Establishing the Use of DARWEN AI Technology in Ophthalmology and Identifying Predictors of Treatment Intervals in nAMD and RVO
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 发起方
- Bayer
- 入组人数
- 1,350
- 试验地点
- 1
- 主要终点
- Validation of DARWEN™ AI.
研究概览
简要总结
This is an observational study in which data already collected from people with the eye disorders below are studied. In observational studies, only observations are made without participants receiving any advice or any changes to healthcare.
Neovascular age-related macular edema (nAMD): an eye disorder caused by the lack of oxygen in the retina. The lack of oxygen leads to the increase of a protein called vascular endothelial growth factor (VEGF). VEGF causes new, weak blood vessels to grow. These vessels can leak fluid or blood into the central part of the retina at the back of the eye (macula). This leads to blurring or a blind spot in the central (straight ahead) vision needed for reading or threading a needle.
Retinal vein occlusion (RVO): an eye disorder where a blood vessel that carries blood away from the retina (vein) becomes blocked. The blocked vein causes a lack of oxygen in the retina which leads to the increase of VEGF and then vision disturbances.
These eye disorders can be treated with a type of medicine called anti-vascular endothelial growth factor (anti-VEGF). Anti-VEGF treatment helps control the growth of new blood vessels in the eye and is given via injection into the eye.
DARWEN AI is a system using artificial intelligence (AI) technology. It has been proven that DARWEN AI can be used to extract data accurately and efficiently in multiple disease areas, including breast cancer, lung cancer, ambulatory care diseases and skin disorders.
The main purpose of this study is to validate if DARWEN AI can extract and sort through information from participants' health records accurately to identify those who need more frequent injections and those who do not.
The secondary purpose of this study is to use DARWEN AI to describe the factors influencing treatment frequencies in participants with nAMD or influencing treatment discontinuation in participants with RVO.
The data will come from the participants' information stored in EyeDoc Electronic Medical Records (EMR) at St. Joseph Health Care in London. Data collected are from January 1, 2009, to May 31, 2023.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Retrospective
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
- •All patients with the diagnosis of nAMD or RVO (Branch or Central) who are patients of Dr. Tom Sheidow listed in the EyeDoc EHR with available patient records from Jan 1, 2009 to May 31, 2023.
排除标准
- •Not applicable.
研究组 & 干预措施
nAMD patients, anti-VEGF naïve on treatment after July 2015
- Cluster A: Likely to require frequent injections
- Cluster B: Probable to extend treatment interval
- Cluster C: Likely to extend treatment interval
干预措施: anti-VEGF treatment (Drug)
nAMD patients, anti-VEGF naïve on treatment before July 2015
- Cluster D: Likely to require frequent injections
- Cluster E: Probable to extend treatment interval
- Cluster F: Likely to extend treatment interval
干预措施: anti-VEGF treatment (Drug)
nAMD patients, anti-VEGF experienced on treatment after July 2015
- Cluster G: Likely to require frequent injections
- Cluster H: Likely to extend treatment interval
干预措施: anti-VEGF treatment (Drug)
CRVO patients, anti-VEGF naïve on treatment after July 2015
- Cluster A: Likely to require continued anti-VEGF treatment
- Cluster B: Likely to be off anti-VEGF treatment
干预措施: anti-VEGF treatment (Drug)
BRVO patients, anti-VEGF naïve on treatment after March 2017
- Cluster C: Likely to require continued anti-VEGF treatment
- Cluster D: Likely to be off anti-VEGF treatment
干预措施: anti-VEGF treatment (Drug)
结局指标
主要结局
Validation of DARWEN™ AI.
时间窗: Retrospective data analysis from January 1, 2009 to May 31, 2023.
Based on defined objective clinical eligibility criteria, the EMR data set was divided into four cohorts using Pentavere's proprietary AI engine DARWEN™. The following ophthalmology-specific variables were validated against a manual review: diagnosis of nAMD, diagnosis of RVO including CRVO and BRVO, treatment intervals of anti-VEGF treatment grouped as \< Q8 weeks or ≥ Q8 weeks for nAMD patients, discontinuation of anti-VEGF treatment for RVO patients, and the final outputted cohorts. The manual review was performed on a random selection of 25 patients from each of the four cohorts (100 patients total). Two trained manual abstractors classified these patients according to the rules outlined in the objective cohort criteria. They aligned on a consensus for each patient and compared with the DARWEN™cohorts. Pentavere then provided a success rate for the accuracy of the classification.
次要结局
- Summary of baseline demographics reported as number of participants with different categories.(Retrospective data analysis from January 1, 2009 to May 31, 2023.)
- Summary of clinical characteristics reported as number of participants with different categories.(Retrospective data analysis from January 1, 2009 to May 31, 2023.)