Prediction Model of Cardiac Risk for Dental Extraction in Elderly Patients with Cardiovascular Diseases

Clinical profile analysis and nomogram for predicting in-hospital mortality among elderly severe community-acquired pneumonia patients with comorbid cardiovascular disease: a retrospective cohort study

Background

Researchers have linked cardiovascular disease (CVD) with advancing age; however, how it drives disease progression in elderly severe community acquired pneumonia (SCAP) patients is still unclear. This study aims to identify leading risk predictors of in-hospital mortality in elderly SCAP patients with CVD, and construct a comprehensive nomogram for providing personalized prediction.

Patients and methods

The study retrospectively enrolled 2365 elderly patients identified SCAP. Among them, 413 patients were found to have CVD. The LASSO regression and multivariate logistic regression analysis were utilized to select potential predictors of in-hospital mortality in elderly SCAP patients with CVD. By incorporating these features, a nomogram was then developed and subjected to internal validations. Discrimination, calibration, and clinical use of the nomogram were assessed via C-index, calibration curve analysis, and decision plot.

Results

Compared with patients without CVD, elderly SCAP patients with CVD had a significant poor outcome. Further analysis of the CVD population identified 7 independent risk factors for in-hospital mortality in elderly SCAP patients, including age, the use of vasopressor, numbers of primary symptoms, body temperature, monocyte, CRP and NLR. The nomogram model incorporated these 7 predictors showed sufficient predictive accuracy, with the C-index of 0.800 (95% CI 0.758–0.842). High C-index value of 0.781 was obtained in the internal validation via bootstrapping validation. Moreover, the calibration curve indicative a good consistency of risk prediction, and the decision curve manifested that the nomogram had good overall net benefits.

Conclusion

An integrated nomogram was developed to facilitate the personalized prediction of in-hospital mortality in elderly SCAP patients with CVD.

A relationship between the incremental values of area under the ROC curve and of area under the precision-recall curve

BACKGROUND

Incremental value (IncV) evaluates the performance change between an existing risk model and a new model. Different IncV metrics do not always agree with each other. For example, compared with a prescribed-dose model, an ovarian-dose model for predicting acute ovarian failure has a slightly lower area under the receiver operating characteristic curve (AUC) but increases the area under the precision-recall curve (AP) by 48%. This phenomenon of disagreement is not uncommon, and can create confusion when assessing whether the added information improves the model prediction accuracy.

METHODS

In this article, we examine the analytical connections and differences between the AUC IncV (ΔAUC) and AP IncV (ΔAP). We also compare the true values of these two IncV metrics in a numerical study. Additionally, as both are semi-proper scoring rules, we compare them with a strictly proper scoring rule: the IncV of the scaled Brier score (ΔsBrS) in the numerical study.

RESULTS

We demonstrate that ΔAUC and ΔAP are both weighted averages of the changes (from the existing model to the new one) in separating the risk score distributions between events and non-events. However, ΔAP assigns heavier weights to the changes in higher-risk regions, whereas ΔAUC weights the changes equally. Due to this difference, the two IncV metrics can disagree, and the numerical study shows that their disagreement becomes more pronounced as the event rate decreases. In the numerical study, we also find that ΔAP has a wide range, from negative to positive, but the range of ΔAUC is much smaller. In addition, ΔAP and ΔsBrS are highly consistent, but ΔAUC is negatively correlated with ΔsBrS and ΔAP when the event rate is low.

CONCLUSIONS

ΔAUC treats the wins and losses of a new risk model equally across different risk regions. When neither the existing or new model is the true model, this equality could attenuate a superior performance of the new model for a sub-region. In contrast, ΔAP accentuates the change in the prediction accuracy for higher-risk regions.