Diagnostic Efficacy of Deep Neural Network Algorithm Based on Preoperative Scheimpflug-based Anterior Segment Image for Implantable Collamer Lens Selection and Prediction
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 发起方
- 入组人数
- 326
- 试验地点
- 1
- 主要终点
- AUROC of convolutional neural network in predicting vault after ICL surgery
研究概览
简要总结
To evaluate the diagnostic efficacy of deep learning network model in implantable collamer lens selection and prediction in a multicenter cross-sectional study
详细描述
Posterior chamber intraocular lens implantation is an main choice for myopia correction. Implantable collamer lens (ICL) is currently the most widely used, and the official reference index is mainly based on biological parameters obtained from eye images. The parameter acquisition and selection of ICL design are often controversial, forcing the doctors to synthesize multiple modal data, making the optimization of ICL formula being a focus of attention in refractive surgery. This research aimed to build an image-based ICL prediction algorithm to assist human physicians in decision-making and improve the accuracy, safety and predictability of ICL implantation.
研究设计
- 研究类型
- Observational
- 观察模型
- Other
- 时间视角
- Cross Sectional
入排标准
- 年龄范围
- 18 Years 至 45 Years（Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •Aged 18-45 years ;
- •Myopia, with or without astigmatism, annual diopter change ≤ 0.50 D for 2 consecutive years ;
- •Anterior chamber depth ≥ 2.80 mm ;
- •Corneal endothelial cell count ≥ 2000 / mm2, stable cell morphology ;
- •There were no other ocular diseases that significantly affected vision and / or systemic organic lesions that affected surgical recovery.
排除标准
- •There were no other ocular diseases that significantly affected vision and / or systemic organic lesions that affected surgical recovery;
- •Have a history of corneal refractive surgery or intraocular surgery ;
- •Corneal endothelial cell count is low ;
- •Those with systemic diseases ;
- •Lactating or pregnant women.
研究组 & 干预措施
Eyes with ICL surgeries
Eyes with SMILE surgeries which were performed by surgeons with experiences.
干预措施: AI diagnostic algorithm (Diagnostic Test)
结局指标
主要结局
AUROC of convolutional neural network in predicting vault after ICL surgery
时间窗: Day 7
The area under the receiver operating characteristic of convolutional neural network in predicting vault after ICL surgery
AUROC of convolutional neural network in predicting anterior chamber angle after ICL implantation
时间窗: Day 7
The area under the receiver operating characteristic of convolutional neural network in predicting anterior chamber angle after ICL implantation
次要结局
- Sensitivity and specificity of convolutional neural network in predicting Vault after ICL implantation(Day 7)
- Sensitivity and specificity of convolutional neural network in predicting anterior chamber angle after ICL implantation(Day 7)
研究者
Jian Xiong
Associate research fellow; Attending physician
Second Affiliated Hospital of Nanchang University