Trial of an Intervention to Improve Acute Heart Failure Outcomes

Lee, Douglas S.; Straus, Sharon E.; Farkouh, Michael E.; Austin, Peter C.; Taljaard, Monica; Chong, Alice; Fahim, Christine; Poon, Stephanie; Cram, Peter; Smith, Stuart J.; McKelvie, Robert S.; Porepa, Liane; Hartleib, Michael; Mitoff, Peter R.; Iwanochko, Robert M.; MacDougall, Arlene; Shadowitz, Steven; Abrams, Howard; Elbarasi, Esam; Fang, Jiming; Udell, Jacob A.; Schull, Michael J.; Mak, Susanna; Ross, Heather J.

doi:10.1056/nejmoa2211680

Cited by 83 publications

(78 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The risk stratification of the ICU patients has become an important strategy in management of HF. Studies have also demonstrated that accurate event risk assessment and active intervention can help improve cardiac disease outcomes ( 4 ). Therefore, effective stratification tools are needed to achieve this goal.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure

Chen

Guo

et al. 2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

ObjectiveRisk stratification of patients with congestive heart failure (HF) is vital in clinical practice. The aim of this study was to construct a machine learning model to predict the in-hospital all-cause mortality for intensive care unit (ICU) patients with HF.MethodseXtreme Gradient Boosting algorithm (XGBoost) was used to construct a new prediction model (XGBoost model) from the Medical Information Mart for Intensive Care IV database (MIMIC-IV) (training set). The eICU Collaborative Research Database dataset (eICU-CRD) was used for the external validation (test set). The XGBoost model performance was compared with a logistic regression model and an existing model (Get with the guideline-Heart Failure model) for mortality in the test set. Area under the receiver operating characteristic cure and Brier score were employed to evaluate the discrimination and the calibration of the three models. The SHapley Additive exPlanations (SHAP) value was applied to explain XGBoost model and calculate the importance of its features.ResultsThe total of 11,156 and 9,837 patients with congestive HF from the training set and test set, respectively, were included in the study. In-hospital all-cause mortality occurred in 13.3% (1,484/11,156) and 13.4% (1,319/9,837) of patients, respectively. In the training set, of 17 features with the highest predictive value were selected into the models with LASSO regression. Acute Physiology Score III (APS III), age and Sequential Organ Failure Assessment (SOFA) were strongest predictors in SHAP. In the external validation, the XGBoost model performance was superior to that of conventional risk predictive methods, with an area under the curve of 0.771 (95% confidence interval, 0.757–0.784) and a Brier score of 0.100. In the evaluation of clinical effectiveness, the machine learning model brought a positive net benefit in the threshold probability of 0%–90%, prompting evident competitiveness compare to the other two models. This model has been translated into an online calculator which is accessible freely to the public (https://nkuwangkai-app-for-mortality-prediction-app-a8mhkf.streamlit.app).ConclusionThis study developed a valuable machine learning risk stratification tool to accurately assess and stratify the risk of in-hospital all-cause mortality in ICU patients with congestive HF. This model was translated into a web-based calculator which access freely.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure

Chen

Guo

et al. 2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“…The role of NPs as biomarkers to guide the clinical behavior in HF has resulted in an improvement in clinical outcomes, though they did not specifically address the impact on the intensity of care. In fact, in the recent COACH (Comparison of Outcomes and Access to Care for Heart Failure) trial, the use of a point-of-care tool for risk stratification in the emergency department to support clinical decision-making and rapid outpatient follow-up was associated with an improvement of 30-day and 20-month clinical outcomes [ 63 ]. In this approach, the use of NPs as routine biomarkers most likely played a role [ 64 ].…”

Section: The Key Role Of Natriuretic Peptides As Clinical Biomarkers ...mentioning

confidence: 99%

Natriuretic Peptides: It Is Time for Guided Therapeutic Strategies Based on Their Molecular Mechanisms

Gallo

Rubattu

Autore

et al. 2023

IJMS

View full text Add to dashboard Cite

Natriuretic peptides (NPs) are the principal expression products of the endocrine function of the heart. They exert several beneficial effects, mostly mediated through guanylate cyclase-A coupled receptors, including natriuresis, diuresis, vasorelaxation, blood volume and blood pressure reduction, and regulation of electrolyte homeostasis. As a result of their biological functions, NPs counterbalance neurohormonal dysregulation in heart failure and other cardiovascular diseases. NPs have been also validated as diagnostic and prognostic biomarkers in cardiovascular diseases such as atrial fibrillation, coronary artery disease, and valvular heart disease, as well as in the presence of left ventricular hypertrophy and severe cardiac remodeling. Serial measurements of their levels may be used to contribute to more accurate risk stratification by identifying patients who are more likely to experience death from cardiovascular causes, heart failure, and cardiac hospitalizations and to guide tailored pharmacological and non-pharmacological strategies with the aim to improve clinical outcomes. On these premises, multiple therapeutic strategies based on the biological properties of NPs have been attempted to develop new targeted cardiovascular therapies. Apart from the introduction of the class of angiotensin receptor/neprilysin inhibitors to the current management of heart failure, novel promising molecules including M-atrial natriuretic peptide (a novel atrial NP-based compound) have been tested for the treatment of human hypertension with promising results. Moreover, different therapeutic strategies based on the molecular mechanisms involved in NP regulation and function are under development for the management of heart failure, hypertension, and other cardiovascular conditions.

show abstract

“…Poor life, and shortened life expectancy (Philbin, 2008). Currently, CHF is not only a cardiovascular disease whose incidence and prevalence are increasing but also a disease that most often requires rehospitalization even though outpatient treatment has been given optimally (Lee et al, 2022). This is by Desai & Stevenson, (2012) statement that patients with CHF have a frequency of re-hospitalization of more than one time in 12 months.…”

Section: Introductionmentioning

confidence: 99%

The Relationship Between Family Support And Rehospitality in Heart Failure Patients in Kemuning Room, Jombang Hospital

Subianto¹,

Kurdi

Khoiri³

2023

jkmi

View full text Add to dashboard Cite

Congestive heart failure is a clinical problem that occurs in patients who have abnormalities, either hereditary or acquired in the structure and function of the heart, causing the development of a series of clinical symptoms of weakness and tightness as well as clinical signs of edema and crackles which result in hospitalization, poor quality of life, and shortened life expectancy. This study aims to determine the relationship between family support and re-hospitalization incidence in heart failure patients in the Kemuning room at Jombang Hospital. The research design used in this study is cross-sectional analytic. The population in this study were all heart failure patients in the Kemuning Room of the Jombang Hospital, with a total of 37 people. A sample of 33 respondents. The sampling technique used is purposive sampling. The research variable is family support and the dependent variable is the incidence of re-hospitalization in heart failure patients. which were analyzed using chi-square with α = 0.05. The results of this study indicated that the majority (60.6%) of respondents had good family support, numbering 20 people, and the majority (69.7%) of respondents who were re-hospitalized in patients with heart failure were up to six months, totaling 23 people. The analysis results obtained 0.000 <0.005, meaning there is a relationship between family support and the incidence of re-hospitalization in heart failure patients in the Kemuning room at Jombang Hospital. From this research, it is hoped that nurses can maximize the role of the family as one of the support systems in caring for congestive heart failure patients undergoing re-hospitalization.

show abstract

Trial of an Intervention to Improve Acute Heart Failure Outcomes

Cited by 83 publications

References 34 publications

Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure

Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure

Natriuretic Peptides: It Is Time for Guided Therapeutic Strategies Based on Their Molecular Mechanisms

The Relationship Between Family Support And Rehospitality in Heart Failure Patients in Kemuning Room, Jombang Hospital

Contact Info

Product

Resources

About