Using Natural Language Processing and Machine Learning to Identify Opioids in Electronic Health Record Data.
Sean P McDermottAjay D WasanPublished in: Journal of pain research (2023)
The automated approach achieved excellent performance in classifying opioids or non-opioids, even with a practical number of human reviewed training examples. This will allow a significant reduction in manual chart review and improve data structuring for retrospective analyses in pain studies. The approach may also be adapted to further analysis and predictive analytics of EHR and other "big data" studies.
Keyphrases
- big data
- electronic health record
- machine learning
- chronic pain
- pain management
- artificial intelligence
- clinical decision support
- endothelial cells
- deep learning
- adverse drug
- case control
- autism spectrum disorder
- cross sectional
- high throughput
- spinal cord
- induced pluripotent stem cells
- pluripotent stem cells
- virtual reality