[ad_1]
A photo of a person’s inner eyelid taken with a standard smartphone camera can be used to screen for anemia, according to a new study.
Researchers in Rhode Island have developed an artificial intelligence (AI) powered model to analyze photos of the inside of people’s lower eyelids, known as the palpebral conjunctiva, which appears paler with anemia.
The technology could power an app that determines whether someone has anemia through smartphone photos, instead of blood tests, experts say.
Anemia, usually caused by a shortage of iron in your body, is a deficiency in the number or quality of red blood cells in your body.
Red blood cells contain hemoglobin, which carries oxygen – and without enough hemoglobin and oxygen, the skin can turn pale.
Scroll down for video
A photo of a person’s inner eyelid taken with a standard smartphone camera can be used to screen for anemia, researchers from Rhode Island report. In the photo is a photo of an eyelid conjunctiva used in the study
The condition affects about 5.6 percent of Americans and more than 25 percent of the world’s population.
This new study, led by Dr. Selim Suner of Brown University and Rhode Island Hospital in the United States, may provide a more accessible diagnostic method.
“Anemia, defined as a low concentration of hemoglobin, has a significant impact on the health of the world’s population,” say Dr. Suner and colleagues in their article.
The images show the hands of a person with severe anemia (bottom) due to loss of blood compared to the skin of a normal healthy individual (top)
“We describe the use of a ubiquitous device, the smartphone, to predict hemoglobin concentration and screen for anemia.”
Experts say anemia is a significant risk factor for death, especially in vulnerable populations such as children, the elderly and the chronically ill.
However, there is an “unmet need” for inexpensive, accessible, and non-invasive point-of-care tools for screening and diagnosing disease.
Previous studies have shown that the palpebral conjunctiva appears paler with anemia and is a more accurate indicator of the disease than a person’s palms or fingernails.
Using this knowledge, the researchers obtained smartphone images of the palpebral conjunctiva of 142 patients with a wide range of hemoglobin levels.
They zoomed in on a small region of the conjunctiva in each photo and developed a new algorithm to increase color resolution – the ability of each pixel to represent a wide variety of color tones.
They then developed a predictive model relating the color of the conjunctiva, compared to surrounding skin and the whites of the eyes, to hemoglobin levels.
Next, the researchers tested the new algorithms on photos collected from 202 new anemic patients.
Anemia is a condition in which you lack enough healthy red blood cells to carry enough oxygen to the tissues in your body (red blood cell stock image)
When analyzing the new set of photographs, the model was 72% accurate in detecting anemia, the team found.
The accuracy of the transfusion thresholds was higher, at 94.4 percent accuracy for a low transfusion threshold and 86 percent accuracy for a higher threshold.
“The transfusion threshold refers to the level of anemia that requires blood transfusion,” said Dr. Suner.
“Typically this is a hemoglobin level of 7.0 g / dL [grams per decilitre]. ‘
Skin tone did not change the results, although the quality of the image did have some effect.
The results suggest that a smartphone app could be used to screen for anemia in a telehealth or remote setting where blood tests are not available.
“Images of the vascular surface of the lower eyelid obtained by a smartphone camera can be used to estimate the concentration of hemoglobin in the blood and predict anemia which is a serious health problem that affects billions of people in the world. the world with a disproportionate effect in developing countries, ”say the authors.
“The use of non-invasive techniques to detect anemia opens the door to widespread screening, early diagnosis and treatment, especially in low-resource settings where access to health care is limited.”
The study was published in the open access journal PLOS One.
[ad_2]
Source link