|
Competency based assessments: Leveraging artificial intelligence to predict sub-competency content This tool is designed to organize narrative feedback on anesthesiology residents in the United States. It is not designed to make decisions on progress through training or achievement of specific competencies. The algorithm built into this tool was developed at Naval Medical Center Portsmouth. It learned from more than 10,000 free-text sentences across three different anesthesiology training programs. This web application is a testing environment to gain insight into how the natural language processing algorithm makes predictions. Since this is a testing environment, compute time takes a few seconds. When built into a dedicated system, this algorithm was shown to read and process several hundred narrative comments in approximately 1 minute. Full methods can be viewed in the publication: ____ The views expressed herein are those of the author(s) and do not necessarily reflect the official policy or position of the Department of the Navy, Department of Defense, or the United States Government. Where applicable, study protocols have been approved by the respective Institutional Review Boards of the military treatment facilities where the research was conducted in compliance with all Federal regulations governing the protection of human subjects. Some authors may be military service members who have contributed as part of their official duties. Title 17, USC, §105 provides that 'Copyright protection under this title is not available for any work of the U.S. Government.' Title 17, USC, §101 defines a U.S. Government work as a work prepared by a military service member or employee of the U.S. Government as part of that person's official duties. Inquiries regarding content hosted on nb-group.org can be directed to CDR Phillip Geiger at phillip.g.geiger2.mil (at) mail.mil. |