Improving the performance of the Cleveland Clinic Score for predicting acute kidney injury after cardiac surgery: a prospective multicenter cohort study
Bibliographic record
Abstract
BACKGROUND: Cardiac surgery-associated acute kidney injury (CSA-AKI) is associated with high short- and long-term mortality rates. The prediction of CSA-AKI is crucial for early detection and treatment. Current predictive models may be improved by potentially useful preoperative and intraoperative information. METHODS: This multicenter prospective cohort study recruited 261 consecutive patients at high risk for developing CSA-AKI, based on a Cleveland Clinical Score (CCS) of ≥4 points from July to December 2017 in 14 hospitals in Spain and the UK. Postoperative AKI occurred in 145 (55.5%) patients. The receiver operating characteristics curve (AUC) of a base model including only the CCS was compared with models including additional preoperative and intraoperative variables such as the estimated glomerular filtration rate (eGFR) instead of plasmatic creatinine, intraoperative urine output, baseline hemoglobin, nadir hemoglobin, and glycosylated hemoglobin (HbA<inf>1c</inf>) instead of diabetes mellitus. The performance of each model for AKI was compared. RESULTS: The CCS alone gave an AUC of 0.67 (95% CI, 0.56-0.78) for postoperative AKI. None of the single variables added to the base model CCS improve discrimination. The AUC for postoperative AKI was improved when baseline hemoglobin, eGFR instead of plasmatic creatinine, HbA<inf>1c</inf>, and nadir hemoglobin were added to the CCS (AUC=0.77; 95% CI, 0.67-0.87; P=0.02). CONCLUSIONS: The addition of baseline hemoglobin, eGFR, HbA<inf>1c</inf>, and nadir intraoperative hemoglobin may be useful for improving the discrimination of the clinical predictive risk scores for AKI.
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
Direct model labels (unvalidated)
Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.
| Model arm | Categories | Study design | Confidence |
|---|---|---|---|
| gemma | no category Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Observational | low |
| gpt | no category Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Observational | high |
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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, unvalidatedLabeled directly by 2 models reading the full record.
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".