Development of Comorbidity Index for in-hospital mortality for patients who underwent coronary artery revascularization

Document Type

Journal Article

Publication Date

11-21-2023

Journal

The Journal of cardiovascular surgery

DOI

10.23736/S0021-9509.23.12833-3

Abstract

BACKGROUND: For myocardial revascularization, coronary artery bypass grafting (CAGB) and percutaneous coronary intervention (PCI) are two common modalities but with high in-hospital mortality. A Comorbidity Index is useful to predict mortality or can be used with other covariates to develop point-scoring systems. This study aimed to develop specific comorbidity indices for patients who underwent coronary artery revascularization. METHODS: Patients who underwent CABG or PCI were identified in the National Inpatient Sample database between Q4 2015-2020. Patients of age <40 were excluded for congenital heart defects. Patients were randomly sampled into experimental (70%) and validation (30%) groups. Thirty-eight Elixhauser comorbidities were identified and included in multivariable regression to discriminate in-hospital mortality. Weight for each comorbidity was assigned and single indices, Li CABG Mortality Index (LCMI) and Li PCI Mortality Index (LPMI), were developed. RESULTS: Mortality discrimination by LCMI approached adequacy (c-statistic=0.691, 95% CI=0.682-0.701) and was comparable to multivariable regression with comorbidities (c-statistic=0.685, 95% CI=0.675-0.694). LCMI discrimination performed significantly better than Elixhauser Comorbidity Index (ECI) (c-statistic=0.621, 95% CI=0.611-0.631) and can be further improved by adjusting age (c-statistic=0.721, 95% CI=0.712-0.730). All models were well-calibrated (Brier score=0.021-0.022). LPMI moderately discriminated in-hospital mortality (c-statistic=0.666, 95% CI=0.660-0.672) and performed significantly better than ECI (c-statistic=0.610, 95% CI=0.604-0.616). LPMI performed better than the all-comorbidity multivariable regression (c-statistic=0.658, 95% CI=0.652-0.663). After age adjustment, LPMI discrimination was significantly increased and was approaching adequacy (c-statistic=0.695, 95% CI=0.690-0.701). All models were well-calibrated (Brier score=0.025-0.026). CONCLUSIONS: LCMI and LPMI effectively discriminated and predicted in-hospital mortality. These indices were validated and performed superior to ECI. These indices can standardize comorbidity measurement as alternatives to ECI to help replicate and compare results across studies.

Department

School of Medicine and Health Sciences Student Works

Link to Full Text

Share

COinS