Related Experiment Videos
Interpretative machine learning for predicting 60-day mortality in burn patients with suspected infection
11Department of Vascular Surgery, the Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou 310009, China.
Background:
Traditional burn severity scores have limited accuracy in predicting mortality in burn patients with infection. This study aimed to develop an interpretative machine learning (ML) model to predict 60-day mortality in burn patients with suspected infection.
Methods:
Data on burn patients with suspected infection were extracted from the Dryad database and divided into a training cohort (70%) and a test cohort (30%). Feature selection was conducted by combining the Boruta algorithm and least absolute shrinkage and selection operator (LASSO) regression. Twelve ML models were developed to predict 60-day mortality. Model robustness was evaluated in the training cohort, and the discrimination capacity was assessed in the test cohort. DeLong's test was performed to compare the area under the curve (AUC) between the optimal model and the traditional scores (abbreviated burn severity index [ABSI] and revised Baux [rBaux]). SHapley Additive exPlanations (SHAP) analysis was used for model interpretation.
Results:
A total of 1,391 adult burn patients with suspected infections were included: training cohort (n=973), test cohort (n=418). The overall mortality was 23.7% (n=329). The percentage of total body surface area (%TBSA), Acute Physiology and Chronic Health Evaluation IV (APACHE IV) score, and age were identified as significant predictors of 60-day mortality among burn patients with suspected infections. CatBoost achieved a well-balanced performance and better ability than the ABSI and rBaux did.
Conclusion:
The ML model incorporating the APACHE IV score improved the predicting performance of 60-day mortality in burn patients with infection. Its high interpretability may facilitates its clinical application for In the future.
Insights
A machine learning model using the APACHE IV score accurately predicts mortality in infected burn patients. This interpretable model offers improved clinical decision-making for burn care and patient outcomes.
Area of Science:
- Medical Informatics
- Computational Biology
- Clinical Medicine
Background:
- Traditional burn severity scores lack accuracy in predicting mortality for infected burn patients.
- Infection significantly complicates outcomes and mortality prediction in burn cases.
Purpose of the Study:
- To develop an interpretable machine learning (ML) model for predicting 60-day mortality in burn patients with suspected infection.
- To enhance the accuracy of mortality prediction beyond existing traditional scoring systems.
Main Methods:
- Utilized data from 1,391 adult burn patients with suspected infections from the Dryad database.
- Employed Boruta and LASSO for feature selection, developing 12 ML models, with CatBoost identified as optimal.
- Assessed model performance using AUC and employed SHAP for interpretability, comparing against ABSI and rBaux scores.
Main Results:
- The CatBoost ML model demonstrated superior performance in predicting 60-day mortality compared to ABSI and rBaux.
- Key predictors identified included %TBSA, APACHE IV score, and age.
- The ML model achieved a well-balanced performance, outperforming traditional scores.
Conclusions:
- An ML model incorporating the APACHE IV score significantly improves 60-day mortality prediction in infected burn patients.
- The model's high interpretability is expected to facilitate its clinical adoption.
- This approach offers a promising tool for optimizing burn patient management and care.
