acm-header
Sign In

Communications of the ACM

ACM TechNews

Crowd Diagnosis Could Spot Rare Diseases Doctors Miss


A crowd.

CrowdMed, a Web-based tool that uses crowdsourcing techniques to help solve difficult medical cases, is aimed at helping those who come down with any of about 7,000 rare diseases.

Credit: Shutterstock

CrowdMed is a Web-based tool that uses crowdsourcing techniques to help solve difficult medical cases. Participants receive points they can use to bet on the correct diagnosis from lists of suggestions.

CrowdMed creates a prediction market, with diagnoses falling and rising in value based on their popularity. Algorithms then calculate the probability that each diagnosis will be correct.

In 20 test cases, about 700 participants identified each of the mystery diseases as one of their top three suggestions.

The goal is to help people who come down with any of about 7,000 rare diseases as defined by health agencies in Europe and the United States. After the crowd reaches a consensus, CrowdMed gives the patient a list of the top three, which they can then explore with their physician.

Patients and doctors also can use FindZebra, a recently launched search engine for rare diseases. FindZebra enables users to search an index of rare disease databases, and has proven to produce more helpful results than Google on searches within the same dataset.

From New Scientist
View Full Article

 

Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA


 

No entries found