Heart failure & cardiomyopathies
Applying Natural Language Processing to Identify Emergency Department and Observation Encounters for Worsening Heart Failure
Authors' conclusion
The use of standard claims-based adjudication for primary diagnosis in the non-inpatient setting may lead to misclassification of WHF events in the ED and overestimate observation stays. Primary diagnoses alone may underestimate the burden of WHF in non-hospitalized settings.
Study context
- Population
- Non-inpatient clinical encounters (emergency department (ED) and observation stays) for worsening HF
- Comparison
- Natural language processing (NLP)-based approach vs traditional diagnostic coding
- Outcome
- Encounters meeting NLP-based WHF criteria
Performance
As reported in the abstract
Encounters meeting NLP-based criteria for worsening heart failure (WHF) (3909 ED visits, 4498 observation stays)
8407
22%
Non-primary HF diagnoses adjudicated by NLP as meeting consensus WHF definitions
3983
12%
Further findings
Observation stays with a secondary HF diagnosis meeting WHF definition by NLP
- Encounters meeting WHF definition by NLP
- 2205 (23%)
- Results primarily driven by observation stays
Original publication
Applying Natural Language Processing to Identify Emergency Department and Observation Encounters for Worsening Heart Failure. ESC Heart Fail. Published 13 May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →