Your idea can become a change
You’ve been trying to make.
Let’s give it and you all possible
chances of success
AI | BLOCKCHAIN | MOBILE | TECHNOLOGY | WEB |
Not many of us would have imagined an App that would detect anaemia, more so through a non-invasive way.
Anaemia is a disorder that occurs with low haemoglobin levels in the blood. This causes severe fatigue, heart problems and other complications. People affected by anaemia are mostly pregnant women and children.
Anaemia is detected through blood samples tested using specialized testing equipment in labs measuring the haemoglobin levels through blood sampling. Researchers from the University of Georgia Tech and Emory University in Atlanta, USA finds that the disorder can be detected through a smartphone app.
Going through the previous studies it was proved that anaemia could be effectively detected through the pale appearance or the pallor of some parts of either the nails, palm or tongue. The authors have published their paper in the science journal, Nature Communications:
According to their observation, pallor is associated with anaemia, they have developed a method that quantitatively analyzes pallor in patient-sourced photos using image analysis algorithms to enable a non-invasive, accurate quantitative smartphone app for detecting anaemia.
The working of the app is based on an algorithm created by Wilbur Lam and his team at Emory University. The app detects the disorder by assessing the concentration of haemoglobin from the colour of people’s fingernail beds, using photos taken on a smartphone.
As nails don’t contain any dark pigment-producing cells that would mask its colour the fingernail colour is a good indicator of the blood’s haemoglobin levels because of our nails. Once the photograph is taken through the app, it uses the images obtained from the smartphone camera and then normalizes the background lighting conditions to accurately detect the actual paleness of the fingernail bed. This understandably is a technique missed in all previous non-invasive methods to detect anaemia.
Testing the app with around 337 people with a range of blood conditions, revealed that the app outperformed physicians in testing the haemoglobin levels through a physical examination.
Though the app-based method could not meet the standards of a blood test, it was found to be better than a number of other approved diagnostic tools available in the market today.
The researchers believe that the app should be used only for screening, and for diagnosis. But they also said that with more research, the app could provide the accuracy it requires to replace blood-based testing methods for a clinical diagnosis of anaemia.
The app can help anaemic patients manage themselves by monitoring their disease and diagnosing through the required therapies. Anaemia is easy to treat once it is detected. It will be interesting to see how people benefit from this app once it becomes operational.
With AI and Machine learning advancing to next levels smartphone based diagnosis is not far from becoming a reality.