[Advance of screening keratoconus before refractive surgery with machine learning].

Artificial intelligence (AI) has made important progress in image recognition and disease prognosis prediction in recent years. Along with the development of computer technology, the application scope of AI in the field of ophthalmology is expanding. Keratoconus screening is an important means to determine the indication of refractive surgery and avoid postoperative corneal ectasia, but the accuracy of traditional diagnostic methods is low, especially for subclinical keratoconus. Machine learning, a method to realize artificial intelligence, makes it possible to improve the accuracy of keratoconus screening, and has become a hotspot in the field of refractive surgery recently. The review has clarified the algorithms commonly used in keratoconus screening for refractive surgery, the extraction of corneal features, and the accuracy of model prediction..