Use of natural language processing method to identify regional anesthesia from clinical notes
Authors' conclusion
We found that NLP was a promising alternative for identifying clinical information when existing databases lack complete documentation.
Study context
- Population
- Patients undergoing elective non-cardiac surgery with GA at 6 Veterans Health Administration hospitals in California, 2017–2022
- Participants
- 27,713 procedures
- Exposure
- Algorithm vs Referent
- Outcome
- Agreement of NLP algorithm with referent in identifying RA (sensitivity, PPV, false negative rate, accuracy)
Methodological detailsmulticentre, six Veterans Health Administration hospitals
- Multicentre
- Six Veterans Health Administration hospitals
Main finding
As reported in the abstract
Identification of RA cases
| Group | Value | Referent RA cases identified | False negative rate | Accuracy |
|---|---|---|---|---|
| Algorithm | 9154 events | 96.6% | 0.8% | 82.5% |
| Referent | 4606 events |
Value
Algorithm9154 events
Referent4606 events
Referent RA cases identified
Algorithm96.6%
Referent— not stated in the abstract
False negative rate
Algorithm0.8%
Referent— not stated in the abstract
Accuracy
Algorithm82.5%
Referent— not stated in the abstract
Observational data: associations, not effects.
Further findings
- Procedures that received RA
- 9310 (33.6%)
Original publication
Use of natural language processing method to identify regional anesthesia from clinical notes. Reg Anesth Pain Med. Published 4 April 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →