It would be possible to detect anemia using a simple photo from a smartphone. This is the conclusion of a new scientific study, published on July 14, 2021 in the journal Plos One.
Believing that there is a lack of practical and accessible tools to detect anemia, even though this pathology affects more than 25% of the world population, a team of researchers from Brown University and Rhode Island Hospital (United States) United) set to work.
Previous studies have shown that the inside of the lower eyelid, an area called the palpebral conjunctiva, is paler in case of anemia, characterized by a low level of hemoglobin (red blood cells) in the blood.
The researchers therefore developed an algorithm capable of identifying anemia thanks to a photo of this specific part of the eye. To do this, they obtained smartphone images of the palpebral conjunctiva of 142 patients with a wide range of blood hemoglobin levels. The device-related the color of the conjunctiva to hemoglobin levels after the color was compared to that of the surrounding skin and the white of the eye.
Secondly, the team tested its algorithm on photos collected from 202 new patients.
Results: the model developed made it possible to detect anemia in 72.6% of cases, with an accuracy of 72.8% and a specificity of 72.5%. While the skin tone did not change the results, the image quality did have some effect.
For the researchers, these results suggest that a smartphone app could be used to screen for anemia in a telehealth setting or remotely when it is not possible to do a blood test.
In the same way that screening tools and applications are developed to have a mole or other skin problems analyzed, we could therefore imagine an application to detect anemia, and then direct the user to appropriate medical advice. to the result, and to carry out more in-depth analyzes.