What question did this study set out to answer?

The aim is to develop a machine learning model to predict acute coronary syndrome based on lipid biomarkers.

March 2, 2026Open Access

A Novel Risk Score Based on Lipid-Related Biomarkers for Acute Coronary Syndromes: A Multicenter Machine Learning Study

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Hospitalized adult Chinese Han patients without advanced heart failure (NYHA III-IV), chronic coronary syndrome, major surgery or infection in preceding months, and severe systemic diseases affecting lipid metabolism (n=10127). Intervention: Light Gradient Boosting Machine (ML risk prediction model based on lipid-related biomarkers and clinical features) vs. Other machine learning models and logistic regression model (Decision Tree, Random Forest, XGBoost, SVM, MLP, Elastic Net, Logistic Regression). Primary outcome: Incidence of acute coronary syndrome (ACS) during hospitalization diagnosed per 2014 ACC/AHA guidelines (AUC 0.790 in test set for LightGBM model).

Key Result

The LightGBM model based on lipid-related biomarkers predicted acute coronary syndrome with an AUC of 0.790 in the test set of hospitalized Chinese patients.

Key Points

The aim is to develop a machine learning model to predict acute coronary syndrome based on lipid biomarkers.
Retrospective study of 10,127 hospitalized patients across three hospitals
Used eight machine learning models for risk calculations
Divided patient data into training (70%) and test (30%) sets
Primary outcome measured was incidence of acute coronary syndrome
ACS occurred in 15.8% of the training set and 15.2% of the test set
LightGBM model showed the best predictive performance with an AUC of 0.829
Final model achieved a C-index of 0.781 on the test set
Effectively stratified patients into low-, intermediate-, and high-risk categories

Study Design

Type

Observational (n=10,127)

Multicenter

Yes

Structured PICO

Does a machine learning-derived risk score based on lipid-related biomarkers accurately predict acute coronary syndrome in hospitalized patients?

Population

10,127 consecutive hospitalized adult patients in the Department of Cardiology across three large hospitals (Chinese Han population), mean age 64.9, 62.8% male. Key exclusions: advanced heart failure (NYHA III/IV), history of cardiac arrest, chronic coronary syndrome, severe systemic diseases affecting lipid metabolism, major surgery within 6 months, and major infectious diseases within 3 months.

Intervention

A novel risk score based on lipid-related biomarkers (UHR, TyG, Lp(a)) and clinical features derived from the Light Gradient Boosting Machine (LightGBM) model

Outcome

Diagnosis of acute coronary syndrome (ACS) during hospital admissionhard clinical

A novel machine learning-derived risk score incorporating lipid-related biomarkers (UHR, TyG, Lp(a)) and clinical features can effectively stratify the risk of acute coronary syndrome in hospitalized patients.

Main Result

Effect estimate: AUC 0.790 in test set for LightGBM model

Absolute Event Rate: 15.2% vs 15.8%

Limitations

Retrospective design cannot establish causality between lipid markers and ACS.
Potential bias from data collection and hospital differences despite multicenter design.
Possible model overfitting indicated by discrepancy in AUC between training and test sets.
No direct comparison to established risk scores like GRACE and TIMI for ACS risk prediction.
Did not assess association between risk score and long-term outcomes.
Exclusion of some traditional risk factors such as smoking and medication use in the model.
Potential confounders like lifestyle and genetics not fully controlled.
Prospective validation needed.

Abstract

Background: This study aimed to develop and test an explainable machine learning (ML) predictive model based on lipid-related biomarkers to predict acute coronary syndrome (ACS) in hospitalized patients. Methods: A total of 10,127 consecutive hospitalized patients at three large hospitals were retrospectively studied between 2022 and 2024. ACS incidence was recorded as the primary outcome. Eight ML models were used to calculate the risk of ACS during hospitalization and to distribute patients into low-, intermediate-, and high-risk groups. Results: All patients were randomly divided into a 70% training set (n = 7088) and a 30% test set (n = 3039). ACS occurred in 1119 (15.8%) and 461 (15.2%) patients, respectively. The Light Gradient Boosting Machine (LightGBM) exhibited the best predictive performance (area under the curve, 0.829) for ACS in the training set. The final model, which included the top 10 features from the LightGBM model, including lipid-related markers and clinical features, achieved a C-index of 0.781 on the test set and demonstrated a significant ability to stratify patients into low-, intermediate-, and high-risk groups. Conclusion: We constructed a risk-stratification model based on lipid-related biomarkers derived from ML models to predict ACS in hospitalized patients, which could assist in identifying patients with high discriminatory capacity.

KI fragen

Bookmark

View Full Paper

KI fragen

Bookmark

View Full Paper

Cite This Study

Wan et al. (Wed,) conducted a observational in Hospitalized adult Chinese Han patients without advanced heart failure (NYHA III-IV), chronic coronary syndrome, major surgery or infection in preceding months, and severe systemic diseases affecting lipid metabolism (n=10,127). Light Gradient Boosting Machine (ML risk prediction model based on lipid-related biomarkers and clinical features) vs. Other machine learning models and logistic regression model (Decision Tree, Random Forest, XGBoost, SVM, MLP, Elastic Net, Logistic Regression) was evaluated on Incidence of acute coronary syndrome (ACS) during hospitalization diagnosed per 2014 ACC/AHA guidelines (AUC 0.790 in test set for LightGBM model). The LightGBM model based on lipid-related biomarkers predicted acute coronary syndrome with an AUC of 0.790 in the test set of hospitalized Chinese patients.

synapsesocial.com/papers/69a52e75f1e85e5c73bf2253 https://doi.org/https://doi.org/10.31083/rcm44578

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: