Dataset Information

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

ABSTRACT:

Background

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.

Results

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 FiO₂, one model produced a test set AUROC of 0.83. Neither a logistic regression comparator nor a simple decision tree outperformed EHMRG.

Conclusions

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.

SUBMITTER: Radhachandran A

PROVIDER: S-EPMC8010502 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:AimsFrailty may be found in heart failure patients especially in the elderly and is associated with a poor prognosis. However, assessment of frailty status is time-consuming, and the electronic frailty indices developed using health records have served as useful surrogates. We hypothesized that an electronic frailty index developed using machine learning can improve short-term mortality prediction in patients with heart failure.Methods and resultsThis was a retrospective observational study that included patients admitted to nine public hospitals for heart failure from Hong Kong between 2013 and 2017. Age, sex, variables in the modified frailty index, Deyo's Charlson co-morbidity index (≥2), neutrophil-to-lymphocyte ratio (NLR), and prognostic nutritional index at baseline were analysed. Gradient boosting, which is a supervised sequential ensemble learning algorithm with weak prediction submodels (typically decision trees), was applied to predict mortality. Variables were ranked in the order of importance with a total score of 100 and used to build the frailty models. Comparisons were made with decision tree and multivariable logistic regression. A total of 8893 patients (median: age 81, Q1-Q3: 71-87 years old) were included, in whom 9% had 30 day mortality and 17% had 90 day mortality. Prognostic nutritional index, age, and NLR were the most important variables predicting 30 day mortality (importance score: 37.4, 32.1, and 20.5, respectively) and 90 day mortality (importance score: 35.3, 36.3, and 14.6, respectively). Gradient boosting significantly outperformed decision tree and multivariable logistic regression. The area under the curve from a five-fold cross validation was 0.90 for gradient boosting and 0.87 and 0.86 for decision tree and logistic regression in predicting 30 day mortality. For the prediction of 90 day mortality, the area under the curve was 0.92, 0.89, and 0.86 for gradient boosting, decision tree, and logistic regression, respectively.ConclusionsThe electronic frailty index based on co-morbidities, inflammation, and nutrition information can readily predict mortality outcomes. Their predictive performances were significantly improved by gradient boosting techniques.

Project description:BackgroundIncreased body mass index (BMI) is associated with better survival in patients with acute heart failure (AHF), which is a paradoxical phenomenon. However, it is unclear whether different nutritional status affects this association.Methods1325 patients with AHF from the Medical Information Mart for Intensive Care III database were retrospectively included. Nutritional status was assessed by serum albumin (SA) and prognostic nutritional index (PNI). Patients were divided into High-SA (≥ 3.5 g/dL) and Low-SA groups (< 3.5 g/dL), and they also were divided into High-PNI (≥ 38) and Low-PNI groups (< 38). Propensity-score matching (PSM) was used to control for the effect of baseline confounding factors, multifactor regression model was adopted to assess the association of nutritional status, BMI, and outcomes in AHF patients.ResultsOf the 1325 patients (mean age 72.4 ± 13.1 years), 52.1% (n = 690) were male, 13.1% (n = 173) died in hospital and 23.5% (n = 311) died within 90 days. Before PSM, after adjusting for potential confounders, in the High-SA population, compared with the under/normal BMI group, overweight and obesity were negatively correlated with 90-day mortality, with adjusted hazard ratios (HR) of 0.47, 95% confidence interval (CI) (0.30-0.74), P = 0.001; HR 0.45, 95%CI (0.28-0.72), P = 0.001, respectively. However, this correlation was much attenuated in the Low-SA group (overweight BMI: HR 1.06, 95%CI 0.75-1.50, P = 0.744; obese BMI: HR 0.86, 95%CI 0.59-1.24, P = 0.413). After PSM, those who were overweight or obese in the High-SA group had a 50-58% reduction in 90-day risk of death, while the protective effect disappeared in the Low-SA group (HR 1.09, 95% CI 0.70-1.71; HR 1.02, 95%CI 0.66 - 0.59). Similarly, results were similar in analyses using PNI as a nutritional assessment criterion.ConclusionOverweight or Obesity was associated with lower short-term mortality in well-nourished AHF patients, whereas this association was significantly attenuated or even disappeared in malnourished patients. Therefore, further research is needed for weight loss recommendations for malnourished obese patients with AHF.