Identifying clinical clusters with distinct trajectories in first-episode psychosis through an unsupervised machine learning technique

Cognitive reserve, depressive symptoms, obesity, and change in employment status predict mental processing speed and executive function after COVID-19

The risk factors for post-COVID-19 cognitive impairment have been poorly described. This study aimed to identify the sociodemographic, clinical, and lifestyle characteristics that characterize a group of post-COVID-19 condition (PCC) participants with neuropsychological impairment. The study sample included 426 participants with PCC who underwent a neurobehavioral evaluation. We selected seven mental speed processing and executive function variables to obtain a data-driven partition. Clustering algorithms were applied, including K-means, bisecting K-means, and Gaussian mixture models. Different machine learning algorithms were then used to obtain a classifier able to separate the two clusters according to the demographic, clinical, emotional, and lifestyle variables, including logistic regression with least absolute shrinkage and selection operator (LASSO) (L1) and Ridge (L2) regularization, support vector machines (linear/quadratic/radial basis function kernels), and decision tree ensembles (random forest/gradient boosting trees). All clustering quality measures were in agreement in detecting only two clusters in the data based solely on cognitive performance. A model with four variables (cognitive reserve, depressive symptoms, obesity, and change in work situation) obtained with logistic regression with LASSO regularization was able to classify between good and poor cognitive performers with an accuracy and a weighted averaged precision of 72%, a recall of 73%, and an area under the curve of 0.72. PCC individuals with a lower cognitive reserve, more depressive symptoms, obesity, and a change in employment status were at greater risk for poor performance on tasks requiring mental processing speed and executive function. Study registration: www.ClinicalTrials.gov , identifier NCT05307575.

Predicting the evolution from first-episode psychosis to mood or psychotic disorder: A systematic review of biological markers

BACKGROUND AND HYPOTHESIS

The development of paraclinical tools to assist clinical assessment is already widespread in nearly all other medical specialties. In psychiatry, many efforts are being made to improve management strategies using these new techniques. The first episode psychosis (FEP) is a clinical entity whose evolution after onset is difficult to predict in the current state of our practices. Our main objective was to identify from the literature the most promising biological markers for early prediction of thymic or psychotic trajectories following FEP.

STUDY DESIGN

We performed a systematic literature review on 4 databases: PubMed, Scopus, PsycINFO, and Web of Science following PRISMA guidelines and using search terms related to FEP and biomarkers.

STUDY RESULTS

Eight studies were included in our final analysis. Several biomarkers showed promising discriminatory capacities for predicting post-FEP evolution: the interleukins IL-6, IL-12p40, IL-1β, and the mRNA expression levels of the DICER-1 and AKT-1 genes. Other studies that opted for broad-spectrum strategies also highlighted new leads for the discovery of additional biomarkers.

CONCLUSIONS

Overall, our results indicate the value of replicating studies targeting the analysis of the predictive capacities of several biological markers. It also appears important to homogenize methodologies and favor the construction of predictive models on several of these markers to reinforce their statistical significance.

Cognitive and clinical profiles in first-episode psychosis and their relationship with functional outcomes

BACKGROUND

While cognitive impairment is a core feature of psychosis, significant heterogeneity in cognitive and clinical outcomes is observed.

AIMS

The aim of this study was to identify cognitive and clinical subgroups in first-episode psychosis (FEP) and determine if these profiles were linked to functional outcomes over time.

METHOD

A total of 323 individuals with FEP were included. Two-step hierarchical and k-means cluster analyses were performed using baseline cognitive and clinical variables. General linear mixed models were used to investigate whether baseline cognitive and clinical clusters were associated with functioning at follow-up time points (6-9, 12 and 15 months).

RESULTS

Three distinct cognitive clusters were identified: a cognitively intact group (N = 59), a moderately impaired group (N = 77) and a more severely impaired group (N = 122). Three distinct clinical clusters were identified: a subgroup characterised by predominant mood symptoms (N = 76), a subgroup characterised by predominant negative symptoms (N = 19) and a subgroup characterised by overall mild symptom severity (N = 94). The subgroup with more severely impaired cognition also had more severe negative symptoms at baseline. Cognitive clusters were significantly associated with later social and occupational function, and associated with changes over time. Clinical clusters were associated with later social functioning but not occupational functioning, and were not associated with changes over time.

CONCLUSIONS

Baseline cognitive impairments are predictive of both later social and occupational function and change over time. This suggests that cognitive profiles offer valuable information in terms of prognosis and treatment needs.

Accuracy of machine learning methods in predicting prognosis of patients with psychotic spectrum disorders: a systematic review

OBJECTIVES

We aimed to examine the predictive accuracy of functioning, relapse or remission among patients with psychotic disorders, using machine learning methods. We also identified specific features that were associated with these clinical outcomes.

DESIGN

The methodology of this review was guided by the Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy.

DATA SOURCES

CINAHL, EMBASE, PubMed, PsycINFO, Scopus and ScienceDirect were searched for relevant articles from database inception until 21 November 2024.

ELIGIBILITY CRITERIA

Studies were included if they involved the use of machine learning methods to predict functioning, relapse and/or remission among individuals with psychotic spectrum disorders.

DATA EXTRACTION AND SYNTHESIS

Two independent reviewers screened the records from the database search. Risk of bias was evaluated using the Quality Assessment of Diagnostic Accuracy Studies tool from Cochrane. Synthesised findings were presented in tables.

RESULTS

23 studies were included in the review, which were mostly conducted in the west (91%). Predictive summary area under the curve values for functioning, relapse and remission were 0.63-0.92 (poor to outstanding), 0.45-0.95 (poor to outstanding), 0.70-0.79 (acceptable), respectively. Logistic regression and random forest were the best performing algorithms. Factors influencing outcomes included demographic (age, ethnicity), illness (duration of untreated illness, types of symptoms), functioning (baseline functioning, interpersonal relationships and activity engagement), treatment variables (use of higher doses of antipsychotics, electroconvulsive therapy), data from passive sensor (call log, distance travelled, time spent in certain locations) and online activities (time of use, use of certain words, changes in search frequencies and length of queries).

CONCLUSION

Machine learning methods show promise in the prediction of prognosis (specifically functioning, relapse and remission) of mental disorders based on relevant collected variables. Future machine learning studies may want to focus on the inclusion of a broader swathe of variables including ecological momentary assessments, with a greater amount of good quality big data covering longer longitudinal illness courses and coupled with external validation of study findings.

PROSPERO REGISTRATION NUMBER

The review was registered on PROSPERO, ID: CRD42023441108.

Elevated Extracellular Free Water in the Brain Predicts Clinical Improvement in First-Episode Psychosis

BACKGROUND

Despite the diverse nature of clinical trajectories after a first episode of psychosis, few baseline characteristics have been predictive of clinical improvement, and the neurobiological underpinnings of this heterogeneity remain largely unknown. Elevated extracellular free water (FW) in the brain is a diffusion imaging measure that has been consistently reported in different phases of psychosis that may indicate a neuroinflammatory state. However, its predictive capacity in terms of clinical outcomes is unknown.

METHODS

We used diffusion imaging to determine FW and tissue-specific fractional anisotropy (FA-t) in first-episode psychosis. Forty-seven participants were categorized as clinical improvers (n = 26) if they achieved a 20% decrease in total Brief Psychiatric Rating Scale score at 12 months. To determine the predictive capacity of FW and FA-t, these measures were introduced in a stepwise logistic regression model to predict clinical improvement. For measures that survived the model, regional between-group differences were also investigated in cortical surface or white matter tracts, as applicable.

RESULTS

Both higher gray matter FW (odds ratio 1.698; 95% CI, 1.134-2.542) and FA-t (odds ratio, 1.358; 95% CI, 0.905-2.038) predicted improver status. FW in gray matter was also linearly correlated with the Brief Psychiatric Rating Scale total score at the 12-month follow-up. When we examined regional specificity, we found that improvers showed greater FW predominantly in temporal regions and higher FA-t values in several white matter tracts, including the bilateral longitudinal superior fasciculus.

CONCLUSIONS

Our results show that elevated FW in gray matter and FA-t predict further clinical improvement during the initial phases of psychosis. The potential roles of brain inflammatory processes in predicting clinical improvement are discussed.

From Genetics to Psychosocial Functioning: Unraveling the Mediating Roles of Cognitive Reserve, Cognition, and Negative Symptoms in First-Episode Psychosis

BACKGROUND

Studies have shown associations between polygenic risk scores for educational attainment (PRSEA), cognitive reserve (CR), cognition, negative symptoms (NS), and psychosocial functioning in first-episode psychosis (FEP). However, their specific interactions remain unclear. This study aimed to investigate the mediating roles of CR, cognition, and NS in the relationship between PRSEA and psychosocial functioning one year after a FEP. Additionally, we sought to explore the impact of two NS subtypes on this relationship: diminished Expression (EXP-NS) and Motivation and Pleasure (MAP-NS).

METHODS

A total of 138 FEP participants, predominantly male (70%), with a mean age of 24.77 years (SD = 5.29), underwent genetic, clinical, and cognitive assessments two months after study enrollment. Functioning evaluation followed at one-year follow-up. To investigate the mediating role of CR, cognition, and NS in the relationship between PRSEA and functioning, a serial mediation model was employed. Two further mediation models were tested to explore the differential impact of EXP-NS and MAP-NS. Mediation analysis was performed using the PROCESS macro version 4.1 within SPSS version 26.

RESULTS

The serial mediation model revealed a causal chain for PRSEA > CR > cognition > NS > Functioning (β = -3.08, 95%CI [-5.73, -0.43], p = 0.023). When differentiating by type of NS, only EXP-NS were significantly associated in the casual chain (β = -0.17, 95% CI [-0.39, -0.01], p < 0.05).

CONCLUSIONS

CR, cognition and NS -specifically EXP-NS- mediate the association between PRSEA and psychosocial functioning at one-year follow-up in FEP patients. These results highlight the potential for personalized interventions based on genetic predisposition.

Multivariable prediction of functional outcome after first-episode psychosis: a crossover validation approach in EUFEST and PSYSCAN

Several multivariate prognostic models have been published to predict outcomes in patients with first episode psychosis (FEP), but it remains unclear whether those predictions generalize to independent populations. Using a subset of demographic and clinical baseline predictors, we aimed to develop and externally validate different models predicting functional outcome after a FEP in the context of a schizophrenia-spectrum disorder (FES), based on a previously published cross-validation and machine learning pipeline. A crossover validation approach was adopted in two large, international cohorts (EUFEST, n = 338, and the PSYSCAN FES cohort, n = 226). Scores on the Global Assessment of Functioning scale (GAF) at 12 month follow-up were dichotomized to differentiate between poor (GAF current < 65) and good outcome (GAF current ≥ 65). Pooled non-linear support vector machine (SVM) classifiers trained on the separate cohorts identified patients with a poor outcome with cross-validated balanced accuracies (BAC) of 65-66%, but BAC dropped substantially when the models were applied to patients from a different FES cohort (BAC = 50-56%). A leave-site-out analysis on the merged sample yielded better performance (BAC = 72%), highlighting the effect of combining data from different study designs to overcome calibration issues and improve model transportability. In conclusion, our results indicate that validation of prediction models in an independent sample is essential in assessing the true value of the model. Future external validation studies, as well as attempts to harmonize data collection across studies, are recommended.

Identification of distinct clinical profiles and trajectories in individuals at high risk of developing psychosis: A latent profile analysis of the north American prodrome longitudinal study consortium-3 dataset

AIM

People at clinical high risk (CHR) for psychosis are a heterogeneous population in regard to clinical presentation and outcome. It is unclear, however, if their baseline clinical characteristics can be used to construct orthogonal subgroups that differ in their clinical trajectory to provide early identification of individuals in need of tailored interventions.

METHODS

We used latent profile analysis (LPA) to determine the number of distinct clinical profiles within the CHR population using the NAPLS-3 dataset, focusing on the clinical features incorporated in the NAPLS psychosis risk calculator (including age, unusual thought content and suspiciousness, processing speed, verbal learning and memory function, social functioning decline, life events, childhood trauma, and family history of psychosis). We then conducted a between-profile comparisons of clinical trajectories based on psychotic and depressive symptoms as well as substance use disorder (SUD) related features over time.

RESULTS

Two distinct profiles emerged. One profile, comprising approximately 25% of the sample, was significantly older, displayed better cognitive performance, experienced more types of traumatic and undesirable life events, exhibited a greater decline in functioning in the past year, and was more likely to have relatives with psychosis. This group showed worse positive symptoms and SUD-related features over time, although groups did not differ in the proportion of individuals who developed psychosis.

CONCLUSIONS

LPA results suggest CHRs can be segregated into two profiles with different clinical trajectories. Characterizing individuals within these clinical profiles may help understand the divergent outcomes of this population and ultimately facilitate the development of specialized interventions.

Emotional intelligence and neurocognition profiles in first-episode psychosis: A two-year follow-up study

Emotional intelligence (EI) and neurocognition (NC) impairments are common in first-episode psychosis (FEP), yet their evolution over time remains unclear. This study identified patient profiles in EI and NC performance in FEP. 98 adult FEP patients and 128 healthy controls (HCs) were tested on clinical, functional, EI, and NC variables at baseline and two-year follow-up (FUP). A repeated-measures ANOVA compared the effects of group (patients and HCs) and time on EI. Significant EI improvements were observed in both groups. Four groups were created based on NC and EI performance at baseline and FUP in patients: impairment in NC and EI, impairment in NC only, impairment in EI only, and no impairment. At FUP, patients impaired in NC and EI showed less cognitive reserve (CR), greater negative and positive symptoms, and poorer functional outcomes. At FUP, three group trajectories were identified: (I) maintain dual impairment (II) maintain no impairment or improve, (III) maintain sole impairment or worsen. The maintain dual impairment group had the lowest levels of CR. EI and NC impairments progress differently in FEP. Greater CR may protect against comorbid EI/NC impairment. Identifying these patient characteristics could contribute to the development of personalised interventions.

A naturalistic cohort study of first-episode schizophrenia spectrum disorder: A description of the early phase of illness in the PSYSCAN cohort

BACKGROUND

We examined the course of illness over a 12-month period in a large, international multi-center cohort of people with a first-episode schizophrenia spectrum disorder (FES) in a naturalistic, prospective study (PSYSCAN).

METHOD

Patients with a first episode of schizophrenia, schizoaffective disorder (depressive type) or schizophreniform disorder were recruited at 16 institutions in Europe, Israel and Australia. Participants (N = 304) received clinical treatment as usual throughout the study.

RESULTS

The mean age of the cohort was 24.3 years (SD = 5.6), and 67 % were male. At baseline, participants presented with a range of intensities of psychotic symptoms, 80 % were taking antipsychotic medication, 68 % were receiving psychological treatment, with 46.5 % in symptomatic remission. The mean duration of untreated psychosis was 6.2 months (SD = 17.0). After one year, 67 % were in symptomatic remission and 61 % were in functional remission, but 31 % had been readmitted to hospital at some time after baseline. In the cohort as a whole, depressive symptoms remained stable over the follow-up period. In patients with a current depressive episode at baseline, depressive symptoms slightly improved. Alcohol, tobacco and cannabis were the most commonly used substances, with daily users of cannabis ranging between 9 and 11 % throughout the follow-up period.

CONCLUSIONS

This study provides valuable insight into the early course of a broad range of clinical and functional aspects of illness in FES patients in routine clinical practice.

Link between cognitive polygenic risk scores and clinical progression after a first-psychotic episode

BACKGROUND

Clinical intervention in early stages of psychotic disorders is crucial for the prevention of severe symptomatology trajectories and poor outcomes. Genetic variability is studied as a promising modulator of prognosis, thus novel approaches considering the polygenic nature of these complex phenotypes are required to unravel the mechanisms underlying the early progression of the disorder.

METHODS

The sample comprised of 233 first-episode psychosis (FEP) subjects with clinical and cognitive data assessed periodically for a 2-year period and 150 matched controls. Polygenic risk scores (PRSs) for schizophrenia, bipolar disorder, depression, education attainment and cognitive performance were used to assess the genetic risk of FEP and to characterize their association with premorbid, baseline and progression of clinical and cognitive status.

RESULTS

Schizophrenia, bipolar disorder and cognitive performance PRSs were associated with an increased risk of FEP [false discovery rate (FDR) ⩽ 0.027]. In FEP patients, increased cognitive PRSs were found for FEP patients with more cognitive reserve (FDR ⩽ 0.037). PRSs reflecting a genetic liability for improved cognition were associated with a better course of symptoms, functionality and working memory (FDR ⩽ 0.039). Moreover, the PRS of depression was associated with a worse trajectory of the executive function and the general cognitive status (FDR ⩽ 0.001).

CONCLUSIONS

Our study provides novel evidence of the polygenic bases of psychosis and its clinical manifestation in its first stage. The consistent effect of cognitive PRSs on the early clinical progression suggests that the mechanisms underlying the psychotic episode and its severity could be partially independent.

Disorganization in first episode affective psychosis: Treatment response and clinical considerations from a 2-year follow-up study in a "real world" setting

INTRODUCTION

Disorganization is a crucial domain in affective psychoses. However, it has received poor research attention, especially at the illness onset. The aims of this study were: (a) to monitor the longitudinal course of disorganization in young people with first episode affective psychosis (FEAP) across 2 years of follow-up, and (b) to investigate any relevant correlation of disorganized symptoms with psychopathology, functioning and the specific treatment elements of an "Early Intervention in Psychosis" (EIP) protocol along the follow-up period.

MATERIALS AND METHODS

Seventy-five FEAP participants (aged 12-35 years) completed the Positive And Negative Syndrome Scale (PANSS) and the Global Assessment of Functioning (GAF). Spearman's rank correlation coefficients were calculated.

RESULTS

During the follow-up, disorganized symptoms showed significant enduring positive correlations with PANSS items representing delusional thought content and uncooperativeness, as well as a persistent negative association with the GAF score. Across the 2-year follow-up period, FEAP individuals also had a relevant reduction in disorganization levels. This symptom decrease was specifically related with the combination of antipsychotic medication with the specific psychosocial components of our EIP intervention offered to FEAP patients during the first 12 months of treatment.

CONCLUSIONS

Disorganization is relevant in FEAP subjects already at their enrollment in specialized EIP protocols. However, it decreases over time, together with the delivery of specific, combined (person-tailored) EIP interventions.

Epigenetic clocks in relapse after a first episode of schizophrenia

The main objective of the present study was to investigate the association between several epigenetic clocks, covering different aspects of aging, with schizophrenia relapse evaluated over a 3-year follow-up period in a cohort of ninety-one first-episode schizophrenia patients. Genome-wide DNA methylation was profiled and four epigenetic clocks, including epigenetic clocks of chronological age, mortality and telomere length were calculated. Patients that relapsed during the follow-up showed epigenetic acceleration of the telomere length clock (p = 0.030). Shorter telomere length was associated with cognitive performance (working memory, r = 0.31 p = 0.015; verbal fluency, r = 0.28 p = 0.028), but no direct effect of cognitive function or symptom severity on relapse was detected. The results of the present study suggest that epigenetic age acceleration could be involved in the clinical course of schizophrenia and could be a useful marker of relapse when measured in remission stages.

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.

Mapping of machine learning approaches for description, prediction, and causal inference in the social and health sciences

Machine learning (ML) methodology used in the social and health sciences needs to fit the intended research purposes of description, prediction, or causal inference. This paper provides a comprehensive, systematic meta-mapping of research questions in the social and health sciences to appropriate ML approaches by incorporating the necessary requirements to statistical analysis in these disciplines. We map the established classification into description, prediction, counterfactual prediction, and causal structural learning to common research goals, such as estimating prevalence of adverse social or health outcomes, predicting the risk of an event, and identifying risk factors or causes of adverse outcomes, and explain common ML performance metrics. Such mapping may help to fully exploit the benefits of ML while considering domain-specific aspects relevant to the social and health sciences and hopefully contribute to the acceleration of the uptake of ML applications to advance both basic and applied social and health sciences research.

Prodromal phase: Differences in prodromal symptoms, risk factors and markers of vulnerability in first episode mania versus first episode psychosis with onset in late adolescence or adulthood

OBJECTIVE

This study was aimed at identifying differences in the prodromal symptoms and their duration, risk factors and markers of vulnerability in patients presenting a first episode mania (FEM) or psychosis (FEP) with onset in late adolescence or adulthood in order to guide tailored treatment strategies.

METHODS

Patients with a FEM or FEP underwent a clinical assessment. Prodromes were evaluated with the Bipolar Prodrome Symptom Scale-Retrospective (BPSS-R). Chi-squared tests were conducted to assess specific prodromal symptoms, risk factors or markers of vulnerability between groups. Significant prodromal symptoms were entered in a stepwise forward logistic regression model. The probabilities of a gradual versus rapid onset pattern of the prodromes were computed with logistic regression models.

RESULTS

The total sample included 108 patients (FEM = 72, FEP = 36). Social isolation was associated with the prodromal stage of a FEP whilst Increased energy or goal-directed activity with the prodrome to a FEM. Physically slowed down presented the most gradual onset whilst Increased energy presented the most rapid. The presence of obstetric complications and difficulties in writing and reading during childhood were risk factors for FEP. As for markers of vulnerability, impairment in premorbid adjustment was characteristic of FEP patients. No specific risk factor or marker of vulnerability was identified for FEM.

CONCLUSION

Early characteristics differentiating FEP from FEM were identified. These findings might help shape early identification and preventive intervention programmes.

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.

Neurocognition, functional outcome, and quality of life in remitted and non-remitted schizophrenia: A comparison with euthymic bipolar I disorder and a control group

There are discrepancies about if the severity of the symptomatology in schizophrenia is related to neurocognitive performance, functional outcome, and quality of life (QoL). Also, there are controversial data about the comparison between euthymic bipolar patients and different subgroups of schizophrenia in neurocognition, functioning, and QoL level. The present study aimed to compare the neurocognitive performance, functional outcome, and QoL of remitted and non-remitted patients with SC with respect to a group of euthymic patients with BD, and a control group. It included 655 subjects: 98 patients with schizophrenia in remission (SC-R), 184 non-remitted patients with schizophrenia (SC-NR), 117 euthymic patients with bipolar I disorder (BD), and 256 healthy subjects. A comprehensive clinical, neurocognitive (six cognitive domains), functional, and QoL assessment was carried out. Remission criteria of Andreasen were used to classify schizophrenia patients as remitted or non-remitted. Compared with control subjects all groups of patients showed impaired neurocognitive performance, functioning and QoL. SC-R patients had an intermediate functioning between control subjects and SC-NR, all at a neurocognitive, functional, or QoL level. There were no significant differences between SC-R and BD. These results suggest that reaching clinical remission is essential to achieve a better level of psychosocial functioning, and QoL. Likewise, the results of this study suggest that euthymic patients with bipolar disorder and patients with schizophrenia in remission are comparable at the neurocognitive and functional levels, which might have implications in the pathophysiology of both disorders.

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

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