Related Experiment Video
Updated: Apr 14, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Learning From the Crowd in Terminology Mapping: The LOINC Experience.
Brian E Dixon1, John Hook2, Daniel J Vreeman3
1Richard M. Fairbanks School of Public Health at Indiana University-Purdue University Indianapolis, Regenstrief Institute, Inc., and Center for Health Information and Communication, Department of Veterans Affairs, Veterans Health Administration, Health Services Research and Development Service, Indianapolis, IN bedixon@iupui.edu.
This study introduces a new tool to improve electronic health record data exchange by sharing existing mappings between local terms and standard vocabularies like Logical Observation Identifiers Names and Codes (LOINC). This crowdsourced approach enhances mapping efficiency and effectiveness for healthcare organizations.
Area of Science:
- Health Informatics
- Clinical Data Standards
- Information Exchange
Background:
- National policies mandate standard terminology for clinical information systems in the US.
- Electronic health record systems often use local, non-standard terms for clinical observations, hindering data exchange.
- Existing mappings between local terms and standard vocabularies are often siloed within healthcare organizations.
Purpose of the Study:
- To develop and describe new functionality for sharing existing mappings between local clinical terms and standard vocabularies.
- To improve the efficiency and effectiveness of mapping processes for healthcare implementers.
- To leverage collective wisdom from healthcare organizations to enhance data interoperability.
Main Methods:
- Developed functionality to display counts of local terms and organizations mapped to specific Logical Observation Identifiers Names and Codes (LOINC) codes.
- Enabled users to view detailed mapping information, including local term names and originating organizations.
- Created a shared repository for users to contribute their local mappings.
Main Results:
- New functionality provides visibility into existing mapping data from multiple healthcare organizations.
- Users can access and contribute to a growing repository of local-to-standard vocabulary mappings.
- The system facilitates a crowdsourced approach to improving the quality and coverage of mappings.
Conclusions:
- The developed functionality offers a valuable resource for healthcare organizations seeking to improve data standardization.
- Sharing mapping knowledge enhances the efficiency and effectiveness of aligning local terms with standard terminologies like LOINC.
- This crowdsourced model promotes collaborative improvement in clinical data exchange and interoperability.
Related Concept Videos
Introduction to Learning
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Cognitive Learning
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Associative Learning
Classical conditioning, also known...
Observational Learning
Purposive Learning
Introduction and Methods of Leveling