Probing the Relationship Between Perioperative Complications in Patients With Valvular Heart Disease: Network Analysis Based on Bayesian Network.

Abstract

Background: Heart valve surgery is associated with a high risk of perioperative complications. However, current approaches for predicting perioperative complications are all based on preoperative or intraoperative factors, without taking into account the fact that perioperative complications are multifactorial, dynamic, heterogeneous, and interdependent.

Objective: We aimed to construct and quantify the association network among multiple perioperative complications to elucidate the possible evolution trajectories.

Methods: This study used the data from China Cardiac Surgery Registry (CCSR), in which 37,285 patients were included in the analysis. A Bayesian network was used to analyze the associations among 12 complications. Score-based hill-climbing algorithms were used to build the structure and the association between them was quantified using conditional probabilities.

Results: We obtained the network of valve surgery complications. A total of 13 nodes represented complications or death, and 34 arcs with arrows represented the directly dependent relationship between them. We identified clusters of complications that were logically related and not related and quantified the associations. The correlation coefficient between complications increases with the severity of the complications, ranging from 0.01 to 0.41. Meanwhile, the probability of death when multiple complications occurred was calculated. Even mild complications, when progressing to multiple organ dysfunction syndrome, result in a mortality rate of over 90%.

Conclusions: Our network facilitates the identification of associations among specific complications, which help to develop targeted measures to halt the cascade of complications in patients undergoing the valve surgery.