Abstract：
Rigid gas permeable contact lenses (RGP) are the most efficient means of providing optimal vision in keratoconus. RGP fitting can be challenging and time-consuming for ophthalmologists and patients. Deep learning predictive models could simplify this process.
To develop a deep learning model to predict the base curve (R0) of rigid gas permeable contact lenses for keratoconus patients.
We conducted a retrospective study at the Rothschild Foundation Hospital between June 2012 and April 2021. We included all keratoconus patients fitted with Menicon Rose K2® lenses. The data was divided into a training set to develop the model and a test set to evaluate the model\'s performance. We used a U-net architecture. The raw matrix of anterior axial curvature in millimeters was extracted from Scheimpflug examinations for each patient and used as input for the model. The mean absolute error (MAE) between the prediction and the prescribed R0 was calculated. Univariate and multivariate analyses were conducted to assess the model\'s errors.
Three hundred fifty-eight eyes from 202 patients were included: 287 eyes were included in the training dataset, and 71 were included in the testing dataset. Our model\'s Pearson coefficient of determination (R2) was calculated at 0.83, compared to 0.75 for the manufacturer\'s recommendation (mean keratometry, Km). The mean square error of our model was calculated at 0.04, compared to 0.11 for Km. The predicted R0 MAE (0.16 ± 0.13) was statistically significantly different from the Km MAE (0.23 ± 0.23) (p = 0.02). In multivariate analysis, an apex center outside the central 5 mm region was the only factor significantly increasing the prediction absolute error.
Our deep learning approach demonstrated superior precision in predicting rigid gas permeable contact lens base curves for keratoconus patients compared to the manufacturer\'s recommendation. This approach has the potential to be particularly beneficial in complex fitting cases and can help reduce the time spent by ophthalmologists and patients during the process.
To develop a deep learning model to predict the base curve (R0) of rigid gas permeable contact lenses for keratoconus patients.
We conducted a retrospective study at the Rothschild Foundation Hospital between June 2012 and April 2021. We included all keratoconus patients fitted with Menicon Rose K2® lenses. The data was divided into a training set to develop the model and a test set to evaluate the model\'s performance. We used a U-net architecture. The raw matrix of anterior axial curvature in millimeters was extracted from Scheimpflug examinations for each patient and used as input for the model. The mean absolute error (MAE) between the prediction and the prescribed R0 was calculated. Univariate and multivariate analyses were conducted to assess the model\'s errors.
Three hundred fifty-eight eyes from 202 patients were included: 287 eyes were included in the training dataset, and 71 were included in the testing dataset. Our model\'s Pearson coefficient of determination (R2) was calculated at 0.83, compared to 0.75 for the manufacturer\'s recommendation (mean keratometry, Km). The mean square error of our model was calculated at 0.04, compared to 0.11 for Km. The predicted R0 MAE (0.16 ± 0.13) was statistically significantly different from the Km MAE (0.23 ± 0.23) (p = 0.02). In multivariate analysis, an apex center outside the central 5 mm region was the only factor significantly increasing the prediction absolute error.
Our deep learning approach demonstrated superior precision in predicting rigid gas permeable contact lens base curves for keratoconus patients compared to the manufacturer\'s recommendation. This approach has the potential to be particularly beneficial in complex fitting cases and can help reduce the time spent by ophthalmologists and patients during the process.
摘要：
背景：刚性透气隐形眼镜（RGP）是在圆锥角膜中提供最佳视力的最有效手段。RGP拟合对于眼科医生和患者来说可能是具有挑战性和耗时的。深度学习预测模型可以简化这个过程。
目的：开发一种深度学习模型，以预测圆锥角膜患者的刚性透气性隐形眼镜的基本曲线（R0）。
方法：我们于2012年6月至2021年4月在罗斯柴尔德基金会医院进行了一项回顾性研究。我们纳入了所有配备MeniconRoseK2®镜片的圆锥角膜患者。将数据分为用于开发模型的训练集和用于评估模型性能的测试集。我们使用了U-net架构。从每位患者的Scheimpflug检查中提取以毫米为单位的前轴曲率的原始矩阵，并用作模型的输入。计算预测与规定R0之间的平均绝对误差(MAE)。进行单变量和多变量分析以评估模型的误差。
结果：纳入202名患者的三百五十八只眼：287只眼纳入训练数据集，和71个被包括在测试数据集中。我们的模型皮尔逊决定系数（R2）计算为0.83，而制造商的建议为0.75（平均角膜曲率，公里）。我们的模型的均方误差计算为0.04，而Km为0.11。预测的R0MAE（0.16±0.13）与KmMAE（0.23±0.23）有统计学显着差异（p=0.02）。在多变量分析中，中心5mm区域以外的顶点中心是唯一显着增加预测绝对误差的因素。
结论：与制造商的建议相比，我们的深度学习方法在预测圆锥角膜患者的刚性透气性角膜接触镜基础曲线方面表现出更高的精度。这种方法有可能在复杂的验配情况下特别有益，并且可以帮助减少眼科医生和患者在此过程中花费的时间。
目的：开发一种深度学习模型，以预测圆锥角膜患者的刚性透气性隐形眼镜的基本曲线（R0）。
方法：我们于2012年6月至2021年4月在罗斯柴尔德基金会医院进行了一项回顾性研究。我们纳入了所有配备MeniconRoseK2®镜片的圆锥角膜患者。将数据分为用于开发模型的训练集和用于评估模型性能的测试集。我们使用了U-net架构。从每位患者的Scheimpflug检查中提取以毫米为单位的前轴曲率的原始矩阵，并用作模型的输入。计算预测与规定R0之间的平均绝对误差(MAE)。进行单变量和多变量分析以评估模型的误差。
结果：纳入202名患者的三百五十八只眼：287只眼纳入训练数据集，和71个被包括在测试数据集中。我们的模型皮尔逊决定系数（R2）计算为0.83，而制造商的建议为0.75（平均角膜曲率，公里）。我们的模型的均方误差计算为0.04，而Km为0.11。预测的R0MAE（0.16±0.13）与KmMAE（0.23±0.23）有统计学显着差异（p=0.02）。在多变量分析中，中心5mm区域以外的顶点中心是唯一显着增加预测绝对误差的因素。
结论：与制造商的建议相比，我们的深度学习方法在预测圆锥角膜患者的刚性透气性角膜接触镜基础曲线方面表现出更高的精度。这种方法有可能在复杂的验配情况下特别有益，并且可以帮助减少眼科医生和患者在此过程中花费的时间。
