Smartphone Photo App Can Detect Anemia in Children

A new study found that a non-invasive diagnosis test could be used to potentially predict the early onset of anemia in children using smartphone photos.

Anemia is a medical condition when the body does not produce enough healthy red blood cells, often leading to fatigue and frailty. Not having enough healthy blood cells leads to a lack of oxygen, often causing various symptoms, including dizziness, headaches, shortness of breath, and irregular heartbeat. It affects approximately two billion individuals worldwide and around 3 million in the United States.

The condition varies in severity, and milder cases can be alleviated by using vitamins, iron supplements, or medications. For more serious types of anemia, a blood transfusion or injections may be required.

Anemia in children can lead to serious developmental complications, such as cognitive impairment and vulnerability to infectious diseases. Anemia is most commonly caused by iron deficiency, but can also arrive through blood loss, malaria, and sickle-cell disease.

Detecting anemia requires a trip to the hospital or doctor's office as blood samples are needed. This can often cause health disparities, as not everyone has access to healthcare near them or adequate financial stability to visit the hospital.

The new method, initiated by researchers at the University College London and the University of Ghana, uses smartphone photos of people's eyes and faces. They formerly developed another app called neoSCB that discerns jaundice in newborns. This new non-invasive diagnostic test makes diagnosing anemia more accessible and cost-friendly.

The team targeted to develop a method that could use a simple smartphone photo to detect anemia by utilizing the light-absorption properties of hemoglobin. Light-absorption properties of hemoglobin transmit a specific hue, allowing scientists to identify the presence of anemia. The study recruited 62 children under four at the Korle Bu Teaching Hospital in Ghana.

Only 43 patients had photo qualities that met the standard and were used to detect the presence of anemia. Photographs included their eyes and lips, areas where pigmentation is scattered. The team utilized a Naive Bayes classifier to screen for anemia using a smartphone and no other tools.

The research team found out that targeting these areas to predict the hemoglobin concentration in blood allowed for the identification of anemia. The new method also identified milder anemia cases, which could be favorable in further research practice.

These findings contribute to the growing body of data indicating that smartphone colorimetry is probably a practical instrument for expanding access to anemia screening. There is still disagreement regarding the best technique for feature extraction from images, particularly regarding different patient groups.

First author Thomas Wemyss of UCL concludes: "Smartphones are globally popular, but research using smartphone imaging to diagnose diseases shows a general trend of experiencing difficulty when transferring results to different groups of people. We are excited to see these promising results in a group which is often underrepresented in research into smartphone diagnostics. An affordable and reliable technique to screen for anemia using a smartphone could drive long-term improvements in quality of life for a large amount of people."