Researchers develop mobile app to non-invasively detect and screen anaemia

The researchers studied fingernail photos and correlated the colour of the fingernail beds with hemoglobin levels to develop the apps algorithm

Researchers of Emory University in US have developed a smartphone app that can detect anaemia accurately and non-invasively. Instead of a blood test, the app uses photos of a person's fingernails taken on a smartphone to accurately measure how much hemoglobin is in their blood.

"All other 'point-of-care' anaemia detection tools require external equipment, and represent trade-offs between invasiveness, cost, and accuracy," said Wilbur Lam, principal investigator of the study appearing in the journal Nature Communications.

"This is a stand-alone app whose accuracy is on par with currently available point-of-care tests without the need to draw blood," said Lam.

The app could facilitate self-management by patients with chronic anaemia, allowing them to monitor their disease and to identify the times when they need to adjust their therapies or receive transfusions.

This could possibly reduce the side effects or complications of having transfusions too early or too late, said Rob Mannino, a former graduate student at Emory University, who worked on the app as part of his PhD.

The researchers said that the app should be used for screening and not clinical diagnosis. The technology could be used by anyone at any time. The app could be of great help for runners or athletes, pregnant women as well as women with abnormal menstrual bleeding.

Anaemia is a blood condition that affects two billion people worldwide and can lead to fatigue, paleness and cardiac distress if left untreated.

Complete blood count (CBC) is considered as the gold standard of anaemia diagonosis. The researchers studied fingernail photos and correlated the colour of the fingernail beds with hemoglobin levels measured by CBC in 337 people, which included a mixture of healthy as well as anaemic people.

The algorithm for converting fingernail colour to blood hemoglobin level was developed with 237 of these subjects and then tested on 100.

A single smartphone image can measure hemoglobin level with an accuracy of 2.4 grammes/decilitre with a sensitivity of up to 97 per cent, researchers said.

In the app, the use of fingernail beds, which do not contain melanin, means the test can be valid for people with a variety of skin tones, the developers said.

The app uses image metadata to adjust background brightness, and can be adapted to phones from multiple manufacturers. While clinical diagnostic tools have strict accuracy requirements, but researchers think that with additional research, they can eventually achieve the accuracy needed to replace blood-based anaemia testing for clinical diagnosis.