Fit error (difference between the C0 and C45 power vector components derived from the postoperatively measured CASIA real power and the respective components predicted with the feedforward shallow neural network or the multivariate linear regression) for the entire dataset (N = 88).

On the left side / right side the prediction error derived from the prediction models from the preoperative IOLM / CASIA keratometric data is shown. The prediction with the neural network performs slightly better as compared to the multivariate linear regression, and the prediction based on the preoperative CASIA data is slightly superior to the prediction based on the preoperative IOLM data. The power vector components in 45°/135° were reversed in sign for all left eyes in our dataset in order to present the data in the same orientation as for right eyes. Mean, SD, Median, and 2.5% / 97.5% refer to the arithmetic mean, standard deviation, median, and the lower and upper bounds of the 95% confidence interval respectively.