Predicting onset of early- and late-treatment resistance in first-episode schizophrenia patients using advanced shrinkage statistical methods in a small sample

Predicting treatment resistance in positive and negative symptom domains from first episode psychosis: Development of a clinical prediction model

BACKGROUND

Treatment resistance (TR) in schizophrenia may be defined by the persistence of positive and/or negative symptoms despite adequate treatment. Whilst previous investigations have focused on positive symptoms, negative symptoms are highly prevalent, impactful, and difficult to treat. In the current study we aimed to develop easily employable prediction models to predict TR in positive and negative symptom domains from first episode psychosis (FEP).

METHODS

Longitudinal cohort data from 1027 individuals with FEP was utilised. Using a robust definition of TR, n = 51 (4.97 %) participants were treatment resistant in the positive domain and n = 56 (5.46 %) treatment resistant in the negative domain 12 months after first presentation. 20 predictor variables, selected by existing evidence and availability in clinical practice, were entered into two LASSO regression models. We estimated the models using repeated nested cross-validation (NCV) and assessed performance using discrimination and calibration measures.

RESULTS

The prediction model for TR in the positive domain showed good discrimination (AUC = 0.72). Twelve predictor variables (male gender, cannabis use, age, positive symptom severity, depression and academic and social functioning) were retained by each outer fold of the NCV procedure, indicating importance in prediction of the outcome. However, our negative domain model failed to discriminate those with and without TR, with results only just over chance (AUC = 0.56).

CONCLUSIONS

Treatment resistance of positive symptoms can be accurately predicted from FEP using routinely collected baseline data, however prediction of negative domain-TR remains a challenge. Detailed negative symptom domains, clinical data, and biomarkers should be considered in future longitudinal studies.

Development and initial evaluation of a clinical prediction model for risk of treatment resistance in first-episode psychosis: Schizophrenia Prediction of Resistance to Treatment (SPIRIT)

BACKGROUND

A clinical tool to estimate the risk of treatment-resistant schizophrenia (TRS) in people with first-episode psychosis (FEP) would inform early detection of TRS and overcome the delay of up to 5 years in starting TRS medication.

AIMS

To develop and evaluate a model that could predict the risk of TRS in routine clinical practice.

METHOD

We used data from two UK-based FEP cohorts (GAP and AESOP-10) to develop and internally validate a prognostic model that supports identification of patients at high-risk of TRS soon after FEP diagnosis. Using sociodemographic and clinical predictors, a model for predicting risk of TRS was developed based on penalised logistic regression, with missing data handled using multiple imputation. Internal validation was undertaken via bootstrapping, obtaining optimism-adjusted estimates of the model's performance. Interviews and focus groups with clinicians were conducted to establish clinically relevant risk thresholds and understand the acceptability and perceived utility of the model.

RESULTS

We included seven factors in the prediction model that are predominantly assessed in clinical practice in patients with FEP. The model predicted treatment resistance among the 1081 patients with reasonable accuracy; the model's C-statistic was 0.727 (95% CI 0.723-0.732) prior to shrinkage and 0.687 after adjustment for optimism. Calibration was good (expected/observed ratio: 0.999; calibration-in-the-large: 0.000584) after adjustment for optimism.

CONCLUSIONS

We developed and internally validated a prediction model with reasonably good predictive metrics. Clinicians, patients and carers were involved in the development process. External validation of the tool is needed followed by co-design methodology to support implementation in early intervention services.

Prevalence of treatment-resistant schizophrenia among people with early psychosis and its clinical and demographic correlates

OBJECTIVE

The prevalence of treatment-resistant schizophrenia (TRS) among people with first-episode schizophrenia (FES) has been sub-optimally researched in Australia and internationally. We evaluated the prevalence of TRS among a cohort of FES patients and compared their sociodemographic and clinical characteristics to those with FES who were treatment responsive.

METHODS

Over 2 years, we collated demographic, clinical and treatment-related data of all patients with ICD-10 (International Classification of Diseases, Tenth revision) diagnosis of schizophrenia who were active in October 2020 at four early psychosis intervention services (EPIS) in Western Australia. We used a modified version of Suzuki et al. criteria to diagnose TRS. The data were analysed utilising descriptive statistics, the Mann-Whitney U test, Student's t-test and the False-Discovery Rate method.

RESULTS

The prevalence of TRS among the 167 patients diagnosed with FES was 41.3%, and the rates did not differ significantly between the services (p = 0.955). Those in the TRS group were less independent (p = 0.011), had more prolonged unemployment (p = 0.014) and were more likely to be on disability pension (p = 0.011) compared to the treatment responsive group. Furthermore, they had greater severity of symptoms (p = 0.002), longer duration of psychiatric symptoms (p = 0.019), more hospitalisations (p = 0.002) and longer cumulative admission durations (p = 0.002).

CONCLUSIONS

Our study revealed that treatment resistance to antipsychotics is prevalent among people with FES managed at EPIS. Notably, it establishes an association between TRS and heightened clinical severity and psychosocial and treatment burden. These findings highlight the imperative for early detection of treatment resistance and timely and specialised interventions for this condition in mental health services.

Predicting treatment resistance in schizophrenia patients: Machine learning highlights the role of early pathophysiologic features

Detecting patients with a high-risk profile for treatment-resistant schizophrenia (TRS) can be beneficial for implementing individually adapted therapeutic strategies and better understanding the TRS etiology. The aim of this study was to explore, with machine learning methods, the impact of demographic and clinical patient characteristics on TRS prediction, for already established risk factors and unexplored ones. This was a retrospective study of 500 patients admitted during 2020 to the University Hospital Group for Paris Psychiatry. We hypothesized potential TRS risk factors. The selected features were coded into structured variables in a new dataset, by processing patients discharge summaries and medical narratives with natural-language processing methods. We compared three machine learning models (XGBoost, logistic elastic net regression, logistic regression without regularization) for predicting TRS outcome. We analysed feature impact on the models, suggesting the following factors as markers of a high-risk TRS profile: early age at first contact with psychiatry, antipsychotic treatment interruptions due to non-adherence, absence of positive symptoms at baseline, educational problems and adolescence mental disorders in the personal psychiatric history. Specifically, we found a significant association with TRS outcome for age at first contact with psychiatry and medication non-adherence. Our findings on TRS risk factors are consistent with the review of the literature and suggest potential in using early pathophysiologic features for TRS prediction. Results were encouraging with the use of natural-langage processing techniques to leverage raw data provided by discharge summaries, combined with machine leaning models. These findings are a promising step for helping clinicians adapt their guidelines to early detection of TRS.

Gene expression imputation provides clinical and biological insights into treatment-resistant schizophrenia polygenic risk

Genome-wide association studies (GWAS) have revealed the polygenic nature of treatment-resistant schizophrenia TRS. Gene expression imputation allowed the translation of GWAS results into regulatory mechanisms and the construction of gene expression (GReX) risk scores (GReX-RS).  In the present study we computed GReX-RS from the largest GWAS of TRS to assess its association with clinical features. We perform transcriptome imputation in the largest GWAS of TRS to find GReX associated with TRS using brain tissues. Then, for each tissue, we constructed a GReX-RS of the identified genes in a sample of 254 genotyped first episode of psychosis (FEP) patients to test its association with clinical phenotypes, including clinical symptomatology, global functioning and cognitive performance. Our analysis provides evidence that the polygenic basis of TRS includes genetic variants that modulate the expression of certain genes in certain brain areas (substantia nigra, hippocampus, amygdala and frontal cortex), which at the same time are related to clinical features in FEP patients, mainly persistence of negative symptoms and cognitive alterations in sustained attention, which have also been suggested as clinical predictors of TRS. Our results provide a clinical explanation of the polygenic architecture of TRS and give more insight into the biological mechanisms underlying TRS.

Development of an individualized risk calculator of treatment resistance in patients with first-episode psychosis (TRipCal) using automated machine learning: a 12-year follow-up study with clozapine prescription as a proxy indicator

About 15-40% of patients with schizophrenia are treatment resistance (TR) and require clozapine. Identifying individuals who have higher risk of development of TR early in the course of illness is important to provide personalized intervention. A total of 1400 patients with FEP enrolled in the early intervention for psychosis service or receiving the standard psychiatric service between July 1, 1998, and June 30, 2003, for the first time were included. Clozapine prescriptions until June 2015, as a proxy of TR, were obtained. Premorbid information, baseline characteristics, and monthly clinical information were retrieved systematically from the electronic clinical management system (CMS). Training and testing samples were established with random subsampling. An automated machine learning (autoML) approach was used to optimize the ML algorithm and hyperparameters selection to establish four probabilistic classification models (baseline, 12-month, 24-month, and 36-month information) of TR development. This study found 191 FEP patients (13.7%) who had ever been prescribed clozapine over the follow-up periods. The ML pipelines identified with autoML had an area under the receiver operating characteristic curve ranging from 0.676 (baseline information) to 0.774 (36-month information) in predicting future TR. Features of baseline information, including schizophrenia diagnosis and age of onset, and longitudinal clinical information including symptoms variability, relapse, and use of antipsychotics and anticholinergic medications were important predictors and were included in the risk calculator. The risk calculator for future TR development in FEP patients (TRipCal) developed in this study could support the continuous development of data-driven clinical tools to assist personalized interventions to prevent or postpone TR development in the early course of illness and reduce delay in clozapine initiation.

The association between clinical, sociodemographic, familial, and environmental factors and treatment resistance in schizophrenia: A machine-learning-based approach

BACKGROUND

Prediction of treatment resistance in schizophrenia (TRS) would be helpful to reduce the duration of ineffective treatment and avoid delays in clozapine initiation. We applied machine learning to identify clinical, sociodemographic, familial, and environmental variables that are associated with TRS and could potentially predict TRS in the future.

STUDY DESIGN

Baseline and follow-up data on trait(-like) variables from the Genetic Risk and Outcome of Psychosis (GROUP) study were used. For the main analysis, we selected patients with non-affective psychotic disorders who met TRS (n = 200) or antipsychotic-responsive criteria (n = 423) throughout the study. For a sensitivity analysis, we only selected patients who met TRS (n = 76) or antipsychotic-responsive criteria (n = 123) at follow-up but not at baseline. Random forest models were trained to predict TRS in both datasets. SHapley Additive exPlanation values were used to examine the variables' contributions to the prediction.

STUDY RESULTS

Premorbid functioning, age at onset, and educational degree were most consistently associated with TRS across both analyses. Marital status, current household, intelligence quotient, number of moves, and family loading score for substance abuse also consistently contributed to the prediction of TRS in the main or sensitivity analysis. The diagnostic performance of our models was modest (area under the curve: 0.66-0.69).

CONCLUSIONS

We demonstrate that various clinical, sociodemographic, familial, and environmental variables are associated with TRS. Our models only showed modest performance in predicting TRS. Prospective large multi-centre studies are needed to validate our findings and investigate whether the model's performance can be improved by adding data from different modalities.

The multimodal Munich Clinical Deep Phenotyping study to bridge the translational gap in severe mental illness treatment research

Introduction

Treatment of severe mental illness (SMI) symptoms, especially negative symptoms and cognitive dysfunction in schizophrenia, remains a major unmet need. There is good evidence that SMIs have a strong genetic background and are characterized by multiple biological alterations, including disturbed brain circuits and connectivity, dysregulated neuronal excitation-inhibition, disturbed dopaminergic and glutamatergic pathways, and partially dysregulated inflammatory processes. The ways in which the dysregulated signaling pathways are interconnected remains largely unknown, in part because well-characterized clinical studies on comprehensive biomaterial are lacking. Furthermore, the development of drugs to treat SMIs such as schizophrenia is limited by the use of operationalized symptom-based clusters for diagnosis.

Methods

In line with the Research Domain Criteria initiative, the Clinical Deep Phenotyping (CDP) study is using a multimodal approach to reveal the neurobiological underpinnings of clinically relevant schizophrenia subgroups by performing broad transdiagnostic clinical characterization with standardized neurocognitive assessments, multimodal neuroimaging, electrophysiological assessments, retinal investigations, and omics-based analyzes of blood and cerebrospinal fluid. Moreover, to bridge the translational gap in biological psychiatry the study includes in vitro investigations on human-induced pluripotent stem cells, which are available from a subset of participants.

Results

Here, we report on the feasibility of this multimodal approach, which has been successfully initiated in the first participants in the CDP cohort; to date, the cohort comprises over 194 individuals with SMI and 187 age and gender matched healthy controls. In addition, we describe the applied research modalities and study objectives.

Discussion

The identification of cross-diagnostic and diagnosis-specific biotype-informed subgroups of patients and the translational dissection of those subgroups may help to pave the way toward precision medicine with artificial intelligence-supported tailored interventions and treatment. This aim is particularly important in psychiatry, a field where innovation is urgently needed because specific symptom domains, such as negative symptoms and cognitive dysfunction, and treatment-resistant symptoms in general are still difficult to treat.

Clinical predictors of antipsychotic treatment resistance: Development and internal validation of a prognostic prediction model by the STRATA-G consortium

INTRODUCTION

Our aim was to, firstly, identify characteristics at first-episode of psychosis that are associated with later antipsychotic treatment resistance (TR) and, secondly, to develop a parsimonious prediction model for TR.

METHODS

We combined data from ten prospective, first-episode psychosis cohorts from across Europe and categorised patients as TR or non-treatment resistant (NTR) after a mean follow up of 4.18 years (s.d. = 3.20) for secondary data analysis. We identified a list of potential predictors from clinical and demographic data recorded at first-episode. These potential predictors were entered in two models: a multivariable logistic regression to identify which were independently associated with TR and a penalised logistic regression, which performed variable selection, to produce a parsimonious prediction model. This model was internally validated using a 5-fold, 50-repeat cross-validation optimism-correction.

RESULTS

Our sample consisted of N = 2216 participants of which 385 (17 %) developed TR. Younger age of psychosis onset and fewer years in education were independently associated with increased odds of developing TR. The prediction model selected 7 out of 17 variables that, when combined, could quantify the risk of being TR better than chance. These included age of onset, years in education, gender, BMI, relationship status, alcohol use, and positive symptoms. The optimism-corrected area under the curve was 0.59 (accuracy = 64 %, sensitivity = 48 %, and specificity = 76 %).

IMPLICATIONS

Our findings show that treatment resistance can be predicted, at first-episode of psychosis. Pending a model update and external validation, we demonstrate the potential value of prediction models for TR.

Clinical correlates of early onset antipsychotic treatment resistance

BACKGROUND

There is evidence of heterogeneity within treatment-resistant schizophrenia (TRS), with some people not responding to antipsychotic treatment from illness onset and others becoming treatment-resistant after an initial response period. These groups may have different aetiologies.

AIM

This study investigates sociodemographic and clinical correlates of early onset of TRS.

METHOD

Employing a retrospective cohort design, we do a secondary analysis of data from a cohort of people with TRS attending the South London and Maudsley. Regression analyses were conducted to identify the correlates of the length of treatment to TRS. Predictors included the following: gender, age, ethnicity, problems with positive symptoms, problems with activities of daily living, psychiatric comorbidities, involuntary hospitalisation and treatment with long-acting injectable antipsychotics.

RESULTS

In a cohort of 164 people with TRS (60% were men), the median length of treatment to TRS was 3 years and 8 months. We observed no cut-off on the length of treatment until TRS presentation differentiating between early and late TRS (i.e. no bimodal distribution). Having mild to very severe problems with hallucinations and delusions at the treatment start was associated with earlier TRS (~19 months earlier). In sensitivity analyses, including only complete cases (subject to selection bias), treatment with a long-acting injectable antipsychotic was additionally associated with later TRS (~15 months later).

CONCLUSION

Our findings do not support a clear separation between early and late TRS but rather a continuum of the length of treatment before TRS onset. Having mild to very severe problems with positive symptoms at treatment start predicts earlier onset of TRS.

Study protocol for the development and internal validation of Schizophrenia Prediction of Resistance to Treatment (SPIRIT): a clinical tool for predicting risk of treatment resistance to antipsychotics in first-episode schizophrenia

INTRODUCTION

Treatment-resistant schizophrenia (TRS) is associated with significant impairment of functioning and high treatment costs. Identification of patients at high risk of TRS at the time of their initial diagnosis may significantly improve clinical outcomes and minimise social and functional disability. We aim to develop a prognostic model for predicting the risk of developing TRS in patients with first-episode schizophrenia and to examine its potential utility and acceptability as a clinical decision tool.

METHODS AND ANALYSIS

We will use two well-characterised longitudinal UK-based first-episode psychosis cohorts: Aetiology and Ethnicity in Schizophrenia and Other Psychoses and Genetics and Psychosis for which data have been collected on sociodemographic and clinical characteristics. We will identify candidate predictors for the model based on current literature and stakeholder consultation. Model development will use all data, with the number of candidate predictors restricted according to available sample size and event rate. A model for predicting risk of TRS will be developed based on penalised regression, with missing data handled using multiple imputation. Internal validation will be undertaken via bootstrapping, obtaining optimism-adjusted estimates of the model's performance. The clinical utility of the model in terms of clinically relevant risk thresholds will be evaluated using net benefit and decision curves (comparative to competing strategies). Consultation with patients and clinical stakeholders will determine potential thresholds of risk for treatment decision-making. The acceptability of embedding the model as a clinical tool will be explored using qualitative focus groups with up to 20 clinicians in total from early intervention services. Clinicians will be recruited from services in Stafford and London with the focus groups being held via an online platform.

ETHICS AND DISSEMINATION

The development of the prognostic model will be based on anonymised data from existing cohorts, for which ethical approval is in place. Ethical approval has been obtained from Keele University for the qualitative focus groups within early intervention in psychosis services (ref: MH-210174). Suitable processes are in place to obtain informed consent for National Health Service staff taking part in interviews or focus groups. A study information sheet with cover letter and consent form have been prepared and approved by the local Research Ethics Committee. Findings will be shared through peer-reviewed publications, conference presentations and social media. A lay summary will be published on collaborator websites.

Interplay between polygenic propensity for ageing-related traits and the consumption of fruits and vegetables on future dementia diagnosis

BACKGROUND

Understanding how polygenic scores for ageing-related traits interact with diet in determining a future dementia including Alzheimer's diagnosis (AD) would increase our understanding of mechanisms underlying dementia onset.

METHODS

Using 6784 population representative adults aged ≥50 years from the English Longitudinal Study of Ageing, we employed accelerated failure time survival model to investigate interactions between polygenic scores for AD (AD-PGS), schizophrenia (SZ-PGS) and general cognition (GC-PGS) and the baseline daily fruit and vegetable intake in association with dementia diagnosis during a 10-year follow-up. The baseline sample was obtained from waves 3-4 (2006-2009); follow-up data came from wave 5 (2010-2011) to wave 8 (2016-2017).

RESULTS

Consuming < 5 portions of fruit and vegetables a day was associated with 33-37% greater risk for dementia in the following 10 years depending on an individual polygenic propensity. One standard deviation (1-SD) increase in AD-PGS was associated with 24% higher risk of dementia and 47% higher risk for AD diagnosis. 1-SD increase in SZ-PGS was associated with an increased risk of AD diagnosis by 66%(95%CI = 1.05-2.64) in participants who consumed < 5 portions of fruit or vegetables. There was a significant additive interaction between GC-PGS and < 5 portions of the baseline daily intake of fruit and vegetables in association with AD diagnosis during the 10-year follow-up (RERI = 0.70, 95%CI = 0.09-4.82; AP = 0.36, 95%CI = 0.17-0.66).

CONCLUSION

A diet rich in fruit and vegetables is an important factor influencing the subsequent risk of dementia in the 10 years follow-up, especially in the context of polygenetic predisposition to AD, schizophrenia, and general cognition.

Prediction models in first-episode psychosis: systematic review and critical appraisal

BACKGROUND

People presenting with first-episode psychosis (FEP) have heterogenous outcomes. More than 40% fail to achieve symptomatic remission. Accurate prediction of individual outcome in FEP could facilitate early intervention to change the clinical trajectory and improve prognosis.

AIMS

We aim to systematically review evidence for prediction models developed for predicting poor outcome in FEP.

METHOD

A protocol for this study was published on the International Prospective Register of Systematic Reviews, registration number CRD42019156897. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidance, we systematically searched six databases from inception to 28 January 2021. We used the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies and the Prediction Model Risk of Bias Assessment Tool to extract and appraise the outcome prediction models. We considered study characteristics, methodology and model performance.

RESULTS

Thirteen studies reporting 31 prediction models across a range of clinical outcomes met criteria for inclusion. Eleven studies used logistic regression with clinical and sociodemographic predictor variables. Just two studies were found to be at low risk of bias. Methodological limitations identified included a lack of appropriate validation, small sample sizes, poor handling of missing data and inadequate reporting of calibration and discrimination measures. To date, no model has been applied to clinical practice.

CONCLUSIONS

Future prediction studies in psychosis should prioritise methodological rigour and external validation in larger samples. The potential for prediction modelling in FEP is yet to be realised.

Structural Covariance of Cortical Gyrification at Illness Onset in Treatment Resistance: A Longitudinal Study of First-Episode Psychoses

Treatment resistance (TR) in patients with first-episode psychosis (FEP) is a major cause of disability and functional impairment, yet mechanisms underlying this severe disorder are poorly understood. As one view is that TR has neurodevelopmental roots, we investigated whether its emergence relates to disruptions in synchronized cortical maturation quantified using gyrification-based connectomes. Seventy patients with FEP evaluated at their first presentation to psychiatric services were followed up using clinical records for 4 years; of these, 17 (24.3%) met the definition of TR and 53 (75.7%) remained non-TR at 4 years. Structural MRI images were obtained within 5 weeks from first exposure to antipsychotics. Local gyrification indices were computed for 148 contiguous cortical regions using FreeSurfer; each subject's contribution to group-based structural covariance was quantified using a jack-knife procedure, providing a single deviation matrix for each subject. The latter was used to derive topological properties that were compared between TR and non-TR patients using a Functional Data Analysis approach. Compared to the non-TR patients, TR patients showed a significant reduction in small-worldness (Hedges's g = 2.09, P < .001) and a reduced clustering coefficient (Hedges's g = 1.07, P < .001) with increased length (Hedges's g = -2.17, P < .001), indicating a disruption in the organizing principles of cortical folding. The positive symptom burden was higher in patients with more pronounced small-worldness (r = .41, P = .001) across the entire sample. The trajectory of synchronized cortical development inferred from baseline MRI-based structural covariance highlights the possibility of identifying patients at high-risk of TR prospectively, based on individualized gyrification-based connectomes.