FindTrial
Sign In

Deep learning for diabetic retinopathy screening based on ultra-widefield fundus images: a prospective multi-center study

Deep learning for diabetic retinopathy screening based on ultra-widefield fundus images: a prospective multi-center study

Status
Active, not recruiting
Phases
Early Phase 1
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2000035102
Enrollment
Unknown
Registered
2020-07-31
Start date
2020-10-01
Completion date
Unknown
Last updated
2020-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Diabetic retinopathy

Interventions

Gold Standard:The diagnosis was made by experienced retina specialist in combination with patient history and artificial fundus examination.
Index test:1.&#32
Diabetic&#32
retinopathy&#32
screening&#32
based&#32
on&#32
ultra-widefield&#32
fundus&#32
images
2.&#32
Traditional&#32
image-based&#32
AI&#32
diabetic&#32
system.

Sponsors

Ningbo Eye Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
19 Years to 100 Years

Inclusion criteria

Inclusion criteria: Diabetic patients.

Exclusion criteria

Exclusion criteria: 1. Patients who cannot cooperate with a photographer such as some paralytics, the patients with dementia and severe psychopaths. 2. Patients who do not agree to sign informed consent.

Design outcomes

Primary

MeasureTime frame
SEN, SPE, ACC, AUC of ROC, NPV, PPV, FPR, FNR.;—

Countries

China

Contacts

Public ContactZhongwen Li

Ningbo Eye Hospital

lizhongwenwxf@foxmail.com+86 15626187616

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026