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

TY - JOUR

T1 - Predicting onset of early- and late-treatment resistance in first-episode schizophrenia patients using advanced shrinkage statistical methods in a small sample

AU - Ajnakina, Olesya

AU - Agbedjro, Deborah

AU - Lally, John

AU - Forti, Marta Di

AU - Trotta, Antonella

AU - Mondelli, Valeria

AU - Pariante, Carmine

AU - Dazzan, Paola

AU - Gaughran, Fiona

AU - Fisher, Helen L.

AU - David, Anthony

AU - Murray, Robin M.

AU - Stahl, Daniel

PY - 2020/10/18

Y1 - 2020/10/18

N2 - 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.

AB - 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.

KW - Prediction

KW - prognosis

KW - Schizophrenia

KW - Statistical learning

KW - Treatment resistance

KW - Treatment response

UR - http://www.scopus.com/inward/record.url?scp=85094122324&partnerID=8YFLogxK

U2 - 10.1016/j.psychres.2020.113527

DO - 10.1016/j.psychres.2020.113527

M3 - Article

AN - SCOPUS:85094122324

SN - 0165-1781

VL - 294

JO - Psychiatry Research

JF - Psychiatry Research

M1 - 113527

ER -