Accuracy is not enough: explainable boosting machine model and identification of candidate biomarkers for real-time sepsis risk assessment in the emergency department
Bibliographic record
Abstract
BACKGROUND: Sepsis poses a significant threat in emergency settings, necessitating tools for early and interpretable risk assessment. This study aimed to develop a robust explainable boosting machine (EBM) model, one of the explainable artificial intelligence (XAI) technologies, to construct a predictive model that balances high accuracy and clinical interpretability for use in emergency departments (EDs) and to examine candidate biomarkers. METHODS: The study identified a significant class imbalance problem in the sepsis distribution among 560 sepsis and 1012 non-sepsis patients. To address the imbalance issue, SMOTE-NC was applied in the training data. The data was divided into two parts, 80% training and 20% testing. To ensure the reliability of the models and to report unbiased results, this process was repeated 100 times and the average performance was reported. To determine the best model for sepsis prediction, five different models (AdaBoost, Gradient Boosting, CatBoost, LightGBM, and EBM) were trained, and their performances were evaluated. In the last stage, we presented local and global explanations of EBM. RESULTS: The EBM model achieved the highest success by reaching 79.1% F1-score, 80.9% sensitivity, and 84.8% AUC after resampling. In the global explanations, the variables with the highest weights in the model's decision process were identified as positive blood culture, oxygen saturation, and procalcitonin, respectively. CONCLUSION: The EBM model accurately predicts sepsis risk based on clinically relevant biomarkers. The model's high performance and inherent transparency can foster trust among clinicians and facilitate its integration into emergency department workflows for real-time decision support.
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 | 0.002 | 0.001 |
| 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, 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".