当前位置: X-MOL 学术Schizophr. Bull. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Individualized Prediction of Prodromal Symptom Remission for Youth at Clinical High Risk for Psychosis
Schizophrenia Bulletin ( IF 5.3 ) Pub Date : 2021-09-28 , DOI: 10.1093/schbul/sbab115
Michelle A Worthington 1 , Jean Addington 2 , Carrie E Bearden 3 , Kristin S Cadenhead 4 , Barbara A Cornblatt 5 , Matcheri Keshavan 6 , Daniel H Mathalon 7 , Thomas H McGlashan 8 , Diana O Perkins 9 , William S Stone 6 , Ming T Tsuang 4 , Elaine F Walker 10 , Scott W Woods 8 , Tyrone D Cannon 1, 8
Affiliation  

Abstract
The clinical high-risk period before a first episode of psychosis (CHR-P) has been widely studied with the goal of understanding the development of psychosis; however, less attention has been paid to the 75%–80% of CHR-P individuals who do not transition to psychosis. It is an open question whether multivariable models could be developed to predict remission outcomes at the same level of performance and generalizability as those that predict conversion to psychosis. Participants were drawn from the North American Prodrome Longitudinal Study (NAPLS3). An empirically derived set of clinical and demographic predictor variables were selected with elastic net regularization and were included in a gradient boosting machine algorithm to predict prodromal symptom remission. The predictive model was tested in a comparably sized independent sample (NAPLS2). The classification algorithm developed in NAPLS3 achieved an area under the curve of 0.66 (0.60–0.72) with a sensitivity of 0.68 and specificity of 0.53 when tested in an independent external sample (NAPLS2). Overall, future remitters had lower baseline prodromal symptoms than nonremitters. This study is the first to use a data-driven machine-learning approach to assess clinical and demographic predictors of symptomatic remission in individuals who do not convert to psychosis. The predictive power of the models in this study suggest that remission represents a unique clinical phenomenon. Further study is warranted to best understand factors contributing to resilience and recovery from the CHR-P state.


中文翻译:

临床精神病高危青少年前驱症状缓解的个体化预测

摘要
精神病首发前的临床高危期(CHR-P)已被广泛研究,目的是了解精神病的发展;然而,对 75%–80% 未转变为精神病的 CHR-P 个体的关注较少。是否可以开发多变量模型来预测缓解结果,其性能和普遍性与预测转化为精神病的模型相同,这是一个悬而未决的问题。参与者来自北美前驱期纵向研究 (NAPLS3)。通过弹性网络正则化选择一组经验得出的临床和人口统计预测变量,并将其包含在梯度增强机算法中以预测前驱症状缓解。预测模型在相当大小的独立样本 (NAPLS2) 中进行了测试。在 NAPLS3 中开发的分类算法在独立外部样本 (NAPLS2) 中测试时,曲线下面积为 0.66 (0.60–0.72),灵敏度为 0.68,特异性为 0.53。总体而言,未来汇款人的基线前驱症状低于非汇款人。这项研究首次使用数据驱动的机器学习方法来评估未转化为精神病的个体症状缓解的临床和人口统计学预测因素。本研究中模型的预测能力表明,缓解代表了一种独特的临床现象。有必要进一步研究以最好地了解有助于从 CHR-P 状态恢复和恢复的因素。在独立外部样本 (NAPLS2) 中测试时,68 和 0.53 的特异性。总体而言,未来汇款人的基线前驱症状低于非汇款人。这项研究首次使用数据驱动的机器学习方法来评估未转化为精神病的个体症状缓解的临床和人口统计学预测因素。本研究中模型的预测能力表明,缓解代表了一种独特的临床现象。有必要进一步研究以最好地了解有助于从 CHR-P 状态恢复和恢复的因素。在独立外部样本 (NAPLS2) 中测试时,68 和 0.53 的特异性。总体而言,未来汇款人的基线前驱症状低于非汇款人。这项研究首次使用数据驱动的机器学习方法来评估未转化为精神病的个体症状缓解的临床和人口统计学预测因素。本研究中模型的预测能力表明,缓解代表了一种独特的临床现象。有必要进一步研究以最好地了解有助于从 CHR-P 状态恢复和恢复的因素。这项研究首次使用数据驱动的机器学习方法来评估未转化为精神病的个体症状缓解的临床和人口统计学预测因素。本研究中模型的预测能力表明,缓解代表了一种独特的临床现象。有必要进一步研究以最好地了解有助于从 CHR-P 状态恢复和恢复的因素。这项研究首次使用数据驱动的机器学习方法来评估未转化为精神病的个体症状缓解的临床和人口统计学预测因素。本研究中模型的预测能力表明,缓解代表了一种独特的临床现象。有必要进一步研究以最好地了解有助于从 CHR-P 状态恢复和恢复的因素。
更新日期:2021-09-28
down
wechat
bug