Researchers from UCLA’s School of Engineering and Applied Science and the School of Medicine have designed a system that can harness distant groups of people to analyze pathology images for signs of disease. They tested the ability of non-professionals to quickly learn to detect malaria when looking at images of red blood cells and have shown that if necessary, with a bit of help from online crowds, large groups of people can potentially be screened for the disease.
The system they built relies on video gaming to attract people to do the visual tasks necessary to spot malaria. The study subjects, mostly untrained newbie undergrads, showed a spotting ability that was within 1.25 percent of medical professionals.
Results from the study info page:
We have shown that by utilizing the innate visual recognition and learning capabilities of human crowds it is possible to conduct reliable microscopic analysis of biomedical samples and make diagnostics decisions based on crowd-sourcing of microscopic data through intelligently designed and entertaining games that are interfaced with artificial learning and processing back-ends. We demonstrated that in the case of binary diagnostics decisions (e.g., infected vs. uninfected), using crowd-sourced games it is possible to approach the accuracy of medical experts in making such diagnoses.
Specifically, using non-professional gamers we report diagnosis of malaria infected red-blood-cells with an accuracy that is within 1.25% of the diagnostic decisions made by a trained professional.