Analyzing the Effect of Surgical and Corneal Parameters on the Postoperative Refractive Outcomes of Smile in Myopic Eyes Based on Machine Learning

Purpose: To analyze the influence of individual parameters on the postoperative refractive outcomes of small incision lenticule extraction (SMILE) in myopic eyes using machine learning. Design: Retrospective Clinical Cohort Study Methods: This study included 477 patients (922 eyes) of SMILE and divided them into two groups based on postoperative spherical equivalent (SE) ≤ -0.50D to analyze the factors influencing postoperative refractive outcomes. The XGBoost model took 72 clinical parameters (34 biomechanical, 31 morphological, 4 surgical-related, and 3 preoperative refractive parameters) as features; randomly selected 42 eyes from the good refractive outcomes group and all eyes (a total of 42 eyes) from the poor refractive outcomes group to conduct 100 times influence factors analysis. Results: The 10 most important factors influencing postoperative refractive outcomes included 3 surgery-related parameters (PTA, LTmax, and RST), 3 corneal biomechanical parameters (HC Time, Deflection Amp Max (ms), and SSI), 2 corneal morphological parameters (R Per F and Rs F), and 2 preoperative refractive parameters (SE and SD). When PTA ≥ 25.09%, LTmax ≥ 139μm, SE ≤ −7.00D, or SD ≤ −6.75D, the postoperative SE significantly increased (all P < 0.05), with averages of −0.183D, −0.171D, −0.188D, and −0.184D. After controlling for age, intraocular pressure, and corneal thickness, the postoperative SE significantly increased when HC time ≥ 17.422 and Deflection Amp Max (ms) ≥ 16.616, reaching −0.209D and −0.202D. Conclusions: More corneal tissue ablation, longer HC Time and Deflection Amp Max (ms), lower SSI, and higher preoperative refractive error may result in poor postoperative refractive outcomes.