App Detecting Jaundice in Babies a Success in First Major Clinical Trial

A smartphone app that identifies severe jaundice in newborn babies by scanning their eyes could be a life-saver in areas that lack access to expensive screening devices, suggests a study co-authored by researchers at UCL (University College London) and the University of Ghana.

The app, called neoSCB, was developed by clinicians and engineers at UCL and was used to screen for jaundice in over 300 newborn babies in Ghana, following an initial pilot study on 37 newborns at University College London Hospital (UCLH) in 2020.

For the large-scale study, published in Paediatrics, the team tested over 300 babies with the app, which analyses images taken on a smartphone camera to quantify the yellowness of the white part of the eye (sclera) - a sign of neonatal jaundice. Analysing the yellowness of the eye just by looking is unreliable, and the neoSCB app can give early diagnosis of neonatal jaundice requiring treatment.

The study compared the effectiveness of the neoSCB app with conventional screening methods. Of the 336 babies tested by the app, 79 were severely jaundiced newborns, and the app correctly identified 74 of them. This is in line with the accuracy of the most common conventional screening method, a non-invasive device known as a transcutaneous bilirubinometer, which correctly identified 76.

The transcutaneous bilirubinometer works by measuring the yellow pigment under the newborn's skin to give a measure of jaundice levels. All screening results are then followed up by blood tests to determine the type of treatment required.

Dr Terence Leung (UCL Medical Physics & Biomedical Engineering) who developed the technology behind the app, said: "The study shows that the neoSCB app is as good as commercial devices currently recommended to screen for severely jaundiced newborns, but the app only requires a smartphone which costs less than a tenth of the commercial device. We hope that, once rolled out widely, our technology can be used to save the lives of newborns in parts of the world that lack access to expensive screening devices."

Study lead Dr Christabel Enweronu-Laryea (University of Ghana Medical School) said: "The neoSCB method was acceptable to mothers in urban and rural communities where the study was conducted. Mothers easily devised ways to keep the baby's eye open, most often by initiating breastfeeding."

Jaundice, where the skin and whites of the eye turn yellow, is common in newborns and is usually harmless. The yellowness is caused by a substance called bilirubin, which in severe cases can enter the brain, leading to death or disabilities such as hearing loss, neurological conditions such as athetoid cerebral palsy and developmental delays.

Every year severe jaundice causes about 114,000 newborn deaths and 178,000 cases of disability worldwide, despite it being a treatable condition. Most cases of neonatal jaundice occur in the first week after birth, and routine screening for early diagnosis in higher income countries has reduced the risks of severe complications.

Newborns in low- and middle-income countries are typically at a greater risk of severe jaundice, or neonatal hyperbilirubinemia, because of the lack of resources required for screening. A commercial transcutaneous bilirubinometer typically costs around £4,000 per device, and blood tests require a large amount of capacity. Additional factors such as a higher prevalence of home births and early postnatal discharge can contribute to fewer newborns going through screening.

Babies in sub-Saharan Africa are also at a greater risk because of a high prevalence of glucose-6-phosphate dehydrogenase (G6PD) deficiency, which is an inherited genetic disorder associated with an increased risk of haemolysis - where red blood cells break down at a faster rate than they are made - and hyperbilirubinemia.

Senior author Dr Judith Meek (UCLH) added: "This app has the potential to prevent death and disability worldwide in many different settings. It will reduce unnecessary hospital visits and potentially empower community health workers and parents to care for newborn babies safely."

In total, 724 newborns aged between 0 and 28 days were initially considered for the study. The 336 whose datasets were used for the paper had had no prior treatment for jaundice. Babies who were born at less than 35 weeks, were critically ill or had a very low birth weight were excluded from the final study. The app was tested with frontline healthcare workers and the babies’ mothers, who provided feedback on the usability of the app.

The study was supported by the Saving Lives at Birth consortium and the EPSRC UCL Centre for Doctoral Training in Intelligent Integrated Imaging in Healthcare.

Enweronu-Laryea C, Leung T, Outlaw F, Brako NO, Insaidoo G, Hagan-Seneadza NA, Ani-Amponsah M, Nixon-Hill M, Meek J.
Validating a Sclera-Based Smartphone Application for Screening Jaundiced Newborns in Ghana.
Pediatrics. 2022 Jun 3:e2021053600. doi: 10.1542/peds.2021-053600

Most Popular Now

Can Language Models Read the Genome? Thi…

The same class of artificial intelligence that made headlines coding software and passing the bar exam has learned to read a different kind of text - the genetic code. That code...

Bayer and Google Cloud to Accelerate Dev…

Bayer and Google Cloud announced a collaboration on the development of artificial intelligence (AI) solutions to support radiologists and ultimately better serve patients. As part of the collaboration, Bayer will...

Study Shows Human Medical Professionals …

When looking for medical information, people can use web search engines or large language models (LLMs) like ChatGPT-4 or Google Bard. However, these artificial intelligence (AI) tools have their limitations...

Shared Digital NHS Prescribing Record co…

Implementing a single shared digital prescribing record across the NHS in England could avoid nearly 1 million drug errors every year, stopping up to 16,000 fewer patients from being harmed...

North West Anglia Works with Clinisys to…

North West Anglia NHS Foundation Trust has replaced two, legacy laboratory information systems with a single instance of Clinisys WinPath. The trust, which serves a catchment of 800,000 patients in North...

Can AI Techniques Help Clinicians Assess…

Investigators have applied artificial intelligence (AI) techniques to gait analyses and medical records data to provide insights about individuals with leg fractures and aspects of their recovery. The study, published in...

AI Makes Retinal Imaging 100 Times Faste…

Researchers at the National Institutes of Health applied artificial intelligence (AI) to a technique that produces high-resolution images of cells in the eye. They report that with AI, imaging is...

SPARK TSL Acquires Sentean Group

SPARK TSL is acquiring Sentean Group, a Dutch company with a complementary background in hospital entertainment and communication, and bringing its Fusion Bedside platform for clinical and patient apps to...

Standing Up for Health Tech and SMEs: Sh…

AS the new chair of the health and social care council at techUK, Shane Tickell talked to Highland Marketing about his determination to support small and innovative companies, by having...

GPT-4 Matches Radiologists in Detecting …

Large language model GPT-4 matched the performance of radiologists in detecting errors in radiology reports, according to research published in Radiology, a journal of the Radiological Society of North America...

ChatGPT Extracts Data for Ischaemic Stro…

In an ischaemic stroke, an artery in the brain is blocked by blood clots and the brain cells can no longer be supplied with blood as a result. Doctors must...

Experts Propose Specific and Suited Guid…

Current Artificial Intelligence (AI) models for cancer treatment are trained and approved only for specific intended purposes. GMAI models, in contrast, can handle a wide range of medical data including...