Identifying High Risk of Atherosclerosis Using Deep Learning and Ensemble Learning
Bibliographic record
Abstract
Atherosclerosis refers to the buildup of plaque on the artery walls. As the disease advances in its further stages, its burden could lead to stroke or heart attack. Atherosclerosis develops gradually, and mild stages of the condition are usually symptomless. Diagnosing patients in their early stages of the disease can facilitate timely clinical interventions enhancing patient's quality of life by altering the course of the disease. The work presented in this paper is focused on classifying patients who are at high risk of Atherosclerosis using simple diagnosis tools available in every clinic. The final system is a prescreening tool providing the medical practitioners with recommendations regarding the disease. High risk patients can be referred to a cardiologist for further assessments. A dataset of 44 patients was collected including 17 low-risk and 27 high-risk patients. Two different approaches were taken, 1. using deep learning and time series data (ECG signals) 2. using traditional machine learning algorithms and tabular data. In the first approach, a Conv-GRU model was trained using ECG signals collected from patients. This method resulted in an average accuracy of 77% which was computed over 4 folds using cross validation. In the second approach, Stacking, an ensemble learning technique in which the final prediction is obtained by combining the prediction of different machine learning models trained on several attributes readily collected in the clinic, was used. An average accuracy of 81% was achieved using this method.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 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".