Unified Documentation and Information Retrieval for Electronic Health Records
Name
Murray-lmurray-SM-EECS-2022-thesis.pdf
Description
Thesis PDF
Size
1.14 MB
Format
Adobe PDF
Checksum (MD5)
d6ff48ca03566d9756da98b1ba44ac40
Author(s)
Murray, Luke
Advisor(s)
Karger, David R.
Date Issued
February 2022
Publisher
Massachusetts Institute of Technology
Abstract
Clinicians in the Emergency Department want to efficiently provide and document high-quality care but cannot, mainly due to challenges exacerbated by Electronic Health Records. For each patient, clinicians have to review the patient history, perform a physical exam, synthesize findings into a differential diagnosis and care plan; coordinate care with other specialists; order and document tests, labs, procedures, and medications; and finally discharge the patient. Existing EHRs have poor usability, time-consuming data entry, and fragmented information exploration and documentation interfaces. As a result, clinicians struggle to synthesize the patient’s history and care plan into a concise and clear data-driven narrative. Additionally, in an Emergency Department Environment, Clinicians often see 35 patients in a single shift and generally have no prior knowledge of any patient’s medical record. With limited time, clinicians often have to satisfice their information needs and synthesis, potentially leading to errors, harm, or non-optimal care.
Clinical tools must enable rapid contextual access to the patient’s medical record with techniques that do not disrupt existing workflows to better support information exploration and documentation. This thesis outlines the development of such a tool, MedKnowts. MedKnowts is an integrated note-taking editor and information retrieval system which unifies the documentation and search process and provides concise synthesized concept-oriented slices of the patient’s medical record. MedKnowts automatically captures structured data while still allowing users the flexibility of natural language. MedKnowts leverages this structure to enable easier parsing of long notes, auto-populated text, and proactive information retrieval, easing the documentation burden.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
