Multivariate Pattern Analysis of Genotype-Phenotype Relationships in Schizophrenia

Polygenic risk for psychotic disorders in relation to cardiac autonomic dysfunction in unmedicated patients with schizophrenia

Cardiac autonomic dysfunction (CADF), mainly characterized by increased heart rate, decreased heart rate variability, and loss of vagal modulation, has been extensively described in patients with schizophrenia (SCZ) and their healthy first-degree relatives. As such, it represents an apparent physiological link that contributes to the increased cardiovascular mortality in these patients. Common genetic variation is a putative underlying mechanism, along with lifestyle factors and antipsychotic medications. However, the extent to which CADF is associated with genetic factors for SCZ is unknown. A sample of 83 drug-naive SCZ patients and 96 healthy controls, all of European origin, underwent a 30-minute autonomic assessment under resting conditions. We incorporated parameters from several domains into our model, including time and frequency domains (mean heart rate, low/high frequency ratio) and compression entropy, each of which provides different insights into the dynamics of cardiac autonomic function. These parameters were used as outcome variables in linear regression models with polygenic risk scores (PRS) for SCZ as predictors and age, sex, BMI, smoking status, principal components of ancestry and diagnosis as covariates. Of the three CADF parameters, SCZ PRS was significantly associated with mean heart rate in the combined case/control sample. However, this association was was no longer significant after including diagnosis as a covariate (p = 0.29). In contrast, diagnostic status is statistically significant for all three CADF parameters, accounting for a significantly greater proportion of the variance in mean heart rate compared to SCZ PRS (approximately 16% vs. 4%). Despite evidence for a common genetic basis of CADF and SCZ, we were unable to provide further support for an association between the polygenic burden of SCZ and cardiac autonomic function beyond the diagnostic state. This suggests that there are other important characteristics associated with SCZ that lead to CADF that are not captured by SCZ PRS.

Enhancing schizophrenia phenotype prediction from genotype data through knowledge-driven deep neural network models

This article explores deep learning model design, drawing inspiration from the omnigenic model and genetic heterogeneity concepts, to improve schizophrenia prediction using genotype data. It introduces an innovative three-step approach leveraging neural networks' capabilities to efficiently handle genetic interactions. A locally connected network initially routes input data from variants to their corresponding genes. The second step employs an Encoder-Decoder to capture relationships among identified genes. The final model integrates knowledge from the first two and incorporates a parallel component to consider the effects of additional genes. This expansion enhances prediction scores by considering a larger number of genes. Trained models achieved an average AUC of 0.83, surpassing other genotype-trained models and matching gene expression dataset-based approaches. Additionally, tests on held-out sets reported an average sensitivity of 0.72 and an accuracy of 0.76, aligning with schizophrenia heritability predictions. Moreover, the study addresses genetic heterogeneity challenges by considering diverse population subsets.

The schizophrenia syndrome, circa 2024: What we know and how that informs its nature

With new data about different aspects of schizophrenia being continually generated, it becomes necessary to periodically revisit exactly what we know. Along with a need to review what we currently know about schizophrenia, there is an equal imperative to evaluate the construct itself. With these objectives, we undertook an iterative, multi-phase process involving fifty international experts in the field, with each step building on learnings from the prior one. This review assembles currently established findings about schizophrenia (construct, etiology, pathophysiology, clinical expression, treatment) and posits what they reveal about its nature. Schizophrenia is a heritable, complex, multi-dimensional syndrome with varying degrees of psychotic, negative, cognitive, mood, and motor manifestations. The illness exhibits a remitting and relapsing course, with varying degrees of recovery among affected individuals with most experiencing significant social and functional impairment. Genetic risk factors likely include thousands of common genetic variants that each have a small impact on an individual's risk and a plethora of rare gene variants that have a larger individual impact on risk. Their biological effects are concentrated in the brain and many of the same variants also increase the risk of other psychiatric disorders such as bipolar disorder, autism, and other neurodevelopmental conditions. Environmental risk factors include but are not limited to urban residence in childhood, migration, older paternal age at birth, cannabis use, childhood trauma, antenatal maternal infection, and perinatal hypoxia. Structural, functional, and neurochemical brain alterations implicate multiple regions and functional circuits. Dopamine D-2 receptor antagonists and partial agonists improve psychotic symptoms and reduce risk of relapse. Certain psychological and psychosocial interventions are beneficial. Early intervention can reduce treatment delay and improve outcomes. Schizophrenia is increasingly considered to be a heterogeneous syndrome and not a singular disease entity. There is no necessary or sufficient etiology, pathology, set of clinical features, or treatment that fully circumscribes this syndrome. A single, common pathophysiological pathway appears unlikely. The boundaries of schizophrenia remain fuzzy, suggesting the absence of a categorical fit and need to reconceptualize it as a broader, multi-dimensional and/or spectrum construct.

Polygenic contributions to performance on the Balloon Analogue Risk Task

Risky decision-making is a common, heritable endophenotype seen across many psychiatric disorders. Its underlying genetic architecture is incompletely explored. We examined behavior in the Balloon Analogue Risk Task (BART), which tests risky decision-making, in two independent samples of European ancestry. One sample (n = 1138) comprised healthy participants and some psychiatric patients (53 schizophrenia, 42 bipolar disorder, 47 ADHD); the other (n = 911) excluded for recent treatment of various psychiatric disorders but not ADHD. Participants provided DNA and performed the BART, indexed by mean adjusted pumps. We constructed a polygenic risk score (PRS) for discovery in each dataset and tested it in the other as replication. Subsequently, a genome-wide MEGA-analysis, combining both samples, tested genetic correlation with risk-taking self-report in the UK Biobank sample and psychiatric phenotypes characterized by risk-taking (ADHD, Bipolar Disorder, Alcohol Use Disorder, prior cannabis use) in the Psychiatric Genomics Consortium. The PRS for BART performance in one dataset predicted task performance in the replication sample (r = 0.13, p = 0.000012, pFDR = 0.000052), as did the reciprocal analysis (r = 0.09, p = 0.0083, pFDR=0.04). Excluding participants with psychiatric diagnoses produced similar results. The MEGA-GWAS identified a single SNP (rs12023073; p = 3.24 × 10-8) near IGSF21, a protein involved in inhibitory brain synapses; replication samples are needed to validate this result. A PRS for self-reported cannabis use (p = 0.00047, pFDR = 0.0053), but not self-reported risk-taking or psychiatric disorder status, predicted behavior on the BART in our MEGA-GWAS sample. The findings reveal polygenic architecture of risky decision-making as measured by the BART and highlight its overlap with cannabis use.

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

PURPOSE OF REVIEW

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

RECENT FINDINGS

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

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.

Artificial intelligence in genetic services delivery: Utopia or apocalypse?

Artificial intelligence (AI) technologies have a long history, with increasing presence and potential in society and medicine. Much of the medical literature is highly optimistic about AI and machine learning, but fears also exist that healthcare professionals will be replaced by machines. AI remains mysterious for many practitioners, so this paper aims to unwind both hype and fear related to the technology for genetics professionals. After an historical introduction to AI in understandable and practical terms, we review its limitations. Building upon this foundation, we discuss current AI applications in medicine, including genomics and genetic counseling, offering grounded ideas about the impact and role of AI in genetic counseling and delivery of genetic services. Since AI is already being used in genomics today, now is the time to fundamentally understand what it is, how it is being used, what its limitations are, and how it will continue to be integrated into genetics as we look ahead.

Predicting rehospitalization within 2 years of initial patient admission for a major depressive episode: a multimodal machine learning approach

Machine learning methods show promise to translate univariate biomarker findings into clinically useful multivariate decision support systems. At current, works in major depressive disorder have predominantly focused on neuroimaging and clinical predictor modalities, with genetic, blood-biomarker, and cardiovascular modalities lacking. In addition, the prediction of rehospitalization after an initial inpatient major depressive episode is yet to be explored, despite its clinical importance. To address this gap in the literature, we have used baseline clinical, structural imaging, blood-biomarker, genetic (polygenic risk scores), bioelectrical impedance and electrocardiography predictors to predict rehospitalization within 2 years of an initial inpatient episode of major depression. Three hundred and eighty patients from the ongoing 12-year Bidirect study were included in the analysis (rehospitalized: yes = 102, no = 278). Inclusion criteria was age ≥35 and <66 years, a current or recent hospitalisation for a major depressive episode and complete structural imaging and genetic data. Optimal performance was achieved with a multimodal panel containing structural imaging, blood-biomarker, clinical, medication type, and sleep quality predictors, attaining a test AUC of 67.74 (p = 9.99^-05). This multimodal solution outperformed models based on clinical variables alone, combined biomarkers, and individual data modality prognostication for rehospitalization prediction. This finding points to the potential of predictive models that combine multimodal clinical and biomarker data in the development of clinical decision support systems.

Polygenic risk scores in psychiatry: Will they be useful for clinicians?

Major psychiatric disorders are heritable but they are genetically complex. This means that, with certain exceptions, single gene markers will not be helpful for diagnosis. However, we are learning more about the large number of gene variants that, in combination, are associated with risk for disorders such as schizophrenia, bipolar disorder, and other psychiatric conditions. The presence of those risk variants may now be combined into a polygenic risk score (PRS). Such a score provides a quantitative index of the genomic burden of risk variants in an individual, which relates to the likelihood that a person has a particular disorder. Currently, such scores are quite useful in research, and they are telling us much about the relationships between different disorders and other indices of brain function. In the future, as the datasets supporting the development of such scores become larger and more diverse and as methodological developments improve predictive capacity, we expect that PRS will have substantial clinical utility in the assessment of risk for disease, subtypes of disease, and even treatment response. Here, we provide an overview of PRS in general terms (including a glossary suitable for informed non-geneticists) and discuss the use of PRS in psychiatry, including their limitations and cautions for interpretation, as well as their applications now and in the future.

Dual-process theory, conflict processing, and delusional belief

Many reasoning biases that may contribute to delusion formation and/or maintenance are common in healthy individuals. Research indicating that reasoning in the general population proceeds via analytic processes (which depend upon working memory and support hypothetical thought) and intuitive processes (which are autonomous and independent of working memory) may therefore help uncover the source of these biases. Consistent with this possibility, recent studies imply that impaired conflict processing might reduce engagement in analytic reasoning, thereby producing reasoning biases and promoting delusions in individuals with schizophrenia. Progress toward understanding this potential pathway to delusions is currently impeded by ambiguity about whether any of these deficits or biases is necessary or sufficient for the formation and maintenance of delusions. Resolving this ambiguity requires consideration of whether particular cognitive deficits or biases in this putative pathway have causal primacy over other processes that may also participate in the causation of delusions. Accordingly, the present manuscript critically evaluates whether impaired conflict processing is the primary initiating deficit in the generation of reasoning biases that may promote the development and/or maintenance of delusions. Suggestions for future research that may elucidate mechanistic pathways by which reasoning deficits might engender and maintain delusions are subsequently offered.

Predicting Barriers to Treatment for Depression in a U.S. National Sample: A Cross-Sectional, Proof-of-Concept Study

OBJECTIVE

Even though safe and effective treatments for depression are available, many individuals with a diagnosis of depression do not obtain treatment. This study aimed to develop a tool to identify persons who might not initiate treatment among those who acknowledge a need.

METHODS

Data were aggregated from the 2008-2014 U.S. National Survey on Drug Use and Health (N=391,753), including 20,785 adults given a diagnosis of depression by a health care provider in the 12 months before the survey. Machine learning was applied to self-report survey items to develop strategies for identifying individuals who might not get needed treatment.

RESULTS

A derivation cohort aggregated between 2008 and 2013 was used to develop a model that identified the 30.6% of individuals with depression who reported needing but not getting treatment. When applied to independent responses from the 2014 cohort, the model identified 72% of those who did not initiate treatment (p<.01), with a balanced accuracy that was also significantly above chance (71%, p<.01). For individuals who did not get treatment, the model predicted 10 (out of 15) reasons that they endorsed as barriers to treatment, with balanced accuracies between 53% and 65% (p<.05 for all).

CONCLUSIONS

Considerable work is needed to improve follow-up and retention rates after the critical initial meeting in which a patient is given a diagnosis of depression. Routinely collected information about patients with depression could identify those at risk of not obtaining needed treatment, which may inform the development and implementation of interventions to reduce the prevalence of untreated depression.