Prediction of psychosis using neural oscillations and machine learning in neuroleptic-naïve at-risk patients

Dopamine Synthesis Capacity and GABA and Glutamate Levels Separate Antipsychotic-Naïve Patients With First-Episode Psychosis From Healthy Control Subjects in a Multimodal Prediction Model

Background

Disturbances in presynaptic dopamine activity and levels of GABA (gamma-aminobutyric acid) and glutamate plus glutamine collectively may have a role in the pathophysiology of psychosis, although separately they are poor diagnostic markers. We tested whether these neurotransmitters in combination improve the distinction of antipsychotic-naïve patients with first-episode psychosis from healthy control subjects.

Methods

We included 23 patients (mean age 22.3 years, 9 male) and 20 control subjects (mean age 22.4 years, 8 male). We determined dopamine metabolism in the nucleus accumbens and striatum from 18F-fluorodopa (18F-FDOPA) positron emission tomography. We measured GABA levels in the anterior cingulate cortex (ACC) and glutamate plus glutamine levels in the ACC and left thalamus with 3T proton magnetic resonance spectroscopy. We used binominal logistic regression for unimodal prediction when we modeled neurotransmitters individually and for multimodal prediction when we combined the 3 neurotransmitters. We selected the best combination based on Akaike information criterion.

Results

Individual neurotransmitters failed to predict group. Three triple neurotransmitter combinations significantly predicted group after Benjamini-Hochberg correction. The best model (Akaike information criterion 48.5) carried 93.5% of the cumulative model weight. It reached a classification accuracy of 83.7% (p = .003) and included dopamine synthesis capacity (Ki4p) in the nucleus accumbens (p = .664), GABA levels in the ACC (p = .019), glutamate plus glutamine levels in the thalamus (p = .678), and the interaction term Ki4p × GABA (p = .016).

Conclusions

Our multimodal approach proved superior classification accuracy, implying that the pathophysiology of patients represents a combination of neurotransmitter disturbances rather than aberrations in a single neurotransmitter. Particularly aberrant interrelations between Ki4p in the nucleus accumbens and GABA values in the ACC appeared to contribute diagnostic information.

Psychotic disorders as a framework for precision psychiatry

People with psychotic disorders can show marked interindividual variations in the onset of illness, responses to treatment and relapse, but they receive broadly similar clinical care. Precision psychiatry is an approach that aims to stratify people with a given disorder according to different clinical outcomes and tailor treatment to their individual needs. At present, interindividual differences in outcomes of psychotic disorders are difficult to predict on the basis of clinical assessment alone. Therefore, current research in psychosis seeks to build models that predict outcomes by integrating clinical information with a range of biological measures. Here, we review recent progress in the application of precision psychiatry to psychotic disorders and consider the challenges associated with implementing this approach in clinical practice.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Machine learning based prediction and the influence of complement - Coagulation pathway proteins on clinical outcome: Results from the NEURAPRO trial

BACKGROUND

Functional outcomes are important measures in the overall clinical course of psychosis and individuals at clinical high-risk (CHR), however, prediction of functional outcome remains difficult based on clinical information alone. In the first part of this study, we evaluated whether a combination of biological and clinical variables could predict future functional outcome in CHR individuals. The complement and coagulation pathways have previously been identified as being of relevance to the pathophysiology of psychosis and have been found to contribute to the prediction of clinical outcome in CHR participants. Hence, in the second part we extended the analysis to evaluate specifically the relationship of complement and coagulation proteins with psychotic symptoms and functional outcome in CHR.

MATERIALS AND METHODS

We carried out plasma proteomics and measured plasma cytokine levels, and erythrocyte membrane fatty acid levels in a sub-sample (n = 158) from the NEURAPRO clinical trial at baseline and 6 months follow up. Functional outcome was measured using Social and Occupational Functional assessment Score (SOFAS) scale. Firstly, we used support vector machine learning techniques to develop predictive models for functional outcome at 12 months. Secondly, we developed linear regression models to understand the association between 6-month follow-up levels of complement and coagulation proteins with 6-month follow-up measures of positive symptoms summary (PSS) scores and functional outcome.

RESULTS AND CONCLUSION

A prediction model based on clinical and biological data including the plasma proteome, erythrocyte fatty acids and cytokines, poorly predicted functional outcome at 12 months follow-up in CHR participants. In linear regression models, four complement and coagulation proteins (coagulation protein X, Complement C1r subcomponent like protein, Complement C4A & Complement C5) indicated a significant association with functional outcome; and two proteins (coagulation factor IX and complement C5) positively associated with the PSS score. Our study does not provide support for the utility of cytokines, proteomic or fatty acid data for prediction of functional outcomes in individuals at high-risk for psychosis. However, the association of complement protein levels with clinical outcome suggests a role for the complement system and the activity of its related pathway in the functional impairment and positive symptom severity of CHR patients.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

Implication of Electrophysiological Biomarkers in Psychosis: Focusing on Diagnosis and Treatment Response

Precision medicine has been considered a promising approach to diagnosis, treatment, and various interventions, considering the individual clinical and biological characteristics. Recent advances in biomarker development hold promise for guiding a new era of precision medicine style trials for psychiatric illnesses, including psychosis. Electroencephalography (EEG) can directly measure the full spatiotemporal dynamics of neural activation associated with a wide variety of cognitive processes. This manuscript reviews three aspects: prediction of diagnosis, prognostic aspects of disease progression and outcome, and prediction of treatment response that might be helpful in understanding the current status of electrophysiological biomarkers in precision medicine for patients with psychosis. Although previous EEG analysis could not be a powerful method for the diagnosis of psychiatric illness, recent methodological advances have shown the possibility of classifying and detecting mental illness. Some event-related potentials, such as mismatch negativity, have been associated with neurocognition, functioning, and illness progression in schizophrenia. Resting state studies, sophisticated ERP measures, and machine-learning approaches could make technical progress and provide important knowledge regarding neurophysiology, disease progression, and treatment response in patients with schizophrenia. Identifying potential biomarkers for the diagnosis and treatment response in schizophrenia is the first step towards precision medicine.

Global fractional anisotropy predicts transition to psychosis after 12 months in individuals at ultra-high risk for psychosis

OBJECTIVE

Psychosis spectrum disorders are associated with cerebral changes, but the prognostic value and clinical utility of these findings are unclear. Here, we applied a multivariate statistical model to examine the predictive accuracy of global white matter fractional anisotropy (FA) for transition to psychosis in individuals at ultra-high risk for psychosis (UHR).

METHODS

110 UHR individuals underwent 3 Tesla diffusion-weighted imaging and clinical assessments at baseline, and after 6 and 12 months. Using logistic regression, we examined the reliability of global FA at baseline as a predictor for psychosis transition after 12 months. We tested the predictive accuracy, sensitivity and specificity of global FA in a multivariate prediction model accounting for potential confounders to FA (head motion in scanner, age, gender, antipsychotic medication, parental socioeconomic status and activity level). In secondary analyses, we tested FA as a predictor of clinical symptoms and functional level using multivariate linear regression.

RESULTS

Ten UHR individuals had transitioned to psychosis after 12 months (9%). The model reliably predicted transition at 12 months (χ²  = 17.595, p = 0.040), accounted for 15-33% of the variance in transition outcome with a sensitivity of 0.70, a specificity of 0.88 and AUC of 0.87. Global FA predicted level of UHR symptoms (R²  = 0.055, F = 6.084, p = 0.016) and functional level (R²  = 0.040, F = 4.57, p = 0.036) at 6 months, but not at 12 months.

CONCLUSION

Global FA provided prognostic information on clinical outcome and symptom course of UHR individuals. Our findings suggest that the application of prediction models including neuroimaging data can inform clinical management on risk for psychosis transition.

Prevention of Suicidal Relapses in Adolescents With a Smartphone Application: Bayesian Network Analysis of a Preclinical Trial Using In Silico Patient Simulations

Background

Recently, artificial intelligence technologies and machine learning methods have offered attractive prospects to design and manage crisis response processes, especially in suicide crisis management. In other domains, most algorithms are based on big data to help diagnose and suggest rational treatment options in medicine. But data in psychiatry are related to behavior and clinical evaluation. They are more heterogeneous, less objective, and incomplete compared to other fields of medicine. Consequently, the use of psychiatric clinical data may lead to less accurate and sometimes impossible-to-build algorithms and provide inefficient digital tools. In this case, the Bayesian network (BN) might be helpful and accurate when constructed from expert knowledge. Medical Companion is a government-funded smartphone application based on repeated questions posed to the subject and algorithm-matched advice to prevent relapse of suicide attempts within several months.

Objective

Our paper aims to present our development of a BN algorithm as a medical device in accordance with the American Psychiatric Association digital healthcare guidelines and to provide results from a preclinical phase.

Methods

The experts are psychiatrists working in university hospitals who are experienced and trained in managing suicidal crises. As recommended when building a BN, we divided the process into 2 tasks. Task 1 is structure determination, representing the qualitative part of the BN. The factors were chosen for their known and demonstrated link with suicidal risk in the literature (clinical, behavioral, and psychometrics) and therapeutic accuracy (advice). Task 2 is parameter elicitation, with the conditional probabilities corresponding to the quantitative part. The 4-step simulation (use case) process allowed us to ensure that the advice was adapted to the clinical states of patients and the context.

Results

For task 1, in this formative part, we defined clinical questions related to the mental state of the patients, and we proposed specific factors related to the questions. Subsequently, we suggested specific advice related to the patient’s state. We obtained a structure for the BN with a graphical representation of causal relations between variables. For task 2, several runs of simulations confirmed the a priori model of experts regarding mental state, refining the precision of our model. Moreover, we noticed that the advice had the same distribution as the previous state and was clinically relevant. After 2 rounds of simulation, the experts found the exact match.

Conclusions

BN is an efficient methodology to build an algorithm for a digital assistant dedicated to suicidal crisis management. Digital psychiatry is an emerging field, but it needs validation and testing before being used with patients. Similar to psychotropics, any medical device requires a phase II (preclinical) trial. With this method, we propose another step to respond to the American Psychiatric Association guidelines.

Trial Registration

ClinicalTrials.gov NCT03975881; https://clinicaltrials.gov/ct2/show/NCT03975881

Longitudinal outcome of attenuated positive symptoms, negative symptoms, functioning and remission in people at clinical high risk for psychosis: a meta-analysis

BACKGROUND

Little is known about clinical outcomes other than transition to psychosis in people at Clinical High-Risk for psychosis (CHR-P). Our aim was to comprehensively meta-analytically evaluate for the first time a wide range of clinical and functional outcomes beyond transition to psychosis in CHR-P individuals.

METHODS

PubMed and Web of Science were searched until November 2020 in this PRISMA compliant meta-analysis (PROSPERO:CRD42020206271). Individual longitudinal studies conducted in individuals at CHR-P providing data on at least one of our outcomes of interest were included. We carried out random-effects pairwise meta-analyses, meta-regressions, and assessed publication bias and study quality. Analyses were two-tailed with α=0.05.

FINDINGS

75 prospective studies were included (n=5,288, age=20.0 years, females=44.5%). Attenuated positive symptoms improved at 12 (Hedges' g=0.753, 95%CI=0.495-1.012) and 24 (Hedges' g=0.836, 95%CI=0.463-1.209), but not ≥36 months (Hedges' g=0.315. 95%CI=-0.176-0.806). Negative symptoms improved at 12 (Hedges' g=0.496, 95%CI=0.315-0.678), but not 24 (Hedges' g=0.499, 95%CI=-0.137-1.134) or ≥36 months (Hedges' g=0.033, 95%CI=-0.439-0.505). Depressive symptoms improved at 12 (Hedges' g=0.611, 95%CI=0.441-0.782) and 24 (Hedges' g=0.583, 95%CI=0.364-0.803), but not ≥36 months (Hedges' g=0.512 95%CI=-0.337-1.361). Functioning improved at 12 (Hedges' g=0.711, 95%CI=0.488-0.934), 24 (Hedges' g=0.930, 95%CI=0.553-1.306) and ≥36 months (Hedges' g=0.392, 95%CI=0.117-0.667). Remission from CHR-P status occurred in 33.4% (95%CI=22.6-44.1%) at 12 months, 41.4% (95%CI=32.3-50.5%) at 24 months and 42.4% (95%CI=23.4-61.3%) at ≥36 months. Heterogeneity across the included studies was significant and ranged from I2=53.6% to I2=96.9%. The quality of the included studies (mean±SD) was 4.6±1.1 (range=2-8).

INTERPRETATION

CHR-P individuals improve on symptomatic and functional outcomes over time, but these improvements are not maintained in the longer term, and less than half fully remit. Prolonged duration of care may be needed for this patient population to optimize outcomes.

FUNDING

None.

The relationship between cognitive deficits and impaired short-term functional outcome in clinical high-risk for psychosis participants: A machine learning and modelling approach

Poor functional outcomes are common in individuals at clinical high-risk for psychosis (CHR-P), but the contribution of cognitive deficits remains unclear. We examined the potential utility of cognitive variables in predictive models of functioning at baseline and follow-up with machine learning methods. Additional models fitted on baseline functioning variables were used as a benchmark to evaluate model performance. Data were available for 1) 146 CHR-P individuals of whom 118 completed a 6- and/or 12-month follow-up, 2) 47 participants not fulfilling CHR criteria (CHR-Ns) but displaying affective and substance use disorders and 3) 55 healthy controls (HCs). Predictors of baseline global assessment of functioning (GAF) scores were selected by L1-regularised least angle regression and then used to train classifiers to predict functional outcome in CHR-P individuals. In CHR-P participants, cognitive deficits together with clinical and functioning variables explained 41% of the variance in baseline GAF scores while cognitive variables alone explained 12%. These variables allowed classification of functional outcome with an average balanced accuracy (BAC) of 63% in both mixed- and cross-site models. However, higher accuracies (68%-70%) were achieved using classifiers fitted only on baseline functioning variables. Our findings suggest that cognitive deficits, alongside clinical and functioning variables, displayed robust relationships with impaired functioning in CHR-P participants at baseline and follow-up. Moreover, these variables allow for prediction of functional outcome. However, models based on baseline functioning variables showed a similar performance, highlighting the need to develop more accurate algorithms for predicting functional outcome in CHR-P participants.

Neural Oscillatory Abnormalities During Gaze Processing in Schizophrenia: Evidence of Reduced Theta Phase Consistency and Inter-areal Theta-Gamma Coupling

BACKGROUND

Abnormal gaze discrimination in schizophrenia (SZ) is associated with impairment in social functioning, but the neural mechanisms remain unclear. Evidence suggests that local neural oscillations and inter-areal communication through neural synchronization are critical physiological mechanisms supporting basic and complex cognitive processes. The roles of these mechanisms in abnormal gaze processing in SZ have not been investigated. The present study examined local neural oscillations and connectivity between anterior and bilateral posterior brain areas during gaze processing.

METHODS

During electroencephalography recording, 28 participants with SZ and 34 healthy control participants completed a gaze discrimination task. Time-frequency decomposition of electroencephalography data was used to examine neural oscillatory power and intertrial phase consistency at bilateral posterior and midline anterior scalp sites. In addition, connectivity between these anterior and posterior sites, in terms of cross-frequency coupling between theta phase and gamma amplitude, was examined using the Kullback-Leibler Modulation Index.

RESULTS

Participants with SZ showed reduced total power of theta-band activity relative to healthy control participants at all sites examined. This group difference could be accounted for by reduced intertrial phase consistency of theta activity in SZ participants, which was related to reduced gaze discrimination accuracy in SZ. In addition, SZ participants exhibited reduced Kullback-Leibler indexing, both feedforward and feedback connectivity, between the posterior and anterior sites.

CONCLUSIONS

These findings suggest that abnormal theta phase consistency and dysconnection between posterior face processing and anterior areas may underlie gaze processing deficits in SZ.

EEG-Based Measures in At-Risk Mental State and Early Stages of Schizophrenia: A Systematic Review

Introduction: Electrophysiological (EEG) abnormalities in subjects with schizophrenia have been largely reported. In the last decades, research has shifted to the identification of electrophysiological alterations in the prodromal and early phases of the disorder, focusing on the prediction of clinical and functional outcome. The identification of neuronal aberrations in subjects with a first episode of psychosis (FEP) and in those at ultra high-risk (UHR) or clinical high-risk (CHR) to develop a psychosis is crucial to implement adequate interventions, reduce the rate of transition to psychosis, as well as the risk of irreversible functioning impairment. The aim of the review is to provide an up-to-date synthesis of the electrophysiological findings in the at-risk mental state and early stages of schizophrenia. Methods: A systematic review of English articles using Pubmed, Scopus, and PsychINFO was undertaken in July 2020. Additional studies were identified by hand-search. Electrophysiological studies that included at least one group of FEP or subjects at risk to develop psychosis, compared to healthy controls (HCs), were considered. The heterogeneity of the studies prevented a quantitative synthesis. Results: Out of 319 records screened, 133 studies were included in a final qualitative synthesis. Included studies were mainly carried out using frequency analysis, microstates and event-related potentials. The most common findings included an increase in delta and gamma power, an impairment in sensory gating assessed through P50 and N100 and a reduction of Mismatch Negativity and P300 amplitude in at-risk mental state and early stages of schizophrenia. Progressive changes in some of these electrophysiological measures were associated with transition to psychosis and disease course. Heterogeneous data have been reported for indices evaluating synchrony, connectivity, and evoked-responses in different frequency bands. Conclusions: Multiple EEG-indices were altered during at-risk mental state and early stages of schizophrenia, supporting the hypothesis that cerebral network dysfunctions appear already before the onset of the disorder. Some of these alterations demonstrated association with transition to psychosis or poor functional outcome. However, heterogeneity in subjects' inclusion criteria, clinical measures and electrophysiological methods prevents drawing solid conclusions. Large prospective studies are needed to consolidate findings concerning electrophysiological markers of clinical and functional outcome.

Thalamus-related anomalies as candidate mechanism-based biomarkers for psychosis

Identification of reliable biomarkers of prognosis in subjects with high risk to psychosis is an essential step to improve care and treatment of this population of help-seekers. Longitudinal studies highlight some clinical criteria, cognitive deficits, patterns of gray matter alterations and profiles of blood metabolites that provide some levels of prediction regarding the conversion to psychosis. Further effort is warranted to validate these results and implement these types of approaches in clinical settings. Such biomarkers may however fall short in entangling the biological mechanisms underlying the disease progression, an essential step in the development of novel therapies. Circuit-based approaches, which map on well-identified cerebral functions, could meet these needs. Converging evidence indicates that thalamus abnormalities are central to schizophrenia pathophysiology, contributing to clinical symptoms, cognitive and sensory deficits. This review highlights the various thalamus-related anomalies reported in individuals with genetic risks and in the different phases of the disorder, from prodromal to chronic stages. Several anomalies are potent endophenotypes, while others exist in clinical high-risk subjects and worsen in those who convert to full psychosis. Aberrant functional coupling between thalamus and cortex, low glutamate content and readouts from resting EEG carry predictive values for transition to psychosis or functional outcome. In this context, thalamus-related anomalies represent a valuable entry point to tackle circuit-based alterations associated with the emergence of psychosis. This review also proposes that longitudinal surveys of neuroimaging, EEG readouts associated with circuits encompassing the mediodorsal, pulvinar in high-risk individuals could unveil biological mechanisms contributing to this psychiatric disorder.

Cortical Complexity in People at Ultra-High-Risk for Psychosis Moderated by Childhood Trauma

Subjects with ultra-high risk (UHR) states for psychosis show brain structural volume changes similar to first-episode psychosis and also elevated incidence of environmental risk factors like childhood trauma. It is unclear, however, whether early neurodevelopmental trajectories are altered in UHR. We screened a total of 12,779 first-year Chinese students to enroll 36 UHR subjects (based on clinical interviews) and 59 non-UHR healthy controls for a case-control study of markers of early neurodevelopment. Subjects underwent 3T MRI scanning and clinical characterization, including the childhood trauma questionnaire (CTQ). We then used the CAT12 toolbox to analyse structural brain scans for cortical surface complexity, a spherical harmonics-based marker of early neurodevelopmental changes. While we did not find statistically significant differences between the groups, a trend level finding for reduced cortical complexity (CC) in UHR vs. non-UHR subjects emerged in the left superior temporal cortex (and adjacent insular and transverse temporal cortices), and this trend level association was significantly moderated by childhood trauma (CTQ score). Our findings indicate that UHR subjects tend to show abnormal cortical surface morphometry, in line with recent research; more importantly, however, this association seems to be considerably modulated by early environmental impacts. Hence, our results provide an indication of environmental or gene × environment interactions on early neurodevelopment leading up to elevated psychosis risk.

Implementing Precision Psychiatry: A Systematic Review of Individualized Prediction Models for Clinical Practice

BACKGROUND

The impact of precision psychiatry for clinical practice has not been systematically appraised. This study aims to provide a comprehensive review of validated prediction models to estimate the individual risk of being affected with a condition (diagnostic), developing outcomes (prognostic), or responding to treatments (predictive) in mental disorders.

METHODS

PRISMA/RIGHT/CHARMS-compliant systematic review of the Web of Science, Cochrane Central Register of Reviews, and Ovid/PsycINFO databases from inception until July 21, 2019 (PROSPERO CRD42019155713) to identify diagnostic/prognostic/predictive prediction studies that reported individualized estimates in psychiatry and that were internally or externally validated or implemented. Random effect meta-regression analyses addressed the impact of several factors on the accuracy of prediction models.

FINDINGS

Literature search identified 584 prediction modeling studies, of which 89 were included. 10.4% of the total studies included prediction models internally validated (n = 61), 4.6% models externally validated (n = 27), and 0.2% (n = 1) models considered for implementation. Across validated prediction modeling studies (n = 88), 18.2% were diagnostic, 68.2% prognostic, and 13.6% predictive. The most frequently investigated condition was psychosis (36.4%), and the most frequently employed predictors clinical (69.5%). Unimodal compared to multimodal models (β = .29, P = .03) and diagnostic compared to prognostic (β = .84, p < .0001) and predictive (β = .87, P = .002) models were associated with increased accuracy.

INTERPRETATION

To date, several validated prediction models are available to support the diagnosis and prognosis of psychiatric conditions, in particular, psychosis, or to predict treatment response. Advancements of knowledge are limited by the lack of implementation research in real-world clinical practice. A new generation of implementation research is required to address this translational gap.

Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes: A Meta-analytic View on the State of the Art

BACKGROUND

The clinical high risk (CHR) paradigm has facilitated research into the underpinnings of help-seeking individuals at risk for developing psychosis, aiming at predicting and possibly preventing transition to the overt disorder. Statistical methods such as machine learning and Cox regression have provided the methodological basis for this research by enabling the construction of diagnostic models (i.e., distinguishing CHR individuals from healthy individuals) and prognostic models (i.e., predicting a future outcome) based on different data modalities, including clinical, neurocognitive, and neurobiological data. However, their translation to clinical practice is still hindered by the high heterogeneity of both CHR populations and methodologies applied.

METHODS

We systematically reviewed the literature on diagnostic and prognostic models built on Cox regression and machine learning. Furthermore, we conducted a meta-analysis on prediction performances investigating heterogeneity of methodological approaches and data modality.

RESULTS

A total of 44 articles were included, covering 3707 individuals for prognostic studies and 1052 individuals for diagnostic studies (572 CHR patients and 480 healthy control subjects). CHR patients could be classified against healthy control subjects with 78% sensitivity and 77% specificity. Across prognostic models, sensitivity reached 67% and specificity reached 78%. Machine learning models outperformed those applying Cox regression by 10% sensitivity. There was a publication bias for prognostic studies yet no other moderator effects.

CONCLUSIONS

Our results may be driven by substantial clinical and methodological heterogeneity currently affecting several aspects of the CHR field and limiting the clinical implementability of the proposed models. We discuss conceptual and methodological harmonization strategies to facilitate more reliable and generalizable models for future clinical practice.

Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up: Comparison of connectomic, structural, and clinical predictors

In a machine learning setting, this study aims to compare the prognostic utility of connectomic, brain structural, and clinical/demographic predictors of individual change in symptom severity in individuals with schizophrenia. Symptom severity at baseline and 1-year follow-up was assessed in 30 individuals with a schizophrenia-spectrum disorder using the Brief Psychiatric Rating Scale. Structural and functional neuroimaging was acquired in all individuals at baseline. Machine learning classifiers were trained to predict whether individuals improved or worsened with respect to positive, negative, and overall symptom severity. Classifiers were trained using various combinations of predictors, including regional cortical thickness and gray matter volume, static and dynamic resting-state connectivity, and/or baseline clinical and demographic variables. Relative change in overall symptom severity between baseline and 1-year follow-up varied markedly among individuals (interquartile range: 55%). Dynamic resting-state connectivity measured within the default-mode network was the most accurate single predictor of change in positive (accuracy: 87%), negative (83%), and overall symptom severity (77%) at follow-up. Incorporating predictors based on regional cortical thickness, gray matter volume, and baseline clinical variables did not markedly improve prediction accuracy and the prognostic utility of these predictors in isolation was moderate (<70%). Worsening negative symptoms at 1-year follow-up were predicted by hyper-connectivity and hypo-dynamism within the default-mode network at baseline assessment, while hypo-connectivity and hyper-dynamism predicted worsening positive symptoms. Given the modest sample size investigated, we recommend giving precedence to the relative ranking of the predictors investigated in this study, rather than the prediction accuracy estimates.

Potential Roles of Redox Dysregulation in the Development of Schizophrenia

Converging evidence implicates redox dysregulation as a pathological mechanism driving the emergence of psychosis. Increased oxidative damage and decreased capacity of intracellular redox modulatory systems are consistent findings in persons with schizophrenia as well as in persons at clinical high risk who subsequently developed frank psychosis. Levels of glutathione, a key regulator of cellular redox status, are reduced in the medial prefrontal cortex, striatum, and thalamus in schizophrenia. In humans with schizophrenia and in rodent models recapitulating various features of schizophrenia, redox dysregulation is linked to reductions of parvalbumin containing gamma-aminobutyric acid (GABA) interneurons and volumes of their perineuronal nets, white matter abnormalities, and microglia activation. Importantly, the activity of transcription factors, kinases, and phosphatases regulating diverse aspects of neurodevelopment and synaptic plasticity varies according to cellular redox state. Molecules regulating interneuron function under redox control include NMDA receptor subunits GluN1 and GluN2A as well as KEAP1 (regulator of transcription factor NRF2). In a rodent schizophrenia model characterized by impaired glutathione synthesis, the Gclm knockout mouse, oxidative stress activated MMP9 (matrix metalloprotease 9) via its redox-responsive regulatory sites, causing a cascade of molecular events leading to microglia activation, perineural net degradation, and impaired NMDA receptor function. Molecular pathways under redox control are implicated in the etiopathology of schizophrenia and are attractive drug targets for individualized drug therapy trials in the contexts of prevention and treatment of psychosis.

Models Predicting Psychosis in Patients With High Clinical Risk: A Systematic Review

OBJECTIVE

The present study reviews predictive models used to improve prediction of psychosis onset in individuals at clinical high risk for psychosis (CHR), using clinical, biological, neurocognitive, environmental, and combinations of predictors.

METHODS

A systematic literature search on PubMed was carried out (from 1998 through 2019) to find all studies that developed or validated a model predicting the transition to psychosis in CHR subjects.

RESULTS

We found 1,406 records. Thirty-eight of them met the inclusion criteria; 11 studies using clinical predictive models, seven studies using biological models, five studies using neurocognitive models, five studies using environmental models, and 18 studies using combinations of predictive models across different domains. While the highest positive predictive value (PPV) in clinical, biological, neurocognitive, and combined predictive models were relatively high (all above 83), the highest PPV across environmental predictive models was modest (63%). Moreover, none of the combined models showed a superiority when compared with more parsimonious models (using only neurocognitive, clinical, biological, or environmental factors).

CONCLUSIONS

The use of predictive models may allow high prognostic accuracy for psychosis prediction in CHR individuals. However, only ten studies had performed an internal validation of their models. Among the models with the highest PPVs, only the biological and neurocognitive but not the combined models underwent validation. Further validation of predicted models is needed to ensure external validity.

Structural and functional imaging markers for susceptibility to psychosis

The introduction of clinical criteria for the operationalization of psychosis high risk provided a basis for early detection and treatment of vulnerable individuals. However, about two-thirds of people meeting clinical high-risk (CHR) criteria will never develop a psychotic disorder. In the effort to increase prognostic precision, structural and functional neuroimaging have received growing attention as a potentially useful resource in the prediction of psychotic transition in CHR patients. The present review summarizes current research on neuroimaging biomarkers in the CHR state, with a particular focus on their prognostic utility and limitations. Large, multimodal/multicenter studies are warranted to address issues important for clinical applicability such as generalizability and replicability, standardization of clinical definitions and neuroimaging methods, and consideration of contextual factors (e.g., age, comorbidity).

Clinical-learning versus machine-learning for transdiagnostic prediction of psychosis onset in individuals at-risk

Predicting the onset of psychosis in individuals at-risk is based on robust prognostic model building methods including a priori clinical knowledge (also termed clinical-learning) to preselect predictors or machine-learning methods to select predictors automatically. To date, there is no empirical research comparing the prognostic accuracy of these two methods for the prediction of psychosis onset. In a first experiment, no improved performance was observed when machine-learning methods (LASSO and RIDGE) were applied-using the same predictors-to an individualised, transdiagnostic, clinically based, risk calculator previously developed on the basis of clinical-learning (predictors: age, gender, age by gender, ethnicity, ICD-10 diagnostic spectrum), and externally validated twice. In a second experiment, two refined versions of the published model which expanded the granularity of the ICD-10 diagnosis were introduced: ICD-10 diagnostic categories and ICD-10 diagnostic subdivisions. Although these refined versions showed an increase in apparent performance, their external performance was similar to the original model. In a third experiment, the three refined models were analysed under machine-learning and clinical-learning with a variable event per variable ratio (EPV). The best performing model under low EPVs was obtained through machine-learning approaches. The development of prognostic models on the basis of a priori clinical knowledge, large samples and adequate events per variable is a robust clinical prediction method to forecast psychosis onset in patients at-risk, and is comparable to machine-learning methods, which are more difficult to interpret and implement. Machine-learning methods should be preferred for high dimensional data when no a priori knowledge is available.

Predictors of Transition to Psychosis in Individuals at Clinical High Risk

PURPOSE OF REVIEW

Current research is examining predictors of the transition to psychosis in youth who are at clinical high risk based on attenuated psychotic symptoms (APS). Determining predictors of the development of psychosis is important for an improved understanding of mechanisms as well as the development of preventative strategies. The purpose is to review the most recent literature identifying predictors of the transition to psychosis in those who are already assessed as being at risk.

RECENT FINDINGS

Multidomain models, in particular, integrated models of symptoms, social functioning, and cognition variables, achieve better predictive performance than individual factors. There are many methodological issues; however, several solutions have now been described in the literature. For youth who already have APS, predicting who may go on to later develop psychosis is possible. Several studies are underway in large consortiums that may overcome some of the methodological concerns and develop improved means of prediction.

Ketamine Alters Lateral Prefrontal Oscillations in a Rule-Based Working Memory Task

Acute administration of N-methyl-D-aspartate receptor (NMDAR) antagonists in healthy humans and animals produces working memory deficits similar to those observed in schizophrenia. However, it is unclear whether they also lead to altered low-frequency (≤60 Hz) neural oscillatory activities similar to those associated with schizophrenia during working memory processes. Here, we recorded local field potentials (LFPs) and single-unit activity from the lateral prefrontal cortex (LPFC) of three male rhesus macaque monkeys while they performed a rule-based prosaccade and antisaccade working memory task both before and after systemic injections of a subanesthetic dose (≤0.7 mg/kg) of ketamine. Accompanying working-memory impairment, ketamine enhanced the low-gamma-band (30-60 Hz) and dampened the beta-band (13-30 Hz) oscillatory activities in the LPFC during both delay periods and intertrial intervals. It also increased task-related alpha-band activities, likely reflecting compromised attention. Beta-band oscillations may be especially relevant to working memory processes because stronger beta power weakly but significantly predicted shorter saccadic reaction time. Also in beta band, ketamine reduced the performance-related oscillation as well as the rule information encoded in the spectral power. Ketamine also reduced rule information in the spike field phase consistency in almost all frequencies up to 60 Hz. Our findings support NMDAR antagonists in nonhuman primates as a meaningful model for altered neural oscillations and synchrony, which reflect a disorganized network underlying the working memory deficits in schizophrenia.SIGNIFICANCE STATEMENT Low doses of ketamine, an NMDAR blocker, produce working memory deficits similar to those observed in schizophrenia. In the lateral prefrontal cortex, a key brain region for working memory, we found that ketamine altered neural oscillatory activities in similar ways that differentiate schizophrenic patients and healthy subjects during both task and nontask periods. Ketamine induced stronger gamma (30-60 Hz) and weaker beta (13-30 Hz) oscillations, reflecting local hyperactivity and reduced long-range communications. Furthermore, ketamine reduced performance-related oscillatory activities, as well as the rule information encoded in the oscillations and in the synchrony between single-cell activities and oscillations. The ketamine model helps link the molecular and cellular basis of neural oscillatory changes to the working memory deficit in schizophrenia.

Machine Learning Approaches for Clinical Psychology and Psychiatry

Machine learning approaches for clinical psychology and psychiatry explicitly focus on learning statistical functions from multidimensional data sets to make generalizable predictions about individuals. The goal of this review is to provide an accessible understanding of why this approach is important for future practice given its potential to augment decisions associated with the diagnosis, prognosis, and treatment of people suffering from mental illness using clinical and biological data. To this end, the limitations of current statistical paradigms in mental health research are critiqued, and an introduction is provided to critical machine learning methods used in clinical studies. A selective literature review is then presented aiming to reinforce the usefulness of machine learning methods and provide evidence of their potential. In the context of promising initial results, the current limitations of machine learning approaches are addressed, and considerations for future clinical translation are outlined.

Prediction of transition to psychosis in patients with a clinical high risk for psychosis: a systematic review of methodology and reporting

BACKGROUND

To enhance indicated prevention in patients with a clinical high risk (CHR) for psychosis, recent research efforts have been increasingly directed towards estimating the risk of developing psychosis on an individual level using multivariable clinical prediction models. The aim of this study was to systematically review the methodological quality and reporting of studies developing or validating such models.

METHOD

A systematic literature search was carried out (up to 14 March 2016) to find all studies that developed or validated a clinical prediction model predicting the transition to psychosis in CHR patients. Data were extracted using a comprehensive item list which was based on current methodological recommendations.

RESULTS

A total of 91 studies met the inclusion criteria. None of the retrieved studies performed a true external validation of an existing model. Only three studies (3.5%) had an event per variable ratio of at least 10, which is the recommended minimum to avoid overfitting. Internal validation was performed in only 14 studies (15%) and seven of these used biased internal validation strategies. Other frequently observed modeling approaches not recommended by methodologists included univariable screening of candidate predictors, stepwise variable selection, categorization of continuous variables, and poor handling and reporting of missing data.

CONCLUSIONS

Our systematic review revealed that poor methods and reporting are widespread in prediction of psychosis research. Since most studies relied on small sample sizes, did not perform internal or external cross-validation, and used poor model development strategies, most published models are probably overfitted and their reported predictive accuracy is likely to be overoptimistic.

Prediction of conversion to psychosis in individuals with an at-risk mental state: a brief update on recent developments

PURPOSE OF REVIEW

So far, only little more than one-third of individuals classified as being at-risk for psychosis have been shown to actually convert to frank psychosis during follow-up. There have therefore been enormous efforts to improve the accuracy of predicting this transition. We reviewed the most recent studies in the field with the aim to clarify whether accuracy of prediction has been improved by the different research endeavors and what could be done to further improve it, and/or what alternative goals research should pursue.

RECENT FINDINGS

A total of 56 studies published between May 2015 and December 2016 were included, of which eight were meta-analyses. New meta-analytical evidence confirms that established instruments for checking clinical risk criteria have an excellent clinical utility in individuals referred to high-risk services. Within a such identified group of ultra-high-risk (UHR) individuals, especially Brief Limited Intermittent Psychotic Symptoms and Attenuated Psychotic Symptoms seem to predict transition. Further assessments should be performed within the UHR individuals, as risk of transition seems particularly high in those with an even higher severity of certain symptoms such as suspiciousness or anhedonia, in those with lower global or social functioning, poor neurocognitive performance or cannabis abuse. Also, electroencephalography, neuroimaging and blood biomarkers might contribute to improving individual prediction. The most promising approach certainly is a staged multidomain assessment. Risk calculators to integrate all data for an individualized prediction are being developed.

SUMMARY

Prediction of psychosis is already possible with an excellent prognostic performance based on clinical assessments. Recent studies show that this accuracy can be further improved by using multidomain approaches and modern statistics for individualized prediction. The challenge now is the translation into the clinic with a broad clinical implementation.

Analysis of Gamma-Band Activity from Human EEG Using Empirical Mode Decomposition

The purpose of this paper is to determine whether gamma-band activity detection is improved when a filter, based on empirical mode decomposition (EMD), is added to the pre-processing block of single-channel electroencephalography (EEG) signals. EMD decomposes the original signal into a finite number of intrinsic mode functions (IMFs). EEGs from 25 control subjects were registered in basal and motor activity (hand movements) using only one EEG channel. Over the basic signal, IMF signals are computed. Gamma-band activity is computed using power spectrum density in the 30–60 Hz range. Event-related synchronization (ERS) was defined as the ratio of motor and basal activity. To evaluate the performance of the new EMD based method, ERS was computed from the basic and IMF signals. The ERS obtained using IMFs improves, from 31.00% to 73.86%, on the original ERS for the right hand, and from 22.17% to 47.69% for the left hand. As EEG processing is improved, the clinical applications of gamma-band activity will expand.

Alpha oscillations underlie working memory abnormalities in the psychosis high-risk state

Working memory (WM) functioning, known to be modulated by neural oscillations, is impaired in schizophrenic psychoses. It remains unclear whether in the psychosis high-risk state, WM encoding is altered or whether patients are impaired at shielding their WM against distractors. We employed single-trial analyses of neurophysiological and behavioral data recorded during a WM paradigm, designed to include predictable distractors, on 18 patients with an at-risk mental state for psychosis (ARMS, 26.1±5.45 years) and 21 healthy controls (HCs, 25.5±3.95 years). Strong distractors were associated with reduced WM accuracy (p=0.036), but only ARMS patients required more processing time for strong distractors (p=0.002). Increased parieto-occipital alpha amplitude preceding distractor presentations was associated with enhanced accuracy only in HCs (p=0.009). During encoding, increased intertrial alpha phase locking values were associated with increased performance. Reduced shielding mechanisms against distractors in ARMS patients could lead to defective WM maintenance, which may result in significant confusion that may contribute to the formation of psychotic symptoms.

A Neurophysiological Perspective on a Preventive Treatment against Schizophrenia Using Transcranial Electric Stimulation of the Corticothalamic Pathway

Schizophrenia patients are waiting for a treatment free of detrimental effects. Psychotic disorders are devastating mental illnesses associated with dysfunctional brain networks. Ongoing brain network gamma frequency (30–80 Hz) oscillations, naturally implicated in integrative function, are excessively amplified during hallucinations, in at-risk mental states for psychosis and first-episode psychosis. So, gamma oscillations represent a bioelectrical marker for cerebral network disorders with prognostic and therapeutic potential. They accompany sensorimotor and cognitive deficits already present in prodromal schizophrenia. Abnormally amplified gamma oscillations are reproduced in the corticothalamic systems of healthy humans and rodents after a single systemic administration, at a psychotomimetic dose, of the glutamate N-methyl-d-aspartate receptor antagonist ketamine. These translational ketamine models of prodromal schizophrenia are thus promising to work out a preventive noninvasive treatment against first-episode psychosis and chronic schizophrenia. In the present essay, transcranial electric stimulation (TES) is considered an appropriate preventive therapeutic modality because it can influence cognitive performance and neural oscillations. Here, I highlight clinical and experimental findings showing that, together, the corticothalamic pathway, the thalamus, and the glutamatergic synaptic transmission form an etiopathophysiological backbone for schizophrenia and represent a potential therapeutic target for preventive TES of dysfunctional brain networks in at-risk mental state patients against psychotic disorders.

Improving Prognostic Accuracy in Subjects at Clinical High Risk for Psychosis: Systematic Review of Predictive Models and Meta-analytical Sequential Testing Simulation

Discriminating subjects at clinical high risk (CHR) for psychosis who will develop psychosis from those who will not is a prerequisite for preventive treatments. However, it is not yet possible to make any personalized prediction of psychosis onset relying only on the initial clinical baseline assessment. Here, we first present a systematic review of prognostic accuracy parameters of predictive modeling studies using clinical, biological, neurocognitive, environmental, and combinations of predictors. In a second step, we performed statistical simulations to test different probabilistic sequential 3-stage testing strategies aimed at improving prognostic accuracy on top of the clinical baseline assessment. The systematic review revealed that the best environmental predictive model yielded a modest positive predictive value (PPV) (63%). Conversely, the best predictive models in other domains (clinical, biological, neurocognitive, and combined models) yielded PPVs of above 82%. Using only data from validated models, 3-stage simulations showed that the highest PPV was achieved by sequentially using a combined (clinical + electroencephalography), then structural magnetic resonance imaging and then a blood markers model. Specifically, PPV was estimated to be 98% (number needed to treat, NNT = 2) for an individual with 3 positive sequential tests, 71%-82% (NNT = 3) with 2 positive tests, 12%-21% (NNT = 11-18) with 1 positive test, and 1% (NNT = 219) for an individual with no positive tests. This work suggests that sequentially testing CHR subjects with predictive models across multiple domains may substantially improve psychosis prediction following the initial CHR assessment. Multistage sequential testing may allow individual risk stratification of CHR individuals and optimize the prediction of psychosis.

Spatiotemporal processing of somatosensory stimuli in schizotypy

Unusual interaction behaviors and perceptual aberrations, like those occurring in schizotypy and schizophrenia, may in part originate from impaired remapping of environmental stimuli in the body space. Such remapping is contributed by the integration of tactile and proprioceptive information about current body posture with other exteroceptive spatial information. Surprisingly, no study has investigated whether alterations in such remapping occur in psychosis-prone individuals. Four hundred eleven students were screened with respect to schizotypal traits using the Schizotypal Personality Questionnaire. A subgroup of them, classified as low, moderate, and high schizotypes were to perform a temporal order judgment task of tactile stimuli delivered on their hands, with both uncrossed and crossed arms. Results revealed marked differences in touch remapping in the high schizotypes as compared to low and moderate schizotypes. For the first time here we reveal that the remapping of environmental stimuli in the body space, an essential function to demarcate the boundaries between self and external world, is altered in schizotypy. Results are discussed in relation to recent models of 'self-disorders' as due to perceptual incoherence.

Genetics of Schizophrenia: Historical Insights and Prevailing Evidence

Schizophrenia's (SZ's) heritability and familial transmission have been known for several decades; however, despite the clear evidence for a genetic component, it has been very difficult to pinpoint specific causative genes. Even so genetic studies have taught us a lot, even in the pregenomic era, about the molecular underpinnings and disease-relevant pathways. Recurring themes emerged revealing the involvement of neurodevelopmental processes, glutamate regulation, and immune system differential activation in SZ etiology. The recent emergence of epigenetic studies aimed at shedding light on the biological mechanisms underlying SZ has provided another layer of information in the investigation of gene and environment interactions. However, this epigenetic insight also brings forth another layer of complexity to the (epi)genomic landscape such as interactions between genetic variants, epigenetic marks-including cross-talk between DNA methylation and histone modification processes-, gene expression regulation, and environmental influences. In this review, we seek to synthesize perspectives, including limitations and obstacles yet to overcome, from genetic and epigenetic literature on SZ through a qualitative review of risk factors and prevailing hypotheses. Encouraged by the findings of both genetic and epigenetic studies to date, as well as the continued development of new technologies to collect and interpret large-scale studies, we are left with a positive outlook for the future of elucidating the molecular genetic mechanisms underlying SZ and other complex neuropsychiatric disorders.

Neural oscillations in antipsychotic-naïve patients with a first psychotic episode

OBJECTIVES

In chronic schizophrenic psychoses, oscillatory abnormalities predominantly occur in prefrontal cortical regions and are associated with reduced communication across cortical areas. Nevertheless, it remains unclear whether similar alterations can be observed in patients with a first episode of psychosis (FEP), a state characterised by pathological features occurring in both late prodromal patients and initial phases of frank schizophrenic psychoses.

METHODS

We assessed resting-state electroencephalographic data of 31 antipsychotic-naïve FEP patients and 29 healthy controls (HC). We investigated the three-dimensional (3D) current source density (CSD) distribution and lagged phase synchronisation (LPS) of oscillations across small-scale and large-scale brain networks. We additionally investigated LPS relationships with clinical symptoms using linear mixed-effects models.

RESULTS

Compared to HC, FEP patients demonstrated abnormal CSD distributions in frontal areas of the brain; while decreased oscillations were found in the low frequencies, an increase was reported in the high frequencies (P < 0.01). Patients also exhibited deviant LPS in the high frequencies, whose dynamics changed over increasing 3D cortico-cortical distances and increasing psychotic symptoms.

CONCLUSIONS

These results indicate that in addition to prefrontal cortical abnormalities, altered synchronised neural oscillations are also present, suggesting possible disruptions in cortico-cortical communications. These findings provide new insights into the pathophysiological mechanisms of emerging schizophrenic psychoses.