Clinical Assistant Diagnosis System Based on Dynamic Uncertain Causality Graph

Artificial intelligence clinical assistant diagnosis system has become one of the mainstream in the field of medical research at present. The main challenge of this system is to have both high diagnostic accuracy and good interpretability for diagnostic results. Dynamic Uncertainty Causality diagram is a probability graph model, which can explain the calculation results in a graphical form. This paper introduces the clinical assistant diagnosis system based on DUCG, and shows the system diagnosis process through a case study. Experiments show that: the system with high accuracy and good interpretability.