Advances in cancer therapy have resulted in more cancer therapy-related cardiac dysfunction (CTRCD), which is the main cause of death in older female survivors of breast cancer. Traditionally, guideline-recommended medications for heart failure, such as beta-blockers and angiotensin-converting enzyme inhibitors/angiotensin receptor blockers (ACEIs/ARBs), are commonly used to prevent or attenuate CTRCD. However, sometimes their effectiveness is not satisfactory. Recently, the drug combination of sacubitril plus valsartan has been proven to be more beneficial for heart failure with reduced ejection fraction in the long term compared with an ACEI/ARB alone. However, there is a lack of evidence of the efficacy and safety of this drug combination in CTRCD. We report a case of worsening CTRCD, despite treatment with traditional medications, in which the patient improved after changing perindopril to sacubitril/valsartan. The patient’s heart function greatly improved after changing this ACEI to sacubitril/valsartan. Changing an ACEI/ARB to sacubitril/valsartan in patients with worsening chemotherapy-induced heart failure is appropriate. Further studies with a high level of evidence are required to assess the efficacy and safety of sacubitril/valsartan for CTRCD.

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.

The fibrosis-4 (FIB-4) index is a non-invasive score used to determine liver fibrosis. The present study aimed to assess the predictive ability of FIB-4 for all-cause mortality in patients with acute myocardial infarction (AMI). It retrospectively analyzed a total of 797 patients who were diagnosed with AMI. The patients were equally divided into three tertiles based on the values of the FIB-4 index scores: Group A (FIB-4 index <3.19; n=265), group B (3.19 ≤FIB-4 <8.14; n=267) and group C (FIB-4 index ≥8.14 group; n=265). Kaplan-Meier curves were used to analyze the incidence of all-cause mortality among the three groups. Multivariate Cox regression analysis was used to assess the association of risk of all-cause mortality in the patients. The Kaplan-Meier curves showed that the incidence of all-cause mortality was statistically significantly higher in group C than in groups A and B (P<0.001). After adjusting for confounding factors, multivariate Cox analysis demonstrated the risk of all-cause mortality in group C was significantly higher than in group A (hazard ratio: 2.898, 95% confidence interval: 1.069-7.857, P= 0.037). In receiver-operating characteristics (ROC) analysis, an FIB-4 index of 6.647 and a Synergy between PCI with Taxus and Cardiac Surgery (SYNTAX) score of 26.75 had sensitivities of 67.3 and 55.8% and specificities of 63 and 71.9%, respectively. Comparing the area under the ROC curve revealed no statistical differences between the FIB-4 index and SYNTAX score (0.654 vs. 0.661; P=0.864). Higher FIB-4 index were associated with increased risks of all-cause mortality among AMI patients. The FIB-4 index, a noninvasive and convenient tool, plays a potential role in the prognosis of AMI.