Artificial Intelligence Methods to Detect Heart Failure with Preserved Ejection Fraction (AIM-HFpEF) within Electronic Health Records: An equitable disease prediction model

Background and aims Heart Failure with Preserved Ejection Fraction (HFpEF) accounts for approximately half of all heart failure cases, with high levels of morbidity and mortality. However, most cases of HFpEF are undiagnosed as conventional risk scores underestimate risk in non-White populations. Our aim was to develop and validate a diagnostic prediction model to detect undiagnosed HFpEF, AIM-HFpEF. Methods We applied natural language processing (NLP) and machine learning methods to routinely collected electronic health record (EHR) data from a tertiary centre hospital trust in London, UK, to derive the AIM-HFpEF model. We then externally validated the model and performed benchmarking against existing HFpEF prediction models (H2FPEF and HFpEF-ABA) for diagnostic power in patients of non-white ethnicity and patients from areas of increased socioeconomic deprivation. Results An XGBoost model combining demographic, clinical and echocardiogram data showed strong diagnostic performance in the derivation dataset (n=3170, AUC=0.88, [95% CI, 0.86-0.91]) and validation cohort (n=5383, AUC: 0.88 [95% CI, 0.87-0.89]). Diagnostic performance was maintained in patients of non-White ethnicity (AUC=0.88 [95% CI, 0.84-0.93]) and patients from areas of high socioeconomic deprivation (AUC=0.89 [95% CI, 0.84-0.94]). and AIM-HFpEF performed favourably in comparison to H2FPEF and HFpEF-ABA models. AIM-HFpEF model probabilities were associated with an increased risk of death, hospitalisation and stroke in the external validation cohort (P<0.001, P=0.01, P<0.001 respectively for highest versus middle tertile). Conclusion AIM-HFpEF represents a validated equitable diagnostic model for HFpEF, which can be embedded within an EHR to allow for fully automated HFpEF detection.