# Risk Model for Laryngeal Complications Prediction in Chinese Patients After Coronary Artery Bypass Grafting

## TL;DR

This study creates a risk model to predict laryngeal complications in Chinese patients after heart surgery, helping doctors identify high-risk patients.

## Contribution

A novel risk prediction model for laryngeal symptoms after CABG in Chinese patients is developed and validated.

## Key findings

- The incidence of laryngeal symptoms after CABG was 6.48%.
- The model achieved an AUC of 0.811 in the validation cohort, indicating good predictive accuracy.

## Abstract

The aim of this study was to identify perioperative risk factors of laryngeal
symptoms and to develop an implementable risk prediction model for Chinese
hospitalized patients undergoing coronary artery bypass grafting (CABG).

A total of 1476 Chinese CABG patients admitted to Wuhan Asian Heart Hospital
from January 2020 to June 2022 were included and then divided into a
modeling cohort and a verification cohort. Univariate analysis was used to
identify laryngeal symptoms risk factors, and multivariate logistic
regression was applied to construct a prediction model for laryngeal
symptoms after CABG. Discrimination and calibration of this model were
validated based on the area under the receiver operating characteristic
(ROC) curve and the Hosmer-Lemeshow (H-L) test, respectively.

The incidence of laryngeal symptoms in patients who underwent CABG was 6.48%.
Four independent risk factors were included in the model, and the
established aryngeal complications risk calculation formula was Logit
(P) = −4.525 + 0.824 × female + 2.09 ×
body mass index < 18.5 Kg/m2 + 0.793 × transesophageal
echocardiogram + 1.218 × intensive care unit intubation time. For
laryngeal symptoms, the area under the ROC curve was 0.769 in the derivation
cohort (95% confidence interval [CI]: 0.698-0.840) and 0.811 in the
validation cohort (95% CI: 0.742-0.879). According to the H-L test, the
P-values in the modeling group and the verification
group were 0.659 and 0.838, respectively.

The prediction model developed in this study can be used to identify
high-risk patients for laryngealsymptoms undergoing CABG, and help
clinicians implement the follow-up treatment.