Early warning of citric acid overdose and timely adjustment of regional citrate anticoagulation based on machine learning methods

BMC Medical Informatics and Decision Making

Hao Wang¹  Longxiang Su¹  Huan Chen¹  Yun Long¹  Huizhen Jiang²  Weiguo Zhu³  Na Hong⁴  Yingying Ma⁴  Jie He⁴  Chun Liu⁴ 

[1] Department of Critical Care Medicine, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, 100730, Beijing, China;Department of General Internal Medicine, Department of Information Center, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, 100730, Beijing, China;Department of Primary Care and Family Medicine, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, 100730, Beijing, China;Department of General Internal Medicine, Department of Information Center, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, 100730, Beijing, China;Digital Health China Technologies Co., Ltd., 100080, Beijing, China;

关键词: Anticoagulants;    Continuous renal replacement therapy;    Machine learning;    Intensive care units;   

DOI  :  10.1186/s12911-021-01489-8

来源: Springer

【 摘 要 】

BackgroundRegional citrate anticoagulation (RCA) is an important local anticoagulation method during bedside continuous renal replacement therapy. To improve patient safety and achieve computer assisted dose monitoring and control, we took intensive care unitspatients into cohort and aiming at developing a data-driven machine learning model to give early warning of citric acid overdose and provide adjustment suggestions on citrate pumping rate and 10% calcium gluconate input rate for RCA treatment.MethodsPatient age, gender, pumped citric acid dose value, 5% NaHCO3 solvent, replacement fluid solvent, body temperature value, and replacement fluid PH value as clinical features, models attempted to classify patients who received regional citrate anticoagulation into correct outcome category. Four models, Adaboost, XGBoost, support vector machine (SVM) and shallow neural network, were compared on the performance of predicting outcomes. Prediction results were evaluated using accuracy, precision, recall and F1-score.ResultsFor classifying patients at the early stages of citric acid treatment, the accuracy of neutral networks model is higher than Adaboost, XGBoost and SVM, the F1-score of shallow neutral networks (90.77%) is overall outperformed than other models (88.40%, 82.17% and 88.96% for Adaboost, XGBoost and SVM). Extended experiment and validation were further conducted using the MIMIC-III database, the F1-scores for shallow neutral networks, Adaboost, XGBoost and SVM are 80.00%, 80.46%, 80.37% and 78.90%, the AUCs are 0.8638, 0.8086, 0.8466 and 0.7919 respectively.ConclusionThe results of this study demonstrated the feasibility and performance of machine learning methods for monitoring and adjusting local regional citrate anticoagulation, and further provide decision-making recommendations to clinicians point-of-care.

【 授权许可】

CC BY