A natural language processing-based approach for early detection of heart failure onset using electronic health records

ObjectiveThis study set out to develop and validate a risk prediction tool for the early detection of heart failure (HF) onset using real-world EHR data. BackgroundWhile existing HF risk assessment models have shown promise in clinical settings, they are often tailored to specific medical conditions, limiting their generalizability. Moreover, most methods rely on hand-crafted features, making it difficult to capture the high-dimensional, sparse, and temporal nature of EHR data, thus reducing their predictive accuracy. Methods A total of 2561 HF and 5493 matched control patients were identified from the OneFlorida+ Clinical Research Consortium. We employed a suite of natural language processing (NLP) models, including Bag of Words, Skip-gram, and ClinicalBERT, to generate EHR embeddings, which were used as inputs for five prediction models. Subgroup analyses were conducted across gender, race, and ethnicity. Model calibration was assessed under three calibration scenarios: no recalibration, recalibration in the large, and logistic recalibration. ResultsThe XGBoost model demonstrated the best overall performance, achieving an AUROC of 0.7672, an F1 score of 0.5547, an AUPRC of 0.6382, and a Matthews correlation coefficient of 0.3993. The most impactful predictors included diagnoses, procedures, medications, lab tests, and patient age. Model performance varied across gender, race, and ethnicity subgroups. Logistic recalibration significantly improved model calibration in the overall cohort and demographic subgroups. ConclusionOur NLP-based approach demonstrated strong predictive performance and practical relevance, highlighting its potential for integration into real-world clinical applications to facilitate the early detection and proactive management of individuals at risk for HF.