Potential Risk Factors and Predictive Model Construction of OBL During SMILE

Second Affiliated Hospital of Nanchang University4,678 enrolled

Overview

To explore the prediction of OBL by deep learning model in SMILE surgery

The DL model was used to predict the OBL area during SMILE surgery by identifying the corneal full-view images before laser scanning. The DL model developed may assist surgeons to predict the possible OBL area of patients in advance, so as to adjust some surgical parameters and reduce the formation of OBL, which can avoid negative effects on surgeons' operation and patients' postoperative visual recovery, which has important practical significance.

Study Type

OBSERVATIONAL

Enrollment

4,678

Conditions

Myopia Small-incision Lenticule Extraction (SMILE) Surgery

Interventions

Small incision lenticule extractionPROCEDURE

Small incision lenticule extraction surgeries performed by two Refractive surgery experts (Refractive surgery expert 1: YYF, Associate Professor with 10 years of experience as a refractive surgeon; Refractive surgery expert 2: GF, Associate Professor with 5 years of experience as a refractive surgeon) and a Attending ophthalmologist (XJ, Attending ophthalmologist with 1 year of experience as a refractive surgeon).

Eligibility

Sex: ALLMin age: 18 YearsMax age: 45 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: * A condition in which the spherical equivalent refractive error of an eye is ≤ -0.50 D when ocular accommodation is relaxed; * Age ≥18 years; * Spherical equivalent (SE) ≥ -10.0D; * Corrected distance visual acuity (CDVA) ≥ 16/20; * Stable myopia for at least 2 years; * No contact lenses wearing for at least 2 weeks Exclusion Criteria: * The presence or history of eye conditions other than myopia and astigmatism, such as keratoconus or external eye injury; * A history of eye surgery; * The presence or history of systemic diseases.

Locations (1)

The Second Affiliated Hospital of Nanchang University

Nanchang, Jiangxi, China

Outcomes

Primary Outcomes

The area of patients with opaque bubble layer in the SMILE surgeries

The area of patients with opaque bubble layer were observed during the SMILE surgeries.

Time frame: Day 0

Secondary Outcomes

Deep learning model

Predictive performance of deep learning model on the OBL in SMILE surgeries.

Time frame: Day 0

ResNet model

Predictive performance of ResNet model on the OBL in SMILE surgeries.

Time frame: Day 0

Vgg19 model

Predictive performance of Vgg model on the OBL in SMILE surgeries.

Time frame: Day 0

U-net model

Predictive performance of U-net model on the OBL in SMILE surgeries.

Time frame: Day 0

Data from ClinicalTrials.gov

This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.