clock menu more-arrow no yes

Filed under:

Enlisting the help of gamers to count malaria parasites

New, 7 comments

Gamers enlisted to identify malaria

A study conducted by the Biomedical Image Technologies Group at the University Politécnica in Madrid has found that it may be possible to crowd-source malaria parasite identification by getting people to play games based on digital images of infected blood smears.

The study states that the current practice for estimating the severity of the disease consists of manually counting the number of the malaria parasites in blood smears through a microscope, a process that can take up to 20 minutes of an expert microscopist's time. This method, while effective, is time-consuming and is easily overwhelmed by the 600,000+ new cases of malaria reported daily worldwide.

The experiment conducted for the study attempted to see whether people who weren't trained in the field of science could identify malaria parasites in blood smears. The blood samples were digitized and coupled with a decision algorithm, which collected data on how the player performed. The game required players to find and tag as many parasites as possible in one minute.

Over one month, anonymous players from 95 countries played more than 12,000 games, generating more than 270,000 clicks. The study found that by combining the results from 22 games from non-expert players, they were able to achieve a parasite count with 99 percent accuracy.

The study concluded:

This research validates the online gaming approach for crowdsourced counting of malaria parasites in images of thick blood films. The findings support the conclusion that nonexperts are able to rapidly learn how to identify the typical features of malaria parasites in digitized thick blood samples and that combining the analyses of several users provides similar parasite counting accuracy rates as those of expert microscopists. This experiment illustrates the potential of the crowdsourced gaming approach for performing routine malaria parasite quantification, and more generally for solving biomedical image analysis problems, with future potential for telediagnosis related to global health challenges.