NCT05682105

Detection of Jaundice From Ocular Images Via Deep Learning

Detection of Jaundice From Ocular Images Via Deep Learning : a Prospective, Multicenter Cohort Study

• Status: Unknown
• Phase: —
• Study type: Observational
• Enrollment: 1,633 (actual)
• Sponsor: Sun Yat-sen University · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Accepted

Summary

Our study presents a detection model predicting a diagnosis of jaundice (clinical jaundice and occult jaundice) trained on prospective cohort data from slit-lamp photos and smartphone photos, demonstrating the model's validity and assisting clinical workers in identifying patient underlying hepatobiliary diseases.

Detailed description

This study demonstrated that deep learning models could detect jaundice using ocular images in blood levels with reasonable accuracy, providing a non-invasive method for jaundice detection and recognition. This algorithm can assist clinical surgeons with daily follow-up visits and provide referral advice. It also highlights the algorithm's potential smartphone application in sizeable real-world population-based disease-detecting or telemedicine programs.

Conditions

• Ophthalmology
• Artificial Intelligence
• Hepatobiliary Disease

Timeline

• Start date: 2018-12-01
• Primary completion: 2022-10-30
• Completion: 2023-06-30
• First posted: 2023-01-12
• Last updated: 2023-01-12

Locations

1 site across 1 country: China