Smartphone cameras may help assess anemia using new app
Researchers at Purdue University (IN, USA) have developed a program that can assess a patient’s hemoglobin level by taking a photo of their inner eyelid. The software could supplement blood tests as a less invasive and faster means of diagnosis for blood disorders.
A team of researchers and engineers at Purdue University (IN, USA) has developed software that uses an image of a patient’s inner eyelid to give a blood hemoglobin count using spectroscopic analysis. Published in Optica, the team employed super-resolution spectroscopy, which converts low-resolution smartphone photos into high-resolution digital signals. These signals show the absorption of visible light by hemoglobin, allowing its level to be quantified.
Conventionally, anemic patients may be identified by doctors looking at how red their inner eyelid is, but a blood test would be needed to confirm any blood conditions. One of the study’s authors, Young Kim (Purdue University), commented: “This technology won’t replace a conventional blood test, but it gives a comparable hemoglobin count right away and is non-invasive and real-time… Depending on the hospital setting, it can take a few hours to get results from a blood test. Some situations also may require multiple blood tests, which lead to more blood loss.”
You may also be interested in:
- Wearable fitness trackers could improve real-time flu surveillance
- Look behind the lecture: innovations derived from PROs
- Wearables pave way for reimagined clinical trials
Supplementing blood tests in this way could be vital, for example, in detecting hemorrhage in patients following traumatic injuries or for clinics without the infrastructure to regularly carry out blood tests. The authors are now working on embedding the software into a mobile app, which could help people with blood disorders manage their condition from home. While several smartphone-based anemia detection technologies are available, they generally lack enough validation to be reliable in clinical settings.
The new software was developed based on data from a study of 153 patients referred for conventional blood tests at the Moi University Teaching and Referral Hospital in Kenya. Each patient undergoing a blood test also had a picture of their inner eyelid taken. These images were then used to train the algorithm to extract information from smartphone photos, which could be compared to the results of the blood tests.
The app will include features to stabilize smartphone images and use the flash consistently. It also provides a guide for the placement of the patient’s inner eyelid in the frame. The researchers chose the inner eyelid as the area to photograph because it does not contain melanocytes, which produce the light-absorbing pigment melanin. This means that the software can use the light absorption by hemoglobin without the interference of differing melanin levels. “The app also wouldn’t be thrown off by skin color. This means that we can easily get robust results without any personal calibrations,” explained Sang Mok Park (Purdue University), the study’s lead author.
The study demonstrated that while the application will require larger clinical studies and usability tests, the software and the use of super-resolution spectroscopy were sufficiently supported to warrant their use for non-invasive blood hemoglobin measurements. The authors highlighted the potential for the app’s use in resource-limited healthcare services and in patients’ own homes.
Park SM, Visbal-Onufrak MA, Haque M et al. mHealth spectroscopy of blood hemoglobin with spectral super-resolution. Optica. 7(6): 563–573 (2020); www.purdue.edu/newsroom/releases/2020/Q2/smartphone-app-to-help-assess-anemia-by-taking-a-picture-of-a-persons-eyelid.html