Machine learning integration of circulating and imaging biomarkers for explainable patient-specific prediction of
Balaji K Tamarappoo1, Andrew Lin2, Frederic Commandeur1
1Department of Imaging and Medicine and the Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Insights
A new machine learning (ML) risk score combining blood biomarkers and CT imaging significantly improves long-term prediction of cardiac events in asymptomatic individuals, outperforming current methods.
Area of Science:
- Cardiology
- Medical Imaging
- Machine Learning
Background:
- Assessing long-term cardiac event risk in asymptomatic individuals is crucial.
- Current risk prediction tools have limitations in accuracy.
Purpose of the Study:
- To evaluate a machine learning (ML) risk score integrating circulating biomarkers and computed tomography (CT) measures.
- To predict hard cardiac events in asymptomatic subjects.
Main Methods:
- A prospective study of 1069 subjects from the EISNER trial.
- Utilized coronary artery calcium (CAC) scoring CT, serum biomarkers, and deep learning for epicardial adipose tissue (EAT) quantification.
- Trained an ML algorithm (XGBoost) with clinical factors, CT measures, and biomarkers, validated via cross-validation.
Main Results:
- The ML risk score achieved an AUC of 0.81, outperforming CAC score (0.75) and ASCVD risk score (0.74).
- Serum biomarkers added significant prognostic value (NRI 0.53, p < 0.0001).
- Key novel biomarkers (MMP-9, pentraxin 3, PIGR, GDF-15) indicated inflammation, matrix remodeling, and fibrosis pathways.
Conclusions:
- ML integration of biomarkers and imaging offers superior long-term cardiac event risk prediction.
- This approach surpasses current risk assessment tools for asymptomatic individuals.
Background And Aims:
We sought to assess the performance of a comprehensive machine learning (ML) risk score integrating circulating biomarkers and computed tomography (CT) measures for the long-term prediction of hard cardiac events in asymptomatic subjects.
Methods:
We studied 1069 subjects (age 58.2 ± 8.2 years, 54.0% males) from the prospective EISNER trial who underwent coronary artery calcium (CAC) scoring CT, serum biomarker assessment, and long-term follow-up. Epicardial adipose tissue (EAT) was quantified from CT using fully automated deep learning software. Forty-eight serum biomarkers, both established and novel, were assayed. An ML algorithm (XGBoost) was trained using clinical risk factors, CT measures (CAC score, number of coronary lesions, aortic valve calcium score, EAT volume and attenuation), and circulating biomarkers, and validated using repeated 10-fold cross validation.
Results:
At 14.5 ± 2.0 years, there were 50 hard cardiac events (myocardial infarction or cardiac death). The ML risk score (area under the receiver operator characteristic curve [AUC] 0.81) outperformed the CAC score (0.75) and ASCVD risk score (0.74; both p = 0.02) for the prediction of hard cardiac events. Serum biomarkers provided incremental prognostic value beyond clinical data and CT measures in the ML model (net reclassification index 0.53 [95% CI: 0.23-0.81], p < 0.0001). Among novel biomarkers, MMP-9, pentraxin 3, PIGR, and GDF-15 had highest variable importance for ML and reflect the pathways of inflammation, extracellular matrix remodeling, and fibrosis.
Conclusions:
In this prospective study, ML integration of novel circulating biomarkers and noninvasive imaging measures provided superior long-term risk prediction for cardiac events compared to current risk assessment tools.
