PROVIDENCE, R.I. — Smartphones could soon be used to diagnose the most common blood disorder, saving billions of people time and pain. An algorithm can determine whether someone is suffering from anemia simply by looking at a photograph taken on a modern phone, according to a new study.
Anemia, a condition where people do not have enough healthy red blood cells to carry oxygen to the body’s tissues, affects around a third of the world’s population. Left untreated, it can cause many health problems, including severe fatigue, pregnancy complications, and heart problems, as well as increasing the chances of death among children, the elderly, and the chronically ill.
Often the only way for people to check whether they have anemia is to take a blood test at a clinic or hospital, although finger-prick home-kits are available. But now, researchers at Brown University have developed a solution that needs no needles and can be carried out from the comfort of a patient’s home. This could especially benefit people living in isolated rural areas and countries where access to healthcare services is limited.
“Images of the lower eyelid’s vascular surface obtained by a smartphone camera can be utilized to estimate blood hemoglobin concentration and predict anemia, which is a serious health condition afflicting billions of people worldwide with a disproportionate effect in developing countries. There is an unmet need for inexpensive, accessible, and non-invasive point-of-care tools to screen for and diagnose anemia,” says study-author Dr. Selim Suner in a statement.
Around 15 percent of women aged between 15 and 49 suffer from anemia, as well as 12 percent of children under five. When a person develops the condition, a part of their lower eyelid called the palpebral conjunctiva appears paler, previous studies have found.
Smartphone images of the affected eye region were collected for 142 patients who had a wide range of red blood cells. In each photo, the researchers zoomed in on a small region of the conjunctiva and developed an algorithm that compared the area’s color with that of its surrounding skin and the whites of the eye. The tool was then tested on 202 new patients, accurately diagnosing anemia in over 70 percent of cases, the researchers found. It was also able to predict when patients required a blood transfusion 85 percent of the time.
While a person’s skin tone did not change the results, the algorithm did not perform as well with images of poorer quality. A smartphone app could therefore be used to screen for anemia, instead of patients having to take a blood test, the researchers say.
This also means testing for the condition could be done at home rather than at a hospital or a clinic. “Utilization of non-invasive techniques to detect anemia opens the door to widespread screening, early diagnosis, and treatment, particularly in low resource settings where access to healthcare is sparse,” notes Dr. Suner.
The findings are published in the journal PLOS ONE.
SWNS writer Tom Campbell contributed to this report.