[ARTIFICIAL INTELLIGENCE IN OPHTHALMOLOGY].

INTRODUCTION: Artificial intelligence (AI) was first introduced in 1956, and effectively represents the fourth industrial revolution in human history. Over time, this medium has evolved to be the preferred method of medical imagery interpretation. Today, the implementation of AI in the medical field as a whole, and the ophthalmological field in particular, is diverse and includes diagnose, follow-up and monitoring of the progression of ocular diseases. For example, AI algorithms can identify ectasia, and pre-clinical signs of keratoconus, using images and information computed from various corneal maps. Machine learning (ML) is a specific technique for implementing AI. It is defined as a series of automated methods that identify patterns and templates in data and leverage these to perform predictions on new data. This technology was first applied in the 1980s. Deep learning is an advanced form of ML inspired by and designed to imitate the human brain process, constructed of layers, each responsible for identifying patterns, thereby successfully modeling complex scenarios. The significant advantage of ML in medicine is in its' ability to monitor and follow patients with efficiency at a low cost. Deep learning is utilized to monitor ocular diseases such as diabetic retinopathy, age-related macular degeneration, glaucoma, cataract, and retinopathy of prematurity. These conditions, as well as others, require frequent follow-up in order to track changes over time. Though computer technology is important for identifying and grading various ocular diseases, it still necessitates additional clinical validation and does not entirely replace human diagnostic skill.

Factors associated with changes in posterior corneal surface following laser-assisted in situ keratomileusis.

PURPOSE: To identify factors associated with changes in the posterior corneal curvature following laser-assisted in situ keratomileusis (LASIK). METHODS: This retrospective study included myopic astigmatic eyes that underwent LASIK between January and December 2013 at Care-Vision Laser Center, Tel-Aviv, Israel. The average posterior keratometry was measured with the Sirius device at a radius of 3 mm from the center. The correlations between the surgically induced change in average posterior keratometry and preoperative parameters such as preoperative sphere, cylinder, spherical equivalent, central corneal thickness (CCT), refraction, Baiocchi Calossi Versaci (BCV) index, ablation depth, percent of tissue altered (PTA), and residual stromal bed (RSB) are reported. RESULTS: A total of 115 eyes with a mean age of 32.5 ± 8.3 years (range 22-56 years) were included. Central corneal thickness (p < 0.005), preoperative sphere (p < 0.001), spherical equivalent (p < 0.005), and preoperative posterior inferior/superior ratio (p < 0.05) were all significantly correlated with the percentage of change in the mean posterior K. According to ranked stepwise multiple regression analysis, 22% of the variance of change in posterior K could be explained by the examined factors. The factors that remained significant were the percentage of change in posterior inferior/superior ratio, preoperative subjective sphere, and preoperative mean posterior K (for all, p < 0.001). CONCLUSIONS: The percentage of change in posterior inferior/superior ratio, subjective sphere, and preoperative mean posterior K are all correlated with change in the mean posterior K after LASIK. Understanding of the variables that can influence posterior corneal changes following refractive surgery may play a role in the prevention of iatrogenic keratectasia.