Anemia affects more than 2 billion people worldwide, and a new smartphone app may help diagnose anemia using photos. Researchers in Atlanta have developed a smartphone app that estimates hemoglobin (Hb) levels by using patient-sourced photos of fingernail beds lacking melanin. By analyzing the color and metadata of these photos, the Hb level can be determined with a greater accuracy than current non-invasive anemia screening methods. Compared to Hb levels measured by a complete blood count (CBC) in 100 subjects, the new app was able to detect Hb levels with an accuracy of +2.4 g/dL and a sensitivity of 97% (95% CI, 89%-100%); personalized calibration techniques can be used to further improve the accuracy of the app. This non-invasive method to diagnose and screen for anemia does not require additional equipment aside from ubiquitous smartphones. The new app could also help reduce burdens and costs of Hb screening for patients at risk for anemia or those with chronic conditions requiring continual monitoring.
Reference:
