Expansion of Integrated AI Solution for Diabetic Retinopathy Screening in Thailand: An Implementation Research
试验速览
- 阶段
- 不适用
- 入组人数
- 34,500
- 主要终点
- Effectiveness of AI in diabetic retinopathy screening
研究概览
简要总结
Efficiency and effectiveness of real-world diabetic retinopathy screening by artificial intelligent (AI) are limited. Investigators will implement AI for diabetic retinopathy screening in 13 health districts in Thailand and investigate the efficiency, effectiveness as well as patients and health care personnel's satisfaction by an implementation research.
研究设计
- 研究类型
- Observational
- 观察模型
- Other
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 —(Adult, Older Adult)
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Type 1 or 2 diabetes mellitus patients whose name are in primary hospital record
- •No full-time ophthalmologists in those primary hospital
- •Age more than or equal to 18 years
- •Eligible for fundus photo imaging at least 1 eye
排除标准
- •Type 1 or 2 diabetes mellitus patients whose name are in primary hospital record that have full-time ophthalmologists
- •Patients who previously diagnosed with other causes of macular edema, for example, Age-related Macular Degeneration, Radiation Retinopathy, Retinal Vein Occlusion etc.
- •History of retinal laser or surgery
- •Other ocular diseases that require referral to ophthalmologists
- •Not eligible for fundus photo imaging for both eyes (any causes)
结局指标
主要结局
Effectiveness of AI in diabetic retinopathy screening
时间窗: Throughout the whole period of screening, approximately 6 months
Referral adherance of patients in AI group in percentage
Efficiency of AI in diabetic retinopathy screening
时间窗: Throughout the whole period of screening, approximately 6 months
Cost in development and implement of AI system in Thai baht unit
次要结局
- Satisfaction of patients and health care personnel in AI-based screening(At the end of the screening, approximately at Month 6)
