Key result
XGBoost model accurately classifies coronary artery stenosis with ~0.92 AUC in suspected CHD.
Why the study?
Accurate, reliable, non-invasive, and cost-effective methods for diagnosing coronary stenosis in suspected CHD patients are required to reduce risks and costs of invasive coronary angiography.
Does a machine learning-based risk-prediction system accurately predict coronary artery stenosis severity in patients with suspected coronary heart disease?
Observational (n=1,577)
Does a machine learning-based risk-prediction system accurately predict coronary artery stenosis severity in patients with suspected coronary heart disease?
Effect estimate: micro-average ROC 0.92
A machine learning-based risk-prediction system using XGBoost accurately classifies coronary artery stenosis severity in patients with suspected CHD, potentially reducing the need for unnecessary invasive angiographies.
May aid noninvasive stenosis assessment in suspected CHD; leaves open prospective validation before clinical use.
Invasive coronary angiography imposes risks and high medical costs. Therefore, accurate, reliable, non-invasive, and cost-effective methods for diagnosing coronary stenosis are required. We designed a machine learning-based risk-prediction system as an accurate, noninvasive, and cost-effective alternative method for evaluating suspected coronary heart disease (CHD) patients. Electronic medical record data were collected from suspected CHD patients undergoing coronary angiography between May 1, 2017, and December 31, 2019. Multi-Class XGBoost, LightGBM, Random Forest, NGBoost, logistic models and MLP were constructed to identify patients with normal coronary arteries (class 0: no coronary artery stenosis), minimum coronary artery stenosis (class 1: 0 < stenosis <50%), and CHD (class 2: stenosis ≥50%). Model stability was verified externally. A risk-assessment and management system was established for patient-specific intervention guidance. Of 1577 suspected CHD patients, 81 (5.14%) had normal coronary arteries. The XGBoost model demonstrated the best overall classification performance (micro-average receiver operating characteristic [ROC] curve: 0.92, macro-average ROC curve: 0.89, class 0 ROC curve: 0.88, class 1 ROC curve: 0.90, class 2 ROC curve: 0.89), with good external verification. In class-specific classification, the XGBoost model yielded F1 values of 0.636, 0.850, and 0.858, for Classes 0, 1, and 2, respectively. The visualization system allowed disease diagnosis and probability estimation, and identified the intervention focus for individual patients. Thus, the system distinguished coronary artery stenosis well in suspected CHD patients. Personalized probability curves provide individualized intervention guidance. This may reduce the number of invasive inspections in negative patients, while facilitating decision-making regarding appropriate medical intervention, improving patient prognosis.
No takes yet. Share an insight, caveat, or question.
Yan et al. (2022) conducted an observational in suspected coronary heart disease (n=1,577). Machine learning-based risk-prediction system (XGBoost) vs. Other machine learning models (LightGBM, Random Forest, NGBoost, logistic models, MLP) was evaluated on Classification of coronary artery stenosis (normal, minimum, CHD) (micro-average ROC 0.92). An XGBoost machine learning model accurately classified coronary artery stenosis in suspected CHD patients, achieving a micro-average ROC of 0.92 and macro-average ROC of 0.89.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: