Pillbox: Enhancing Patient Safety through a Mashup of Government Data, High-Resolution Imaging and Analysis, and Community-Developed Tools
|
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). |
Abstract
Medication identification is a key component in mitigating the 1.5 million adverse drug events which occur annually in the United States. Poison control centers receive over 500,000 medication identification calls annually. An IOM study reported that doctors and pharmacists can correctly identify pills no more than one-third of the time.
While a variety of electronic databases exist to assist in the identification of unknown medications, quality standards for images of solid-dosage medications do not exist. Further complications arise from the lack of interoperability between pharmaceutical information systems at various federal agencies.
The National Library of Medicine (NLM), at the National Institutes of Health, is leading an inter-agency patient safety initiative involving the development of a public domain library of high-resolution macro images of solid-dosage pharmaceuticals. Advanced image processing and analysis using open source software developed at the NLM creates a unique physical characteristic profiles for every pharmaceutical imaged.
The focal point of this initiative is Pillbox, an application which mashes pharmaceutical data from the FDA, NLM, and image analysis, enabling rapid identification of unknowns and creating connections across various federal pharmaceutical information databases. Pillbox's UI is built on Adobe Flex, which allows a platform-independent rich user experience, based on user profiles generated through ethnographic field study in a variety of modalities. A long-term goal of the project is automated identification of unknowns, based on an image taken with a mobile device.
All data generated from Pillbox (including high-resolution macro images and image analysis/search UI code) will be placed in the public domain. NLM will present the project and schema, and demonstrate the identification system. Through dialogue with the health information technology community, NLM seeks to facilitate development of applications based on the data, images, and software. Areas of innovation currently being explored include emergency response, disaster relief, clinical practice, anti-counterfeiting, and citizen use.
Polka, a mobile health company, while participating in a community workshop where Pillbox was presented, saw the opportunity to build upon this data. After the workshop, Polka set about describing a consumer application for the NLM data and a lightweight framework to leverage high resolution images and profiles for next generation mobile and web pill search and quality information delivery.
In this demonstration, Polka will show examples of how visual recognition of a medication can have profound impact on the experience for the user in tracking their regimen accurately and easily. Mobile devices, in the hands of patients and providers, can assist in real-time identification during emergencies, as these applications become adopted in consumer and clinical environments simultaneously.
Personal health observations have increased utility when they have a backbone of data quality and precision. Polka is exploring submitting this application as a component of a project for Project Health Design to further explore leverage points and opportunities to allow others to fund commercialization where appropriate.
While a variety of electronic databases exist to assist in the identification of unknown medications, quality standards for images of solid-dosage medications do not exist. Further complications arise from the lack of interoperability between pharmaceutical information systems at various federal agencies.
The National Library of Medicine (NLM), at the National Institutes of Health, is leading an inter-agency patient safety initiative involving the development of a public domain library of high-resolution macro images of solid-dosage pharmaceuticals. Advanced image processing and analysis using open source software developed at the NLM creates a unique physical characteristic profiles for every pharmaceutical imaged.
The focal point of this initiative is Pillbox, an application which mashes pharmaceutical data from the FDA, NLM, and image analysis, enabling rapid identification of unknowns and creating connections across various federal pharmaceutical information databases. Pillbox's UI is built on Adobe Flex, which allows a platform-independent rich user experience, based on user profiles generated through ethnographic field study in a variety of modalities. A long-term goal of the project is automated identification of unknowns, based on an image taken with a mobile device.
All data generated from Pillbox (including high-resolution macro images and image analysis/search UI code) will be placed in the public domain. NLM will present the project and schema, and demonstrate the identification system. Through dialogue with the health information technology community, NLM seeks to facilitate development of applications based on the data, images, and software. Areas of innovation currently being explored include emergency response, disaster relief, clinical practice, anti-counterfeiting, and citizen use.
Polka, a mobile health company, while participating in a community workshop where Pillbox was presented, saw the opportunity to build upon this data. After the workshop, Polka set about describing a consumer application for the NLM data and a lightweight framework to leverage high resolution images and profiles for next generation mobile and web pill search and quality information delivery.
In this demonstration, Polka will show examples of how visual recognition of a medication can have profound impact on the experience for the user in tracking their regimen accurately and easily. Mobile devices, in the hands of patients and providers, can assist in real-time identification during emergencies, as these applications become adopted in consumer and clinical environments simultaneously.
Personal health observations have increased utility when they have a backbone of data quality and precision. Polka is exploring submitting this application as a component of a project for Project Health Design to further explore leverage points and opportunities to allow others to fund commercialization where appropriate.
Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.
This work is licensed under a Creative Commons Attribution 3.0 License.