Simple, non-invasive testing of hemoglobin in blood with smartphone-app

13 September 2016
In this particular case the smartphone is used to measure hemoglobin within blood. These kinds of measurements  helps to diagnose and manage a number of conditions, but this requires either blood draws or expensive pulse oximeters. The researchers, led by Edward Jay Wang, wanted to find out if a cheaper and less invasive method is available with current everyday technology. They have developed an app called HemaApp that uses the phone’s built-in light and camera to detect the color intensity of blood passing through a finger. The user simply places a finger over the camera lens, making a solid contact, and runs the app to do its thing. The app turns on the nearby LED light, which shines light through the finger, and uses the camera to detect specific features that point to the amount of hemoglobin. Though the built-in light is not too bad, the team also tested the app using a nearby incandescent bulb in addition to the camera light, as well as with the help of a small accessory light attached to the phone. In their small study on 31 patients, the HemaApp with the attached light accessory was as accurate (82%) as Masimo’s Pronto (81%) in estimating hemoglobin count. The app without any accessories, and relying only on its own light, had an accuracy of 69%, which is pretty impressive as well.

Explained by the research team

HemaApp is a smartphone application that noninvasively monitors blood hemoglobin concentration using the smartphone’s camera and various lighting sources. Hemoglobin measurement is a standard clinical tool commonly used for screening anemia and assessing a patient’s response to iron supplement treatments. Given a light source shining through a patient’s finger, we perform a chromatic analysis, analysing the color of their blood to estimate hemoglobin level.  We evaluate HemaApp on 31 patients ranging from 6 – 77 years of age, yielding a 0.82 rank order correlation with the gold standard blood test. In screening for anemia, HemaApp achieve a sensitivity and precision of 85.7% and 76.5%. Both the regression and classification performance compares favorably with our control, an FDA-approved noninvasive hemoglobin measurement device. We also evaluate and discuss the effect of using different kinds of lighting sources.