Online Crowdsourcing Game Could Improve Diagnosis of Malaria

TOPIC ALERT:

A team of researchers from the University of California-Los Angeles have created an online game designed to use crowdsourcing techniques to improve malaria diagnoses, Healthcare IT News reports (Miliard, Healthcare IT News, 5/3).

Playing the Game

The no-cost game can be played by anyone around the world who has access to a computing device, such as a smartphone or a personal computer.

Before the game, players receive a brief online tutorial that uses sample images to explain what a malaria-infected red blood cell looks like.

During the game, players view a screen containing several digital images of healthy and infected red blood cells. The players then use a "syringe" tool to "kill" the infected cells.

For a certain percentage of the cell images displayed, the computer knows whether the cell is healthy or infected. By evaluating the player's performance on these control images, the game is able to estimate the player's accuracy in diagnosing the cells with an unknown status (Mearian, Computerworld, 5/4).

Preliminary Findings

The UCLA researchers recruited a small group of nonexperts -- consisting primarily of undergraduate volunteers -- to play the online game.

They found that the nonexperts collectively were able to diagnose malaria-infected red blood cells with an accuracy that was within 1.25% of the diagnostic decisions made by trained medical professionals.

Aydogan Ozcan -- an associate professor of electrical engineering and bioengineering at UCLA and author of the study -- said, "The idea is, if you carefully combine the decisions of people -- even nonexperts -- they become very competitive." He added, "Also, if you just look at one person's response, it may be OK, but that one person will inevitably make some mistakes. But if you combine 10 to 20, maybe 50 nonexpert gamers together, you improve your accuracy greatly in terms of analysis."

According to Healthcare IT News, training hundreds of individuals to identify malaria-infected cells could be a low-cost way to improve the number and accuracy of malaria diagnoses made (Healthcare IT News, 5/3).


to share your thoughts on this article.