Natural Language Processing

PubMed For Handhelds

Research Area: Natural Language Processing

Researchers: Paul Fontelo

Project link:

These tools will no longer be maintained as of December 31, 2024. Archived website can be found here. PubMed4Hh GitHub repository can be found here. Contact NLM Customer Service if you have questions.

Project icon for PubMed for HandheldsPubMed for Handhelds ( research brings medical information to the point of care via devices like smartphones. This includes developing algorithms and public-domain tools for searching by text message (askMEDLINE), applying clinical filters (PICO) and viewing summary abstracts (The Bottom Line and Consensus Abstracts) in MEDLINE/PubMed, and evaluating the use of these tools in Clinical Decision Support.

PubMed4Hh has six components:

  • askMEDLINE - askMEDLINE is a free-text natural language query tool to search for and retrieve relevant citations in MEDLINE/PubMed. askMEDLINE research is developing this search tool for users who may not know specialized medical vocabularies.
  • PICO (Patient, Intervention, Comparison, and Outcome) - PICO research and development are enabling the search of MEDLINE/PubMed for information about conditions and diseases, interventions, comparisons of interventions, and outcomes. PICO lets the user structure clinical questions via a fill-in-the-blank and menu format. It can also be used to structure literature searches.
    A health care provider or a consumer inputs a patient's condition or disease and selects an intervention or treatment, other interventions or treatments for comparison (optional), and desired outcomes (also optional). A dropdown menu prompts for publication type from among clinical trial, meta-analysis, randomized controlled trial, systematic reviews, reviews, and practice guideline, or, if none is specified, any of the above. PICO returns MEDLINE/PubMed articles responsive to the input.
  • The Bottom Line - The Bottom Line (TBL) research and development are enabling the summarization of journal abstracts for quick reading or text messaging. TBL results are derived by applying computer algorithms, not by summarizations performed by humans. TBLs were originally created to shorten abstracts sent as SMS text messages. The Conclusion section in structured abstracts is used as the TBL. If an abstract has no Conclusion section, TBL results are derived by using a word counting algorithm plus the last two sentences of the abstract.
  • Consensus Abstracts - Consensus Abstracts research and development are creating a Web application formatted for wireless mobile devices (for example, cell phones, smartphones, and tablet computers), whereby health care providers and consumers can search for current medical literature from MEDLINE/PubMed.
    Either askMEDLINE or PICO can be used to initiate a search.
    With askMEDLINE, a health care provider or a consumer can search using free-text, natural language terms. An example is “For a child with acute abdominal pain, will analgesics mask the diagnosis of acute appendicitis?” The search algorithm parses the query then sends it to the MEDLINE/PubMed database.
    Consensus Abstracts retrieves relevant MEDLINE/PubMed articles, which are displayed as a list of journal citations (author, title, publication date, PubMed ID). A checkbox next to each item allows the searcher to choose citations of interest or, if the first series of articles are deemed relevant, those articles can be selected for display through a "Submit" button. The exact number of articles can be entered in an input box.
    Consensus Abstracts presents on a results Web page the summaries of each abstract found by The Bottom Line (TBL); the search terms and publication types are also displayed. TBL results and full abstracts can also be displayed on the results page by clicking on links, so a searcher doesn't need to leave that page. Full-text articles, if available, and lists of related articles can be retrieved through links from citations.
  • Clinical Decision Support - Physicians and researchers can have difficulty keeping up with the continuing expansion of medical information, novel diagnostic tools, and therapeutic discoveries reported in the medical literature. They need to access relevant information when they need it and where they are -- for example at the point of care. Studies have shown that although they perceive the need to be high, they seek current information only when it is easily accessible. Medical information from MEDLINE/PubMed accessed through mobile devices and the above-mentioned components of PubMed for Handhelds can help inform clinical decisions.