Prediction of Postoperative Venous Thromboembolism in Patients With Traumatic Brain Injury: Model Development and Validation Study
Bibliographic record
Abstract
BACKGROUND: Venous thromboembolism (VTE) remains a critical cause of mortality among patients who are hospitalized. Patients with traumatic brain injury (TBI) are particularly susceptible to VTE due to coagulation abnormalities and immobilization. Despite this elevated risk, no validated predictive model currently exists for postoperative VTE in populations with TBI. OBJECTIVE: This study aims to develop machine learning (ML)-based predictive models for VTE in patients with TBI undergoing surgical procedures, with a focus on clinical translatability. METHODS: Data were collected from patients with TBI who underwent surgical treatment at Chongqing University Central Hospital (from October 2016 to December 2024). The dataset was randomly partitioned into a training set and an internal test set in a 7:3 ratio. The recursive feature elimination algorithm was applied for feature selection, followed by the synthetic minority oversampling technique to address class imbalance. Six ML models, including logistic regression (LR), random forest, gradient boosting decision tree, extreme gradient boosting, support vector machine, and categorical boosting, were trained and validated. Model performance was evaluated using receiver operating characteristic analysis, calibration curves (assessing probability-observation alignment), and decision curve analysis to quantify clinical net benefit. For the LR model, clinical utility was enhanced through nomogram construction, with Shapley additive explanation values providing interpretability. RESULTS: A total of 1806 participants were enrolled in this study, and 257 (14.2%) experienced VTE events. All ML models demonstrated strong predictive performance, with area under the receiver operating characteristic curve values ranging from 0.79 to 0.83. The LR model exhibited the highest discriminatory power (area under the receiver operating characteristic curve 0.83; accuracy 0.80; specificity 0.83). Calibration curves confirmed that the LR model provided well-calibrated probability estimates. Shapley additive explanations analysis identified key contributors to VTE risk and transformed model outputs into individualized risk predictions. A user-friendly postoperative VTE risk prediction nomogram was developed for patients with TBI. CONCLUSIONS: This study successfully developed and validated multiple ML models for postoperative VTE prediction in patients with TBI. The LR-based nomogram, supported by calibration and decision curve validation, offers a clinically actionable tool to guide thromboprophylaxis strategies. Future external validation across diverse populations is warranted to confirm generalizability.
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 | 0.012 | 0.013 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".