Combining clinical and radiological features improves prediction of bowel ischemia in patients with CT findings of pneumatosis intestinalis
Bibliographic record
Abstract
Abstract Background: Pneumatosis intestinalis on CT presents a diagnostic dilemma, because it could reflect bowel ischemia or benign finding. Purpose: To determine radiological and clinical features that can predict bowel ischemia in patients with pneumatosis intestinalis on CT. Materials and Methods: Patients with “pneumatosis” in abdominal CT reports performed between 1/1/2002 and 12/31/2018 were retrospectively included. Pneumatosis intestinalis was confirmed by review of images. Radiological features of pneumatosis, laboratory data, clinical signs and symptoms were collected. Pathologic pneumatosis intestinalis (PPI) was defined as presence of ischemic (viable or dead) bowel on surgery or death during admission or within 30 days of discharge due to ischemia. Univariate statistical analysis was used to identify features associated with PPI, followed by multivariate logistic regression models. Results: A total of 313 consecutive patients with pneumatosis intestinalis (162 (52%) men, median age 67 years, IQR 55 – 78 years) were included. Pathologic pneumatosis intestinalis was present in 114/313 (36%) patients. Presence of arterial or venous thrombosis, porto-mesenteric gas, fat stranding, and location in the small bowel were significantly associated with PPI. A combined clinical and radiological model, which included age, WBC, creatinine, abdominal distention, rebound or guarding, shock, presence of porto-mesenteric gas and fat stranding showed an AUC of 0.85 for prediction of PPI, higher than models using clinical (AUC=0.80, p=0.005) or radiological factors (AUC=0.80, p<0.0001) alone. Conclusion: Improved prediction of pathological pneumatosis intestinalis can be achieved by a model incorporating both clinical and radiological features (AUC=0.85)rather than by either clinical (AUC=0.80) or radiological (AUC=0.80) features alone.
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 | 0.001 | 0.004 |
| 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 | 0.000 | 0.001 |
| 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".