Classification Criteria for Acute Posterior Multifocal Placoid Pigment Epitheliopathy.
Classification Criteria for Acute Posterior Multifocal Placoid Pigment Epitheliopathy.
复制标题
DOI：
10.1016/j.ajo.2021.03.056
复制
发表时间：
2021-08
影响因子：
4.2
通讯作者：
Standardization of Uveitis Nomenclature (SUN) Working Group
中科院分区：
文献类型：
--
作者：
Standardization of Uveitis Nomenclature (SUN) Working Group
确定急性后部多灶性片状色素上皮病（APMPPE）的分类标准。APMPPE和其他8种后葡萄膜炎病例的机器学习。后葡萄膜炎病例收集在信息学设计的初步数据库中，最终数据库的构建采用正式的共识技术，在诊断上达到绝大多数一致的病例。将病例分为训练集和验证集。在训练集上使用使用多项逻辑回归的机器学习来确定一组最小化后葡萄膜中的错误分类率的简约标准。在验证集上评价所得标准。通过机器学习评估了1068例后葡萄膜炎，包括82例APMPPE。APMPPE的关键标准包括：1）具有斑块样或斑块样外观的脉络膜病变和2）荧光素血管造影的特征性成像（病变“早期阻塞，晚期弥漫性染色”）。后葡萄膜炎的总体准确度在训练集中为92.7%，在验证集中为98.0%（95%置信区间94.3，99.3）。APMPPE的错误分类率在训练集中为5%，在验证集中为0%。APMPPE的标准具有较低的错误分类率，并且在临床和转化研究中表现良好。使用正式的方法来制定分类标准，包括基于信息学的病例收集，基于共识技术的病例选择和机器学习，制定了急性后部多灶性鳞状色素上皮病的分类标准。关键标准包括脉络膜病变的斑块样或板样外观和特征性荧光素血管造影（病变是低荧光早期和弥漫性高荧光晚期）。由此产生的分类标准有一个低的错误分类率。
To determine classification criteria for acute posterior multifocal placoid pigment epitheliopathy (APMPPE). Machine learning of cases with APMPPE and 8 other posterior uveitides. Cases of posterior uveitides were collected in an informatics-designed preliminary database, and a final database was constructed of cases achieving supermajority agreement on diagnosis, using formal consensus techniques. Cases were split into a training set and a validation set. Machine learning using multinomial logistic regression was used on the training set to determine a parsimonious set of criteria that minimized the misclassification rate among the posterior uveitides. The resulting criteria were evaluated on the validation set. One thousand sixty-eight cases of posterior uveitides, including 82 cases of APMPPE, were evaluated by machine learning. Key criteria for APMPPE included: 1) choroidal lesions with a plaque-like or placoid appearance and 2) characteristic imaging on fluorescein angiography (lesions “block early and stain late diffusely”). Overall accuracy for posterior uveitides was 92.7% in the training set and 98.0% (95% confidence interval 94.3, 99.3) in the validation set. The misclassification rates for APMPPE were 5% in the training set and 0% in the validation set. The criteria for APMPPE had a low misclassification rate and appeared to perform sufficiently well for use in clinical and translational research. Using a formalized approach to developing classification criteria, including informatics-based case collection, consensus-technique-based case selection, and machine learning, classification criteria for acute posterior multifocal placoid pigment epitheliopathy were developed. Key criteria included choroidal lesions with a plaque-like or placoid appearance and a characteristic fluorescein angiogram (lesions are hypofluorescent early and diffusely hyperfluorescent late). The resulting classification criteria had a low misclassification rate.
登录
查看更多内容
影响因子：
4.2
作者：
Standardization of Uveitis Nomenclature (SUN) Working Group
通讯作者：
Standardization of Uveitis Nomenclature (SUN) Working Group
影响因子：
1.7
作者：
Trusko B;Thorne J;Jabs D;Belfort R;Dick A;Gangaputra S;Nussenblatt R;Okada A;Rosenbaum J;Standardization of Uveitis Nomenclature (SUN) Project
通讯作者：
Standardization of Uveitis Nomenclature (SUN) Project
影响因子：
--
作者：
Malamos P;Masaoutis P;Georgalas I;Maselos S;Andrianopoulos K;Koutsandrea C;Markomichelakis NN
通讯作者：
Markomichelakis NN
影响因子：
1
作者：
Furino, Claudio;Shalchi, Zaid;Pavesio, Carlos
通讯作者：
Pavesio, Carlos
影响因子：
4.7
作者：
Aggarwal, Rohit;Ringold, Sarah;Khanna, Dinesh;Neogi, Tuhina;Johnson, Sindhu R.;Miller, Amy;Brunner, Hermine I.;Ogawa, Rikke;Felson, David;Ogdie, Alexis;Aletaha, Daniel;Feldman, Brian M.
通讯作者：
Feldman, Brian M.