Related Experiment Video
Updated: Mar 27, 2026
Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
Unsupervised Phenomapping of Perioperative Risk in Stable Coronary Artery Disease: Revealing Limitations of the
RunZe Ye1, Jinan Yang1, Mengsha Shi1
1Department of Cardiology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Insights
Unsupervised learning identified six patient phenotypes for stable coronary artery disease (CAD) undergoing surgery. The CHALSA score demonstrated more consistent risk prediction across these phenotypes than the Revised Cardiac Risk Index (RCRI).
Area of Science:
- Cardiology
- Medical Informatics
- Risk Stratification
Background:
- Patients with stable coronary artery disease (CAD) undergoing non-cardiac surgery face variable perioperative risks.
- Existing risk indices may not adequately capture this heterogeneity.
Purpose of the Study:
- To derive unsupervised clinical phenotypes in stable CAD patients undergoing elective non-cardiac surgery.
- To evaluate the performance of the Revised Cardiac Risk Index (RCRI) and the laboratory-augmented CHALSA score stratified by these phenotypes for predicting major adverse cardiovascular events (MACE).
Main Methods:
- Retrospective cohort study of 9,171 patients with stable CAD undergoing elective non-cardiac surgery.
- Unsupervised machine learning applied to 22 preoperative variables to identify patient clusters (phenotypes).
- Assessed discrimination, calibration, and clinical utility of RCRI and CHALSA within each phenotype.
Main Results:
- Six distinct clinical phenotypes were identified, with perioperative MACE incidence ranging from 1.0% to 16.4%.
- The CHALSA score demonstrated superior overall discrimination (AUROC 0.816) compared to RCRI (AUROC 0.711).
- RCRI performance varied significantly across phenotypes, while CHALSA showed more stable predictive accuracy, particularly in phenotypes where RCRI underperformed.
Conclusions:
- Perioperative cardiovascular risk in stable CAD is significantly phenotype-dependent.
- The RCRI may misclassify risk in certain high-risk phenotypes, especially those with occult ischemia or metabolic issues.
- The CHALSA score offers more consistent risk stratification across phenotypes, warranting further validation for clinical use.
Aims:
To derive unsupervised clinical phenotypes in patients with stable coronary artery disease (CAD) undergoing elective non-cardiac surgery and evaluate phenotype-stratified performance of the Revised Cardiac Risk Index (RCRI) and laboratory-augmented CHALSA score for perioperative major adverse cardiovascular events (MACE).
Methods:
This single-center retrospective cohort included 9,171 patients with stable CAD undergoing elective non-cardiac surgery between 2013 and 2023. Unsupervised machine learning identified clusters using 22 preoperative variables. Discrimination, calibration, and clinical utility were evaluated overall and within each phenotype.
Results:
Overall, 514 (5.6%) patients experienced perioperative MACE. Six clinically interpretable phenotypes were identified, with MACE incidence ranging from 1.0% to 16.4%. CHALSA showed higher overall discrimination than RCRI (AUROC 0.816 vs 0.711; P<0.001). RCRI discrimination varied substantially across phenotypes and was non-significant in three phenotypes accounting for 60% of MACE burden. The greatest incremental discrimination was observed in Non-revascularized Ischemia (ΔAUROC 0.221), Severe Metabolic Burden (ΔAUROC 0.264), and Stable Revascularized (ΔAUROC 0.205), while CHALSA also showed incremental discrimination in Low-Risk (ΔAUROC 0.172), Ischemic HF (ΔAUROC 0.086), and Elderly Frailty (ΔAUROC 0.142). Across phenotypes, CHALSA showed more stable performance, particularly where RCRI underperformed.
Conclusion:
Perioperative risk in stable CAD is phenotype-dependent. In this single-center cohort, RCRI performance varied by phenotype and may misclassify risk in clinically important high-risk phenotypes, particularly those characterized by occult ischemia or metabolic dysregulation. CHALSA showed more stable performance across phenotypes, but external validation is needed before broader clinical adoption.
More Related Videos
Related Concept Videos
01:27Coronary Artery Disease V: Interprofessional Care
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:30Coronary Artery Disease I: Introduction
01:28Cardiomyopathy VII: Pre and Post Operative Nursing Management
01:26Coronary Artery Disease IV: Preventive Measures
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT