Individualized Prediction of Prodromal Symptom Remission for Youth at Clinical High Risk for Psychosis

Abstract

The clinical high-risk period before a first episode of psychosis (CHR-P) has been widely studied with the goal of understanding the development of psychosis; however, less attention has been paid to the 75%–80% of CHR-P individuals who do not transition to psychosis. It is an open question whether multivariable models could be developed to predict remission outcomes at the same level of performance and generalizability as those that predict conversion to psychosis. Participants were drawn from the North American Prodrome Longitudinal Study (NAPLS3). An empirically derived set of clinical and demographic predictor variables were selected with elastic net regularization and were included in a gradient boosting machine algorithm to predict prodromal symptom remission. The predictive model was tested in a comparably sized independent sample (NAPLS2). The classification algorithm developed in NAPLS3 achieved an area under the curve of 0.66 (0.60–0.72) with a sensitivity of 0.68 and specificity of 0.53 when tested in an independent external sample (NAPLS2). Overall, future remitters had lower baseline prodromal symptoms than nonremitters. This study is the first to use a data-driven machine-learning approach to assess clinical and demographic predictors of symptomatic remission in individuals who do not convert to psychosis. The predictive power of the models in this study suggest that remission represents a unique clinical phenomenon. Further study is warranted to best understand factors contributing to resilience and recovery from the CHR-P state.

RETRACTED: Dynamic Prediction of Outcomes for Youth at Clinical High Risk for Psychosis

“…Criteria for achieving conversion to psychosis or symptom remission were based on SOPS criteria for assessing psychoticlevel symptoms (conversion) or subthreshold prodromal symptoms (symptom remission) and are consistent with definitions used in previous studies. 11,23 Individuals were classified as remitters if they met criteria for sustained remission, eg, scoring below the prodromal threshold on the SOPS scale at the 6-month, 12-month, or 18-month visit and continuing to meet this criterion 6 months later. In predicting conversion, the comparison group consisted of nonconverters and remitters; in predicting remission, the comparison group consisted of nonremitters and converters.…”

“…17 For the baseline proportional hazards regression models, we used existing models, including the NAPLS 2 risk calculator 5 predicting conversion and a multivariable model developed in the NAPLS study predicting symptom remission (originally developed in a gradientboosting machine algorithm and converted for this purpose to a proportional hazards regression model). 11 For more details about these models, see eAppendix 1 in Supplement 1. To account for the added effect of including longitudinal variables in the joint model stage, we also included the baseline value of the longitudinal variable in the baseline model.…”

Prediction and Prevention in the Clinical High-Risk for Psychosis Paradigm: A Review of the Current Status and Recommendations for Future Directions of Inquiry

“…Only one study has developed a generalizable multivariable model predicting remission as an outcome variable. This study took a data-driven approach to selecting relevant features and building a model predicting remission in the NAPLS3 sample and performed well when tested in an independent validation sample (AUC = 0.66), exhibiting performance comparable to models predicting conversion to psychosis (45).…”

“…Balanced sampling approaches should only be used in discovery samples and models should not be validated in synthetically balanced samples. Implementing these sampling approaches has shown to increase model performance in predicting remission (45) and should be considered as a tool to improve prediction in the CHR-P population.…”

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

“…The classification accuracy was obtained at 60.0–72.0% with a sensitivity of 0.68% and specificity of 0.53%. The Worthington et al’s study is notable as the first to examine interactive clinical and demographic predictors of symptomatic remission in people who do not progress to psychosis using an advanced data-driven techniques 26 .…”