A Natural Language Processing Approach to Automated Highlighting of New Information in Clinical Notes
| Autor: | Pei-Ju Lee, Ling-Chien Hung, Yu-Hsiang Su, Ching-Ping Chao, Sheng-Feng Sung |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
020205 medical informatics
Computer science Bigram health care facilities manpower and services 02 engineering and technology computer.software_genre information overload lcsh:Technology Task (project management) lcsh:Chemistry 03 medical and health sciences 0302 clinical medicine health services administration 0202 electrical engineering electronic engineering information engineering electronic medical records General Materials Science 030212 general & internal medicine natural language processing lcsh:QH301-705.5 Instrumentation health care economics and organizations Fluid Flow and Transfer Processes Copying lcsh:T business.industry Process Chemistry and Technology Medical record General Engineering Workload lcsh:QC1-999 Information overload Computer Science Applications bigram language model Identification (information) lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 Artificial intelligence Language model lcsh:Engineering (General). Civil engineering (General) business computer lcsh:Physics Natural language processing |
| Zdroj: | Applied Sciences Volume 10 Issue 8 Applied Sciences, Vol 10, Iss 2824, p 2824 (2020) |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app10082824 |
| Popis: | Electronic medical records (EMRs) have been used extensively in most medical institutions for more than a decade in Taiwan. However, information overload associated with rapid accumulation of large amounts of clinical narratives has threatened the effective use of EMRs. This situation is further worsened by the use of &ldquo copying and pasting&rdquo leading to lots of redundant information in clinical notes. This study aimed to apply natural language processing techniques to address this problem. New information in longitudinal clinical notes was identified based on a bigram language model. The accuracy of automated identification of new information was evaluated using expert annotations as the reference standard. A two-stage cross-over user experiment was conducted to evaluate the impact of highlighting of new information on task demands, task performance, and perceived workload. The automated method identified new information with an F1 score of 0.833. The user experiment found a significant decrease in perceived workload associated with a significantly higher task performance. In conclusion, automated identification of new information in clinical notes is feasible and practical. Highlighting of new information enables healthcare professionals to grasp key information from clinical notes with less perceived workload. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|