Science & Technology, UK (Commonwealth Union) – In a pioneering research collaboration between the University College London (UCL) and the Royal Free Hospital, a smartphone camera has demonstrated the ability to identify changes in skin tone and eye color that warrant medical attention. The study, featured in PLOS Digital Health, represents the first investigation into how smartphone images of the forehead, the whites of the eyes, and the lower eyelid can effectively predict bilirubin levels in patients with advanced cirrhosis. The study determined that images of the whites of the eyes offered the most accurate means of estimating bilirubin levels from a photograph.
This breakthrough approach holds the potential to revolutionize the monitoring of cirrhosis patients in a cost-effective and user-friendly manner compared to current methods. It is anticipated that this innovation will enable the early detection of worsening symptoms before they become critical, streamlining healthcare workflows.
Liver disease ranks as the third most common cause of premature death among working-age individuals in the UK. While significant progress has been made in reducing mortality rates for various chronic conditions, the mortality rate for liver disease in the UK surged by 400% from 1970 to 2010. This has underscored the need for non-invasive and cost-effective techniques to monitor the progression of cirrhosis.
Bilirubin, a yellow pigment that becomes visible in the skin or eyes, serves as an indicator of impaired liver function, a condition commonly referred to as jaundice. In patients with advanced cirrhosis, the skin and eyes tend to exhibit a more pronounced yellow hue as bilirubin concentrations in the blood rise.
Presently, bilirubin levels are assessed through a blood test conducted by healthcare professionals in clinical settings. Any elevation in these levels signifies a further decline in the patient’s liver function, necessitating medical intervention.
In this study, researchers developed a smartphone application capable of accurately detecting the severity of jaundice. They used a smartphone to capture images of the forehead, the whites of the eyes, and the lower eyelid in 66 cirrhosis patients. After adjusting the images for variations in lighting conditions, they were analyzed and utilized to train an algorithm capable of predicting bilirubin levels based on the degree of yellowness in the images.
When these predictions were compared to data from blood tests, it was evident that images of the whites of the eyes yielded the strongest correlation.
Professor Raj Mookerjee, affiliated with UCL Medicine and a co-author of the study, explains that liver disease presents a unique challenge because patients can experience rapid deterioration. Sadly, when a patient arrives at the clinic significantly more jaundiced than before, it often indicates that their disease has already advanced significantly. The method evaluated in this study has the potential to enable us to monitor patients in their own homes more frequently than current practices permit. This increased monitoring frequency can hopefully facilitate the early detection of deteriorating clinical signs and symptoms before they reach a critical stage.
“You can look at a patient and tell if they have jaundice right away. But it’s a not a question of if the skin looks yellow or not, it’s about how much more yellow it looks, which gives you an indication of how badly the liver function has deteriorated,” added Professor Mookerjee. “The smartphone app gives us this degree of accuracy. It’s a remarkable feat of engineering and shows the power of clinicians and engineers collaborating to solve urgent healthcare problems.”
Researchers pointed out that the subsequent phase entails conducting a larger trial to confirm the safety and precision of this approach. In practical terms, this method would likely involve patients regularly capturing images of their eyes through a mobile app. These images would then alert healthcare providers to significant changes in bilirubin levels that might necessitate adjustments in patient care.
