Development and validation of a novel combinatorial nomogram model to predict in-hospital deaths in heart failure patients

Abstract

Background: The purpose of this study was to develop a Nomogram model to identify the risk of all-cause mortality during hospitalization in patients with heart failure (HF).

Methods: HF patients who had been registered in the Medical Information Mart for Intensive Care (MIMIC) III and IV databases were included. The primary outcome was the occurrence of all-cause mortality during hospitalization. Two Logistic Regression models (LR1 and LR2) were developed to predict in-hospital death for HF patients from the MIMIC-IV database. The MIMIC-III database were used for model validation. The area under the receiver operating characteristic curve (AUC) was used to compare the discrimination of each model. Calibration curve was used to assess the fit of each developed models. Decision curve analysis (DCA) was used to estimate the net benefit of the predictive model.

Results: A total of 16,908 HF patients were finally enrolled through screening, of whom 2,283 (13.5%) presented with in-hospital death. Totally, 48 variables were included and analyzed in the univariate and multifactorial regression analysis. The AUCs for the LR1 and LR2 models in the test cohort were 0.751 (95% CI: 0.735∼0.767) and 0.766 (95% CI: 0.751-0.781), respectively. Both LR models performed well in the calibration curve and DCA process. Nomogram and online risk assessment system were used as visualization of predictive models.

Conclusion: A new risk prediction tool and an online risk assessment system were developed to predict mortality in HF patients, which performed well and might be used to guide clinical practice.

Keywords: Heart failure; In-hospital death; Logistic regression; Medical information mart for intensive care; Nomogram.

Fig. 1

Flow diagram of the selection process of patients

Fig. 2

ROC curves for LR1 and LR2 model in training and test cohorts. A ROC curves for LR1 model in training and test cohorts; B ROC curves for LR2 model in training and test cohorts; C AUC and 95% confidence interval for LR1 and LR2 models in training and test cohorts

Fig. 3

Nomogram developed to predict in-hospital all-cause mortality. Nomogram for in-hospital deaths in heart failure patients. First row: point allocation of variables; second to twelfth rows: eleven predictors; thirteenth row: total number of points for eleven predictors

Fig. 4

Calibration curves for LR1 and LR2 predicting in-hospital all-cause mortality in the training cohort and test cohort. A Calibration curves for the LR1 model predicting in-hospital all-cause mortality in the training cohort. B Calibration curves for the LR1 model predicting in-hospital all-cause mortality in the test cohort. C Calibration curves for the LR2 model predicting in-hospital all-cause mortality in the training cohort. D Calibration curves for the LR2 model predicting in-hospital all-cause mortality in the test cohort

Fig. 5

Decision curve analysis of the model. x-axis represents the threshold probability of in-hospital death and y-axis represents the net benefit. A DCA curves for the LR1 model predicting in-hospital all-cause mortality in the training cohort. B DCA curves of the LR1 model predicting in-hospital all-cause mortality in the test cohort. C Calibration curves for the LR2 model predicting in-hospital all-cause mortality in the training cohort. D Calibration curves for the LR2 model predicting in-hospital all-cause mortality in the test cohort

Fig. 6

Comparison of LR1 model and LR2 for predicting in-hospital all-cause mortality. A NRI was calculated in the training cohort. we used 10% and 30% as thresholds to define low-risk (< 10%), intermediate-risk (10–30%), and high-risk (> 30%) patients. the IDI is also listed above. B Calculation of NRI and IDI in the test cohort

Fig. 7

An example of an application to predict the risk of in-hospital all-cause mortality in HF patients