askHermes header             Physicians and healthcare providers have many questions when seeing patients and there is limited time and resources to search for answers to these questions. AskHERMES is a computational system that uses natural language processing approaches to automatically analyze large sets of documents pertaining to specific questions and generates short text from them as output. 


In order to help health care providers quickly and efficiently answer the questions that arise during their meetings with patients, we have created AskHERMES, a computational system that automatically analyzes large sets of documents pertaining to specific questions and generates short text from them as output. The system is designed to enable providers to efficiently seek information in clinical settings.

 Health care providers often have questions regarding the care of their patients, and published medical literature and online medical resources are important sources for answering such questions and consequently improve quality of patient care. Although there are some annotated medical knowledge databases, including UpToDate and Thomson Micromedex, available to health care providers with questions, studies have found that health care providers often need to consult primary literature for the latest information in patient care. To meet this need, information retrieval systems including PubMed return lists of retrieved documents in response to user queries, but such searches often yield large sets of documents numbering in the hundreds and sometimes thousands or more. While health care providers usually have limited time to browse retrieved information, and studies indicate that physicians are likely to abandon a search if it takes longer than two minutes.AskHERMES has the promise to provide physicians the best clinical evidence extracted from primary literature within the time frame demanded in clinical settings.