Key result
The abstract describes a methodology to evaluate the predictive accuracy of ICD-10 heart failure codes for identifying ejection fraction, but does not report quantitative results.
Why the study?
EF is unavailable in claims data, and previous ICD-9 analyses showed low sensitivity for identifying patients with HFrEF or HFpEF, leaving the accuracy of ICD-10 codes unclear.
Observational
This study evaluates the accuracy of ICD-10 administrative claims codes in identifying heart failure with reduced versus preserved ejection fraction using a natural language processing algorithm.
NLP algorithm accurately classifies HF by EF subtype in claims data; extends prior ICD-9 limitations to enable subtype-specific quality measures and research.
No takes yet. Share an insight, caveat, or question.
Sandhu et al. (2023) conducted an observational in Heart failure. ICD-10 heart failure codes vs. Natural language processing-extracted ejection fraction was evaluated on Predictive accuracy of ICD-10 HF codes for identifying HFrEF and HFpEF. The abstract describes a methodology to evaluate the predictive accuracy of ICD-10 heart failure codes for identifying ejection fraction, but does not report quantitative results.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: