NLM hosted a Pill Image Recognition Challenge as part of its research and development in Computational Photography Project for Pill Identification (C3PI). The Challenge asked for submissions from teams that will contribute to the creation of a software system that can match photos taken by a smartphone to the NLM RxIMAGE database of high-resolution prescription pill images. This can give consumers a simple way to recognize mystery pills, help prevent unnecessary medication errors, and reduce waste by identifying pills that might otherwise be discarded.

The need for a pill image recognition tool is more important today than ever before. More Americans than ever take prescription pills and take more of them. Almost 60% of adults took prescription pills in 2012, up from 50% in 2000. And 15% of adults took 5 or more prescription pills in 2012, up from 10% in 2000. Trends in prescription pill use showed increases for statins, antidepressants, and to treat high blood pressure. [1]

Americans' increase in pill use and the challenges of managing that use are also seen in the 44% increase in calls to U.S. poison control centers from 2003 to 2007, with the majority of that increase traced to questions about "pill identification." Calls from the public and the police doubled in that time period, while calls from healthcare facilities decreased, highlighting the need for a tool that the public can use to identify pills. [2]

The pharmaceutical industry has responded to the increased use and cost of prescription pills by offering both brand-name and often cheaper generic pills. Generic pills now make up 70% of the total number of U.S. pill prescriptions. The choices multiply from there, with each generic pill manufacturer selling a pharmacologically equivalent pill in a different shape, color, and size. [3]

The Pill Image Recognition Challenge responds to the increase in prescription pill use, the increased need for prescription pill management, and the attendant challenges the public faces in the changing look of prescription pills.

Listen to Michael J. Ackerman, lead, Pill Image Recognition Challenge talk about what led to the Challenge:

[1] Kantor ED, Rehm CD, Haas JS, Chan AT, Giovannucci EL. Trends in Prescription Drug Use Among Adults in the United States From 1999-2012. JAMA. 2015 Nov 3;314(17):1818-31. doi: 10.1001/jama.2015.13766. PubMed PMID: 26529160; PubMed Central PMCID: PMC4752169.

[2] Spiller HA, Griffith JR. Increasing burden of pill identification requests to US Poison Centers. Clin Toxicol (Phila). 2009 Mar;47(3):253-5. doi:10.1080/15563650902754877. PubMed PMID: 19225960.

[3] Greene JA, Kesselheim AS. Why do the same drugs look different? Pills, trade dress, and public health. N Engl J Med. 2011 Jul 7;365(1):83-9. doi:10.1056/NEJMhle1101722. PubMed PMID: 21732842.