No CrossRef data available.
Article contents
Advances in Staging of schizophrenia. Development of an empirical staging model for schizophrenia.
Published online by Cambridge University Press: 19 July 2023
Abstract
After a short review of the state of the art of clinical staging in schizophrenia, I will present a recently developed empirical staging model.
Two hundred twelve stable outpatients with schizophrenia from Oviedo (Spain) were assessed with: an ad hoc questionnaire (demographic, clinical information); psychopathology: PANSS, CDS, OSQ, CGI-S; functioning: PSP; cognition: MATRICS; lab tests: C-Reactive Protein, IL-1RA, IL-6, Platelet/Lymphocyte (PLR), Neutrophil/Lymphocyte (NLR), and Monocyte/Lymphocyte (MLR) ratios.
An ad hoc genetic algorithm (GA) was developed to select those variables showing the best performance for patients’ CGI classification. The objective function of the GA maximizes the individual’s correct classification of a support vector machines (SVM) model that employs as input variables those given by the GA. Models’ performance was assessed with the help of 3-fold cross-validation, and this process was repeated 10,000 times for each one of the models evaluated. Once developed, we used the ANOVA test (Duncan’s post-hoc) for all the variables included in the model to demonstrate its construct validity.
Our model included the following variables: positive, negative, depressive, and general psychopathological symptoms, processing speed, visual learning, social cognition, and real-world functioning. Its classification accuracy is 64.54% (SD=4.83%) with a specificity and sensitivity of 0.85 and 0.63. The external validity of the new model is being tested using a French sample from the FACE-SZ (FondaMental Advanced Centers of Expertise-Schizophrenia) cohort.
We developed an SVM model including psychopathological, cognitive, and functional variables.
Our model demonstrated good construct validity since all the variables included behaved as expected. That is, they score significantly worse as the patients’ severity increases. Besides, it showed good accuracy, specificity, and sensitivity classification properties.
Using staging models in daily clinical practice will help clinicians to better.
None Declared
- Type
- Abstract
- Information
- European Psychiatry , Volume 66 , Special Issue S1: Abstracts of the 31st European Congress of Psychiatry , March 2023 , pp. S4 - S5
- Creative Commons
- This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
- Copyright
- © The Author(s), 2023. Published by Cambridge University Press on behalf of the European Psychiatric Association
Comments
No Comments have been published for this article.