Severe anemia often results from malnutrition, parasitic infections, or underlying diseases. It is a significant risk factor for death and morbidity, especially in
A recent study that appears in the open access journal
As healthcare professionals typically diagnose anemia through a complete blood count using sensitive lab equipment, there is a disproportionate occurrence of anemia in rural settings where people have inadequate access to healthcare.
According to the study authors, there is a need for an inexpensive, accessible, and noninvasive point-of-care tool capable of identifying anemia. The ideal tool would use preexisting, widely available technology.
Researchers conducted a two-phase study to assess the possibility of using a smartphone camera to aid in the detection of anemia. The first phase involved taking images of the inner lower eyelids of 142 patients in an emergency department using a smartphone.
The researchers selected the inner lower eyelid, called the palpebral conjunctiva, because it has the following unique features:
By zooming in on a small region in each photo, the researchers were able to develop an algorithm that maximizes color resolution and a predictive model comparing the skin and whites of the eyes to hemoglobin levels.
The second phase involved testing the algorithm on smartphone images of 202 different patients in the emergency department. The findings showed that the model was 72.6% accurate in predicting anemia. Its accuracy in predicting severe anemia that would necessitate a blood transfusion was higher, at between 86% and 94.4%.
Lead study author Dr. Selim Suner, of Brown University and Rhode Island Hospital, explained that following a diagnosis of anemia, people just need iron supplements, which are cheap and easy to take. “Making the diagnosis is the hard part,” Suner said.
Dr. Girish Nadkarni, clinical director of the Hasso Plattner Institute for Digital Health at Mount Sinai Health System, agrees. He commented, “Using a smartphone to screen for anemia is beneficial due to the decentralized nature of the screening — avoiding the need to draw blood — and the time and effort savings this entails.”
The results of the study showed that flash photography was not necessary to yield acceptable images for anemia detection. In addition, the authors write, “RAW images provide data directly from the camera sensor without the typical processing and compression that occurs with common formats, such as JPEG.”
Potential limitations that the researchers noted included variable image quality. However, this could have been due to the person retracting their eyelid during the recording of the image. Also, the lighting was not standardized, and it is unknown whether varying levels of brightness played a role in image quality.
In 2019, 36% of the world’s population used smartphones. Trends suggest that while affluent individuals are more likely to own smartphones, the use of these devices in lower socioeconomic regions is growing steadily worldwide.
“These results set the stage for the development of an application within a smartphone, which can not only acquire the image but also analyze the elements within the image to predict hemoglobin concentration in real time,” say the authors.
“This is an especially attractive opportunity for developing countries, which may have sparse, rudimentary, and poorly distributed medical systems but are well-interconnected by established telecommunication networks.”
Future development will center on the design of a user interface that makes it simple for the lay public to take a suitable photograph — one in which the lighting, focus, and area of interest are all optimized. The authors also note that imaging tools and further algorithm developments validated through model prediction are necessary.
According to Dr. Suner, this study indicates that anemia prediction using a smartphone is a viable concept. This project, and those to follow, could have a positive effect on large populations, contributing to health worldwide.