Clinical, Brain, and Multilevel Clustering in Early Psychosis and Affective Stages.

Importance: Approaches are needed to stratify individuals in early psychosis stages beyond positive symptom severity to investigate specificity related to affective and normative variation and to validate solutions with premorbid, longitudinal, and genetic risk measures. Objective: To use machine learning techniques to cluster, compare, and combine subgroup solutions using clinical and brain structural imaging data from early psychosis and depression stages. Design, Setting, and Participants: A multisite, naturalistic, longitudinal cohort study (10 sites in 5 European countries; including major follow-up intervals at 9 and 18 months) with a referred patient sample of those with clinical high risk for psychosis (CHR-P), recent-onset psychosis (ROP), recent-onset depression (ROD), and healthy controls were recruited between February 1, 2014, to July 1, 2019. Data were analyzed between January 2020 and January 2022. Main Outcomes and Measures: A nonnegative matrix factorization technique separately decomposed clinical (287 variables) and parcellated brain structural volume (204 gray, white, and cerebrospinal fluid regions) data across CHR-P, ROP, ROD, and healthy controls study groups. Stability criteria determined cluster number using nested cross-validation. Validation targets were compared across subgroup solutions (premorbid, longitudinal, and schizophrenia polygenic risk scores). Multiclass supervised machine learning produced a transferable solution to the validation sample. Results: There were a total of 749 individuals in the discovery group and 610 individuals in the validation group. Individuals included those with CHR-P (n = 287), ROP (n = 323), ROD (n = 285), and healthy controls (n = 464), The mean (SD) age was 25.1 (5.9) years, and 702 (51.7%) were female. A clinical 4-dimensional solution separated individuals based on positive symptoms, negative symptoms, depression, and functioning, demonstrating associations with all validation targets. Brain clustering revealed a subgroup with distributed brain volume reductions associated with negative symptoms, reduced performance IQ, and increased schizophrenia polygenic risk scores. Multilevel results distinguished between normative and illness-related brain differences. Subgroup results were largely validated in the external sample. Conclusions and Relevance: The results of this longitudinal cohort study provide stratifications beyond the expression of positive symptoms that cut across illness stages and diagnoses. Clinical results suggest the importance of negative symptoms, depression, and functioning. Brain results suggest substantial overlap across illness stages and normative variation, which may highlight a vulnerability signature independent from specific presentations. Premorbid, longitudinal, and genetic risk validation suggested clinical importance of the subgroups to preventive treatments.

Pattern of predictive features of continued cannabis use in patients with recent-onset psychosis and clinical high-risk for psychosis.

Continued cannabis use (CCu) is an important predictor for poor long-term outcomes in psychosis and clinically high-risk patients, but no generalizable model has hitherto been tested for its ability to predict CCu in these vulnerable patient groups. In the current study, we investigated how structured clinical and cognitive assessments and structural magnetic resonance imaging (sMRI) contributed to the prediction of CCu in a group of 109 patients with recent-onset psychosis (ROP). We tested the generalizability of our predictors in 73 patients at clinical high-risk for psychosis (CHR). Here, CCu was defined as any cannabis consumption between baseline and 9-month follow-up, as assessed in structured interviews. All patients reported lifetime cannabis use at baseline. Data from clinical assessment alone correctly classified 73% (p < 0.001) of ROP and 59 % of CHR patients. The classifications of CCu based on sMRI and cognition were non-significant (ps > 0.093), and their addition to the interview-based predictor via stacking did not improve prediction significantly, either in the ROP or CHR groups (ps > 0.065). Lower functioning, specific substance use patterns, urbanicity and a lack of other coping strategies contributed reliably to the prediction of CCu and might thus represent important factors for guiding preventative efforts. Our results suggest that it may be possible to identify by clinical measures those psychosis-spectrum patients at high risk for CCu, potentially allowing to improve clinical care through targeted interventions. However, our model needs further testing in larger samples including more diverse clinical populations before being transferred into clinical practice.

Using combined environmental-clinical classification models to predict role functioning outcome in clinical high-risk states for psychosis and recent-onset depression.

BACKGROUND: Clinical high-risk states for psychosis (CHR) are associated with functional impairments and depressive disorders. A previous PRONIA study predicted social functioning in CHR and recent-onset depression (ROD) based on structural magnetic resonance imaging (sMRI) and clinical data. However, the combination of these domains did not lead to accurate role functioning prediction, calling for the investigation of additional risk dimensions. Role functioning may be more strongly associated with environmental adverse events than social functioning. AIMS: We aimed to predict role functioning in CHR, ROD and transdiagnostically, by adding environmental adverse events-related variables to clinical and sMRI data domains within the PRONIA sample. METHOD: Baseline clinical, environmental and sMRI data collected in 92 CHR and 95 ROD samples were trained to predict lower versus higher follow-up role functioning, using support vector classification and mixed k-fold/leave-site-out cross-validation. We built separate predictions for each domain, created multimodal predictions and validated them in independent cohorts (74 CHR, 66 ROD). RESULTS: Models combining clinical and environmental data predicted role outcome in discovery and replication samples of CHR (balanced accuracies: 65.4% and 67.7%, respectively), ROD (balanced accuracies: 58.9% and 62.5%, respectively), and transdiagnostically (balanced accuracies: 62.4% and 68.2%, respectively). The most reliable environmental features for role outcome prediction were adult environmental adjustment, childhood trauma in CHR and childhood environmental adjustment in ROD. CONCLUSIONS: Findings support the hypothesis that environmental variables inform role outcome prediction, highlight the existence of both transdiagnostic and syndrome-specific predictive environmental adverse events, and emphasise the importance of implementing real-world models by measuring multiple risk dimensions.

Novel Gyrification Networks Reveal Links with Psychiatric Risk Factors in Early Illness.

Adult gyrification provides a window into coordinated early neurodevelopment when disruptions predispose individuals to psychiatric illness. We hypothesized that the echoes of such disruptions should be observed within structural gyrification networks in early psychiatric illness that would demonstrate associations with developmentally relevant variables rather than specific psychiatric symptoms. We employed a new data-driven method (Orthogonal Projective Non-Negative Matrix Factorization) to delineate novel gyrification-based networks of structural covariance in 308 healthy controls. Gyrification within the networks was then compared to 713 patients with recent onset psychosis or depression, and at clinical high-risk. Associations with diagnosis, symptoms, cognition, and functioning were investigated using linear models. Results demonstrated 18 novel gyrification networks in controls as verified by internal and external validation. Gyrification was reduced in patients in temporal-insular, lateral occipital, and lateral fronto-parietal networks (pFDR < 0.01) and was not moderated by illness group. Higher gyrification was associated with better cognitive performance and lifetime role functioning, but not with symptoms. The findings demonstrated that gyrification can be parsed into novel brain networks that highlight generalized illness effects linked to developmental vulnerability. When combined, our study widens the window into the etiology of psychiatric risk and its expression in adulthood.

Toward Generalizable and Transdiagnostic Tools for Psychosis Prediction: An Independent Validation and Improvement of the NAPLS-2 Risk Calculator in the Multisite PRONIA Cohort.

BACKGROUND: Transition to psychosis is among the most adverse outcomes of clinical high-risk (CHR) syndromes encompassing ultra-high risk (UHR) and basic symptom states. Clinical risk calculators may facilitate an early and individualized interception of psychosis, but their real-world implementation requires thorough validation across diverse risk populations, including young patients with depressive syndromes. METHODS: We validated the previously described NAPLS-2 (North American Prodrome Longitudinal Study 2) calculator in 334 patients (26 with transition to psychosis) with CHR or recent-onset depression (ROD) drawn from the multisite European PRONIA (Personalised Prognostic Tools for Early Psychosis Management) study. Patients were categorized into three risk enrichment levels, ranging from UHR, over CHR, to a broad-risk population comprising patients with CHR or ROD (CHR|ROD). We assessed how risk enrichment and different predictive algorithms influenced prognostic performance using reciprocal external validation. RESULTS: After calibration, the NAPLS-2 model predicted psychosis with a balanced accuracy (BAC) (sensitivity, specificity) of 68% (73%, 63%) in the PRONIA-UHR cohort, 67% (74%, 60%) in the CHR cohort, and 70% (73%, 66%) in patients with CHR|ROD. Multiple model derivation in PRONIA-CHR|ROD and validation in NAPLS-2-UHR patients confirmed that broader risk definitions produced more accurate risk calculators (CHR|ROD-based vs. UHR-based performance: 67% [68%, 66%] vs. 58% [61%, 56%]). Support vector machines were superior in CHR|ROD (BAC = 71%), while ridge logistic regression and support vector machines performed similarly in CHR (BAC = 67%) and UHR cohorts (BAC = 65%). Attenuated psychotic symptoms predicted psychosis across risk levels, while younger age and reduced processing speed became increasingly relevant for broader risk cohorts. CONCLUSIONS: Clinical-neurocognitive machine learning models operating in young patients with affective and CHR syndromes facilitate a more precise and generalizable prediction of psychosis. Future studies should investigate their therapeutic utility in large-scale clinical trials.

Multimodal prognosis of negative symptom severity in individuals at increased risk of developing psychosis.

Negative symptoms occur frequently in individuals at clinical high risk (CHR) for psychosis and contribute to functional impairments. The aim of this study was to predict negative symptom severity in CHR after 9 months. Predictive models either included baseline negative symptoms measured with the Structured Interview for Psychosis-Risk Syndromes (SIPS-N), whole-brain gyrification, or both to forecast negative symptoms of at least moderate severity in 94 CHR. We also conducted sequential risk stratification to stratify CHR into different risk groups based on the SIPS-N and gyrification model. Additionally, we assessed the models' ability to predict functional outcomes in CHR and their transdiagnostic generalizability to predict negative symptoms in 96 patients with recent-onset psychosis (ROP) and 97 patients with recent-onset depression (ROD). Baseline SIPS-N and gyrification predicted moderate/severe negative symptoms with significant balanced accuracies of 68 and 62%, while the combined model achieved 73% accuracy. Sequential risk stratification stratified CHR into a high (83%), medium (40-64%), and low (19%) risk group regarding their risk of having moderate/severe negative symptoms at 9 months follow-up. The baseline SIPS-N model was also able to predict social (61%), but not role functioning (59%) at above-chance accuracies, whereas the gyrification model achieved significant accuracies in predicting both social (76%) and role (74%) functioning in CHR. Finally, only the baseline SIPS-N model showed transdiagnostic generalization to ROP (63%). This study delivers a multimodal prognostic model to identify those CHR with a clinically relevant negative symptom severity and functional impairments, potentially requiring further therapeutic consideration.

Association between age of cannabis initiation and gray matter covariance networks in recent onset psychosis.

Cannabis use during adolescence is associated with an increased risk of developing psychosis. According to a current hypothesis, this results from detrimental effects of early cannabis use on brain maturation during this vulnerable period. However, studies investigating the interaction between early cannabis use and brain structural alterations hitherto reported inconclusive findings. We investigated effects of age of cannabis initiation on psychosis using data from the multicentric Personalized Prognostic Tools for Early Psychosis Management (PRONIA) and the Cannabis Induced Psychosis (CIP) studies, yielding a total sample of 102 clinically-relevant cannabis users with recent onset psychosis. GM covariance underlies shared maturational processes. Therefore, we performed source-based morphometry analysis with spatial constraints on structural brain networks showing significant alterations in schizophrenia in a previous multisite study, thus testing associations of these networks with the age of cannabis initiation and with confounding factors. Earlier cannabis initiation was associated with more severe positive symptoms in our cohort. Greater gray matter volume (GMV) in the previously identified cerebellar schizophrenia-related network had a significant association with early cannabis use, independent of several possibly confounding factors. Moreover, GMV in the cerebellar network was associated with lower volume in another network previously associated with schizophrenia, comprising the insula, superior temporal, and inferior frontal gyrus. These findings are in line with previous investigations in healthy cannabis users, and suggest that early initiation of cannabis perturbs the developmental trajectory of certain structural brain networks in a manner imparting risk for psychosis later in life.

Multimodal Machine Learning Workflows for Prediction of Psychosis in Patients With Clinical High-Risk Syndromes and Recent-Onset Depression.

Importance: Diverse models have been developed to predict psychosis in patients with clinical high-risk (CHR) states. Whether prediction can be improved by efficiently combining clinical and biological models and by broadening the risk spectrum to young patients with depressive syndromes remains unclear. Objectives: To evaluate whether psychosis transition can be predicted in patients with CHR or recent-onset depression (ROD) using multimodal machine learning that optimally integrates clinical and neurocognitive data, structural magnetic resonance imaging (sMRI), and polygenic risk scores (PRS) for schizophrenia; to assess models' geographic generalizability; to test and integrate clinicians' predictions; and to maximize clinical utility by building a sequential prognostic system. Design, Setting, and Participants: This multisite, longitudinal prognostic study performed in 7 academic early recognition services in 5 European countries followed up patients with CHR syndromes or ROD and healthy volunteers. The referred sample of 167 patients with CHR syndromes and 167 with ROD was recruited from February 1, 2014, to May 31, 2017, of whom 26 (23 with CHR syndromes and 3 with ROD) developed psychosis. Patients with 18-month follow-up (n = 246) were used for model training and leave-one-site-out cross-validation. The remaining 88 patients with nontransition served as the validation of model specificity. Three hundred thirty-four healthy volunteers provided a normative sample for prognostic signature evaluation. Three independent Swiss projects contributed a further 45 cases with psychosis transition and 600 with nontransition for the external validation of clinical-neurocognitive, sMRI-based, and combined models. Data were analyzed from January 1, 2019, to March 31, 2020. Main Outcomes and Measures: Accuracy and generalizability of prognostic systems. Results: A total of 668 individuals (334 patients and 334 controls) were included in the analysis (mean [SD] age, 25.1 [5.8] years; 354 [53.0%] female and 314 [47.0%] male). Clinicians attained a balanced accuracy of 73.2% by effectively ruling out (specificity, 84.9%) but ineffectively ruling in (sensitivity, 61.5%) psychosis transition. In contrast, algorithms showed high sensitivity (76.0%-88.0%) but low specificity (53.5%-66.8%). A cybernetic risk calculator combining all algorithmic and human components predicted psychosis with a balanced accuracy of 85.5% (sensitivity, 84.6%; specificity, 86.4%). In comparison, an optimal prognostic workflow produced a balanced accuracy of 85.9% (sensitivity, 84.6%; specificity, 87.3%) at a much lower diagnostic burden by sequentially integrating clinical-neurocognitive, expert-based, PRS-based, and sMRI-based risk estimates as needed for the given patient. Findings were supported by good external validation results. Conclusions and Relevance: These findings suggest that psychosis transition can be predicted in a broader risk spectrum by sequentially integrating algorithms' and clinicians' risk estimates. For clinical translation, the proposed workflow should undergo large-scale international validation.

Modeling Social Sensory Processing During Social Computerized Cognitive Training for Psychosis Spectrum: The Resting-State Approach.

Background: Greater impairments in early sensory processing predict response to auditory computerized cognitive training (CCT) in patients with recent-onset psychosis (ROP). Little is known about neuroimaging predictors of response to social CCT, an experimental treatment that was recently shown to induce cognitive improvements in patients with psychosis. Here, we investigated whether ROP patients show interindividual differences in sensory processing change and whether different patterns of SPC are (1) related to the differential response to treatment, as indexed by gains in social cognitive neuropsychological tests and (2) associated with unique resting-state functional connectivity (rsFC). Methods: Twenty-six ROP patients completed 10 h of CCT over the period of 4-6 weeks. Subject-specific improvement in one CCT exercise targeting early sensory processing-a speeded facial Emotion Matching Task (EMT)-was studied as potential proxy for target engagement. Based on the median split of SPC from the EMT, two patient groups were created. Resting-state activity was collected at baseline, and bold time series were extracted from two major default mode network (DMN) hubs: left medial prefrontal cortex (mPFC) and left posterior cingulate cortex (PCC). Seed rsFC analysis was performed using standardized Pearson correlation matrices, generated between the average time course for each seed and each voxel in the brain. Results: Based on SPC, we distinguished improvers-i.e., participants who showed impaired performance at baseline and reached the EMT psychophysical threshold during CCT-from maintainers-i.e., those who showed intact EMT performance at baseline and sustained the EMT psychophysical threshold throughout CCT. Compared to maintainers, improvers showed an increase of rsFC at rest between PCC and left superior and medial frontal regions and the cerebellum. Compared to improvers, maintainers showed increased rsFC at baseline between PCC and superior temporal and insular regions bilaterally. Conclusions: In ROP patients with an increase of connectivity at rest in the default mode network, social CCT is still able to induce sensory processing changes that however do not translate into social cognitive gains. Future studies should investigate if impairments in short-term synaptic plasticity are responsible for this lack of response and can be remediated by pharmacological augmentation during CCT.

Traces of Trauma: A Multivariate Pattern Analysis of Childhood Trauma, Brain Structure, and Clinical Phenotypes.

BACKGROUND: Childhood trauma (CT) is a major yet elusive psychiatric risk factor, whose multidimensional conceptualization and heterogeneous effects on brain morphology might demand advanced mathematical modeling. Therefore, we present an unsupervised machine learning approach to characterize the clinical and neuroanatomical complexity of CT in a larger, transdiagnostic context. METHODS: We used a multicenter European cohort of 1076 female and male individuals (discovery: n = 649; replication: n = 427) comprising young, minimally medicated patients with clinical high-risk states for psychosis; patients with recent-onset depression or psychosis; and healthy volunteers. We employed multivariate sparse partial least squares analysis to detect parsimonious associations between combinations of items from the Childhood Trauma Questionnaire and gray matter volume and tested their generalizability via nested cross-validation as well as via external validation. We investigated the associations of these CT signatures with state (functioning, depressivity, quality of life), trait (personality), and sociodemographic levels. RESULTS: We discovered signatures of age-dependent sexual abuse and sex-dependent physical and sexual abuse, as well as emotional trauma, which projected onto gray matter volume patterns in prefronto-cerebellar, limbic, and sensory networks. These signatures were associated with predominantly impaired clinical state- and trait-level phenotypes, while pointing toward an interaction between sexual abuse, age, urbanicity, and education. We validated the clinical profiles for all three CT signatures in the replication sample. CONCLUSIONS: Our results suggest distinct multilayered associations between partially age- and sex-dependent patterns of CT, distributed neuroanatomical networks, and clinical profiles. Hence, our study highlights how machine learning approaches can shape future, more fine-grained CT research.

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.

Brain Subtyping Enhances The Neuroanatomical Discrimination of Schizophrenia.

Identifying distinctive subtypes of schizophrenia could ultimately enhance diagnostic and prognostic accuracy. We aimed to uncover neuroanatomical subtypes of chronic schizophrenia patients to test whether stratification can enhance computer-aided discrimination of patients from control subjects. Unsupervised, data-driven clustering of structural MRI (sMRI) data was used to identify 2 subtypes of schizophrenia patients drawn from a US-based open science repository (n = 71) and we quantified classification improvements compared to controls (n = 74) using supervised machine learning. We externally validated the unsupervised and supervised learning models in a heterogeneous German validation sample (n = 316), and characterized symptom, cognition, and longitudinal symptom change signatures. Stratification improved classification accuracies from 68.5% to 73% (subgroup 1) and 78.8% (subgroup 2), respectively. Increased accuracy was also found when models were externally validated, and an average gain of 9% was found in supplementary analyses. The first subgroup was associated with cortical and subcortical volume reductions coupled with substantially longer illness duration, whereas the second subgroup was mainly characterized by cortical reductions, reduced illness duration, and comparatively less negative symptoms. Individuals within each subgroup could be identified using just 10 clinical questions at an accuracy of 81.2%, and differential cognitive and symptom course signatures were suggested in multivariate analyses. Our findings suggest that sMRI-based subtyping enhances the neuroanatomical discrimination of schizophrenia by identifying generalizable brain patterns that align with a clinical staging model of the disorder. These findings could be used to improve illness stratification for biomarker-based computer-aided diagnoses.