Impact of Inflammation After Cardiac Surgery on 30-Day Mortality and Machine Learning Risk Prediction
Bibliographic record
Abstract
OBJECTIVES: To investigate the impact of systemic inflammatory response syndrome (SIRS) on 30-day mortality following cardiac surgery and develop a machine learning model to predict SIRS. DESIGN: Retrospective cohort study. SETTING: Single tertiary care hospital. PARTICIPANTS: Patients who underwent elective or urgent cardiac surgery with cardiopulmonary bypass (CPB) from 2016 to 2020 (N = 1,908). INTERVENTIONS: Mixed cardiac surgery operations were performed on CPB. Data analysis was made of preoperative, intraoperative, and postoperative variables without direct interventions. MEASUREMENTS AND MAIN RESULTS: SIRS, defined using American College of Chest Physicians/Society of Critical Care Medicine parameters, was assessed on the first postoperative day. The primary outcome was 30-day mortality. SIRS incidence was 28.7%, with SIRS-positive patients showing higher 30-day mortality (12.2% v 1.5%, p < 0.001). A multivariate logistic model identified predictors of SIRS. Propensity score matching balanced 483 patient pairs. SIRS was associated with increased mortality (OR 2.77; 95% CI 1.40-5.47, p = 0.003). Machine learning models to predict SIRS were developed. The baseline risk model achieved an area under the curve of 0.77 ± 0.04 in cross-validation and 0.73 (95% CI 0.70-0.85) on the test set, while the procedure-adjusted risk model showed improved performance with an area under the curve of 0.81 ± 0.02 in cross-validation and 0.82 (95% CI 0.76-0.85) on the test set. CONCLUSIONS: SIRS is significantly associated with increased 30-day mortality following cardiac surgery. Machine learning models effectively predict SIRS, paving the way for future investigations on potential targeted interventions that may mitigate adverse outcomes.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".