Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 26:12:1573874.
doi: 10.3389/fcvm.2025.1573874. eCollection 2025.

A novel scoring model for predicting prolonged mechanical ventilation in cardiac surgery patients: development and validation

Quan Liu #  1   2 , Pengfei Chen #  3 , Wuwei Wang #  2 , Yifei Zhou  1   2 , Yichen Xu  2 , Xu Cao  2 , Rui Fan  2 , Wen Chen  2 , Fuhua Huang  2 , Xin Chen  1   2
Affiliations

A novel scoring model for predicting prolonged mechanical ventilation in cardiac surgery patients: development and validation

Quan Liu et al. Front Cardiovasc Med. .

Abstract

Objective: Prolonged mechanical ventilation (PMV) is a significant postoperative complication in cardiac surgery, associated with increased mortality and healthcare costs. This study aims to develop and validate a novel scoring model to predict the risk of PMV in cardiac surgery patients.

Methods: A retrospective analysis was conducted using data from 14 comprehensive hospitals in Jiangsu Province, including adult patients who underwent coronary artery bypass grafting (CABG), valve surgery, and aortic surgery from January 2021 to December 2022. Predictive variables were selected based on clinical expertise and prior literature, and a nomogram was developed using LASSO regression and multiple logistic regression. Model performance was evaluated using the C-index, calibration plots, and decision curve analysis (DCA).

Results: A total of 5,206 patients were included in the final analysis. The incidence rate of PMV were 11.83% in the training set, 8.65% in the internal validation set, and 15.4% in the external validation set. The nomogram identified 9 significant predictors, including age, gender, preoperative conditions, and surgical factors. The model demonstrated robust performance with C-index values of 0.79 in the training and internal validation sets and 0.75 in the external validation set, indicating good predictive capability. Calibration curves confirmed the accuracy of predicted probabilities, and DCA indicated substantial net benefits for clinical decision-making.

Conclusions: This study presents a validated scoring model for predicting PMV in cardiac surgery patients, integrating a comprehensive range of clinical variables. The model facilitates early identification of high-risk patients, enabling tailored perioperative strategies and potentially improving patient outcomes and resource utilization in cardiac surgery.

Keywords: cardiac surgery; multiple centers; predicting model; prolonged mechanical ventilation; retrospective study.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Participant selection and dataset division.
Figure 2
Figure 2
Variables selection using the LASSO regression models. (A) LASSO coefficient profiles of the 29 variables. Variables are included in the LASSO regression model for selection, the regression coefficients progressively diminish towards zero with increasing penalty. (B) Optimal parameter (lambda) selection in the LASSO model used 10-fold cross-validation via minimum criteria.
Figure 3
Figure 3
Nomogram derived from training set for predicting prolonged mechanical ventilation.
Figure 4
Figure 4
Model performance of the nomogram for predicting prolonged mechanical ventilation after cardiac surgery in train set (A,D,G), internal validation set (B,E,H) and external validation set (C,F,I).
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Rahimi S, Abdi A, Salari N, Shohaimi S, Naghibeiranvand M. Factors associated with long-term mechanical ventilation in patients undergoing cardiovascular surgery. BMC Cardiovasc Disord. (2023) 23(1):276. 10.1186/s12872-023-03315-7 - DOI - PMC - PubMed
    1. Aksoy R, Karakoc AZ, Cevirme D, Elibol A, Yigit F, Yilmaz Ü, et al. Predictive factors of prolonged ventilation following cardiac surgery with cardiopulmonary bypass. Braz J Cardiovasc Surg. (2021) 36(6):780–7. 10.21470/1678-9741-2020-0164 - DOI - PMC - PubMed
    1. Jin M, Ma WG, Liu S, Zhu J, Sun L, Lu J, et al. Predictors of prolonged mechanical ventilation in adults after acute type-a aortic dissection repair. J Cardiothorac Vasc Anesth. (2017) 31(5):1580–7. 10.1053/j.jvca.2017.03.036 - DOI - PubMed
    1. Diaz-Castrillon CE, Brown JA, Navid F, Serna-Gallegos D, Yousef S, Thoma F, et al. The impact of prolonged mechanical ventilation after acute type a aortic dissection repair. J Thorac Cardiovasc Surg. (2022) 167(5):1672–9.S0022522322007309. - PubMed
    1. Mathis MR, Duggal NM, Likosky DS, Haft JW, Douville NJ, Vaughn MT, et al. Intraoperative mechanical ventilation and postoperative pulmonary complications after cardiac surgery. Anesthesiology. (2019) 131(5):1046–62. 10.1097/ALN.0000000000002909 - DOI - PMC - PubMed

LinkOut - more resources