Paul A Kudlow*, University of Toronto, Toronto, Canada Gunther Eysenbach*, University of Toronto, Toronto, Canada Track: Business Presentation Topic: Mobile & Tablet Health Applications Presentation Type: Startup Pitch Submission Type: Single Presentation Building: Mermaid Room: Main Auditorium Date: 2013-09-23 02:00 PM – 03:30 PM Last modified: 2013-09-25

If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL).

With over 2000 new publications added to the PubMed database daily, it is becoming almost impossible to keep up-to- date with new biomedical literature. Conventional methods of browsing through high-impact, and specialty specific journals simply don’t work; research indicates health professionals miss 50%, or more, of articles relevant to their specialty. Initiating searches for articles, which lack focus, often result in thousands inappropriate “hits.”

trendMD (www.trendmd.com) is a medical trending engine that enables physicians, medical students, clinical researchers, and possibly the public to keep up-to-date with new publications. It is a web-application that is designed to instantly deliver personalized, high-impact research articles. Instead of getting hundreds/thousands of articles per query, users get much fewer, higher impact publications, most relevant to one’s specialty needs.

We do so by “cleaning” the PubMed database with clinical and specialty specific filters. Our filters are rigorously tested against hand-selection and have been optimized to filter out >95% of non-applicable articles. Applying filters allows us to organize and substantially reduce the “noise” in the PubMed database.

Once filtered, trendMD ranks publications based on a series of journal and article-level metrics. Currently, our ranking system is built on three metrics: time, journal impact factor, and aggregate level social media citations. While in preliminary stages, early research completed by Dr. Eysenbach suggests that highly tweeted articles were 11 times more likely to be highly cited. Additionally, top-cited articles were predicted from top-tweeted articles with 93% specificity and 75% sensitivity (J Med Internet Res 2011;13(4):e123). In short, preliminary data suggests that aggregate social media metrics can be used as an early and reliable proxy for future citations. Dr. Eysenbach named this metric – “Twimpact factor” and this forms the core of our article ranking metrics at trendMD.

trendMD was founded in 2013 by physicians looking for an easier way to keep up. The solution is trendMD; our goal is to keep you current and save you time.