Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach

Jessica De Nijs ,René S Kahn ,Ruud Van Winkel ,Mariken B De Koning ,Claudia Simons ,Wiepke Cahn ,Philippe Delespaul ,Richard Bruggeman ,Jim Van Os ,Frederike Schirmbeck ,Ronald J Janssen ,Behrooz Z Alizadeh ,Thijs Jan Burger ,Nico J Van Beveren ,Jurjen J Luykx ,Seyed Mostafa Kia ,Inez Myin-Germeys ,Thérèse Van Amelsvoort ,Lieuwe De Haan ,Agna A Bartels-Velthuis ,Daniël P J Van Opstal ,Hugo G Schnack

doi:10.1038/s41537-021-00162-3

Abstract

Schizophrenia and related disorders have heterogeneous outcomes. Individualized prediction of long-term outcomes may be helpful in improving treatment decisions. Utilizing extensive baseline data of 523 patients with a psychotic disorder and variable illness duration, we predicted symptomatic and global outcomes at 3-year and 6-year follow-ups. We classified outcomes as (1) symptomatic: in remission or not in remission, and (2) global outcome, using the Global Assessment of Functioning (GAF) scale, divided into good (GAF ≥ 65) and poor (GAF < 65). Aiming for a robust and interpretable prediction model, we employed a linear support vector machine and recursive feature elimination within a nested cross-validation design to obtain a lean set of predictors. Generalization to out-of-study samples was estimated using leave-one-site-out cross-validation. Prediction accuracies were above chance and ranged from 62.2% to 64.7% (symptomatic outcome), and 63.5–67.6% (global outcome). Leave-one-site-out cross-validation demonstrated the robustness of our models, with a minor drop in predictive accuracies of 2.3% on average. Important predictors included GAF scores, psychotic symptoms, quality of life, antipsychotics use, psychosocial needs, and depressive symptoms. These robust, albeit modestly accurate, long-term prognostic predictions based on lean predictor sets indicate the potential of machine learning models complementing clinical judgment and decision-making. Future model development may benefit from studies scoping patient’s and clinicians' needs in prognostication.

Highlights

Schizophrenia is a heterogeneous illness and its long-term outcomes are highly variable[1,2,3]
T3 and T6, 49%, 37%, and 41% of patients were in symptomatic remission (according to the consensus definition by Andreasen et al (2005)) respectively; 31%, 44%, and 36% had good global functioning status (Global Assessment of Functioning (GAF) scale ≥ 65) at respective measurements
Using a rigorous machine learning approach, we developed individualized models to predict 3- and 6-year symptomatic and global outcomes of patients with schizophrenia-spectrum disorders based on patient-reportable data

Summary

Introduction

Schizophrenia is a heterogeneous illness and its long-term outcomes are highly variable[1,2,3]. An additional challenge is that “outcome” entails symptomatic, social, functional, and personal dimensions, which are only partly interrelated[8,9], and may have differing significance for individual patients[10,11] These matters complicate clinical decision-making, for example when considering an early switch to clozapine[12], antipsychotic dose reduction or discontinuation strategies[13], allocations of sheltered housing[14], or occupational support[15]. Machine learning potentially presents a way to develop models reliably predicting individual outcomes for multifactorial and heterogeneous illnesses such as schizophrenia[17,18,19,20,21]. Modern prospective multicenter studies facilitate the development of prediction models based on machine learning. They provide well-established outcome measures and large numbers of potential predictors Unemployment, lower education, functional deficits, and unmet psychosocial needs were found most valuable in predicting 4- and 52-week outcomes

Objectives

Methods

Results

Conclusion