Abstract:Heart failure is a common presentation to the emergency department (ED), which can be confused with other clinical conditions. This review provides an evidence-based summary of the current ED evaluation of heart failure. Acute heart failure is the gradual or rapid decompensation of heart failure, resulting from either fluid overload or maldistribution. Typical symptoms can include dyspnea, orthopnea, or systemic edema. The physical examination may reveal pulmonary rales, an S3 heart sound, or extremity edema. … Show more
“…These data were not available within our dataset, and so could not be incorporated as input features. BNP and NT-proBNP can be useful in diagnostic evaluation and have prognostic value, including for mortality prediction [ 9 , 53 – 56 ]. Models 33F and Top5F were able to perform well without these laboratory results, and adaptations of these models to clinical datasets in which these results are available have the potential to perform better.…”
Section: Discussionmentioning
confidence: 99%
“…Expenditures for AHF in the United States approach $39 billion per year, and are expected to almost double by 2030 [ 4 , 5 ]. An episode of AHF can herald the onset of rapidly progressive and ultimately fatal disease: up to half of heart failure patients die within 5 years of first diagnosis [ 6 – 9 ].…”
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.
“…These data were not available within our dataset, and so could not be incorporated as input features. BNP and NT-proBNP can be useful in diagnostic evaluation and have prognostic value, including for mortality prediction [ 9 , 53 – 56 ]. Models 33F and Top5F were able to perform well without these laboratory results, and adaptations of these models to clinical datasets in which these results are available have the potential to perform better.…”
Section: Discussionmentioning
confidence: 99%
“…Expenditures for AHF in the United States approach $39 billion per year, and are expected to almost double by 2030 [ 4 , 5 ]. An episode of AHF can herald the onset of rapidly progressive and ultimately fatal disease: up to half of heart failure patients die within 5 years of first diagnosis [ 6 – 9 ].…”
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.
“…Based on the functional status of the heart (systolic and diastolic function), HF is classi ed into HF with a reduced ejection fraction (HFrEF) and HF with a preserved ejection fraction (HFpEF) [36]. HFrEF is de ned by the impaired LV contraction and ejection function with an EF < 40%, while HFpEF refers to impaired LV relaxation and lling function with an EF > 50% (borderline range from > 40-55%) [1,36]. Additionally, HFrEF is the most common form.…”
Background: Heart failure (HF), the leading cause of adult mortality and morbidity worldwide, is the end-stage of various diseases, especially ischemic cardiomyopathy (ICM) and dilated cardiomyopathy (DCM). This study aimed to investigate the common molecular mechanism of ICM and DCM.Methods: Four gene expression datasets, GSE1869, GSE5406, GSE57338, and GSE79962, were obtained from the Gene Expression Omnibus (GEO) database. The differentially expressed genes (DEGs) of ICM or DCM samples compared with those of nonfailing samples were identified. Gene ontology (GO) annotation, Kyoto encyclopedia of gene and genome (KEGG) pathway analysis, and the protein-protein network (PPI) of the coregulated DEGs in at least three datasets were performed using the online tools of DAVID, the KOBAS database, and the STRING database, respectively. Hub genes of HF were analyzed for their correlation with left ventricular ejection fraction (LVEF) in dataset GSE19303. The expression levels of notable DEGs were further validated in our tissue microarray (TMA).Results: Fifty-nine coregulated ICM and sixty-eight coregulated DCM relevant DEGs were identified (in at least three datasets). Moreover, 38 common DEGs between ICM and DCM relevant DEGs were obtained that were mainly involved in inflammatory/stress processes, proliferation, and some lipid metabolism pathways. Among the ten hub genes with top degrees, four genes showed a correlation with LVEF, and ASPN had the most significant correlation. Finally, the expression of ASPN protein was validated in our TMA and was significantly increased in ICM and DCM left ventricular samples.Conclusion: The present study revealed some common molecular mechanisms of HF with different causes. Furthermore, ASPN may be a potential promising biomarker for HF.
“…Test results such as high serum C‐reactive protein, B‐type natriuretic peptide, and/or D‐dimer were evaluated. Other tests like sputum culture or echocardiography were carried out when needed 6,7,8 . The attending physician, emergency physician, and/or internal physician comprehensively diagnosed the cause of hypoxia.…”
Section: Methodsmentioning
confidence: 99%
“…Other tests like sputum culture or echocardiography were carried out when needed. 6,7,8 The attending physician, emergency physician, and/or internal physician comprehensively diagnosed the cause of hypoxia. Hypoxia with unknown cause was defined as undetermined hypoxia after all examinations were carried out by the attending physician.…”
Section: Patient Grouping and Hypoxia Diagnostic Processmentioning
In the multivariable analysis, age (adjusted odds ratio [OR] 1.07; 95% confidence interval [CI], 1.00–1.14;
P
= 0.038) D‐dimer (adjusted OR 1.02; 95% CI, 1.00–1.03;
P
= 0.005), and transtricuspid pressure gradient (adjusted OR 1.03; 95% CI, 1.00–1.07;
P
= 0.015) were independently associated with hypoxia in patients with femoral neck fractures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.