AI-Powered Preoperative Chest Radiograph-Derived Cardiovascular Border Indices and Risk of Postoperative Major Adverse Cardiovascular Events: A Large-Scale Retrospective Cohort Study.
5 affiliations
- 1Department of Anesthesiology and Pain Medicine, Asan Medical Center, Brain Korea 21 Project, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Republic of Korea.
- 2Department of Radiology (Cardiovascular Imaging), Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Republic of Korea.
- 3Big Data Research Center, Asan Institute for Life Science, Asan Medical Center, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Republic of Korea.
- 4Biomedical Engineering Research Center, Asan Institute for Life Science, Asan Medical Center, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Republic of Korea.
- 5Institute of Digital Healthcare, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Republic of Korea.
Abstract
Background and Objectives: Routine preoperative chest radiography (CXR) has limited value for perioperative risk prediction when interpreted qualitatively. The Automated Diagnosis of Cardiovascular abnormalities (ADC) model enables automated quantification of cardiomediastinal vascular border (CVB) parameters on CXR. This study evaluated the associations of AI-derived CVB metrics with postoperative major adverse cardiovascular events (MACE) and their incremental predictive value beyond clinical factors. Materials and Methods: This retrospective cohort study included patients who underwent surgery under general anesthesia at a tertiary academic center. The ADC model quantified CVB parameters as raw measurements and age- and sex-adjusted z-scores. The primary outcome was postoperative in-hospital MACE. Associations were assessed using multivariable logistic regression, and discrimination was evaluated using receiver operating characteristic curve analysis. Incremental predictive performance was assessed by adding selected CVB parameters to a clinical reference model. Results: Among 101,531 patients, MACE occurred in 1655 patients (1.6%). All ADC-derived CVB parameters remained independently associated with MACE after multivariable adjustment. For cardiothoracic ratio, the adjusted OR was 1.64 (95% CI, 1.58-1.70; p < 0.001), with an AUC of 0.789. For the composite CVB z-score, the adjusted OR was 1.88 (95% CI, 1.79-1.97; p < 0.001), with an AUC of 0.762. Adding either the CT ratio or composite CVB z-score to the clinical reference model increased the AUC from 0.894 to 0.906 (p < 0.001 for both), with similar improvement in temporal validation. Conclusions: AI-derived CVB parameters from preoperative CXR were independently associated with postoperative in-hospital MACE and provided modest incremental predictive information beyond routinely available clinical factors. Automated CVB analysis may provide additional cardiovascular risk information from a routinely obtained preoperative CXR without additional imaging or patient burden, although further external validation is required to establish its clinical utility.
Related
- Association of preoperative systemic immune-inflammation index and geriatric nutritional risk index with prolonged postoperative length of stay in older patients with hip fracture : A retrospective cohort study
- Preoperative HbA1c and postoperative day 1 fasting plasma glucose are associated with early glycemic improvement after transsphenoidal surgery in patients with acromegaly and preoperative dysglycemia: a retrospective cohort study.
- Preoperative metabolic–inflammatory profiles and early postoperative recovery after immediate breast reconstruction in patients with and without neoadjuvant chemotherapy: a retrospective cohort study
- Can Routine Preoperative Endoscopy and Colonoscopy Be Meaningful for the Surgery and Postoperative Course of Patients with Advanced Ovarian Cancer? A Single-Centre Retrospective Cohort Study.
- Association of Preoperative Plateletcrit and Other Inflammatory Indices with Postoperative Pain Severity and Opioid Consumption in Morbidly Obese Patients Receiving Transversus Abdominis Plane Block: A Retrospective Observational Study
BibTeX
@article{jang2026aipowered,
title = {{AI-Powered Preoperative Chest Radiograph-Derived Cardiovascular Border Indices and Risk of Postoperative Major Adverse Cardiovascular Events: A Large-Scale Retrospective Cohort Study.}},
author = {Hwa-Young Jang and Jeong Hwan Kim and Hong Min Oh and Hong-Cheol Yoon and Chang-Woo Kim and Woo-Jin Kim and Hyun-Seok Kim and Woo-Young Seo and Dong Hyun Yang and Sung-Hoon Kim},
journal = {Medicina (Kaunas, Lithuania)},
year = {2026},
month = sep,
doi = {10.3390/medicina62101897},
url = {https://europepmc.org/article/MED/42942428},
note = {CC BY},
}
RIS
TY - JOUR
TI - AI-Powered Preoperative Chest Radiograph-Derived Cardiovascular Border Indices and Risk of Postoperative Major Adverse Cardiovascular Events: A Large-Scale Retrospective Cohort Study.
AU - Hwa-Young Jang
AU - Jeong Hwan Kim
AU - Hong Min Oh
AU - Hong-Cheol Yoon
AU - Chang-Woo Kim
AU - Woo-Jin Kim
AU - Hyun-Seok Kim
AU - Woo-Young Seo
AU - Dong Hyun Yang
AU - Sung-Hoon Kim
PY - 2026
DA - 2026/09/30
JO - Medicina (Kaunas, Lithuania)
DO - 10.3390/medicina62101897
UR - https://europepmc.org/article/MED/42942428
AB - Background and Objectives: Routine preoperative chest radiography (CXR) has limited value for perioperative risk prediction when interpreted qualitatively. The Automated Diagnosis of Cardiovascular abnormalities (ADC) model enables automated quantification of cardiomediastinal vascular border (CVB) parameters on CXR. This study evaluated the associations of AI-derived CVB metrics with postoperative major adverse cardiovascular events (MACE) and their incremental predictive value beyond clinical factors. Materials and Methods: This retrospective cohort study included patients who underwent surgery under general anesthesia at a tertiary academic center. The ADC model quantified CVB parameters as raw measurements and age- and sex-adjusted z-scores. The primary outcome was postoperative in-hospital MACE. Associations were assessed using multivariable logistic regression, and discrimination was evaluated using receiver operating characteristic curve analysis. Incremental predictive performance was assessed by adding selected CVB parameters to a clinical reference model. Results: Among 101,531 patients, MACE occurred in 1655 patients (1.6%). All ADC-derived CVB parameters remained independently associated with MACE after multivariable adjustment. For cardiothoracic ratio, the adjusted OR was 1.64 (95% CI, 1.58-1.70; p < 0.001), with an AUC of 0.789. For the composite CVB z-score, the adjusted OR was 1.88 (95% CI, 1.79-1.97; p < 0.001), with an AUC of 0.762. Adding either the CT ratio or composite CVB z-score to the clinical reference model increased the AUC from 0.894 to 0.906 (p < 0.001 for both), with similar improvement in temporal validation. Conclusions: AI-derived CVB parameters from preoperative CXR were independently associated with postoperative in-hospital MACE and provided modest incremental predictive information beyond routinely available clinical factors. Automated CVB analysis may provide additional cardiovascular risk information from a routinely obtained preoperative CXR without additional imaging or patient burden, although further external validation is required to establish its clinical utility.
SN - 1010-660X
SN - 1648-9144
ER -