Abstract
Due to the absence of medications on Alzheimer's disease (AD), lifestyle exposures that could improve cognitive functionality have become extremely important. Thus, the objective of the study was to show the feasibility of using natural language processing (NLP) methods to extract lifestyle exposures from clinical texts. The proposed named-entity recognition (NER) task's results indicate that NLP models can detect lifestyle information (i.e., excessive diet, physical activity, sleep deprivation and substance abuse) from clinical notes, which has the potential for improving efficiency in information acquisition and accrual for AD clinical trials.
Original language | English (US) |
---|---|
Title of host publication | 2020 IEEE International Conference on Healthcare Informatics, ICHI 2020 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781728153827 |
DOIs | |
State | Published - Nov 2020 |
Event | 8th IEEE International Conference on Healthcare Informatics, ICHI 2020 - Virtual, Oldenburg, Germany Duration: Nov 30 2020 → Dec 3 2020 |
Publication series
Name | 2020 IEEE International Conference on Healthcare Informatics, ICHI 2020 |
---|
Conference
Conference | 8th IEEE International Conference on Healthcare Informatics, ICHI 2020 |
---|---|
Country/Territory | Germany |
City | Virtual, Oldenburg |
Period | 11/30/20 → 12/3/20 |
Bibliographical note
Publisher Copyright:© 2020 IEEE.
Keywords
- Alzheimer's disease
- Deep learning
- Electronic health records
- Information extraction
- Lifestyle exposure
- Machine learning
- Natural language processing