Ensemble Machine Learning and Its Validation for Prediction of Coronary Artery Disease and Acute Coronary Syndrome Using Focused Carotid Ultrasound
Bibliographic record
Abstract
The objective of this study is to demonstrate the effectiveness of ensemble-learning-driven machine learning (EML) algorithms over the conventional ML (CML) algorithms in predicting cardiovascular events (CVEs) such as coronary artery disease (CAD) and acute coronary syndrome (ACS). Furthermore, this study demonstrates the improvement in overall CVE prediction by including carotid ultrasound image phenotypes in the feature set. The methodology consisted of collecting and amalgamating 24 risk predictors along with coronary angiography as the gold standard. We further hypothesize that for such a fused set of predictors, EML systems can perform better compared with CML systems. The EML system design consisted of risk predictors for each of 459 participants undergoing baseline characteristics and independent K10-based training model generation based on three sets of algorithms: seven CML, three homogeneous ensemble ML (EML-homo), and five heterogeneous ensemble ML (EML-hetro). These training models were then applied to the test patients to predict CAD and ACS. As part of the performance, the AUC for EML-homo improved over CML by 4.3% for CAD and 1.1% for ACS, respectively. Similarly, the AUC for EML-hetro improved over CML by 3.23% for CAD and 2.11% for ACS, respectively. The proposed EML-based system was validated against the two validation databases consisting of 303 and 522 participants for CAD and ACS. We thus conclude that the EML-based algorithms are better in predicting CAD and ACS, compared with CML, proving our hypothesis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".