Researchers from the University of Washington (DC, USA) have developed an app that measures hemoglobin and screens for anemia in patients. The new non-invasive technology utilizes a smartphone camera to estimate the concentration of hemoglobin by analyzing color absorption and reflection.
Measuring haemoglobin concentrations is particularly important in diagnosing anemia and determining whether patients need blood transfusions in blood disorders such as leukemia.
Current methods of measuring hemoglobin include invasively drawing blood via a needle or using costly specialized devices that measure haemoglobin levels non-invasively.
The newly developed device overcomes shortcomings of cost and patient discomfort of existing methods.
Termed the HemaApp, the app utilizes light from the camera flash combined with algorithms to analyze the color of the patient’s blood providing an estimate of haemoglobin levels.
The app was recently presented at the Association for Computing Machinery’s 2016 International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2016) in Germany.
Demonstrated in a trial consisting of 31 patients, HemaApp was compared with an existing FDA approved non-invasive device named Masimo Pronto. In this study, the developers were able to demonstrate HemaApp worked as well as Masimo Pronto, but was less expensive and more pragmatic, factors valuable in developing countries.
Lead author and UW doctoral student Edward Wang commented: “In developing countries, community health workers have so much specialized equipment to monitor different conditions that they literally have whole bags full of devices. We are trying to make these screening tools work on one ubiquitous platform — a smartphone.”
The team tested the app in three different contexts: utilizing the smartphone camera’s flash only, camera flash combined with an incandescent lightbulb, and finally camera flash plus an LED lighting add-on.
Of the three scenarios, the LED lighting attachment produced the highest correlation – 82% – to a patient’s complete blood count (CDC). This was followed by the incandescent light bulb at 74%, and lastly the smartphone camera alone at 69%.
In the case of anemia, HemaApp identified anemia 86% of the time when assisted with additional light sources, and 79% using the phone camera flash alone.
The additional light sources provide exposure to other parts of the electromagnetic spectrum that have valuable absorption properties presently not found on all smartphones.
Although the app will not replace standard blood tests, which are still the most accurate method of measuring haemoglobin, initial test indicate that HemaApp is a more effective and inexpensive approach, especially when determining whether further blood testing is required.
Terry Gernsheimer, a fellow researcher added: “Every time we draw blood, we are invading the patient in some way, shape or form. If we don’t already have a line in, we are sticking a needle into their arm, which involves discomfort and infection risk, albeit low.
“It would be really nice to not have to perform a procedure every time we want to answer that question.”
The next steps for the team include improving the apps accuracy and finding further applications in other blood disorders including sickle cell disease and more.
“We’re just starting to scratch the surface here,” added senior author Shwetak Patel. “There’s a lot that we want to tackle in using phones for non-invasively screening disease.”