Department of Ophthalmology, Seirei Hamamatsu General Hospital, Hamamatsu, Shizuoka, Japan.
Seirei Christopher University, Hamamatsu, Shizuoka, Japan.
Sci Rep. 2021 Feb 11;11(1):3687. doi: 10.1038/s41598-020-80839-4.
The purpose of the current study was to predict intraocular pressure (IOP) using color fundus photography with a deep learning (DL) model, or, systemic variables with a multivariate linear regression model (MLM), along with least absolute shrinkage and selection operator regression (LASSO), support vector machine (SVM), and Random Forest: (RF). Training dataset included 3883 examinations from 3883 eyes of 1945 subjects and testing dataset 289 examinations from 289 eyes from 146 subjects. With the training dataset, MLM was constructed to predict IOP using 35 systemic variables and 25 blood measurements. A DL model was developed to predict IOP from color fundus photographs. The prediction accuracy of each model was evaluated through the absolute error and the marginal R-squared (mR), using the testing dataset. The mean absolute error with MLM was 2.29 mmHg, which was significantly smaller than that with DL (2.70 dB). The mR with MLM was 0.15, whereas that with DL was 0.0066. The mean absolute error (between 2.24 and 2.30 mmHg) and mR (between 0.11 and 0.15) with LASSO, SVM and RF were similar to or poorer than MLM. A DL model to predict IOP using color fundus photography proved far less accurate than MLM using systemic variables.
本研究的目的是使用深度学习 (DL) 模型或使用多元线性回归模型 (MLM) 结合最小绝对收缩和选择算子回归 (LASSO)、支持向量机 (SVM) 和随机森林 (RF)，利用眼底彩色照相术预测眼压 (IOP)。训练数据集包括来自 1945 名受试者的 3883 只眼的 3883 次检查，测试数据集包括来自 146 名受试者的 289 只眼的 289 次检查。使用训练数据集，构建了 MLM，使用 35 个系统变量和 25 个血液测量值来预测 IOP。开发了一个从眼底彩色照片预测 IOP 的 DL 模型。使用测试数据集评估了每个模型的绝对误差和边际 R 平方 (mR) 的预测准确性。MLM 的平均绝对误差为 2.29 mmHg，明显小于 DL 的平均绝对误差 (2.70 dB)。MLM 的 mR 为 0.15，而 DL 的 mR 为 0.0066。LASSO、SVM 和 RF 的平均绝对误差 (在 2.24 到 2.30 mmHg 之间) 和 mR (在 0.11 到 0.15 之间) 与 MLM 相似或更差。使用眼底彩色照相术预测 IOP 的 DL 模型的准确性远低于使用系统变量的 MLM。
