Purdue researchers create a smartphone app to help assess anemia

Shane McGlaun - May 22, 2020, 8:24 am CDT
0
Purdue researchers create a smartphone app to help assess anemia

One of the methods that doctors use to diagnose the condition known as anemia is by looking at the person’s eyelid and judging its redness, which indicates the number of red blood cells. The challenge for doctors is that the simple test isn’t precise enough to give a diagnosis without drawing a blood sample from the patient. Researchers at Purdue University have developed software that could enable medical staff to take a picture of the inner eyelid of the patient using a smartphone and receive a near-accurate count of hemoglobin, a protein in red blood cells.

The team is currently working to embed the software into a mobile app that will allow the diagnostic software to run on a smartphone. Researchers believe that the app could help doctors diagnose and treat anemia earlier or allow the user to better manage the blood disorder from home.

The technology could also be used in developing countries to better treat patients when there is no infrastructure for blood tests. Researchers working on the project say the technology won’t replace a conventional blood test, but it does give a comparable hemoglobin count right away and is noninvasive. Using the software is near real-time as well, something important in the hospital setting if it might take a few hours to get the results of a blood test.

The software is a portable version of a commonly used technique called spectroscopic analysis that can detect hemoglobin by the way it absorbs visible light. Researchers developed an algorithm that uses an approach known as super-resolution spectroscopy to convert low-resolution smartphone photos to high-resolution digital spectral signals.

Another computational algorithm detects the signals and uses them to quantify blood hemoglobin content. Researchers say that the idea is to get a spectrum of colors using a simple photo. The smartphone app the team is working to develop wouldn’t require any extra hardware to detect and measure hemoglobin levels.


Must Read Bits & Bytes