A risk model to predict an unplanned admission to the intensive care unit following lung resection
Bibliographic record
Abstract
OBJECTIVES: The goal of this study was to develop a risk-adjusting model to stratify the risk of an unplanned admission to the intensive care unit (following lung resection). METHODS: We performed a retrospective analysis of 3123 patients undergoing anatomical lung resections (2014-2019) in 2 centres. A risk score was developed by testing several variables for a possible association with a subsequent ICU admission using stepwise logistic regression analyses, validated by the bootstrap resampling technique. Variables associated with ICU admission were assigned weighted scores based on their regression coefficients. These scores were summed for each patient to generate the ICU risk score, and patients were grouped into risk classes. RESULTS: A total of 103 patients (3.3%) required an unplanned admission to the ICU after the operation. The average ICU stay was 17.6 days. The following variables remained significantly associated with ICU admission following logistic regression: male gender (P = 0.004), body mass index <18.5 (P = 0.002), predicted postoperative forced expiratory volume in 1 s < 60% (P = 0.004), predicted postoperative carbon monoxide lung diffusion capacity <50% (P = 0.013), open access (P = 0.004) and pneumonectomy (P = 0.041). All variables were weighted 1 point except body mass index <18.5 (2 points). The final ICU risk score ranged from 0 to 7 points. Patients were grouped into 6 risk classes showing an incremental unplanned ICU admission rate: class A (score 0), 0.7%; class B (score 1), 1.7%; class C (score 2), 3%; class D (score 3), 7.1%; class E (score 4), 12%; and class F (score > 4), 13% (P < 0.001). CONCLUSIONS: This risk score may assist in reliably planning the response to a sudden increase in the demand of critical care resources.
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 | 0.005 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".