Research Progress of Artificial Intelligence Image Analysis in Systemic Disease-Related Ophthalmopathy

Table 4

Summary of NMO diagnosis model based on deep learning method.

Study	Task	Sample size	AI model	Output
Huang et al. [37]	Detection and identification	116 images of magnetic resonance	A multi-parameter multivariate random forest model	In training, the accuracy of the MM-RF model was 0.849, and the AUC value was 0.826; for testing, the accuracy of the MM-RF model was 0.871, and the AUC value was 0.902.
Hagiwara et al. [38]	Detection and identification	53 patients’ examination results	SqueezeNet	The AUC value of the model is 0.859, and the accuracies of NMO and MS are 81.1% and 83.3%, respectively.
Kim et al. [39]	Detection and identification	338 patients’ images of magnetic resonance	ResNeXt	The AUC value of the model was 0.82, and the accuracy was 71.1%.
Khoury et al. [40]	Identification	202 serum samples	A random forest classification machine learning algorithm	The sensitivity and specificity were 1.00 and 1.00.