A novel machine learning model with Stacking Ensemble Learner for predicting emergency readmission of heart-disease patients
Bibliographic record
Abstract
Early detection of heart complications is highly effective in treating patients with cardiovascular diseases. Various machine learning methods have previously been used for the early detection of heart diseases. However, existing data-driven machine learning (ML) approaches fall short of providing efficient and accurate heart disease detection. This misdiagnosis causes significant overcrowding in medical care facilities by patients that do not need emergency readmission or fatalities caused by discharging patients requiring emergency. This study proposes a novel model for detecting emergency readmission of heart disease patients by effectively identifying patients who require emergency assistance before the onset of heart attacks or other heart-related complications. A robust Stacking Ensemble Learner (SEL) is developed using ensemble learning to maximize the detection performance. Our SEL method predicts whether a patient with heart problems is required to get admitted as an emergency case after a preliminary admission. To ensure robustness and high accuracy in the prediction results across multiple runs, the XGBoost is used as a meta-learner in the SEL model. The novelty of this paper lies in (1) the use of behavior-based features to create a new class label for emergency readmission, which has not been previously explored in the existing data-driven machine learning approaches, (2) the paper utilizes a comprehensive private dataset from the MIT Laboratory for Computational Physiology, not adopted in clinical studies on heart failure and cardiovascular disease, and (3) The development of a robust Stacking Ensemble Learner (SEL) using ensemble learning, with XGBoost as a meta-learner, also contributes to the novelty of this study, as it achieves higher prediction performance compared to the baseline models, the use of ensemble learning in the SEL model helps to overcome the limitations of unstable training of the individual classification models. Experimental results show that the stacking model provides high accuracy, Recall, and F1 score compared to the baseline models such as logistic regression, k-nearest neighbor, Decision tree, Random Forest, support vector machines, bagging, and boosting. The SEL model has achieved an accuracy of 88% in predicting emergency readmission of heart-disease patients, which is very promising for the production-ready model in clinical practice.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".