Comparative Analysis of Four Risk Stratification Models to Identify Patients with Acute Pulmonary Embolism at Risk of Short-term Mortality
Bibliographic record
Abstract
Acute pulmonary embolism (PE) is potentially life-threatening, with up to 15% risk of death. We compared four risk stratification models to identify outpatients at risk of mortality up to 90 days post acute PE. A retrospective cohort study included outpatients aged ≥18 years with confirmed PE from June 1, 2014 to May 31, 2019, identified via diagnostic imaging reports. Simplified Pulmonary Embolism Severity Index (sPESI) and Hestia scores were calculated as per original derivation methods. Patients were stratified by four models: sPESI alone, Hestia alone, sPESI plus right ventricular dysfunction (RVD), and Hestia plus RVD. Model accuracy and discriminatory power for 30- and 90-day mortality were assessed by area under the receiver operating curve (AUC). The study comprised 785 outpatients (mean age 65.0 years; 42.2% male). Overall mortality rates were 4.1% at 30 days and 7.8% at 90 days. sPESI identified 31.5% as low risk versus 19.1% by Hestia. All models demonstrated 100% sensitivity and negative predictive value for 30-day mortality, but modest discriminatory power (AUC range: 59.2-67.1). sPESI consistently outperformed other models in both timeframes. Including RVD with sPESI or Hestia did not enhance accuracy and slightly reduced performance. The net reclassification index indicated minor improvement in non-event classification with RVD, but no benefit for identifying deaths. sPESI remains a modest yet effective predictor of mortality risk within 90 days following acute PE, consistently outperforming sPESI + RVD, Hestia alone, and Hestia + RVD at both 30 and 90 days. Adding RVD minimally improved predictive accuracy.
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 | 0.018 | 0.022 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 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".