Heart failure & cardiomyopathies
Race- and Ethnicity-Related Differences in Heart Failure With Preserved Ejection Fraction Using Natural Language Processing
Authors' conclusion
Leveraging an NLP-based artificial intelligence approach to quantify health inequities in HFpEF diagnosis, we discovered that established markers systematically underdiagnose HFpEF in Black patients, possibly due to differences in the underlying comorbidity patterns.
Study context
- Population
- Patients meeting ESC criteria for heart failure with preserved ejection fraction (HFpEF) in a large London hospital, identified by a validated Natural Language Processing (NLP) algorithm
- Participants
- 1,261 / 578 / 134
- Exposure
- Black and Asian vs White patients with HFpEF
- Whiten = 1,261reference
- Blackn = 578
- Asiann = 134
- Outcome
- Clinical presentation and diagnostic performance of existing HFpEF diagnostic tools (NT-proBNP, H2FPEF score) by ethnicity
Methodological detailsNLP applied to electronic health records, single hospital (London), adjusted for socioeconomic status
- NLP applied to electronic health records
- Single hospital (London)
- Adjusted for socioeconomic status
Main finding
As reported in the abstract
H2FPEF score ≥6 (likely HFpEF)
P < 0.0001
Observational data: associations, not effects.
Further findings
| Outcome | White | Black | P value |
|---|---|---|---|
| AFBlack vs White · less likely in Black patients | 30% | 13% | P < 0.001 |
Original publication
Race- and Ethnicity-Related Differences in Heart Failure With Preserved Ejection Fraction Using Natural Language Processing. JACC Adv. Published 2 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →