Construction of diagnostic and prognostic models for premature coronary artery disease based on multiple machine
Yu-Chan He1,2, Ye Li1,2, Xiu-Jin Qin1,2
1Department of Cardiology, Liuzhou People's Hospital, Affiliated of Guangxi Medical University, Liuzhou, Guangxi, China.
Insights
The pan-immune-inflammation value (PIV) and triglyceride-glucose (TyG) index effectively diagnose premature coronary artery disease (PCAD). Elevated PIV and TyG levels predict poorer prognosis and increased mortality in PCAD patients.
Area of Science:
- Cardiology
- Biomarkers
- Machine Learning
Background:
- Premature coronary artery disease (PCAD) poses a significant health challenge.
- Identifying reliable diagnostic and prognostic markers for PCAD is crucial for patient management.
Purpose of the Study:
- To evaluate the diagnostic and prognostic predictive value of the pan-immune-inflammation value (PIV) and triglyceride-glucose (TyG) index in PCAD.
- To assess the combined utility of PIV, TyG, and white blood cell count (WBC) in predicting PCAD outcomes.
Main Methods:
- Analysis of data from 5,653 patients with chest pain using machine learning algorithms (GBM, XGBoost, SVM, Lasso, RF, logistic regression).
- Development of a decision tree model integrating key PCAD-related variables.
- Propensity score matching (PSM) for cohort comparability and Receiver Operating Characteristic (ROC) analysis for optimal cutoff values.
Main Results:
- Logistic regression identified PIV (OR 2.651) and TyG (OR 1.003) as significant risk factors for PCAD.
- The decision tree model incorporating PIV, TyG, and WBC achieved an accuracy of 0.88 and an AUC of 0.86 for PCAD diagnosis.
- Survival analysis indicated that lower PIV and TyG levels were associated with reduced mortality, while higher levels correlated with poorer prognosis over 36 months.
Conclusions:
- The combined assessment of PIV, TyG, and WBC provides robust diagnostic and prognostic value for PCAD.
- Elevated PIV and TyG levels are indicative of a poor prognosis in PCAD patients.
- PIV and TyG show potential as valuable clinical biomarkers for PCAD management.
Objective:
To evaluate the diagnostic and prognostic predictive value of the pan-immune-inflammation value (PIV) and triglyceride-glucose (TyG) index in premature coronary artery disease (PCAD).
Methods:
This study analyzed data from 26,883 patients admitted with chest pain at Liuzhou People's Hospital (January 2014 to December 2020), with 5,653 patients included after screening. Multiple machine learning algorithms, including Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Lasso regression, Random Forest (RF), and logistic regression, were applied to identify PCAD-related variables, which were integrated into a decision tree model. Propensity score matching (PSM) ensured cohort comparability. The Mime1 package facilitated ensemble feature selection and visualization, while optimal PIV and TyG cutoff values were determined via Receiver Operating Characteristic (ROC) analysis for 36-month survival subgroup analysis.
Results:
Logistic regression identified PIV [odds ratio [OR] 2.651, 95% CI [to be specified], P < 0.001] and TyG [OR 1.003, 95% CI (to be specified), P < 0.001] as PCAD risk factors. The decision tree model, incorporating PIV, TyG, and white blood cell count (WBC), achieved an accuracy of 0.88 and an area under the ROC curve (AUC) of 0.86 for PCAD diagnosis. Survival analysis over 36 months revealed that low PIV and TyG levels were associated with reduced all-cause mortality, whereas elevated levels correlated with poorer prognosis (P < 0.001), with TyG showing a pronounced effect.
Conclusion:
The combined evaluation of PIV, TyG, and WBC offers robust diagnostic and prognostic value for PCAD, with elevated PIV and TyG levels indicating a poor prognosis, underscoring their potential as clinical biomarkers.
