Deep Learning in the Detection and Prediction of Hydroxychloroquine Maculopathy

Condition(s) studied

Investigational drug(s) / intervention(s)

Retinopathy group: OCT scans and Retinai algorithm will be performed

Control group: OCT scans and Retinai algorithm will be performed

Study summary

Hydroxychloroquine retinal toxicity affects a significant number of patients using this medication. Detection of toxicity is difficult in the early stages of the disease and depends on the subjectivity of the clinician who reads the tests (optical coherence tomography, autofluorescence and visual fields). Automating the reading of these diagnostic exams could lead to earlier detection of this pathology and reduce the burden associated with interpreting these exams in the ophthalmology service. The images that are usually taken in the screening and monitoring of hydroxychloroquine toxicity by will be collected - photography of the ocular fundus and optical coherence tomography with autofluorescence.

Eligibility

Primary outcome measure(s)

• To develop an automated screening method in hydroxychloroquine (HCQ) screening based on OCT features — One year
  We hypothesize that HCQ toxicity can be detected with a deep learning system with OCT

Trial sites (1)

More Centro Hospitalar de Lisboa Central trials in Portugal