Am J Ophthalmol. 2021 Aug;228:96-105. doi: 10.1016/j.ajo.2021.03.061. Epub 2021 Apr 20.
To develop classification criteria for 25 of the most common uveitides.
Machine learning using 5,766 cases of 25 uveitides.
Cases were collected in an informatics-designed preliminary database. Using formal consensus techniques, a final database was constructed of 4,046 cases achieving supermajority agreement on the diagnosis. Cases were analyzed within uveitic class and were split into a training set and a validation set. Machine learning used multinomial logistic regression with lasso regularization on the training set to determine a parsimonious set of criteria for each disease and to minimize misclassification rates. The resulting criteria were evaluated in the validation set. Accuracy of the rules developed to express the machine learning criteria was evaluated by a masked observer in a 10% random sample of cases.
Overall accuracy estimates by uveitic class in the validation set were as follows: anterior uveitides 96.7% (95% confidence interval [CI] 92.4, 98.6); intermediate uveitides 99.3% (95% CI 96.1, 99.9); posterior uveitides 98.0% (95% CI 94.3, 99.3); panuveitides 94.0% (95% CI 89.0, 96.8); and infectious posterior uveitides / panuveitides 93.3% (95% CI 89.1, 96.3). Accuracies of the masked evaluation of the "rules" were anterior uveitides 96.5% (95% CI 91.4, 98.6) intermediate uveitides 98.4% (91.5, 99.7), posterior uveitides 99.2% (95% CI 95.4, 99.9), panuveitides 98.9% (95% CI 94.3, 99.8), and infectious posterior uveitides / panuveitides 98.8% (95% CI 93.4, 99.9).
The classification criteria for these 25 uveitides had high overall accuracy (ie, low misclassification rates) and seemed to perform well enough for use in clinical and translational research.
为 25 种最常见的葡萄膜炎制定分类标准。
使用 5766 例 25 种葡萄膜炎病例进行机器学习。
病例在信息学设计的初步数据库中收集。使用正式共识技术，构建了一个包含 4046 例病例的最终数据库，这些病例对诊断达成了绝大多数的一致意见。病例在葡萄膜炎类别内进行分析，并分为训练集和验证集。在训练集上使用多项逻辑回归和套索正则化进行机器学习，为每种疾病确定一套简洁的标准，并将分类错误率最小化。在验证集中评估得到的标准。通过对 10%的病例进行盲法评估，评估观察者对表达机器学习标准的规则的准确性。
验证集中，按葡萄膜炎类型的总体准确率估计如下：前葡萄膜炎 96.7%（95%置信区间[CI]92.4%，98.6%）；中间葡萄膜炎 99.3%（95%CI96.1%，99.9%）；后葡萄膜炎 98.0%（95%CI94.3%，99.3%）；全葡萄膜炎 94.0%（95%CI89.0%，96.8%）；感染性后葡萄膜炎/全葡萄膜炎 93.3%（95%CI89.1%，96.3%）。对“规则”进行盲法评估的准确率分别为：前葡萄膜炎 96.5%（95%CI91.4%，98.6%）；中间葡萄膜炎 98.4%（91.5%，99.7%）；后葡萄膜炎 99.2%（95%CI95.4%，99.9%）；全葡萄膜炎 98.9%（95%CI94.3%，99.8%）；感染性后葡萄膜炎/全葡萄膜炎 98.8%（95%CI93.4%，99.9%）。
这些 25 种葡萄膜炎的分类标准具有较高的总体准确性（即较低的分类错误率），似乎足以用于临床和转化研究。
