A Prospective Study: Smart Phone Application for Measure Serum Bilirubin Through Sclera Images

A Prospective Study: A Computer Vision Model on a Smartphone Platform for Real-time Evaluation of Serum Bilirubin Through Sclera Images

The primary efficacy endpoints are the standard deviation and coefficient of determination (R2) between predicted and actual values for the bilirubin regression model, and the grading accuracy for the jaundice severity classification model. The secondary efficacy endpoint is the mean percentage error between predicted and actual bilirubin values. There are no relevant safety risks.

Statistical differences for categorical variables (e.g., jaundice grading evaluation indicators) will be analyzed using the chi-square test or Fisher's exact probability test. For continuous variables (e.g., bilirubin prediction evaluation indicators), t-tests (normal distribution) or non-parametric tests (non-normal distribution) will be used. The 95% confidence interval for jaundice grading accuracy will be calculated using the Wilson method.

The study duration is estimated to be 3 months.

Inclusion Criteria:

Age 14 years or older. Subjects who are visiting the Gastroenterology Department of Xijing Hospital and will undergo liver function tests on the same day. The disease spectrum of the subjects mainly includes pancreatitis, pancreatic tumors, hepatobiliary stones, biliary tumors, and colonic polyps.

Exclusion Criteria:

Subjects with diseases that may cause abnormal changes in scleral color, such as glaucoma, Wilson's disease, pterygium, or scleritis.

Subjects who have recently consumed a large amount of carotenoid-rich foods (such as oranges or carrots).

Subjects who are unable to provide informed consent.

Elimination Criteria:

Subjects with incomplete scleral exposure due to limited eye movement or excessive tension during external eye examination.

Subjects who are unable to understand the instructions for eye rotation during scleral examination or are unable to cooperate due to reasons such as poor hearing.