Files in this item



application/pdf132_ready.pdf (1MB)
(no description provided)PDF


Title:Is there a Doctor in the Crowd? Diagnosis Needed! (for less than $5)
Author(s):Cheng, James; Manoharan, Monisha; Zhang, Yan; Lease, Matthew
Subject(s):health informtics
information technology and work
distributed work
Abstract:We investigate the feasibility of crowd-based medical diagnosis by posting medical cases on a variety of crowdsourcing platforms: general and specialized volunteer question answering sites, and pay-based Mechanical Turk (MTurk) and oDesk. To assess the crowd’s ability to diagnose cases of varying difficulty, three sets of medical cases are considered. While volunteer channels proved ineffective for us, we discuss design limitations and opportunities for improvement. In contrast, Mechanical Turk workers without medical training not only correctly diagnosed easy cases, but also a previously unsolved case from CrowdMed involving extensive patient details. Likely due to varying expertise, MTurk workers and oDesk health professionals also differed in their willingness to provide uncertain diagnoses, diagnosis rationales, and reliance on personal experience with a disease to diagnose it.
Issue Date:2015-03-15
Series/Report:iConference 2015 Proceedings
Genre:Conference Paper/Presentation
Peer Reviewed:yes
Rights Information:Copyright 2015 is held by the authors. Copyright permissions, when appropriate, must be obtained directly from the authors.
Date Available in IDEALS:2015-03-24

This item appears in the following Collection(s)

Item Statistics