Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data

• Published in: BioData mining Vol. 14; no. 1; p. 23
• Main Authors: Radhachandran, Ashwath, Garikipati, Anurag, Zelin, Nicole S, Pellegrini, Emily, Ghandian, Sina, Calvert, Jacob, Hoffman, Jana, Mao, Qingqing, Das, Ritankar
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 31.03.2021; BioMed Central; BMC
• Subjects: Acute heart failure; Age; Artificial intelligence; Blood pressure; Business metrics; Cardiac patients; Clinical decision support; Congestive heart failure; Decision support systems; Decision trees; Electronic health records; Electronic medical records; Electronic records; Emergencies; Emergency medical care; Emergency medical services; Emergency medicine; Health care; Heart; Heart failure; Hospitalization; Laboratories; Learning algorithms; Machine learning; Management decisions; Medical records; Model testing; Morbidity; Mortality; Patient outcomes; Patients; Prediction; Predictions; Respiration; Respiratory rate; Risk assessment; Test sets; United States > US; Clinical decision support; Mortality; Acute heart failure; Machine learning; Prediction
• ISSN: 1756-0381; 1756-0381
• DOI: 10.1186/s13040-021-00255-w

Acute heart failure (AHF) is associated with significant morbidity and mortality. Effective patient risk stratification is essential to guiding hospitalization decisions and the clinical management of AHF. Clinical decision support systems can be used to improve predictions of mortality made in emergency care settings for the purpose of AHF risk stratification. In this study, several models for the prediction of seven-day mortality among AHF patients were developed by applying machine learning techniques to retrospective patient data from 236,275 total emergency department (ED) encounters, 1881 of which were considered positive for AHF and were used for model training and testing. The models used varying subsets of age, sex, vital signs, and laboratory values. Model performance was compared to the Emergency Heart Failure Mortality Risk Grade (EHMRG) model, a commonly used system for prediction of seven-day mortality in the ED with similar (or, in some cases, more extensive) inputs. Model performance was assessed in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. When trained and tested on a large academic dataset, the best-performing model and EHMRG demonstrated test set AUROCs of 0.84 and 0.78, respectively, for prediction of seven-day mortality. Given only measurements of respiratory rate, temperature, mean arterial pressure, and FiO , one model produced a test set AUROC of 0.83. Neither a logistic regression comparator nor a simple decision tree outperformed EHMRG. A model using only the measurements of four clinical variables outperforms EHMRG in the prediction of seven-day mortality in AHF. With these inputs, the model could not be replaced by logistic regression or reduced to a simple decision tree without significant performance loss. In ED settings, this minimal-input risk stratification tool may assist clinicians in making critical decisions about patient disposition by providing early and accurate insights into individual patient's risk profiles.