Nicole M. Christ , Ryan A. Schubert , Rhea Mundle , Sarah Pridgen , Philip Held
{"title":"使用机器学习预测创伤后应激障碍强化治疗的突然收益。","authors":"Nicole M. Christ , Ryan A. Schubert , Rhea Mundle , Sarah Pridgen , Philip Held","doi":"10.1016/j.janxdis.2023.102783","DOIUrl":null,"url":null,"abstract":"<div><p>Sudden gains have been found in PTSD treatment across samples and treatment modality. Sudden gains have consistently predicted better treatment response, illustrating clear clinical implications, though attempts to identify predictors of sudden gains have produced inconsistent findings. To date, sudden gains have not been examined in intensive PTSD treatment programs (ITPs). This study explored the occurrence of sudden gains in a 3-week and 2-week ITP (<em>n</em> = 465 and <em>n</em> = 235), evaluated the effect of sudden gains on post-treatment and follow-up PTSD severity while controlling for overall change, and used three machine learning algorithms to assess our ability to predict sudden gains. We found 31% and 19% of our respective samples experienced a sudden gain during the ITP. In both ITPs, sudden gain status predicted greater PTSD symptom improvement at post-treatment (t<sub>2 W</sub>=−8.57, t<sub>3 W</sub>=−14.86, p < .001) and at 3-month follow-up (t<sub>2 W</sub>=−3.82, t<sub>3 W</sub>=−5.32, p < .001). However, the effect for follow-up was no longer significant after controlling for total symptom reduction across the ITP (t<sub>2 W</sub>=−1.59, t<sub>3 W</sub>=−0.32, p > .05). Our ability to predict sudden gains was poor (AUC <.7) across all three machine learning algorithms. These findings demonstrate that sudden gains can be detected in intensive treatment for PTSD, though their implications for treatment outcomes may be limited. Moreover, despite the use of three machine-learning methods across two fairly large clinical samples, we were still unable to identify variables that accurately predict whether an individual will experience a sudden gain during treatment. Implications for clinical application of these findings and for future studies are discussed.</p></div>","PeriodicalId":48390,"journal":{"name":"Journal of Anxiety Disorders","volume":null,"pages":null},"PeriodicalIF":4.8000,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Using machine learning to predict sudden gains in intensive treatment for PTSD\",\"authors\":\"Nicole M. Christ , Ryan A. Schubert , Rhea Mundle , Sarah Pridgen , Philip Held\",\"doi\":\"10.1016/j.janxdis.2023.102783\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Sudden gains have been found in PTSD treatment across samples and treatment modality. Sudden gains have consistently predicted better treatment response, illustrating clear clinical implications, though attempts to identify predictors of sudden gains have produced inconsistent findings. To date, sudden gains have not been examined in intensive PTSD treatment programs (ITPs). This study explored the occurrence of sudden gains in a 3-week and 2-week ITP (<em>n</em> = 465 and <em>n</em> = 235), evaluated the effect of sudden gains on post-treatment and follow-up PTSD severity while controlling for overall change, and used three machine learning algorithms to assess our ability to predict sudden gains. We found 31% and 19% of our respective samples experienced a sudden gain during the ITP. In both ITPs, sudden gain status predicted greater PTSD symptom improvement at post-treatment (t<sub>2 W</sub>=−8.57, t<sub>3 W</sub>=−14.86, p < .001) and at 3-month follow-up (t<sub>2 W</sub>=−3.82, t<sub>3 W</sub>=−5.32, p < .001). However, the effect for follow-up was no longer significant after controlling for total symptom reduction across the ITP (t<sub>2 W</sub>=−1.59, t<sub>3 W</sub>=−0.32, p > .05). Our ability to predict sudden gains was poor (AUC <.7) across all three machine learning algorithms. These findings demonstrate that sudden gains can be detected in intensive treatment for PTSD, though their implications for treatment outcomes may be limited. Moreover, despite the use of three machine-learning methods across two fairly large clinical samples, we were still unable to identify variables that accurately predict whether an individual will experience a sudden gain during treatment. Implications for clinical application of these findings and for future studies are discussed.</p></div>\",\"PeriodicalId\":48390,\"journal\":{\"name\":\"Journal of Anxiety Disorders\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2023-10-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Anxiety Disorders\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0887618523001214\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHIATRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Anxiety Disorders","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0887618523001214","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHIATRY","Score":null,"Total":0}
Using machine learning to predict sudden gains in intensive treatment for PTSD
Sudden gains have been found in PTSD treatment across samples and treatment modality. Sudden gains have consistently predicted better treatment response, illustrating clear clinical implications, though attempts to identify predictors of sudden gains have produced inconsistent findings. To date, sudden gains have not been examined in intensive PTSD treatment programs (ITPs). This study explored the occurrence of sudden gains in a 3-week and 2-week ITP (n = 465 and n = 235), evaluated the effect of sudden gains on post-treatment and follow-up PTSD severity while controlling for overall change, and used three machine learning algorithms to assess our ability to predict sudden gains. We found 31% and 19% of our respective samples experienced a sudden gain during the ITP. In both ITPs, sudden gain status predicted greater PTSD symptom improvement at post-treatment (t2 W=−8.57, t3 W=−14.86, p < .001) and at 3-month follow-up (t2 W=−3.82, t3 W=−5.32, p < .001). However, the effect for follow-up was no longer significant after controlling for total symptom reduction across the ITP (t2 W=−1.59, t3 W=−0.32, p > .05). Our ability to predict sudden gains was poor (AUC <.7) across all three machine learning algorithms. These findings demonstrate that sudden gains can be detected in intensive treatment for PTSD, though their implications for treatment outcomes may be limited. Moreover, despite the use of three machine-learning methods across two fairly large clinical samples, we were still unable to identify variables that accurately predict whether an individual will experience a sudden gain during treatment. Implications for clinical application of these findings and for future studies are discussed.
期刊介绍:
The Journal of Anxiety Disorders is an interdisciplinary journal that publishes research papers on all aspects of anxiety disorders for individuals of all age groups, including children, adolescents, adults, and the elderly. Manuscripts that focus on disorders previously classified as anxiety disorders such as obsessive-compulsive disorder and posttraumatic stress disorder, as well as the new category of illness anxiety disorder, are also within the scope of the journal. The research areas of focus include traditional, behavioral, cognitive, and biological assessment; diagnosis and classification; psychosocial and psychopharmacological treatment; genetics; epidemiology; and prevention. The journal welcomes theoretical and review articles that significantly contribute to current knowledge in the field. It is abstracted and indexed in various databases such as Elsevier, BIOBASE, PubMed/Medline, PsycINFO, BIOSIS Citation Index, BRS Data, Current Contents - Social & Behavioral Sciences, Pascal Francis, Scopus, and Google Scholar.