Danyang Li , Yuhao Lin , Helena Davies , Evangelos Vassos , Raquel Iniesta , Gerome Breen
{"title":"PREDICTION OF ANTIDEPRESSANT SIDE EFFECTS IN THE GENETIC LINK TO ANXIETY AND DEPRESSION STUDY","authors":"Danyang Li , Yuhao Lin , Helena Davies , Evangelos Vassos , Raquel Iniesta , Gerome Breen","doi":"10.1016/j.euroneuro.2024.08.065","DOIUrl":null,"url":null,"abstract":"<div><div>Antidepressants are the most common treatment for moderate or severe depression. Side effects are crucial indicators for antidepressants, but their expression varies widely among individuals.</div><div>In this study, we leveraged genetic and phenotypic data from self-reported questionnaires in the Genetic Link to Anxiety and Depression (GLAD) study to predict side effects and discontinuation (due to side effect) across three antidepressant classes (SSRI, SNRI, tricyclic antidepressants (TCA)) at the first and the last (most recent) year of prescription. About 260 predictors spanning genetic, clinical, comorbidity, demographic, and antidepressant information were included. XGBoost, random forest, cubist, elastic net, and support vector machine (with RBF and polynomial kernel) were trained, and their performance was compared.</div><div>The final dataset comprised 5358 individuals, with 4354 in the first and 3414 in the last year of prescription. The average prevalence of side effects and discontinuation was 74.1% and 28.7%, respectively. In the initial year, the best AUROC for predicting SSRI discontinuation and side effects were 0.65 and 0.60. In the last year of SSRI prescription, the highest AUROC reached 0.73 for discontinuation and 0.87 for side effects. Models for predicting discontinuation and side effects of SNRI and TCA showed comparable performance. The history of side effects and discontinuation of antidepressant use were the most influential predictors of the outcomes in the last year. When examining 30 common antidepressant side effect symptoms, most of them were differentially prevalent between antidepressant classes.</div><div>Our findings demonstrate the feasibility of predicting antidepressant side effects using a self-reported questionnaire, particularly for the last prescription. These results contribute valuable insights for the development of clinical decisions aimed at optimising treatment selection with enhanced tolerability.</div></div>","PeriodicalId":12049,"journal":{"name":"European Neuropsychopharmacology","volume":"87 ","pages":"Page 25"},"PeriodicalIF":6.1000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Neuropsychopharmacology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0924977X24002645","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Antidepressants are the most common treatment for moderate or severe depression. Side effects are crucial indicators for antidepressants, but their expression varies widely among individuals.
In this study, we leveraged genetic and phenotypic data from self-reported questionnaires in the Genetic Link to Anxiety and Depression (GLAD) study to predict side effects and discontinuation (due to side effect) across three antidepressant classes (SSRI, SNRI, tricyclic antidepressants (TCA)) at the first and the last (most recent) year of prescription. About 260 predictors spanning genetic, clinical, comorbidity, demographic, and antidepressant information were included. XGBoost, random forest, cubist, elastic net, and support vector machine (with RBF and polynomial kernel) were trained, and their performance was compared.
The final dataset comprised 5358 individuals, with 4354 in the first and 3414 in the last year of prescription. The average prevalence of side effects and discontinuation was 74.1% and 28.7%, respectively. In the initial year, the best AUROC for predicting SSRI discontinuation and side effects were 0.65 and 0.60. In the last year of SSRI prescription, the highest AUROC reached 0.73 for discontinuation and 0.87 for side effects. Models for predicting discontinuation and side effects of SNRI and TCA showed comparable performance. The history of side effects and discontinuation of antidepressant use were the most influential predictors of the outcomes in the last year. When examining 30 common antidepressant side effect symptoms, most of them were differentially prevalent between antidepressant classes.
Our findings demonstrate the feasibility of predicting antidepressant side effects using a self-reported questionnaire, particularly for the last prescription. These results contribute valuable insights for the development of clinical decisions aimed at optimising treatment selection with enhanced tolerability.
期刊介绍：
European Neuropsychopharmacology is the official publication of the European College of Neuropsychopharmacology (ECNP). In accordance with the mission of the College, the journal focuses on clinical and basic science contributions that advance our understanding of brain function and human behaviour and enable translation into improved treatments and enhanced public health impact in psychiatry. Recent years have been characterized by exciting advances in basic knowledge and available experimental techniques in neuroscience and genomics. However, clinical translation of these findings has not been as rapid. The journal aims to narrow this gap by promoting findings that are expected to have a major impact on both our understanding of the biological bases of mental disorders and the development and improvement of treatments, ideally paving the way for prevention and recovery.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
