Artificial Intelligence System for the Detection and Prediction of Kidney Diseases Using Ocular Information
试验速览
- 阶段
- 不适用
- 发起方
- 入组人数
- 4,000
- 试验地点
- 1
- 主要终点
- Area under the receiver operating characteristic curve of the deep learning system
研究概览
简要总结
This is an retrospective and prospective multicenter study to develop and validate an artificial intelligent (AI) aided diagnosis, therapeutic effect assessment model including chronic kidney disease (CKD) and dialysis patients starting from April 2009, which is based on ophthalmic examinations (e.g. retinal fundus photography, slit-lamp images, OCTA, etc.) and CKD diagnostic and therapeutic data (routine clinical evaluations and laboratory data), to provide a reliable basis and guideline for clinical diagnosis and treatment.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Other
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •Patients previously received kidney biopsy, ophthalmic examinations and routine examinations of the department of nephrology during in-hospital period with BCVA>0.5.
排除标准
- •Patients without retinal fundus images or kidney diseases.
- •The quality of the retinal fundus images can not meet the requirement for furthur analysis.
- •Severe loss of results of routine examinations of the department of nephrology.
结局指标
主要结局
Area under the receiver operating characteristic curve of the deep learning system
时间窗: baseline
The investigators will calculate the area under the receiver operating characteristic curve of deep learning system and compare this index between deep learning system and human doctors
次要结局
- Sensitivity and specificity of the deep learning system(baseline)
研究者
Haotian Lin
Principal Investigator
Sun Yat-sen University