DME, Neovascular (Wet) Age-Related Macular Degeneration, Retinal Vein Occlusion (RVO)
Conditions
Brief summary
We developed an artificial intelligence system, called QiLin, which was designed to assist anti-VEGF treatment decisions in retinal diseases. QiLin was trained and validated via over 20,000 optical coherence tomography images from multicenter datasets, demonstrating strong performance on both internal and external validation. To evaluate its real-world clinical utility, we conducted a randomized controlled trial that rigorously compares the accuracy of treatment decisions between a physician-only arm and an AI-assisted physician arm.
Interventions
OTHERQiLin-assisted
A Comprehensive Deep Learning Model for Assisting the decision of anti-VEGF therapy: QiLin system
OTHERphysician only, without QiLin assisted
without QiLin assisted
Sponsors
Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
OTHER
Masking
DOUBLE (Subject, Outcomes Assessor)
Eligibility
Sex/Gender
ALL
Age
50 Years to 85 Years
Healthy volunteers
No
Inclusion criteria
Patients with a diagnosis of nAMD, DME, and RVO; Patients who have completed the loading-dose treatment of anti-VEGF agents; Patients who were willing to participate and provided written informed consent.
Exclusion criteria
Refusal to undergo OCT testing; Refusal to complete the 3-month follow-up period; Screening for a history of intraocular surgery within the past 6 months; Subjects with severe systemic diseases, intellectual developmental disorders, psychiatric illnesses, etc.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Accuracy of the current anti-VEGF injection decision | At enrollment | The accuracy of the current anti-VEGF injection decision was defined as the proportion of injection decisions (yes or no) made by the physicians in the two arms that were in agreement with the independent senior expert. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Accuracy of detecting active biomarkers on the current OCT image | At enrollment | The secondary endpoint was defined as the accuracy of detecting active biomarkers. For each patient, the physician was required to perform a binary classification (present vs. absent) for all of 8 pre-defined active biomarkers (PED, NV, IRF, SRF, SHRM, HRF, DRT or DME, and VMT), and was further confirmed by an independent senior retina specialist. The accuracy for per biomarker was calculated as the proportion of correct classifications for that biomarker, and then the average accuracy was calculated as the secondary endpoint. |
Countries
China
Contacts
CONTACTXiaodong Prof. Sun, PhD
CONTACTHuixun Jia, PhD
PRINCIPAL_INVESTIGATORXiaodong Sun, PhD
Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine
Outcome results
None listed