Prognostic Value of Machine Learning-based Time-to-Event Analysis Using Coronary CT Angiography in Patients with
Maximilian J Bauer1, Nejva Nano1, Rafael Adolf1
1Institute for Radiology and Nuclear Medicine, Deutsches Herzzentrum München, Klinik an der Technischen Universität München, Lazarettstr 36, 80636 Munich, Germany.
Insights
A machine learning (ML) model using coronary CT angiography (CCTA) data significantly improved prediction of major adverse cardiovascular events compared to traditional methods. This ML approach offers enhanced prognostic value for patients with suspected coronary artery disease.
Area of Science:
- Cardiovascular Imaging
- Machine Learning in Medicine
- Prognostic Modeling
Background:
- Coronary artery disease (CAD) risk stratification is crucial for patient management.
- Traditional methods using clinical data and CT angiography (CCTA) parameters have limitations in long-term prediction.
- Novel approaches are needed to improve the accuracy of prognostic assessments.
Purpose of the Study:
- To evaluate the long-term prognostic capability of a machine learning (ML) model.
- To compare the ML model's performance against conventional methods using CCTA-derived and clinical parameters.
- To assess the ML model's effectiveness in predicting major adverse cardiovascular events (MACE).
Main Methods:
- Retrospective analysis of 5457 patients undergoing CCTA for suspected CAD.
- Development of two predictive models: a Cox proportional hazards model and a random survival forest ML model.
- Inclusion of clinical and CCTA-derived parameters, with validation using nested cross-validation and Harrell concordance index (C-index).
Main Results:
- The ML model achieved a higher predictive power (C-index, 0.74) compared to the Cox model (C-index, 0.71; P = .02).
- The ML model outperformed the best CCTA-derived parameter (segment stenosis score, C-index, 0.69) and the best clinical parameter (age, C-index, 0.66).
- The ML model demonstrated superior performance in predicting major adverse cardiovascular events.
Conclusions:
- A machine learning model based on random survival forests shows superior performance in time-to-event analysis.
- This ML approach provides enhanced long-term prognostic value for major adverse cardiovascular events.
- The ML model surpasses conventional clinical and CCTA-derived metrics for risk prediction in CAD.
Purpose:
To assess the long-term prognostic value of a machine learning (ML) approach in time-to-event analyses incorporating coronary CT angiography (CCTA)-derived and clinical parameters in patients with suspected coronary artery disease.
Materials And Methods:
The retrospective analysis included patients with suspected coronary artery disease who underwent CCTA between October 2004 and December 2017. Major adverse cardiovascular events were defined as the composite of all-cause death, myocardial infarction, unstable angina, or late revascularization (>90 days after index scan). Clinical and CCTA-derived parameters were assessed as predictors of major adverse cardiovascular events and incorporated into two models: a Cox proportional hazards model with recursive feature elimination and an ML model based on random survival forests. Both models were trained and validated by employing repeated nested cross-validation. Harrell concordance index (C-index) was used to assess the predictive power.
Results:
A total of 5457 patients (mean age, 61 years ± 11 [SD]; 3648 male patients) were evaluated. The predictive power of the ML model (C-index, 0.74; 95% CI: 0.71, 0.76) was significantly higher than the Cox model (C-index, 0.71; 95% CI: 0.68, 0.74; P = .02). The ML model also outperformed the segment stenosis score (C-index, 0.69; 95% CI: 0.66, 0.72; P < .001), which was the best performing CCTA-derived parameter, and patient age (C-index, 0.66; 95% CI: 0.63, 0.69; P < .001), the best performing clinical parameter.
Conclusion:
An ML model for time-to-event analysis based on random survival forests had higher performance in predicting major adverse cardiovascular events compared with established clinical or CCTA-derived metrics and a conventional Cox model.Keywords: Machine Learning, CT Angiography, Cardiac, Arteries, Heart, Arteriosclerosis, Coronary Artery DiseaseSupplemental material is available for this article.© RSNA, 2023.
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:28Imaging Studies for Cardiovascular System V: CT