Department of Ophthalmology and University Eye Hospital, Erlangen, Germany.
J Glaucoma. 2012 Jan;21(1):27-34. doi: 10.1097/IJG.0b013e3182027766.
To develop a diagnostic setup with classification rules for combined analysis of morphology [Heidelberg Retina Tomograph (HRT)] and function [frequency doubling technology (FDT) perimetry] measurements.
We used 2 independent case-control studies from the Erlangen eye department as learning and test data for automated classification using random forests. One eye of 334 open angle glaucoma patients and 254 controls entered the study. All individuals underwent HRT scanning tomography of the optic disc, FDT screening, conventional perimetry, and evaluation of fundus photographs. Random forests were learned on individuals of the Erlangen glaucoma registry (102 preperimetric patients, 130 perimetric patients, 161 controls). The classification performances of random forests and built-in classifiers were examined by receiver operator characteristic analysis on an independent second cohort of individuals (47 preperimetric patients, 55 perimetric patients, 93 controls).
HRT measurements had a higher diagnostic power for early glaucomas and FDT perimetry for glaucoma patients with visual field loss. A combination of all parameters using automated classification was superior to single tests in comparison to the diagnostic instrument with the higher diagnostic power in the respective group. Highest sensitivities at a fixed specificity (95%) in the patients of the present test population were: HRT=32%, FDT=19%, combined analysis=47% in preperimetric patients and HRT=76%, FDT=89%, combined analysis=96% in perimetric patients.
The feasibility of machine learning for medical diagnostic assistance could be demonstrated in patients from 2 independent study populations. A predictive model using automated classification is able to combine the advantages of morphology and function, resulting in a higher diagnostic power for glaucoma detection.
开发一种具有分类规则的诊断设置，用于联合分析形态学[海德堡视网膜断层扫描仪（HRT）]和功能[频域加倍技术（FDT）视野计]测量。
我们使用来自埃尔兰根眼科部门的 2 个独立病例对照研究作为学习和测试数据，用于使用随机森林进行自动分类。334 名开角型青光眼患者和 254 名对照者的一只眼进入研究。所有个体均接受 HRT 扫描视神经盘断层扫描、FDT 筛查、常规视野计检查和眼底照片评估。随机森林是在埃尔兰根青光眼登记处的个体（102 名前期青光眼患者、130 名青光眼患者、161 名对照者）上学习的。在独立的第二组个体（47 名前期青光眼患者、55 名青光眼患者、93 名对照者）上，通过接收者操作特征分析检查随机森林和内置分类器的分类性能。
HRT 测量对于早期青光眼具有更高的诊断能力，而 FDT 视野计对于有视野损失的青光眼患者具有更高的诊断能力。与各自组中具有更高诊断能力的诊断仪器相比，使用自动分类对所有参数进行组合在比较中优于单项测试。在当前测试人群的患者中，固定特异性（95%）下的最高敏感性为：HRT=32%、FDT=19%、联合分析=47%在前期青光眼患者中，HRT=76%、FDT=89%、联合分析=96%在青光眼患者中。
在来自 2 个独立研究人群的患者中，可以证明机器学习用于医学诊断辅助的可行性。使用自动分类的预测模型能够结合形态学和功能的优势，从而提高青光眼检测的诊断能力。
