Outlaw, Felix;
(2021)
Screening for Neonatal Jaundice by Smartphone Sclera Imaging.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Outlaw_2021__PhD_Thesis__Screening_for_Neonatal_Jaundice.pdf Download (28MB) | Preview |
Abstract
Jaundice is observed in over 60% of neonates and must be carefully monitored. Ifsevere cases go unnoticed, death or permanent disability can result. Neonatal jaun-dice causes 100,000 deaths yearly, with low-income countries in Africa and SouthAsia particularly affected. There is an unmet need for an accessible and objectivescreening method. This thesis proposes a smartphone camera-based method forscreening based on quantification of yellow discolouration in the sclera.The primary aim is to develop and test an app to screen for neonatal jaundicethat requires only the smartphone itself. To this end, a novel ambient subtractionmethod is proposed and validated, with less dependence on external hardware orcolour cards than previous app-based methods. Another aim is to investigate thebenefits of screening via the sclera. An existing dataset of newborn sclera images(n=87) is used to show that sclera chromaticity can predict jaundice severity.The neoSCB app is developed to predict total serum bilirubin (TSB) fromambient-subtracted sclera chromaticity via a flash/ no-flash image pair. A studyis conducted in Accra, Ghana to evaluate the app. With 847 capture sessions, thisis the largest study on image-based jaundice detection to date. A model trained onsclera chromaticity is found to be more accurate than one based on skin. The modelis validated on an independent dataset collected at UCLH (n=38).The neoSCB app has a sensitivity of 100% and a specificity of 76% in iden-tifying neonates with TSB≥250μmol/L (n=179). This is equivalent to the TcB(JM-105) data collected concurrently, and as good as the best-performing app in theliterature (BiliCam). Following a one-time calibration, neoSCB works without spe-cialist equipment, which could help widen access to effective jaundice screening.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Screening for Neonatal Jaundice by Smartphone Sclera Imaging |
| Event: | UCL (University College London) |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2021. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10134694 |
Archive Staff Only
 |
View Item |
