Cross-sectional study: Does combining optical coherence tomography measurements using the 'Random Forest' decision tree classifier improve the prediction of the presence of perimetric deterioration in glaucoma suspects?
Cross-sectional study: Does combining optical coherence tomography measurements using the 'Random Forest' decision tree classifier improve the prediction of the presence of perimetric deterioration in glaucoma suspects?
复制标题
DOI：
10.1136/bmjopen-2013-003114
复制
发表时间：
2013-10-07
期刊：
影响因子：
2.9
通讯作者：
Asaoka R
中科院分区：
文献类型：
--
作者：
Sugimoto K;Murata H;Hirasawa H;Aihara M;Mayama C;Asaoka R
开发一种分类器，用于基于光学相干断层扫描（OCT）测量结果，使用称为“随机森林”算法的机器学习方法预测青光眼疑似患者是否存在视野（VF）恶化。病例对照研究。179名开角型青光眼（OAG）或疑似OAG参与者的293只眼。对所有参与者进行光谱域OCT（Topcon 3D OCT-2000）和视野检查（Humphrey Field Analyser，24-2或30-2 SITA标准）测量。VF损伤（高眼压治疗研究标准（2002））被用作“金标准”来分类青光眼。然后使用“随机森林”方法分析是否存在昏迷性VF损伤与以下变量之间的关系：年龄、性别、右眼或左眼、眼轴长度加上237个不同的OCT测量值。然后使用青光眼的概率（如随机森林分类器中的投票比例所建议的）推导受试者工作特征曲线下面积（AROC）。为了比较，基于以下导出五个AROC：（1）单独的黄斑视网膜神经纤维层（m-RNFL）;（2）单独的视乳头周围（cp-RNFL）;（3）单独的神经节细胞层和内网状层（GCL+IPL）;（4）单独的边缘面积和（5）使用与随机森林算法相同的变量的决策树方法。来自组合随机森林分类器的AROC（0.90）显著大于基于m-RNFL（0.86）、cp-RNFL（0.77）、GCL+IPL（0.80）、边缘面积（0.78）和决策树方法（0.75; p<0.05）的个体测量的AROC。使用随机森林方法评价OCT测量结果可准确预测青光眼可疑患者是否存在视野恶化。
To develop a classifier to predict the presence of visual field (VF) deterioration in glaucoma suspects based on optical coherence tomography (OCT) measurements using the machine learning method known as the ‘Random Forest’ algorithm. Case–control study. 293 eyes of 179 participants with open angle glaucoma (OAG) or suspected OAG. Spectral domain OCT (Topcon 3D OCT-2000) and perimetry (Humphrey Field Analyser, 24-2 or 30-2 SITA standard) measurements were conducted in all of the participants. VF damage (Ocular Hypertension Treatment Study criteria (2002)) was used as a ‘gold-standard’ to classify glaucomatous eyes. The ‘Random Forest’ method was then used to analyse the relationship between the presence/absence of glaucomatous VF damage and the following variables: age, gender, right or left eye, axial length plus 237 different OCT measurements. The area under the receiver operating characteristic curve (AROC) was then derived using the probability of glaucoma as suggested by the proportion of votes in the Random Forest classifier. For comparison, five AROCs were derived based on: (1) macular retinal nerve fibre layer (m-RNFL) alone; (2) circumpapillary (cp-RNFL) alone; (3) ganglion cell layer and inner plexiform layer (GCL+IPL) alone; (4) rim area alone and (5) a decision tree method using the same variables as the Random Forest algorithm. The AROC from the combined Random Forest classifier (0.90) was significantly larger than the AROCs based on individual measurements of m-RNFL (0.86), cp-RNFL (0.77), GCL+IPL (0.80), rim area (0.78) and the decision tree method (0.75; p<0.05). Evaluating OCT measurements using the Random Forest method provides an accurate prediction of the presence of perimetric deterioration in glaucoma suspects.
登录
查看更多内容
影响因子：
--
作者：
Lee JY;Hwang YH;Lee SM;Kim YY
通讯作者：
Kim YY
影响因子：
3.9
作者：
Garas, A.;Vargha, P.;Hollo, G.
通讯作者：
Hollo, G.
影响因子：
4.4
作者：
Kim, Na Rae;Lee, Eun Suk;Kim, Chan Yun
通讯作者：
Kim, Chan Yun
影响因子：
4.4
作者：
Cho, Jung Woo;Sung, Kyung Rim;Kook, Michael S.
通讯作者：
Kook, Michael S.
影响因子：
6.1
作者：
Fang Yuan;Pan Ying-zi;Cai Yu
通讯作者：
Cai Yu