Predicting the risk of psychosis onset: advances and prospects.
Predicting the risk of psychosis onset: advances and prospects.
复制标题
DOI：
10.1111/j.1751-7893.2012.00383.x
复制
发表时间：
2012-11
影响因子：
2
通讯作者：
Visweswaran S
中科院分区：
文献类型：
--
作者：
Strobl EV;Eack SM;Swaminathan V;Visweswaran S
对用于预测精神病发作的模型的方法和性能特征进行系统评价。我们进行了一次全面的文献检索，仅限于英文文章，并使用PubMed、Medline和PsychINFO以及已发表研究和综述的参考文献列表进行识别。入选标准包括选择一个以上的变量来预测精神病或精神分裂症的发作，以及有家族或临床高风险的受试者。18项研究符合这些标准，我们根据所选的受试者、使用的预测变量以及统计或机器学习方法的选择对这些研究进行了比较。生活质量和生活功能以及结构脑成像成为精神病发作最有前途的预测因子，特别是当它们与适当的降维方法和预测模型算法（如支持向量机（SVM））相结合时。在使用SVM的四项研究中，平衡准确度范围从100%到78%，在使用一般线性模型的十四项研究中，平衡准确度范围从81%到67%。预测模型的性能随着生活质量测量、生活功能测量、结构性脑成像数据以及SVM等方法的使用而提高。尽管取得了这些进展，精神病预测模型的整体性能仍然是适度的。在未来，除了目前使用的预测因子外，还可以通过包括遗传变异和新的功能成像数据来提高性能。
To conduct a systematic review of the methods and performance characteristics of models developed for predicting the onset of psychosis. We performed a comprehensive literature search restricted to English articles and identified using PubMed, Medline, and PsychINFO as well as the reference lists of published studies and reviews. Inclusion criteria involved the selection of more than one variable to predict psychosis or schizophrenia onset, and subjects at familial or clinical high risk. Eighteen studies met these criteria, and we compared these studies based on the subjects selected, predictor variables used and the choice of statistical or machine learning methods. Quality of life and life functioning as well as structural brain imaging emerged as the most promising predictors of psychosis onset, particularly when they were coupled with appropriate dimensionality reduction methods and predictive model algorithms like the support vector machine (SVM). Balanced accuracy ranged from 100% to 78% in four studies using the SVM, and 81% to 67% in fourteen studies using general linear models. Performance of the predictive models improves with quality of life measures, life functioning measures, structural brain imaging data as well as with the use of methods like SVM. Despite these advances, the overall performance of psychosis predictive models is still modest. In the future, performance can potentially be improved by including genetic variant and new functional imaging data in addition to the predictors that are used currently.
登录
查看更多内容
DOI：
10.1176/appi.ajp.2010.10091340
发表时间：
2011-03
期刊：
The American journal of psychiatry
影响因子：
--
作者：
Gershon ES;Alliey-Rodriguez N;Liu C
通讯作者：
Liu C
影响因子：
4.5
作者：
Job, DE;Whalley, HC;Lawrie, SM
通讯作者：
Lawrie, SM
影响因子：
--
作者：
Amminger, G. Paul;Schafer, Miriam R.;Berger, Gregor E.
通讯作者：
Berger, Gregor E.
DOI：
10.1007/s00406-009-0022-4
发表时间：
2010-03-01
影响因子：
4.7
作者：
Bogren, Mats;Mattisson, Cecilia;Nettelbladt, Per
通讯作者：
Nettelbladt, Per
影响因子：
4.8
作者：
Gothelf D;Hoeft F;Ueno T;Sugiura L;Lee AD;Thompson P;Reiss AL
通讯作者：
Reiss AL