Research Article

Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study

Table 1

The optimal feature subset of each machine learning method.

FeaturesTGHDLLDLPTAPTTTTINRFIBR-timeK-timeαMAIL-6PCTBUNCreatinineK+Na+AUC

LR0.8401
QDA0.8653
NB0.8646
SVM0.8390
AdaBoost0.8629
BP0.8616

Abbreviations: TG: triglyceride; HDL: high-density lipoprotein; LDL: low-density lipoprotein; PT: prothrombin time; APTT: activated partial thromboplastin time; TT: thrombin time; INR: international normalized ratio; FIB: fibrinogen; R-time: reaction time; K-time: kinetic time; α: alpha angle; MA: maximum amplitude; IL-6: interleukin-6; PCT: procalcitonin; BUN: blood urea nitrogen; K+: potassium; Na+: sodium.