IEEE J Biomed Health Inform. 2022 May 3;PP. doi: 10.1109/JBHI.2022.3171673. Online ahead of print.
ABSTRACT
Sepsis is a systemic inflammatory response caused by pathogens such as bacteria. Because its pathogenesis is not clear, the clinical manifestations of patients vary greatly, and the alarming incidence and mortality pose a great threat to patients and medical systems, especially in Intensive Care Unit (ICU). The traditional judgment criteria have the problem of low specificity. Artificial intelligence models could greatly improve the accuracy of sepsis prediction and judgment. Based on the XGBoost machine learning framework taken demographic, vital signs, laboratory tests and medical intervention data as input, this paper proposes a novel model for dynamically predicting sepsis and assessing risk. To realize the model, two methods for feature construction are introduced. For the observed time series data of vital signs and laboratory tests, time-dependent method performs to construct the time- dependent characteristics after statistical screening. For the clinical intervention data, statistical counting method is applied to construct count-dependent characteristics. Moreover, a new objective function is proposed for the XGBoost framework, and the first-order and second-order gradient of the objective function are also given for model training. Compared with the state-of-the-art methods at present, the proposed model has the best performance, with AUROC improved by 5.4% on the MIMIC-III dataset and 2.1% on PhysioNet Challenge 2019 dataset. The data processing and training methods of this model can be conveniently applied in different electronic health record systems, and has a wide application prospect.
PMID:35503852 | DOI:10.1109/JBHI.2022.3171673
