Currently, the most accurate method of checking for anemia is to draw a blood sample and conduct a count of a patient's red blood cells, which contain iron-rich hemoglobin. Soon, however, a smartphone app may be able to non-invasively do the same job.
The experimental app was developed as part of the PhD work by Rob Mannino, a former biomedical engineering graduate student at Atlanta's Emory University. Mannino himself has an inherited blood disorder known as beta-thalassemia, which requires him to frequently get checked for anemia via complete blood counts (CBCs). If potentially-serious anemia is detected, then a transfusion is required.
"My doctors would test my hemoglobin levels more if they could, but it's a hassle for me to get to the hospital in between transfusions to receive this blood test," he says. "Instead, my doctors currently have to just estimate when I'm going to need a transfusion, based on my hemoglobin level trends."
Mannino's app could put an end to this problem, allowing patients to check their hemoglobin levels at home as often as they wish. It was developed by manually correlating fingernail-bed color with hemoglobin levels, based on photos of 337 peoples' fingers – all of those people had undergone CBC testing, so their levels were already known.
An algorithm was subsequently developed using 237 of those photos, incorporated into the app, and then tested on 100 of the participants. Without first being calibrated to each person, and based on a single smartphone photo of their fingernail bed, the app had an accuracy of plus or minus 2.4 grams per deciliter (as compared to CBC readings) when identifying which people were healthy and which were anemic.
When a personal calibration process was added, that rate improved to +/- 0.92 grams/deciliter, which is described as being "on par with point-of-care blood-based hemoglobin tests." For reference, normal hemoglobin levels sit at 13.5 to 17.5 grams/deciliter for males and 12.0 to 15.5 grams/deciliter for females.
Because fingernail beds don't contain melanin, the app should work on people with both light and dark skin. The technology also automatically compensates for background brightness, and should be compatible with a wide variety of phones. It is hoped that the app will be commercially available as of next spring (Northern Hemisphere).
A paper on the research, which was conducted under the supervision of Dr. Wilbur Lam, was recently published in the journal Nature Communications.
Source: Emory University
