A team of biomedical engineers has created a smartphone app that could take the sting out of detecting anemia.

A condition characterized by weakness and fatigue due to a red blood cell (or hemoglobin) deficiency that impairs the body’s ability to carry oxygen to the tissues of the body, anemia is often detected in people by way of a blood test. Left untreated, the condition could lead to cardiac arrest in extreme cases.

The smartphone app developed by a team of biomedical engineers simply assesses photos of a person’s fingernails to determine if their red blood cell levels are low.

“All other ‘point-of-care’ anemia detection tools require external equipment, and represent trade-offs between invasiveness, cost, and accuracy,” said principal investigator Wilbur Lam, clinical hematologist-bioengineer at the Aflac Cancer and Blood Disorders Center of Children’s Healthcare of Atlanta, associate professor of pediatrics at Emory University School of Medicine and a faculty member in the Wallace H. Coulter Department of Biomedical Engineering at Georgia Tech. “This is a standalone app that can look at hemoglobin levels without the need to draw blood.”

The original author of the study, Rob Mannino, who was a Georgia Tech graduate research assistant in biomedical engineering but has since graduated, was inspired to develop the app based on his own experience with an inherited blood disorder called beta-thalassemia, which is the result of a mutation in the beta-globin gene.

“Treatment for my disease requires monthly blood transfusions,” Mannino said. “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. Instead, my doctors currently have to just estimate when I’m going to need a transfusion, based on my hemoglobin level trends.”

“This whole project couldn’t have been done by anyone but Rob,” Lam said. “He took pictures of himself before and after transfusions as his hemoglobin levels were changing, which enabled him to constantly refine and tweak his technology on himself in a very efficient manner. So essentially, he was his own perfect initial test subject with each iteration of the app.”

The biomedical engineers believe the app would be suitable for helping patients to self-manage their chronic anemia, enabling them to monitor the condition and to pinpoint times for adjusting their therapies or for receiving transfusions — potentially reducing the side effects of receiving transfusions either too early or too late.

Likewise, the technology might also prove useful for pregnant women, women with abnormal menstrual bleeding as well as for runners and athletes. Because its design is fairly simplistic, the app might also be appropriate for use in developing countries.

However, such diagnostic tools have strict requirements, but the team believes that with some additional work, the app could offer the accuracy necessary to become a painless alternative to standard blood-based anemia testing such as the measure of complete blood count (CBC), which is determined by way of a blood sample.

Looking at fingernail photos of 337 study participants (some of whom were healthy while others had anemia diagnoses), researchers established a connection between fingernail bed color and hemoglobin levels as measured by CBC.

Using an algorithm that converted fingernail color to blood hemoglobin levels, researchers were able to demonstrate that just one smartphone image could measure hemoglobin levels with an accuracy of 2.4 grams/deciliter (with sensitivity nearing 97%).

The team is continuing to calibrate the system and is working with a number of doctors from Children’s and Emory to gather even more data.

“This is just a snapshot of the accuracy right now,” Lam said. “The algorithm gets smarter with every patient enrolled.”

The research is published in the journal Nature Communications.