwide, with impairment in thinking and behaviour that may be significantly disabling to daily living. Multiple artificial intelligence and machine learning algorithms have been utilized to analyze the different components of schizophrenia, such as in prediction of disease, and assessment of current prevention methods. These are carried out in hope of assisting with diagnosis and provision of viable options for individuals affected. In this paper, we review the progress of the use of artificial intelligence in schizophrenia.

Classification of first-episode psychosis using cortical thickness: A large multicenter MRI study

Machine learning classifications of first-episode psychosis (FEP) using neuroimaging have predominantly analyzed brain volumes. Some studies examined cortical thickness, but most of them have used parcellation approaches with data from single sites, which limits claims of generalizability. To address these limitations, we conducted a large-scale, multi-site analysis of cortical thickness comparing parcellations and vertex-wise approaches. By leveraging the multi-site nature of the study, we further investigated how different demographical and site-dependent variables affected predictions. Finally, we assessed relationships between predictions and clinical variables. 428 subjects (147 females, mean age 27.14) with FEP and 448 (230 females, mean age 27.06) healthy controls were enrolled in 8 centers by the ClassiFEP group. All subjects underwent a structural MRI and were clinically assessed. Cortical thickness parcellation (68 areas) and full cortical maps (20,484 vertices) were extracted. Linear Support Vector Machine was used for classification within a repeated nested cross-validation framework. Vertex-wise thickness maps outperformed parcellation-based methods with a balanced accuracy of 66.2% and an Area Under the Curve of 72%. By stratifying our sample for MRI scanner, we increased generalizability across sites. Temporal brain areas resulted as the most influential in the classification. The predictive decision scores significantly correlated with age at onset, duration of treatment, and positive symptoms. In conclusion, although far from the threshold of clinical relevance, temporal cortical thickness proved to classify between FEP subjects and healthy individuals. The assessment of site-dependent variables permitted an increase in the across-site generalizability, thus attempting to address an important machine learning limitation.

Machine learning for genetic prediction of psychiatric disorders: a systematic review

Machine learning methods have been employed to make predictions in psychiatry from genotypes, with the potential to bring improved prediction of outcomes in psychiatric genetics; however, their current performance is unclear. We aim to systematically review machine learning methods for predicting psychiatric disorders from genetics alone and evaluate their discrimination, bias and implementation. Medline, PsycInfo, Web of Science and Scopus were searched for terms relating to genetics, psychiatric disorders and machine learning, including neural networks, random forests, support vector machines and boosting, on 10 September 2019. Following PRISMA guidelines, articles were screened for inclusion independently by two authors, extracted, and assessed for risk of bias. Overall, 63 full texts were assessed from a pool of 652 abstracts. Data were extracted for 77 models of schizophrenia, bipolar, autism or anorexia across 13 studies. Performance of machine learning methods was highly varied (0.48-0.95 AUC) and differed between schizophrenia (0.54-0.95 AUC), bipolar (0.48-0.65 AUC), autism (0.52-0.81 AUC) and anorexia (0.62-0.69 AUC). This is likely due to the high risk of bias identified in the study designs and analysis for reported results. Choices for predictor selection, hyperparameter search and validation methodology, and viewing of the test set during training were common causes of high risk of bias in analysis. Key steps in model development and validation were frequently not performed or unreported. Comparison of discrimination across studies was constrained by heterogeneity of predictors, outcome and measurement, in addition to sample overlap within and across studies. Given widespread high risk of bias and the small number of studies identified, it is important to ensure established analysis methods are adopted. We emphasise best practices in methodology and reporting for improving future studies.

Baseline structural and functional magnetic resonance imaging predicts early treatment response in schizophrenia with radiomics strategy

Multimodal neuroimaging features provide opportunities for accurate classification and personalized treatment options in the psychiatric domain. This study aimed to investigate whether brain features predict responses to the overall treatment of schizophrenia at the end of the first or a single hospitalization. Structural and functional magnetic resonance imaging (MRI) data from two independent samples (N = 85 and 63, separately) of schizophrenia patients at baseline were included. After treatment, patients were classified as responders and non-responders. Radiomics features of gray matter morphology and functional connectivity were extracted using Least Absolute Shrinkage and Selection Operator. Support vector machine was used to explore the predictive performance. Prediction models were based on structural features (cortical thickness, surface area, gray matter regional volume, mean curvature, metric distortion, and sulcal depth), functional features (functional connectivity), and combined features. There were 12 features after dimensionality reduction. The structural features involved the right precuneus, cuneus, and inferior parietal lobule. The functional features predominately included inter-hemispheric connectivity. We observed a prediction accuracy of 80.38% (sensitivity: 87.28%; specificity 82.47%) for the model using functional features, and 69.68% (sensitivity: 83.96%; specificity: 72.41%) for the one using structural features. Our model combining both structural and functional features achieved a higher accuracy of 85.03%, with 92.04% responder and 80.23% non-responders to the overall treatment to be correctly predicted. These results highlight the power of structural and functional MRI-derived radiomics features to predict early response to treatment in schizophrenia. Prediction models of the very early treatment response in schizophrenia could augment effective therapeutic strategies.

Improving Mental Health Services: A 50-Year Journey from Randomized Experiments to Artificial Intelligence and Precision Mental Health

This conceptual paper describes the current state of mental health services, identifies critical problems, and suggests how to solve them. I focus on the potential contributions of artificial intelligence and precision mental health to improving mental health services. Toward that end, I draw upon my own research, which has changed over the last half century, to highlight the need to transform the way we conduct mental health services research. I identify exemplars from the emerging literature on artificial intelligence and precision approaches to treatment in which there is an attempt to personalize or fit the treatment to the client in order to produce more effective interventions.

Artificial intelligence-based classification of schizophrenia: A high density electroencephalographic and support vector machine study

BACKGROUND

Interview-based schizophrenia (SCZ) diagnostic methods are not completely valid. Moreover, SCZ-the disease entity is very heterogeneous. Supervised-Machine-Learning (sML) application of Artificial-Intelligence holds a tremendous promise in solving these issues.

AIMS

To sML-based discriminating validity of resting-state electroencephalographic (EEG) quantitative features in classifying SCZ from healthy and, positive (PS) and negative symptom (NS) subgroups, using a high-density recording.

SETTINGS AND DESIGN

Data collected at a tertiary care mental-health institute using a cross-sectional study design and analyzed at a premier Engineering Institute.

MATERIALS AND METHODS

Data of 38-SCZ patients and 20-healthy controls were retrieved. The positive-negative subgroup classification was done using Positive and Negative Syndrome Scale operational-criteria. EEG was recorded using 256-channel high-density equipment. Eight priori regions-of-interest were selected. Six-level wavelet decomposition and Kernel-Support Vector Machine (SVM) method were used for feature extraction and data classification.

STATISTICAL ANALYSIS

Mann-Whitney test was used for comparison of machine learning-features. Accuracy, sensitivity, specificity, and area under receiver operating characteristics-curve were measured as discriminatory indices of classifications.

RESULTS

Accuracy of classifying SCZ from healthy and PS from NS SCZ, were 78.95% and 89.29%, respectively. While beta and gamma frequency related features most accurately classified SCZ from healthy controls, delta and theta frequency related features most accurately classified positive from negative SCZ. Inferior frontal gyrus features most accurately contributed to both the classificatory instances.

CONCLUSIONS

SVM-based classification and sub-classification of SCZ using EEG data is optimal and might help in improving the "validity" and reducing the "heterogeneity" in the diagnosis of SCZ. These results might only be generalized to acute and moderately ill male SCZ patients.

Applying speech technologies to assess verbal memory in patients with serious mental illness

Verbal memory deficits are some of the most profound neurocognitive deficits associated with schizophrenia and serious mental illness in general. As yet, their measurement in clinical settings is limited to traditional tests that allow for limited administrations and require substantial resources to deploy and score. Therefore, we developed a digital ambulatory verbal memory test with automated scoring, and repeated self-administration via smart devices. One hundred and four adults participated, comprising 25 patients with serious mental illness and 79 healthy volunteers. The study design was successful with high quality speech recordings produced to 92% of prompts (Patients: 86%, Healthy: 96%). The story recalls were both transcribed and scored by humans, and scores generated using natural language processing on transcriptions were comparable to human ratings (R = 0.83, within the range of human-to-human correlations of R = 0.73-0.89). A fully automated approach that scored transcripts generated by automatic speech recognition produced comparable and accurate scores (R = 0.82), with very high correlation to scores derived from human transcripts (R = 0.99). This study demonstrates the viability of leveraging speech technologies to facilitate the frequent assessment of verbal memory for clinical monitoring purposes in psychiatry.

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.

Using Machine Learning in Psychiatry: The Need to Establish a Framework That Nurtures Trustworthiness

The rapid embracing of artificial intelligence in psychiatry has a flavor of being the current "wild west"; a multidisciplinary approach that is very technical and complex, yet seems to produce findings that resonate. These studies are hard to review as the methods are often opaque and it is tricky to find the suitable combination of reviewers. This issue will only get more complex in the absence of a rigorous framework to evaluate such studies and thus nurture trustworthiness. Therefore, our paper discusses the urgency of the field to develop a framework with which to evaluate the complex methodology such that the process is done honestly, fairly, scientifically, and accurately. However, evaluation is a complicated process and so we focus on three issues, namely explainability, transparency, and generalizability, that are critical for establishing the viability of using artificial intelligence in psychiatry. We discuss how defining these three issues helps towards building a framework to ensure trustworthiness, but show how difficult definition can be, as the terms have different meanings in medicine, computer science, and law. We conclude that it is important to start the discussion such that there can be a call for policy on this and that the community takes extra care when reviewing clinical applications of such models..

Neuroanatomical Features That Predict Response to Electroconvulsive Therapy Combined With Antipsychotics in Schizophrenia: A Magnetic Resonance Imaging Study Using Radiomics Strategy

OBJECTIVE

Neuroimaging-based brain signatures may be informative in identifying patients with psychosis who will respond to antipsychotics. However, signatures that inform the electroconvulsive therapy (ECT) health care professional about the response likelihood remain unclear in psychosis with radiomics strategy. This study investigated whether brain structure-based signature in the prediction of ECT response in a sample of schizophrenia patients using radiomics approach.

METHODS

This high-resolution structural magnetic resonance imaging study included 57 patients at baseline. After ECT combined with antipsychotics, 28 and 29 patients were classified as responders and non-responders. Features of gray matter were extracted and compared. The logistic regression model/support vector machine (LRM/SVM) analysis was used to explore the predictive performance.

RESULTS

The regularized multivariate LRM accurately discriminated responders from non-responders, with an accuracy of 90.91%. The structural features were further confirmed in the validating data set, resulting in an accuracy of 87.59%. The accuracy of the SVM in the training set was 90.91%, and the accuracy in the validation set was 91.78%.

CONCLUSION

Our results support the possible use of structural brain feature-based radiomics as a potential tool for predicting ECT response in patients with schizophrenia undergoing antipsychotics, paving the way for utilization of markers in psychosis.

Examination of retinal vascular trajectory in schizophrenia and bipolar disorder

AIM

Evidence suggests microvascular dysfunction (wider retinal venules and narrower arterioles) in schizophrenia (SCZ) and bipolar disorder (BD). The vascular development is synchronous with neuronal development in the retina and brain. The retinal vessel trajectory is related to retinal nerve fiber layer thinning and cerebrovascular abnormalities in SCZ and BD and has not yet been examined. Hence, in this study we examined the retinal vascular trajectory in SCZ and BD in comparison with healthy volunteers (HV).

METHODS

Retinal images were acquired from 100 HV, SCZ patients, and BD patients, respectively, with a non-mydriatic fundus camera. Images were quantified to obtain the retinal arterial and venous trajectories using a validated, semiautomated algorithm. Analysis of covariance and regression analyses were conducted to examine group differences. A supervised machine-learning ensemble of bagged-trees method was used for automated classification of trajectory values.

RESULTS

There was a significant difference among groups in both the retinal venous trajectory (HV: 0.17 ± 0.08; SCZ: 0.25 ± 0.17; BD: 0.27 ± 0.20; P < 0.001) and the arterial trajectory (HV: 0.34 ± 0.15; SCZ: 0.29 ± 0.10; BD: 0.29 ± 0.11; P = 0.003) even after adjusting for age and sex (P < 0.001). On post-hoc analysis, the SCZ and BD groups differed from the HV on retinal venous and arterial trajectories, but there was no difference between SCZ and BD patients. The machine learning showed an accuracy of 86% and 73% for classifying HV versus SCZ and BD, respectively.

CONCLUSION

Smaller trajectories of retinal arteries indicate wider and flatter curves in SCZ and BD. Considering the relation between retinal/cerebral vasculatures and retinal nerve fiber layer thinness, the retinal vascular trajectory is a potential marker for SCZ and BD. As a relatively affordable investigation, retinal fundus photography should be further explored in SCZ and BD as a potential screening measure.

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.

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.

Automation to optimise physician treatment of individual patients: examples in psychiatry

There is widespread agreement by health-care providers, medical associations, industry, and governments that automation using digital technology could improve the delivery and quality of care in psychiatry, and reduce costs. Many benefits from technology have already been realised, along with the identification of many challenges. In this Review, we discuss some of the challenges to developing effective automation for psychiatry to optimise physician treatment of individual patients. Using the perspective of automation experts in other industries, three examples of automation in the delivery of routine care are reviewed: (1) effects of electronic medical records on the patient interview; (2) effects of complex systems integration on e-prescribing; and (3) use of clinical decision support to assist with clinical decision making. An increased understanding of the experience of automation from other sectors might allow for more effective deployment of technology in psychiatry.