Open heart · 2026
Explainable machine-learning model for coronary artery disease diagnosis in non-AMI patients: integrating inflammatory and traditional risk factors.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Yang Kexin, Liu Sheng, Wang Chenyang, Ni Siyao, Bi Ludan, Yang Yunxiao, Zhang Ming
Аннотация
OBJECTIVE: To develop and interpret an explainable machine learning (ML) model integrating inflammatory biomarkers and traditional risk factors for the diagnosis of coronary artery disease (CAD).
METHODS: We retrospectively analysed 4656 patients undergoing coronary angiography for suspected CAD. Demographic, clinical, biochemical and 12 inflammatory cytokine variables were collected. Least absolute shrinkage and selection operator regression identified 21 candidate features. 10 ML algorithms were trained using cross-validation. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, specificity and F1 score. Model explainability was assessed using SHapley Additive exPlanations (SHAP).
RESULTS: Among the evaluated models, the generalised linear model showed balanced performance and was selected as the final model (AUC=0.815). SHAP analysis identified hypertension, hyperlipidaemia, sex, triglycerides and interleukin-6 as the most influential predictors of CAD.
CONCLUSIONS: These findings underscore the potential of interpretable ML approaches that combine inflammatory and traditional markers to enhance early CAD diagnosis and inform clinical decision-making.
METHODS: We retrospectively analysed 4656 patients undergoing coronary angiography for suspected CAD. Demographic, clinical, biochemical and 12 inflammatory cytokine variables were collected. Least absolute shrinkage and selection operator regression identified 21 candidate features. 10 ML algorithms were trained using cross-validation. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, specificity and F1 score. Model explainability was assessed using SHapley Additive exPlanations (SHAP).
RESULTS: Among the evaluated models, the generalised linear model showed balanced performance and was selected as the final model (AUC=0.815). SHAP analysis identified hypertension, hyperlipidaemia, sex, triglycerides and interleukin-6 as the most influential predictors of CAD.
CONCLUSIONS: These findings underscore the potential of interpretable ML approaches that combine inflammatory and traditional markers to enhance early CAD diagnosis and inform clinical decision-making.