Experiences with Web Search on Medical Concerns and Self有网络搜索的医疗问题和自我的经验.pptxVIP

Experiences with Web Search on Medical Concerns and Self Diagnosis Ryen W. White PhD and Eric Horvitz MD, PhD Microsoft Research {ryenw, horvitz}@ Outline Motivation Online Medical Search Cyberchondria Study Research Questions Methodology Findings Undiagnosed Conditions Diagnosed Conditions Implications Online Medical Search Healthcare websites for worried well Provide valuable information, address concerns, etc. 80% US adults use search engines to find medical info 75% don’t verify quality (validity, date, etc.) Problem: Search engines for diagnostic reasoning Link to pages with alarming content More written about serious than benign explanations Ranking algorithms use click logs; reinforce alarming pages Online Medical Search Challenge: Linking to troubling scenarios in absence of likelihood information Consumers seek confirmation and disconfirmation Search engines relied upon for quality information but perform information retrieval rather than diagnosis Likelihood information not considered in ranking of lists Influence of signs symptoms on likelihoods not provided Search engines suffer from fuel biases of judgment: base-rate neglect, availability, confirmation Cyberchondria Unfounded escalation of concerns about common symptomology based on review of search results and literature online ? Query search engine for [headache] ? Review results ? Browse Web pages ? Query for [brain tumor] – Medical anxiety ? Query for [caffeine withdrawal] Previous log analyses - cyberchondria common; lacked qualitative data headache brain tumor caffeine withdrawal Study: Overview Objectives Survey of experiences with Web use for self diagnosis Considered diagnosed undiagnosed conditions Research Questions: What are characteristics of Web-based medical diagnosis? Are these characteristics associated with age or gender? What are key dependencies among characteristics? Prior studies have not answered these questions