Predicting prolonged length of in-hospital stay in patients with non-ST elevation myocardial infarction (NSTEMI) using artificial intelligence
Bibliographic record
Abstract
BACKGROUND: Patients presenting with non-ST elevation myocardial infarction (NSTEMI) are typically evaluated using coronary angiography and managed through coronary revascularization. Numerous studies have demonstrated the benefits of expedited discharge following revascularization in this patient population. However, individuals with concomitant heart failure, hemodynamic instability, or arrhythmias often necessitate prolonged hospitalization. Using aortic pressure (AP) wave assessment, we aim to predict a prolonged length of stay (> 4 days, PLoS) in patients with NSTEMI treated with percutaneous coronary intervention (PCI). METHODS: In this single-center, retrospective cohort study, we included 497 patients with NSTEMI [66.3 ± 12.9 years, 37.6 % (187) females]. We developed a predictive model for PLoS using features primarily extracted from the AP signal recorded throughout PCI. We performed feature selection using recursive feature elimination (RFE) with cross-validation and built a machine learning (ML) model using the CatBoost tree-based classifier. The decision-making process of the ML model was analyzed using SHapley Additive exPlanations (SHAP). RESULTS: We achieved average accuracy, specificity, sensitivity, precision, and receiver operating characteristic curve area under the curve (AUC) values of 77 %, 78 %, 76 %, 67 %, and 77 %, respectively. Using SHAP, we identified the ejection systolic period, ejection systolic time, the difference between systolic blood pressure and dicrotic notch pressure (DesP), the age modified shock index (mSI_age) and mean arterial pressure (MAP) as the most characteristic features extracted from the AP signal. CONCLUSIONS: In conclusion, this study demonstrates the potential of using ML and features extracted from the AP signal to predict PLoS in patients with NSTEMI.
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 | 0.000 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".