| Sumario: | Objective: To construct a risk prediction model for unplanned return to intensive care unit (ICU) based on machine learning algorithm. Methods: A total of 3 250 ICU patients from a tertiary grade A hospital in Shanxi province from October 12, 2019 to May 21, 2023 were selected as the research subjects. A risk prediction model for return to ICU was constructed based on multiple machine learning algorithms, and the performance of the models was compared. Analyze the importance ranking of each variable based on the best performing model. Results: The light gradient boosting machine had the best comprehensive performance, with area under the receiver operating characteristic curve (AUROC) of 0.996 8, followed by random forest (AUROC = 0.996 4), gradient boosting decision tree (AUROC = 0. 992 4), adaptive boosting (AUROC = 0.953 0), and Logistic regression (AUROC = 0.814 5). The top 15 variables in the importance ranking based on light gradient boosting machine were K+, blood loss, score of Glasgow Coma Scale, score of Acute Physiology and Chronic Health Evaluation II, Na+, CRP, alcohol consumption history, minimum body temperature, ICU stay time, blood creatinine, minimum heart rate, neutrophil count, minimum diastolic blood pressure, bicarbonate, and maximum systolic blood pressure. Conclusion: The risk prediction models for unplanned return to ICU based on machine learning algorithm performs well. Researchers can use this type of algorithm to establish the risk prediction model to identify high-risk patients, provide targeted intervention measures, and improve the quality of healthcare.
|
|---|