Key result
A random forest machine learning model trained on immediate postoperative laboratory values predicted 30-day postoperative mortality with an AUROC of 0.82, outperforming the SASA scoring system.
Why the study?
Few studies have investigated postoperative risk factors affecting survival after surgery, despite multiple models existing for preoperative risk stratification.
Do machine learning models using routine immediate postoperative laboratory values improve the prediction of 30-day postoperative mortality compared to the SASA scoring system?
Observational (n=3,817)
Yes
Do machine learning models using routine immediate postoperative laboratory values improve the prediction of 30-day postoperative mortality compared to the SASA scoring system?
Machine learning models utilizing immediate postoperative laboratory values, particularly phosphorus levels, can effectively predict 30-day postoperative mortality and outperform traditional scoring systems.
Answers are grounded in this paper and cite their sources.
Postoperative lab-based ML models may aid mortality risk identification; leaves open prospective validation before clinical adoption.
BACKGROUND: Several prediction models have been proposed for preoperative risk stratification for mortality. However, few studies have investigated postoperative risk factors, which have a significant influence on survival after surgery. This study aimed to develop prediction models using routine immediate postoperative laboratory values for predicting postoperative mortality. METHODS: Two tertiary hospital databases were used in this research: one for model development and another for external validation of the resulting models. The following algorithms were utilized for model development: LASSO logistic regression, random forest, deep neural network, and XGBoost. We built the models on the lab values from immediate postoperative blood tests and compared them with the SASA scoring system to demonstrate their efficacy. RESULTS: There were 3817 patients who had immediate postoperative blood test values. All models trained on immediate postoperative lab values outperformed the SASA model. Furthermore, the developed random forest model had the best AUROC of 0.82 and AUPRC of 0.13, and the phosphorus level contributed the most to the random forest model. CONCLUSIONS: Machine learning models trained on routine immediate postoperative laboratory values outperformed previously published approaches in predicting 30-day postoperative mortality, indicating that they may be beneficial in identifying patients at increased risk of postoperative death.
No takes yet. Share an insight, caveat, or question.
Cho et al. (2021) conducted an observational in Postoperative mortality (n=3,817). Machine learning models using immediate postoperative laboratory values vs. SASA scoring system was evaluated on 30-day postoperative mortality (AUROC 0.82). A random forest machine learning model trained on immediate postoperative laboratory values predicted 30-day postoperative mortality with an AUROC of 0.82, outperforming the SASA scoring system.
Synapse has enriched 10 related papers. Consider them for comparative context: