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

Prediction of non-suicidal self-injury in adolescents at the family level using regression methods and machine learning

BACKGROUND

Adolescent non-suicidal self-injury (NSSI) is a major public health issue. Family factors are significantly associated with NSSI in adolescents, while studies on forecasting NSSI at the family level are still limited. In addition to regression methods, machine learning (ML) techniques have been recommended to improve the accuracy of family-level risk prediction for NSSI.

METHODS

Using a dataset of 7967 students and their primary caregivers from a cross-sectional study, logistic regression model and random forest model were used to test the forecasting accuracy of NSSI predictions at the family level. Cross-validation was used to assess model prediction performance, including the area under the receiver operator curve (AUC), precision, Brier score, accuracy, sensitivity, specificity, positive predictive value and negative predictive value.

RESULTS

The top three important family-related predictors within the random forest algorithm included family function (importance:42.66), family conflict (importance:42.18), and parental depression (importance:27.21). The most significant family-related risk predictors and protective predictors identified by the logistic regression model were family history of mental illness (OR:2.25) and help-seeking behaviors of mental distress from parents (OR:0.65), respectively. The AUCs of the two models, logistic regression and random forest, were 0.852 and 0.835, respectively.

LIMITATIONS

The key limitation is that this cross-sectional survey only enabled the authors to examine predictors that were considered to be proximal rather than distal.

CONCLUSIONS

These findings highlight the significance of family-related factors in forecasting NSSI in adolescents. Combining both conventional statistical methods and ML methods to improve risk assessment of NSSI at the family level deserves attention.

Exploring Characteristics of Homicide Offenders With Schizophrenia Spectrum Disorders Via Machine Learning

The link between schizophrenia and homicide has long been the subject of research with significant impact on mental health policy, clinical practice, and public perception of people with psychiatric disorders. The present study investigates factors contributing to completed homicides committed by offenders diagnosed with schizophrenia referred to a Swiss forensic institution, using machine learning algorithms. Data were collected from 370 inpatients at the Centre for Inpatient Forensic Therapy at the Zurich University Hospital of Psychiatry. A total of 519 variables were explored to differentiate homicidal and other (violent and non-violent) offenders. The dataset was split employing variable filtering, model building, and selection embedded in a nested resampling approach. Ten factors regarding criminal and psychiatric history and clinical factors were identified to be influential in differentiating between homicidal and other offenders. Findings expand the research on influential factors for completed homicide in patients with schizophrenia. Limitations, clinical relevance, and future directions are discussed.

Heterogeneity of clinical symptomatology in pediatric patients at clinical high risk for psychosis

OBJECTIVE

Widespread use of diagnostic tools like the Structured Interview for Prodromal Symptoms (SIPS) has highlighted that youth at Clinical High Risk for Psychosis (CHR-P) present with heterogeneous symptomatology. This pilot study aims to highlight the range of clinical characteristics of CHR-P youth, investigate the role of the non-positive (negative, disorganization, and general) symptoms in risk assessment, and determine if specific profiles are associated with severe symptomatology.

METHODS

38 participants aged 7-18 were administered the SIPS and designated as CHR-P. Descriptive statistics and mean difference t-tests were used to describe the range in prevalence and severity of SIPS symptoms and to identify symptoms associated with greater overall symptomatology.

RESULTS

Participants who had a greater number of positive symptoms also had significantly more negative, disorganization, and general symptoms. A number of SIPS symptoms were associated with greater number of positive symptoms.

CONCLUSION

CHR-P youth represent a heterogeneous group, presenting with a wide range in clinical presentation as reflected in both the number of SIPS symptoms and their severity. Though the severity and duration of positive SIPS symptoms determines the CHR-P classification, high ratings on several of the other SIPS negative, disorganization, and general items may be useful indicators of elevated symptomatology.

N-acetylcysteine during critical neurodevelopmental periods prevents behavioral and neurochemical deficits in the Poly I:C rat model of schizophrenia

Schizophrenia is a chronic neurodevelopmental disorder with an inflammatory/prooxidant component. N-acetylcysteine (NAC) has been evaluated in schizophrenia as an adjuvant to antipsychotics, but its role as a preventive strategy has not been sufficiently explored. We aimed to evaluate the potential of NAC administration in two-time windows before the onset of symptoms in a schizophrenia-like maternal immune stimulation (MIS) rat model. Pregnant Wistar rats were injected with Poly I:C or Saline on gestational day (GD) 15. Three different preventive approaches were evaluated: 1) NAC treatment during periadolescence in the offspring (from postnatal day [PND] 35 to 49); 2) NAC treatment during pregnancy after MIS challenge until delivery (GD15-21); and 3) NAC treatment throughout all pregnancy (GD1-21). At postnatal day (PND) 70, prepulse inhibition (PPI) and anxiety levels were evaluated. In vivo magnetic resonance (MR) imaging was acquired on PND100 to assess structural changes in gray and white matter, and brain metabolite concentrations. Additionally, inflammation and oxidative stress (IOS) markers were measured ex vivo in selected brain regions. MIS offspring showed behavioral, neuroanatomical, and biochemical alterations. Interestingly, NAC treatment during periadolescence prevented PPI deficits and partially counteracted some biochemical imbalances. Moreover, NAC treatments during pregnancy not only replicated the beneficial outcomes reported by the treatment in periadolescence, but also prevented some neuroanatomical deficits, including reductions in hippocampal and corpus callosum volumes. This study suggests that early reduction of inflammation and prooxidation could help prevent the onset of schizophrenia-like symptoms, supporting the importance of anti-IOS compounds in ameliorating this disorder.

Risk stratification for treating people at ultra-high risk for psychosis: A cost-effectiveness analysis

People who are at ultra-high risk (UHR) for psychosis receive clinical care with the aim to prevent first-episode psychosis (FEP), regardless of the risk of conversion to psychosis. An economic model from the Canadian health system perspective was developed to evaluate the cost-effectiveness of treating all with UHR compared to risk stratification over a 15-year time horizon, based on conversion probability, expected quality-of-life and costs. The analysis used a decision tree followed by a Markov model. Health states included: Not UHR, UHR with <20 % risk of conversion to FEP (based on the North American Prodrome Longitudinal Study risk calculator), UHR with ≥20 % risk, FEP, Remission, Post-FEP, and Death. The analysis found that: risk stratification (i.e., only treating those with ≥20 % risk) had lower costs ($1398) and quality-adjusted life-years (0.055 QALYs) per person compared to treating all. The incremental cost-effectiveness ratio for 'treat all' was $25,448/QALY, and suggests treating all may be cost-effective. The model was sensitive to changes to the probability of conversion.

Prognostic models predicting transition to psychotic disorder using blood-based biomarkers: a systematic review and critical appraisal

Accumulating evidence suggests individuals with psychotic disorder show abnormalities in metabolic and inflammatory processes. Recently, several studies have employed blood-based predictors in models predicting transition to psychotic disorder in risk-enriched populations. A systematic review of the performance and methodology of prognostic models using blood-based biomarkers in the prediction of psychotic disorder from risk-enriched populations is warranted. Databases (PubMed, EMBASE and PsycINFO) were searched for eligible texts from 1998 to 15/05/2023, which detailed model development or validation studies. The checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) was used to guide data extraction from eligible texts and the Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias and applicability of the studies. A narrative synthesis of the included studies was performed. Seventeen eligible studies were identified: 16 eligible model development studies and one eligible model validation study. A wide range of biomarkers were assessed, including nucleic acids, proteins, metabolites, and lipids. The range of C-index (area under the curve) estimates reported for the models was 0.67-1.00. No studies assessed model calibration. According to PROBAST criteria, all studies were at high risk of bias in the analysis domain. While a wide range of potentially predictive biomarkers were identified in the included studies, most studies did not account for overfitting in model performance estimates, no studies assessed calibration, and all models were at high risk of bias according to PROBAST criteria. External validation of the models is needed to provide more accurate estimates of their performance. Future studies which follow the latest available methodological and reporting guidelines and adopt strategies to accommodate required sample sizes for model development or validation will clarify the value of including blood-based biomarkers in models predicting psychosis.

Self-Harm Among Forensic Psychiatric Inpatients With Schizophrenia Spectrum Disorders: An Explorative Analysis

The burden of self-injury among offenders undergoing inpatient treatment in forensic psychiatry is substantial. This exploratory study aims to add to the previously sparse literature on the correlates of self-injury in inpatient forensic patients with schizophrenia spectrum disorders (SSD). Employing a sample of 356 inpatients with SSD treated in a Swiss forensic psychiatry hospital, patient data on 512 potential predictor variables were retrospectively collected via file analysis. The dataset was examined using supervised machine learning to distinguish between patients who had engaged in self-injurious behavior during forensic hospitalization and those who had not. Based on a combination of ten variables, including psychiatric history, criminal history, psychopathology, and pharmacotherapy, the final machine learning model was able to discriminate between self-injury and no self-injury with a balanced accuracy of 68% and a predictive power of AUC = 71%. Results suggest that forensic psychiatric patients with SSD who self-injured were younger both at the time of onset and at the time of first entry into the federal criminal record. They exhibited more severe psychopathological symptoms at the time of admission, including higher levels of depression and anxiety and greater difficulty with abstract reasoning. Of all the predictors identified, symptoms of depression and anxiety may be the most promising treatment targets for the prevention of self-injury in inpatient forensic patients with SSD due to their modifiability and should be further substantiated in future studies.

Investigation of social and cognitive predictors in non-transition ultra-high-risk' individuals for psychosis using spiking neural networks

Finding predictors of social and cognitive impairment in non-transition Ultra-High-Risk individuals (UHR) is critical in prognosis and planning of potential personalised intervention strategies. Social and cognitive functioning observed in youth at UHR for psychosis may be protective against transition to clinically relevant illness. The current study used a computational method known as Spiking Neural Network (SNN) to identify the cognitive and social predictors of transitioning outcome. Participants (90 UHR, 81 Healthy Control (HC)) completed batteries of neuropsychological tests in the domains of verbal memory, working memory, processing speed, attention, executive function along with social skills-based performance at baseline and 4 × 6-month follow-up intervals. The UHR status was recorded as Remitters, Converters or Maintained. SNN were used to model interactions between variables across groups over time and classify UHR status. The performance of SNN was examined relative to other machine learning methods. Higher interaction between social and cognitive variables was seen for the Maintained, than Remitter subgroup. Findings identified the most important cognitive and social variables (particularly verbal memory, processing speed, attention, affect and interpersonal social functioning) that showed discriminative patterns in the SNN models of HC vs UHR subgroups, with accuracies up to 80%; outperforming other machine learning models (56-64% based on 18 months data). This finding is indicative of a promising direction for early detection of social and cognitive impairment in UHR individuals that may not anticipate transition to psychosis and implicate early initiated interventions to stem the impact of clinical symptoms of psychosis.

Predictive validity of psychosis risk models when applied to adolescent psychiatric patients

BACKGROUND

Several multivariate algorithms have been developed for predicting psychosis, as attempts to obtain better prognosis prediction than with current clinical high-risk (CHR) criteria. The models have typically been based on samples from specialized clinics. We evaluated the generalizability of 19 prediction models to clinical practice in an unselected adolescent psychiatric sample.

METHODS

In total, 153 adolescent psychiatric patients in the Helsinki Prodromal Study underwent an extensive baseline assessment including the SIPS interview and a neurocognitive battery, with 50 participants (33%) fulfilling CHR criteria. The adolescents were followed up for 7 years using comprehensive national registers. Assessed outcomes were (1) any psychotic disorder diagnosis (n = 18, 12%) and (2) first psychiatric hospitalization (n = 25, 16%) as an index of overall deterioration of functioning.

RESULTS

Most models improved the overall prediction accuracy over standard CHR criteria (area under the curve estimates ranging between 0.51 and 0.82), although the accuracy was worse than that in the samples used to develop the models, also when applied only to the CHR subsample. The best models for transition to psychosis included the severity of positive symptoms, especially delusions, and negative symptoms. Exploratory models revealed baseline negative symptoms, low functioning, delusions, and sleep problems in combination to be the best predictor of psychiatric hospitalization in the upcoming years.

CONCLUSIONS

Including the severity levels of both positive and negative symptomatology proved beneficial in predicting psychosis. Despite these advances, the applicability of extended psychosis-risk models to general psychiatric practice appears limited.

Prediction of depressive symptoms onset and long-term trajectories in home-based older adults using machine learning techniques

OBJECTIVES

Our aim was to explore the possibility of using machine learning (ML) in predicting the onset and trajectories of depressive symptom in home-based older adults over a 7-year period.

METHODS

Depressive symptom data (collected in the year 2011, 2013, 2015 and 2018) of home-based older Chinese (n = 2650) recruited in the China Health and Retirement Longitudinal Study (CHARLS) were included in the current analysis. The latent class growth modeling (LCGM) and growth mixture modeling (GMM) were used to classify different trajectory classes. Based on the identified trajectory patterns, three ML classification algorithms (i.e. gradient boosting decision tree, support vector machine and random forest) were evaluated with a 10-fold cross-validation procedure and a metric of the area under the receiver operating characteristic curve (AUC).

RESULTS

Four trajectories were identified for the depressive symptoms: no symptoms (63.9%), depressive symptoms onset {incident increasing symptoms [new-onset increasing (16.8%)], chronic symptoms [slowly decreasing (12.5%), persistent high (6.8%)]}. Among the analyzed baseline variables, the 10-item Center for Epidemiologic Studies Depression Scale (CESD-10) score, cognition, sleep time, self-reported memory were the top five important predictors across all trajectories. The mean AUCs of the three predictive models had a range from 0.661 to 0.892.

CONCLUSIONS

ML techniques can be robust in predicting depressive symptom onset and trajectories over a 7-year period with easily accessible sociodemographic and health information.

Supplemental data for this article is available online at http://dx.doi.org/10.1080/13607863.2022.2031868.

Development and Validation of Predictive Model for a Diagnosis of First Episode Psychosis Using the Multinational EU-GEI Case-control Study and Modern Statistical Learning Methods

Background and Hypothesis

It is argued that availability of diagnostic models will facilitate a more rapid identification of individuals who are at a higher risk of first episode psychosis (FEP). Therefore, we developed, evaluated, and validated a diagnostic risk estimation model to classify individual with FEP and controls across six countries.

Study Design

We used data from a large multi-center study encompassing 2627 phenotypically well-defined participants (aged 18-64 years) recruited from six countries spanning 17 research sites, as part of the European Network of National Schizophrenia Networks Studying Gene-Environment Interactions study. To build the diagnostic model and identify which of important factors for estimating an individual risk of FEP, we applied a binary logistic model with regularization by the least absolute shrinkage and selection operator. The model was validated employing the internal-external cross-validation approach. The model performance was assessed with the area under the receiver operating characteristic curve (AUROC), calibration, sensitivity, and specificity.

Study Results

Having included preselected 22 predictor variables, the model was able to discriminate adults with FEP and controls with high accuracy across all six countries (rangesAUROC = 0.84-0.86). Specificity (range = 73.9-78.0%) and sensitivity (range = 75.6-79.3%) were equally good, cumulatively indicating an excellent model accuracy; though, calibration slope for the diagnostic model showed a presence of some overfitting when applied specifically to participants from France, the UK, and The Netherlands.

Conclusions

The new FEP model achieved a good discrimination and good calibration across six countries with different ethnic contributions supporting its robustness and good generalizability.

A hybrid machine learning model of depression estimation in home-based older adults: a 7-year follow-up study

BACKGROUND

Our aim was to explore whether a two-step hybrid machine learning model has the potential to discover the onset of depression in home-based older adults.

METHODS

Depression data (collected in the year 2011, 2013, 2015 and 2018) of home-based older Chinese (n = 2,548) recruited in the China Health and Retirement Longitudinal Study were included in the current analysis. The long short-term memory network (LSTM) was applied to identify the risk factors of participants in 2015 utilizing the first 2 waves of data. Based on the identified predictors, three ML classification algorithms (i.e., gradient boosting decision tree, support vector machine and random forest) were evaluated with a 10-fold cross-validation procedure and a metric of the area under the receiver operating characteristic curve (AUROC) to estimate the depressive outcome.

RESULTS

Time-varying predictors of the depression were successfully identified by LSTM (mean squared error =0.8). The mean AUCs of the three predictive models had a range from 0.703 to 0.749. Among the prediction variables, self-reported health status, cognition, sleep time, self-reported memory and ADL (activities of daily living) disorder were the top five important variables.

CONCLUSIONS

A two-step hybrid model based on "LSTM+ML" framework can be robust in predicting depression over a 5-year period with easily accessible sociodemographic and health information.

Early cognitive comorbidities before disease onset: A common symptom towards prevention of related brain diseases?

Brain diseases are very heterogeneous; however they also display multiple common risk factors and comorbidities. With a paucity of disease-modifying therapies, prevention became a health priority. Towards prevention, one strategy is to focus on similar symptoms of brain diseases occurring before disease onset. Cognitive deficits are a promising candidate as they occur across brain diseases before disease onset. Based on recent research, this review highlights the similarity of brain diseases and discusses how early cognitive deficits can be exploited to tackle disease prevention. After briefly introducing common risk factors, I review common comorbidities across brain diseases, with a focus on cognitive deficits before disease onset, reporting both experimental and clinical findings. Next, I describe network abnormalities associated with early cognitive deficits and discuss how these abnormalities can be targeted to prevent disease onset. A scenario on brain disease etiology with the idea that early cognitive deficits may constitute a common symptom of brain diseases is proposed.

Prediction of psychosis: model development and internal validation of a personalized risk calculator

BACKGROUND

Over the past two decades, early detection and early intervention in psychosis have become essential goals of psychiatry. However, clinical impressions are insufficient for predicting psychosis outcomes in clinical high-risk (CHR) individuals; a more rigorous and objective model is needed. This study aims to develop and internally validate a model for predicting the transition to psychosis within 10 years.

METHODS

Two hundred and eight help-seeking individuals who fulfilled the CHR criteria were enrolled from the prospective, naturalistic cohort program for CHR at the Seoul Youth Clinic (SYC). The least absolute shrinkage and selection operator (LASSO)-penalized Cox regression was used to develop a predictive model for a psychotic transition. We performed k-means clustering and survival analysis to stratify the risk of psychosis.

RESULTS

The predictive model, which includes clinical and cognitive variables, identified the following six baseline variables as important predictors: 1-year percentage decrease in the Global Assessment of Functioning score, IQ, California Verbal Learning Test score, Strange Stories test score, and scores in two domains of the Social Functioning Scale. The predictive model showed a cross-validated Harrell's C-index of 0.78 and identified three subclusters with significantly different risk levels.

CONCLUSIONS

Overall, our predictive model showed a predictive ability and could facilitate a personalized therapeutic approach to different risks in high-risk individuals.

Developing and internally validating a prognostic model (P Risk) to improve the prediction of psychosis in a primary care population using electronic health records: The MAPPED study

BACKGROUND

An accurate risk prediction algorithm could improve psychosis outcomes by reducing duration of untreated psychosis.

OBJECTIVE

To develop and validate a risk prediction model for psychosis, for use by family doctors, using linked electronic health records.

METHODS

A prospective prediction study. Records from family practices were used between 1/1/2010 to 31/12/2017 of 300,000 patients who had consulted their family doctor for any nonpsychotic mental health problem. Records were selected from Clinical Practice Research Datalink Gold, a routine database of UK family doctor records linked to Hospital Episode Statistics, a routine database of UK secondary care records. Each patient had 5-8 years of follow up data. Study predictors were consultations, diagnoses and/or prescribed medications, during the study period or historically, for 13 nonpsychotic mental health problems and behaviours, age, gender, number of mental health consultations, social deprivation, geographical location, and ethnicity. The outcome was time to an ICD10 psychosis diagnosis.

FINDINGS

830 diagnoses of psychosis were made. Patients were from 216 family practices; mean age was 45.3 years and 43.5 % were male. Median follow-up was 6.5 years (IQR 5.6, 7.8). Overall 8-year psychosis incidence was 45.8 (95 % CI 42.8, 49.0)/100,000 person years at risk. A risk prediction model including age, sex, ethnicity, social deprivation, consultations for suicidal behaviour, depression/anxiety, substance abuse, history of consultations for suicidal behaviour, smoking history and prescribed medications for depression/anxiety/PTSD/OCD and total number of consultations had good discrimination (Harrell's C = 0.774). Identifying patients aged 17-100 years with predicted risk exceeding 1.0 % over 6 years had sensitivity of 71 % and specificity of 84 %.

FUNDING

NIHR, School for Primary Care Research, Biomedical Research Centre.

Clinical prediction models in psychiatry: a systematic review of two decades of progress and challenges

Recent years have seen the rapid proliferation of clinical prediction models aiming to support risk stratification and individualized care within psychiatry. Despite growing interest, attempts to synthesize current evidence in the nascent field of precision psychiatry have remained scarce. This systematic review therefore sought to summarize progress towards clinical implementation of prediction modeling for psychiatric outcomes. We searched MEDLINE, PubMed, Embase, and PsychINFO databases from inception to September 30, 2020, for English-language articles that developed and/or validated multivariable models to predict (at an individual level) onset, course, or treatment response for non-organic psychiatric disorders (PROSPERO: CRD42020216530). Individual prediction models were evaluated based on three key criteria: (i) mitigation of bias and overfitting; (ii) generalizability, and (iii) clinical utility. The Prediction model Risk Of Bias ASsessment Tool (PROBAST) was used to formally appraise each study's risk of bias. 228 studies detailing 308 prediction models were ultimately eligible for inclusion. 94.5% of developed prediction models were deemed to be at high risk of bias, largely due to inadequate or inappropriate analytic decisions. Insufficient internal validation efforts (within the development sample) were also observed, while only one-fifth of models underwent external validation in an independent sample. Finally, our search identified just one published model whose potential utility in clinical practice was formally assessed. Our findings illustrated significant growth in precision psychiatry with promising progress towards real-world application. Nevertheless, these efforts have been inhibited by a preponderance of bias and overfitting, while the generalizability and clinical utility of many published models has yet to be formally established. Through improved methodological rigor during initial development, robust evaluations of reproducibility via independent validation, and evidence-based implementation frameworks, future research has the potential to generate risk prediction tools capable of enhancing clinical decision-making in psychiatric care.

A systematic review of premorbid cognitive functioning and its timing of onset in schizophrenia spectrum disorders

Cognitive impairments are core features of established schizophrenia spectrum disorders (SSD). However, it remains unclear whether specific cognitive functions are differentially impaired pre-onset and at what age these impairments can be detected. The purpose of this review was to elucidate these issues through a systematic summary of results from longitudinal studies investigating impairment in specific cognitive domains as antecedents of SSD. Relevant studies were identified by electronic and manual literature searches and included any original study of cognitive domains any time pre-onset of SSDs that included a control group. Effect sizes were calculated by domain for studies comparing high-risk participants who developed SSD with those who did not. The strongest evidence for impairment pre-onset was for mental processing speed, verbal learning and memory, executive function, and social cognition. Some verbal impairments, like language abilities at age 3 and verbal learning and memory at age 7, may develop as static deficits. Conversely, some non-verbal impairments, like mental processing speed, visuospatial abilities, and visual working memory manifest as developmental lag and become significant later in life. Most effect sizes were small to moderate, except for verbal fluency (d' = 0,85), implying this impairment as central in high-risk participants who develop SSD. The present review documents extensive cognitive impairments pre-onset of SSD, and that these impairments start early in life, in line with the neurodevelopmental hypothesis of schizophrenia. Increased knowledge about cognitive impairments preonset can provide a better basis for understanding the complex pathogenesis of SSD as well as informing cognitive remediation programs.

Towards identifying cancer patients at risk to miss out on psycho-oncological treatment via machine learning

OBJECTIVE

In routine oncological treatment settings, psychological distress, including mental disorders, is overlooked in 30% to 50% of patients. High workload and a constant need to optimise time and costs require a quick and easy method to identify patients likely to miss out on psychological support.

METHODS

Using machine learning, factors associated with no consultation with a clinical psychologist or psychiatrist were identified between 2011 and 2019 in 7,318 oncological patients in a large cancer treatment centre. Parameters were hierarchically ordered based on statistical relevance. Nested resampling and cross validation were performed to avoid overfitting.

RESULTS

Patients were least likely to receive psycho-oncological (i.e., psychiatric/psychotherapeutic) treatment when they were not formally screened for distress, had inpatient treatment for less than 28 days, had no psychiatric diagnosis, were aged 65 or older, had skin cancer or were not being discussed in a tumour board. The final validated model was optimised to maximise sensitivity at 85.9% and achieved an area under the curve (AUC) of 0.75, a balanced accuracy of 68.5% and specificity of 51.2%.

CONCLUSION

Beyond conventional screening tools, results might contribute to identify patients at risk to be neglected in terms of referral to psycho-oncology within routine oncological care.

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.

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.

Escape and absconding among offenders with schizophrenia spectrum disorder - an explorative analysis of characteristics

BACKGROUND

Escape and absconding, especially in forensic settings, can have serious consequences for patients, staff and institutions. Several characteristics of affected patients could be identified so far, albeit based on heterogeneous patient populations, a limited number of possible factors and basal statistical analyses. The aim of this study was to determine the most important characteristics among a large number of possible variables and to describe the best statistical model using machine learning in a homogeneous group of offender patients with schizophrenia spectrum disorder.

METHODS

A database of 370 offender patients suffering from schizophrenia spectrum disorder and 507 possible predictor variables was explored by machine learning. To counteract overfitting, the database was divided into training and validation set and a nested validation procedure was used on the training set. The best model was tested on the validation set and the most important variables were extracted.

RESULTS

The final model resulted in a balanced accuracy of 71.1% (95% CI = [58.5, 83.1]) and an AUC of 0.75 (95% CI = [0.63, 0.87]). The variables identified as relevant and related to absconding/ escape listed from most important to least important were: more frequent forbidden intake of drugs during current hospitalization, more index offences, higher neuroleptic medication, more frequent rule breaking behavior during current hospitalization, higher PANSS Score at discharge, lower age at admission, more frequent dissocial behavior during current hospitalization, shorter time spent in current hospitalization and higher PANSS Score at admission.

CONCLUSIONS

For the first time a detailed statistical model could be built for this topic. The results indicate the presence of a particularly problematic subgroup within the group of offenders with schizophrenic spectrum disorder who also tend to escape or abscond. Early identification and tailored treatment of these patients could be of clinical benefit.

Towards clinical application of prediction models for transition to psychosis: A systematic review and external validation study in the PRONIA sample

A multitude of prediction models for a first psychotic episode in individuals at clinical high-risk (CHR) for psychosis have been proposed, but only rarely validated. We identified transition models based on clinical and neuropsychological data through a registered systematic literature search and evaluated their external validity in 173 CHRs from the Personalised Prognostic Tools for Early Psychosis Management (PRONIA) study. Discrimination performance was assessed with the area under the receiver operating characteristic curve (AUC), and compared to the prediction of clinical raters. External discrimination performance varied considerably across the 22 identified models (AUC 0.40-0.76), with two models showing good discrimination performance. None of the tested models significantly outperformed clinical raters (AUC = 0.75). Combining predictions of clinical raters and the best model descriptively improved discrimination performance (AUC = 0.84). Results show that personalized prediction of transition in CHR is potentially feasible on a global scale. For implementation in clinical practice, further rounds of external validation, impact studies, and development of an ethical framework is necessary.

Pattern classification as decision support tool in antipsychotic treatment algorithms

Pattern classification aims to establish a new approach in personalized treatment. The scope is to tailor treatment on individual characteristics during all phases of care including prevention, diagnosis, treatment, and clinical outcome. In psychotic disorders, this need results from the fact that a third of patients with psychotic symptoms do not respond to antipsychotic treatment and are described as having treatment-resistant disorders. This, in addition to the high variability of treatment responses among patients, enhances the need of applying advanced classification algorithms to identify antipsychotic treatment patterns. This review comprehensively summarizes advancements and challenges of pattern classification in antipsychotic treatment response to date and aims to introduce clinicians and researchers to the challenges of including pattern classification into antipsychotic treatment decision algorithms.

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.

Third external replication of an individualised transdiagnostic prediction model for the automatic detection of individuals at risk of psychosis using electronic health records

BACKGROUND

Primary indicated prevention is a key target for reducing the incidence and burden of schizophrenia and related psychotic disorders. An individualised, clinically-based transdiagnostic model for the detection of individuals at risk of psychosis has been developed and validated in two large, urban healthcare providers. We tested its external validity in a geographically and demographically different non-urban population.

METHOD

Retrospective EHR cohort study. All individuals accessing secondary healthcare provided by Oxford Health NHS Foundation Trust between 1st January 2011 and 30th November 2019 and receiving a primary index diagnosis of a non-psychotic or non-organic mental disorder were considered eligible. The previously developed model was applied to this database and its external prognostic accuracy was measured with Harrell's C.

FINDINGS

The study included n = 33,710 eligible individuals, with an average age of 27.7 years (SD = 19.8), mostly white (92.0%) and female (57.3%). The mean follow-up was 1863.9 days (SD = 948.9), with 868 transitions to psychosis and a cumulative incidence of psychosis at 6 years of 2.9% (95%CI: 2.7-3.1). Compared to the urban development database, Oxford Health was characterised by a relevant case mix, lower incidence of psychosis, different distribution of baseline predictors, higher proportion of white females, and a lack of specialised clinical services for at risk individuals. Despite these differences the model retained an adequate prognostic performance (Harrell's C = 0.79, 95%CI: 0.78-0.81), with no major miscalibration.

INTERPRETATION

The transdiagnostic, individualised, clinically-based risk calculator is transportable outside urban healthcare providers. Further research should test transportability of this risk prediction model in an international setting.

Identifying Adolescents at Risk for Depression: A Prediction Score Performance in Cohorts Based in 3 Different Continents

OBJECTIVE

Prediction models have become frequent in the medical literature, but most published studies are conducted in a single setting. Heterogeneity between development and validation samples has been posited as a major obstacle for the generalization of models. We aimed to develop a multivariable prognostic model using sociodemographic variables easily obtainable from adolescents at age 15 to predict a depressive disorder diagnosis at age 18 and to evaluate its generalizability in 2 samples from diverse socioeconomic and cultural settings.

METHOD

Data from the 1993 Pelotas Birth Cohort were used to develop the prediction model, and its generalizability was evaluated in 2 representative cohort studies: the Environmental Risk (E-Risk) Longitudinal Twin Study and the Dunedin Multidisciplinary Health and Development Study.

RESULTS

At age 15, 2,192 adolescents with no evidence of current or previous depression were included (44.6% male). The apparent C-statistic of the models derived in Pelotas ranged from 0.76 to 0.79, and the model obtained from a penalized logistic regression was selected for subsequent external evaluation. Major discrepancies between the samples were identified, impacting the external prognostic performance of the model (Dunedin and E-Risk C-statistics of 0.63 and 0.59, respectively). The implementation of recommended strategies to account for this heterogeneity among samples improved the model's calibration in both samples.

CONCLUSION

An adolescent depression risk score comprising easily obtainable predictors was developed with good prognostic performance in a Brazilian sample. Heterogeneity among settings was not trivial, but strategies to deal with sample diversity were identified as pivotal for providing better risk stratification across samples. Future efforts should focus on developing better methodological approaches for incorporating heterogeneity in prognostic research.

Combined pattern of childhood psycho-behavioral characteristics in patients with schizophrenia: a retrospective study in Japan

BACKGROUND

Although epidemiological and genetic studies have provided scientific evidence that places schizophrenia into the framework of early neurodevelopmental disorders, the psycho-behavioral characteristics of children that later go on to develop schizophrenia have not been sufficiently clarified. This study aimed to retrospectively identify characteristics specific to patients with schizophrenia during childhood via their guardians' reporting of these characteristics.

METHODS

Participants included 54 outpatients with schizophrenia in their twenties who fulfilled DSM-IV-TR criteria. Additionally, 192 normal healthy subjects participated as sex- and age-matched controls. The guardians of all participants were recruited to rate participants' childhood characteristics from 6 to 8 years of age on a modified version of the Child Behavior Checklist (CBCL), which was used as a retrospective assessment questionnaire. Using t-tests, logistic regression, and Receiver Operating Characteristic (ROC) curve analysis, we estimated the psycho-behavioral characteristics specific to schizophrenia during childhood. Using the obtained logistic regression model, we prototyped a risk-predicting algorithm based on the CBCL scores.

RESULTS

Among the eight CBCL subscale t-scores, "withdrawn" (p = 0.002), "thought problems" (p = 0.001), and "lack of aggressive behavior" (p = 0.002) were each significantly associated with the later diagnosis of schizophrenia, although none of these mean scores were in the clinical range at the time of childhood. The algorithm of the logistic regression model, based on eight CBCL subscales, had an area under the ROC curve of 82.8% (95% CI: 76-89%), which indicated that this algorithm's prediction of late development of schizophrenia has moderate accuracy.

CONCLUSIONS

The results suggest that according to guardian reports, participants showed psycho-behavioral characteristics during childhood, different to those of healthy controls, which could be predictive of the later development of schizophrenia. Our newly developed algorithm is available to use in future studies to further test its validity.

Development and external validation of an admission risk prediction model after treatment from early intervention in psychosis services

Early Intervention in psychosis (EIP) teams are the gold standard treatment for first-episode psychosis (FEP). EIP is time-limited and clinicians are required to make difficult aftercare decisions that require weighing up individuals' wishes for treatment, risk of relapse, and health service capacity. Reliable decision-making tools could assist with appropriate resource allocation and better care. We aimed to develop and externally validate a readmission risk tool for application at the point of EIP discharge. All persons from EIP caseloads in two NHS Trusts were eligible for the study. We excluded those who moved out of the area or were only seen for assessment. We developed a model to predict the risk of hospital admission within a year of ending EIP treatment in one Trust and externally validated it in another. There were n = 831 participants in the development dataset and n = 1393 in the external validation dataset, with 79 (9.5%) and 162 (11.6%) admissions to inpatient hospital, respectively. Discrimination was AUC = 0.76 (95% CI 0.75; 0.77) in the development dataset and AUC = 0.70 (95% CI 0.66; 0.75) in the external dataset. Calibration plots in external validation suggested an underestimation of risk in the lower predicted probabilities and slight overestimation at predicted probabilities in the 0.1-0.2 range (calibration slope = 0.86, 95% CI 0.68; 1.05). Recalibration improved performance at lower predicted probabilities but underestimated risk at the highest range of predicted probabilities (calibration slope = 1.00, 95% CI 0.79; 1.21). We showed that a tool for predicting admission risk using routine data has good performance and could assist clinical decision-making. Refinement of the model, testing its implementation and further external validation are needed.

Comparison of Regression and Machine Learning Methods in Depression Forecasting Among Home-Based Elderly Chinese: A Community Based Study

BACKGROUND

Depression is highly prevalent and considered as the most common psychiatric disorder in home-based elderly, while study on forecasting depression risk in the elderly is still limited. In an endeavor to improve accuracy of depression forecasting, machine learning (ML) approaches have been recommended, in addition to the application of more traditional regression approaches.

METHODS

A prospective study was employed in home-based elderly Chinese, using baseline (2011) and follow-up (2013) data of the China Health and Retirement Longitudinal Study (CHARLS), a nationally representative cohort study. We compared four algorithms, including the regression-based models (logistic regression, lasso, ridge) and ML method (random forest). Model performance was assessed using repeated nested 10-fold cross-validation. As the main measure of predictive performance, we used the area under the receiver operating characteristic curve (AUC).

RESULTS

The mean AUCs of the four predictive models, logistic regression, lasso, ridge, and random forest, were 0.795, 0.794, 0.794, and 0.769, respectively. The main determinants were life satisfaction, self-reported memory, cognitive ability, ADL (activities of daily living) impairment, CESD-10 score. Life satisfaction increased the odds ratio of a future depression by 128.6% (logistic), 13.8% (lasso), and 13.2% (ridge), and cognitive ability was the most important predictor in random forest.

CONCLUSIONS

The three regression-based models and one ML algorithm performed equally well in differentiating between a future depression case and a non-depression case in home-based elderly. When choosing a model, different considerations, however, such as easy operating, might in some instances lead to one model being prioritized over another.

Development of Proteomic Prediction Models for Transition to Psychotic Disorder in the Clinical High-Risk State and Psychotic Experiences in Adolescence

IMPORTANCE

Biomarkers that are predictive of outcomes in individuals at risk of psychosis would facilitate individualized prognosis and stratification strategies.

OBJECTIVE

To investigate whether proteomic biomarkers may aid prediction of transition to psychotic disorder in the clinical high-risk (CHR) state and adolescent psychotic experiences (PEs) in the general population.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study comprised 2 case-control studies nested within the European Network of National Schizophrenia Networks Studying Gene-Environment Interactions (EU-GEI) and the Avon Longitudinal Study of Parents and Children (ALSPAC). EU-GEI is an international multisite prospective study of participants at CHR referred from local mental health services. ALSPAC is a United Kingdom-based general population birth cohort. Included were EU-GEI participants who met CHR criteria at baseline and ALSPAC participants who did not report PEs at age 12 years. Data were analyzed from September 2018 to April 2020.

MAIN OUTCOMES AND MEASURES

In EU-GEI, transition status was assessed by the Comprehensive Assessment of At-Risk Mental States or contact with clinical services. In ALSPAC, PEs at age 18 years were assessed using the Psychosis-Like Symptoms Interview. Proteomic data were obtained from mass spectrometry of baseline plasma samples in EU-GEI and plasma samples at age 12 years in ALSPAC. Support vector machine learning algorithms were used to develop predictive models.

RESULTS

The EU-GEI subsample (133 participants at CHR (mean [SD] age, 22.6 [4.5] years; 68 [51.1%] male) comprised 49 (36.8%) who developed psychosis and 84 (63.2%) who did not. A model based on baseline clinical and proteomic data demonstrated excellent performance for prediction of transition outcome (area under the receiver operating characteristic curve [AUC], 0.95; positive predictive value [PPV], 75.0%; and negative predictive value [NPV], 98.6%). Functional analysis of differentially expressed proteins implicated the complement and coagulation cascade. A model based on the 10 most predictive proteins accurately predicted transition status in training (AUC, 0.99; PPV, 76.9%; and NPV, 100%) and test (AUC, 0.92; PPV, 81.8%; and NPV, 96.8%) data. The ALSPAC subsample (121 participants from the general population with plasma samples available at age 12 years (61 [50.4%] male) comprised 55 participants (45.5%) with PEs at age 18 years and 61 (50.4%) without PEs at age 18 years. A model using proteomic data at age 12 years predicted PEs at age 18 years, with an AUC of 0.74 (PPV, 67.8%; and NPV, 75.8%).

CONCLUSIONS AND RELEVANCE

In individuals at risk of psychosis, proteomic biomarkers may contribute to individualized prognosis and stratification strategies. These findings implicate early dysregulation of the complement and coagulation cascade in the development of psychosis outcomes.

Präzisionspsychiatrie und der Beitrag von Brain Imaging und anderen Biomarkern

'Precision Psychiatry' as the psychiatric variant of 'Precision Medicine' aims to provide high-level diagnosis and treatment based on robust biomarkers and tailored to the individual clinical, neurobiological, and genetic constitution of the patient. The specific peculiarity of psychiatry, in which disease entities are normatively defined based on clinical experience and are also significantly influenced by contemporary history, society and philosophy, has so far made the search for valid and reliable psychobiological connections difficult. Nevertheless, considerable progress has now been made in all areas of psychiatric research, made possible above all by the critical review and renewal of previous concepts of disease and psychopathology, the increased orientation towards neurobiology and genetics, and in particular the use of machine learning methods. Notably, modern machine learning methods make it possible to integrate high-dimensional and multimodal data sets and generate models which provide new psychobiological insights and offer the possibility of individualized, biomarker-driven single-subject prediction of diagnosis, therapy response and prognosis. The aim of the present review is therefore to introduce the concept of 'Precision Psychiatry' to the interested reader, to concisely present modern, machine learning methods required for this, and to clearly present the current state and future of biomarker-based 'precision psychiatry'.

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

Evidence suggests there are two treatment-resistant schizophrenia subtypes (i.e. early treatment resistant (E-TR) and late-treatment resistant (L-TR)). We aimed to develop prediction models for estimating individual risk for these outcomes by employing advanced statistical shrinkage methods. 239 first-episode schizophrenia (FES) patients were followed-up for approximately 5 years after first presentation to psychiatric services; of these, n=56 (25.2%) were defined as E-TR and n=24 (12.6%) were defined as L-TR. Using known risk factors for poor schizophrenia outcomes, we developed prediction models for E-TR and L-TR using LASSO and RIDGE logistic regression models. Models' internal validation was performed employing Harrell's optimism-correction with repeated cross-validation; their predictive accuracy was assessed through discrimination and calibration. Both LASSO and RIDGE models had high discrimination, good calibration. While LASSO had moderate sensitivity for estimating an individual risk for E-TR and L-TR, sensitivity estimated for RIDGE model for these outcomes was extremely low, which was due to having a very large estimated optimism. Although it was possible to discriminate with sufficient accuracy who would meet criteria for E-TR and L-TR during the 5-year follow-up after first contact with mental health services for schizophrenia, further work is necessary to improve sensitivity for these models.

Predicting the individual risk of psychosis conversion in at-risk mental state (ARMS): a multivariate model reveals the influence of nonpsychotic prodromal symptoms

To improve the prediction of the individual risk of conversion to psychosis in UHR subjects, by considering all CAARMS' symptoms at first presentation and using a multivariate machine learning method known as logistic regression with Elastic-net shrinkage. 46 young individuals who sought help from the specialized outpatient unit at Sainte-Anne hospital and who met CAARMS criteria for UHR were assessed, among whom 27 were reassessed at follow-up (22.4 ± 6.54 months) and included in the analysis. Elastic net logistic regression was trained, using CAARMS items at baseline to predict individual evolution between converters (UHR-P) and non-converters (UHR-NP). Elastic-net was used to select the few CAARMS items that best predict the clinical evolution. All validations and significances of predictive models were computed with non-parametric re-sampling strategies that provide robust estimators even when the distributional assumption cannot be guaranteed. Among the 25 CAARMS items, the Elastic net selected 'obsessive-compulsive symptoms' and 'aggression/dangerous behavior' as risk factors for conversion while 'anhedonia' and 'mood swings/lability' were associated with non-conversion at follow-up. In the ten-fold stratified cross-validation, the classification achieved 81.8% of sensitivity (P = 0.035) and 93.7% of specificity (P = 0.0016). Non-psychotic prodromal symptoms bring valuable information to improve the prediction of conversion to psychosis. Elastic net logistic regression applied to clinical data is a promising way to switch from group prediction to an individualized prediction.

Transdiagnostic individualized clinically-based risk calculator for the automatic detection of individuals at-risk and the prediction of psychosis: external replication in 2,430,333 US patients

The real-world impact of psychosis prevention is reliant on effective strategies for identifying individuals at risk. A transdiagnostic, individualized, clinically-based risk calculator to improve this has been developed and externally validated twice in two different UK healthcare trusts with convincing results. The prognostic performance of this risk calculator outside the UK is unknown. All individuals who accessed primary or secondary health care services belonging to the IBM® MarketScan® Commercial Database between January 2015 and December 2017, and received a first ICD-10 index diagnosis of nonorganic/nonpsychotic mental disorder, were included. According to the risk calculator, age, gender, ethnicity, age-by-gender, and ICD-10 cluster diagnosis at index date were used to predict development of any ICD-10 nonorganic psychotic disorder. Because patient-level ethnicity data were not available city-level ethnicity proportions were used as proxy. The study included 2,430,333 patients with a mean follow-up of 15.36 months and cumulative incidence of psychosis at two years of 1.43%. There were profound differences compared to the original development UK database in terms of case-mix, psychosis incidence, distribution of baseline predictors (ICD-10 cluster diagnoses), availability of patient-level ethnicity data, follow-up time and availability of specialized clinical services for at-risk individuals. Despite these important differences, the model retained accuracy significantly above chance (Harrell's C = 0.676, 95% CI: 0.672-0.679). To date, this is the largest international external replication of an individualized prognostic model in the field of psychiatry. This risk calculator is transportable on an international scale to improve the automatic detection of individuals at risk of psychosis.

Progression from being at-risk to psychosis: next steps

Over the past 20 years there has been a great deal of research into those considered to be at risk for developing psychosis. Much has been learned and studies have been encouraging. The aim of this paper is to offer an update of the current status of research on risk for psychosis, and what the next steps might be in examining the progression from CHR to psychosis. Advances have been made in accurate prediction, yet there are some methodological issues in ascertainment, diagnosis, the use of data-driven selection methods and lack of external validation. Although there have been several high-quality treatment trials the heterogeneity of this clinical high-risk population has to be addressed so that their treatment needs can be properly met. Recommendations for the future include more collaborative research programmes, and ensuring they are accessible and harmonized with respect to criteria and outcomes so that the field can continue to move forward with the development of large collaborative consortiums as well as increased funding for multisite projects.

Real-World Clinical Outcomes Two Years After Transition to Psychosis in Individuals at Clinical High Risk: Electronic Health Record Cohort Study

The objective of this study is to describe the 2-year real-world clinical outcomes after transition to psychosis in patients at clinical high-risk. The study used the clinical electronic health record cohort study including all patients receiving a first index primary diagnosis of nonorganic International Classification of Diseases (ICD)-10 psychotic disorder within the early psychosis pathway in the South London and Maudsley (SLaM) National Health Service (NHS) Trust from 2001 to 2017. Outcomes encompassed: cumulative probability (at 3, 6, 12, and 24 months) of receiving a first (1) treatment with antipsychotic, (2) informal admission, (3) compulsory admission, and (4) treatment with clozapine and (5) numbers of days spent in hospital (at 12 and 24 months) in patients transitioning to psychosis from clinical high-risk services (Outreach and Support in south London; OASIS) compared to other first-episode groups. Analyses included logistic and 0-inflated negative binomial regressions. In the study, 1561 patients were included; those who had initially been managed by OASIS and had subsequently transitioned to a first episode of psychosis (n = 130) were more likely to receive antipsychotic medication (at 3, 6, and 24 months; all P < .023), to be admitted informally (at all timepoints, all P < .004) and on a compulsory basis (at all timepoints, all P < .013), and to have spent more time in hospital (all timepoints, all P < .007) than first-episode patients who were already psychotic when seen by the OASIS service (n = 310), or presented to early intervention services (n = 1121). The likelihood of receiving clozapine was similar across all groups (at 12/24 months, all P < .101). Transition to psychosis from a clinical high-risk state is associated with severe real-world clinical outcomes. Prevention of transition to psychosis should remain a core target of future research. The study protocol was registered on www.researchregistry.com; researchregistry5039).

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.

Reductions in Complex Mismatch Negativity to Extra Tone Gestalt Pattern Deviance in First-Episode Schizophrenia

Although "simple" mismatch negativity (sMMN) to stimulus parameter changes is robustly reduced in long-term schizophrenia (Sz), it is much less reduced in individuals at their first psychotic episode in the schizophrenia-spectrum (FESz). "Complex" MMN (cMMN) reflecting pre-attentive acoustic pattern analysis is also markedly reduced in Sz, but is little studied in FESz. The computational complexity of pattern analysis reflected in cMMN may more greatly stress auditory processing, providing a more sensitive measure of auditory processing deficits at first break. If so, cMMN would provide information about the underlying pathophysiology early in disease course, and may serve as a biomarker for pathology in the Sz prodrome. Twenty-two FESz individuals were compared to 22 volunteer healthy controls (HC) on sMMN and cMMN tasks. For sMMN, pitch- and duration-deviants were presented among standard repetitive tones. For cMMN, repeated groups of 3 identical tones were presented with occasional (14%) groups including an extra identical 4th tone deviant. FESz did not show reductions of pitch-deviant (Cohen's d = 0.08) or duration-deviant MMNs (d =-0.02), but showed large reduction in extra-tone cMMN (d = 0.83). Reduced cMMN was associated with poor social functioning. Reduction in cMMN but not in sMMNs in FESz suggests impairments in late perceptual pattern processing. cMMN is sensitive to subtle pathology and functioning early in disease course which may, in turn, impact social functioning. Future studies in clinical high risk individuals are needed to determine whether this putative biomarker of disease presence is sensitive to the prodromal stage of schizophrenia.

Dynamic ElecTronic hEalth reCord deTection (DETECT) of individuals at risk of a first episode of psychosis: a case-control development and validation study

BACKGROUND

Many individuals who will experience a first episode of psychosis (FEP) are not detected before occurrence, limiting the effect of preventive interventions. The combination of machine-learning methods and electronic health records (EHRs) could help address this gap.

METHODS

This case-control development and validation study is based on EHR data from IBM Explorys. The IBM Explorys Platform holds standardised, longitudinal, de-identified, patient-level EHR data pooled from different health-care systems with distinct EHRs. The present EHR-based studies were retrospective, matched (1:1), case-control studies compliant with RECORD, STROBE, and TRIPOD statements. The study included individuals in the IBM Explorys database who at some point between 1990 and 2018 had a diagnosis of FEP followed by schizophrenia, and psychosis-free matched control individuals from a random subsample of the full cohort. For every individual in the FEP cohort, the individual in the control cohort was matched to have a similar date for inclusion in the database and a similar total observation time. Individuals in the FEP cohort had their index date defined as the first diagnosis of psychosis or the first prescription of antipsychotic medication. Individuals in the control cohort had their index date defined to occur the same number of days after inclusion in the database as their matching FEP individual. The FEP and control cohorts were both randomly split into development and validation datasets in a ratio of 7:3. The subset of individuals in the validation dataset who had all their health-care encounters at providers that were not seen in the development dataset made up the external validation subset. A novel recurrent neural network model was developed to predict the risk of FEP 1 year before the index date by employing demographics and medical events (in the categories diagnoses, prescriptions, procedures, encounters and admissions, observations, and laboratory test results) dynamically collected in the EHR as part of clinical routine. We named the recurrent neural network Dynamic ElecTronic hEalth reCord deTection (DETECT). The main outcomes were accuracy and area under receiver operating characteristic curve (AUROC). Decision-curve analyses and dynamic patient journey plots were used to evaluate clinical usefulness.

FINDINGS

The FEP and control cohorts each comprised 72 860 individuals. 102 030 individuals (51 015 matching pairs) were randomly allocated to the development dataset and the remaining 43 690 to the validation dataset. In the validation dataset, 4770 individuals had all their encounters outside of the 118 790 health-care providers that were encountered in the development dataset. The data from these individuals made up the external validation subset. The median follow-up (observation time before index date) was 6·0 years (IQR 3·0-10·4). In the development dataset, DETECT's prognostic accuracy was 0·787 and AUROC was 0·868. In the validation dataset, DETECT's prognostic accuracy was 0·774 and AUROC was 0·856. In the external test subset, DETECT's balanced prognostic accuracy was 0·724 and AUROC was 0·799. Prevalence-adjusted decision-curve analyses suggested that DETECT was associated with a positive net benefit in two different scenarios for FEP detection.

INTERPRETATION

DETECT showed adequate prognostic accuracy to detect individuals at risk of developing a FEP in primary and secondary care. Replication and refinement in a population-based setting are needed to consolidate these findings.

FUNDING

Lundbeck.

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.

Prospective prediction of suicide attempts in community adolescents and young adults, using regression methods and machine learning

BACKGROUND

The use of machine learning (ML) algorithms to study suicidality has recently been recommended. Our aim was to explore whether ML approaches have the potential to improve the prediction of suicide attempt (SA) risk. Using the epidemiological multiwave prospective-longitudinal Early Developmental Stages of Psychopathology (EDSP) data set, we compared four algorithms-logistic regression, lasso, ridge, and random forest-in predicting a future SA in a community sample of adolescents and young adults.

METHODS

The EDSP Study prospectively assessed, over the course of 10 years, adolescents and young adults aged 14-24 years at baseline. Of 3021 subjects, 2797 were eligible for prospective analyses because they participated in at least one of the three follow-up assessments. Sixteen baseline predictors, all selected a priori from the literature, were used to predict follow-up SAs. Model performance was assessed using repeated nested 10-fold cross-validation. As the main measure of predictive performance we used the area under the curve (AUC).

RESULTS

The mean AUCs of the four predictive models, logistic regression, lasso, ridge, and random forest, were 0.828, 0.826, 0.829, and 0.824, respectively.

CONCLUSIONS

Based on our comparison, each algorithm performed equally well in distinguishing between a future SA case and a non-SA case in community adolescents and young adults. When choosing an algorithm, different considerations, however, such as ease of implementation, might in some instances lead to one algorithm being prioritized over another. Further research and replication studies are required in this regard.

Towards Precision Medicine in Psychosis: Benefits and Challenges of Multimodal Multicenter Studies-PSYSCAN: Translating Neuroimaging Findings From Research into Clinical Practice

In the last 2 decades, several neuroimaging studies investigated brain abnormalities associated with the early stages of psychosis in the hope that these could aid the prediction of onset and clinical outcome. Despite advancements in the field, neuroimaging has yet to deliver. This is in part explained by the use of univariate analytical techniques, small samples and lack of statistical power, lack of external validation of potential biomarkers, and lack of integration of nonimaging measures (eg, genetic, clinical, cognitive data). PSYSCAN is an international, longitudinal, multicenter study on the early stages of psychosis which uses machine learning techniques to analyze imaging, clinical, cognitive, and biological data with the aim of facilitating the prediction of psychosis onset and outcome. In this article, we provide an overview of the PSYSCAN protocol and we discuss benefits and methodological challenges of large multicenter studies that employ neuroimaging measures.

Development and Validation of a Dynamic Risk Prediction Model to Forecast Psychosis Onset in Patients at Clinical High Risk

The prediction of outcomes in patients at Clinical High Risk for Psychosis (CHR-P) almost exclusively relies on static data obtained at a single snapshot in time (ie, baseline data). Although the CHR-P symptoms are intrinsically evolving over time, available prediction models cannot be dynamically updated to reflect these changes. Hence, the aim of this study was to develop and internally validate a dynamic risk prediction model (joint model) and to implement this model in a user-friendly online risk calculator. Furthermore, we aimed to explore the prognostic performance of extended dynamic risk prediction models and to compare static with dynamic prediction. One hundred ninety-six CHR-P patients were recruited as part of the "Basel Früherkennung von Psychosen" (FePsy) study. Psychopathology and transition to psychosis was assessed at regular intervals for up to 5 years using the Brief Psychiatric Rating Scale-Expanded (BPRS-E). Various specifications of joint models were compared with regard to their cross-validated prognostic performance. We developed and internally validated a joint model that predicts psychosis onset from BPRS-E disorganization and years of education at baseline and BPRS-E positive symptoms during the follow-up with good prognostic performance. The model was implemented as online risk calculator (http://www.fepsy.ch/DPRP/). The use of extended joint models slightly increased the prognostic accuracy compared to basic joint models, and dynamic models showed a higher prognostic accuracy than static models. Our results confirm that extended joint modeling could improve the prediction of psychosis in CHR-P patients. We implemented the first online risk calculator that can dynamically update psychosis risk prediction.

Identifying Direct Coercion in a High Risk Subgroup of Offender Patients With Schizophrenia via Machine Learning Algorithms

PURPOSE

This study aims to explore risk factors for direct coercive measures (seclusion, restraint, involuntary medication) in a high risk subpopulation of offender patients with schizophrenia spectrum disorders.

METHODS

Five hundred sixty nine potential predictor variables were explored in terms of their predictive power for coercion/no coercion in a set of 131 (36.6%) offender patients who experienced coercion and 227 who did not, using machine learning analysis. The dataset was split (70/30%) applying variable filtering, machine learning model building, and selection embedded in nested resampling approach in one subset. The best model was then selected, and the most important variables extracted on the second data subset.

RESULTS

In the final model the following variables identified coercion with a balanced accuracy of 73.28% and a predictive power (area under the curve, AUC) of 0.8468: threat of violence, (actual) violence toward others, the application of direct coercive measures during past psychiatric inpatient treatments, the positive and negative syndrome scales (PANSS) poor impulse control, uncooperativeness, and hostility and the total PANSS-score at admission, prescription of haloperidol during inpatient treatment, the daily cumulative olanzapine equivalent antipsychotic dosage at discharge, and the legal prognosis estimated by a team of licensed forensic psychiatrists.

CONCLUSIONS

Results confirm prior findings, add detail on factors indicative for the use of direct coercion, and provide clarification on inconsistencies. Limitations, clinical relevance, and avenues for future research are discussed.

The Prodrome of Psychotic Disorders: Identification, Prediction, and Preventive Treatment

Twenty-five years ago "at risk" for psychosis criteria were introduced to the field. Prediction studies have identified a range of risk factors involved in transition from "at risk" status to first episode psychotic illness, with recent interest in dynamic and multimodal prediction models. Treatment studies have indicated that risk of transition to psychotic disorder can at least be delayed in this clinical population. Although the strongest evidence to date is for cognitive behavioral therapy, the optimal type and sequence of treatment remains an active area of research.