Cited 0 times in Scipus Cited Count

Deep-learning-based smartphone application for self-diagnosis of scleral jaundice in patients with hepatobiliary and pancreatic diseases

Authors
Park, JH | Yang, MJ  | Kim, JS | Park, B  | Kim, JH  | Sunwoo, MH
Citation
Journal of personalized medicine, 11(9). : 928-928, 2021
Journal Title
Journal of personalized medicine
ISSN
2075-4426
Abstract
Outpatient detection of total bilirubin levels should be performed regularly to monitor the recurrence of jaundice in hepatobiliary and pancreatic disease patients. However, frequent hospital visits for blood testing are burdensome for patients with poor medical conditions. This study validates a novel deep-learning-based smartphone application for the self-diagnosis of scleral jaundice in such patients. The system predicts total serum bilirubin levels using the deep-learning-based regression analysis of scleral photos taken by the smartphone’s built-in camera. Enrolled patients were randomly assigned to either the training cohort (n = 90, 1034 photos) or the valida-tion cohort (n = 40, 426 photos). The intraclass correlation coefficient value for predicted serum total bilirubin (PSB) derived from the images repeatedly taken at the same time for the same patient showed good reliability (0.86). A strong correlation between measured serum total bilirubin (MSB) and PSB was observed in the subgroup with MSB levels ≥1.5 mg/dL (Spearman rho = 0.70, p < 0.001). The receiver operating characteristic curve for PSB showed that the area under the curve was 0.93, demonstrating good test performance as a predictor of hyperbilirubinemia (p < 0.001). Using a cut-off PSB ≥1.5, the prediction sensitivity of hyperbilirubinemia was 80.0%, with a specificity of 92.6%. Hence, the tool is effective for patient monitoring.
Keywords

DOI
10.3390/jpm11090928
PMID
34575705
Appears in Collections:
Journal Papers > School of Medicine / Graduate School of Medicine > Gastroenterology
Journal Papers > School of Medicine / Graduate School of Medicine > Biomedical Informatics
Ajou Authors
김, 진홍  |  박, 범희  |  양, 민재
Full Text Link
Files in This Item:
34575705.pdfDownload
Export

qrcode

해당 아이템을 이메일로 공유하기 원하시면 인증을 거치시기 바랍니다.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse