KAMLN: A Knowledge-aware Multi-label Network for Lung Cancer Complication Prediction

Surgical resection is now the only curative approach for early stage lung cancer patients. However, postoperative complications pose a significant threat to the health and life of patients. The current complication prediction methods usually ignore the potential causal relationships between different complications, which may limit their predictive performances. To exploit this knowledge, we propose a knowledge-aware multi-label network (KAMLN) for complication prediction. In this approach, we first construct a knowledge graph to describe the potential causal relationships between different complications. Then, we design a neural network based on this knowledge graph to learn the relationships between different complications to achieve better predictive performances. Experiments using 593 lung cancer patients’ data show that the KAMLN achieves a micro-AUC value of 0.664±0.100, which is better than the baseline methods. The SHAP analysis indicates lymph node dissection has a significant impact on multiple complications. Based on the experimental results, the proposed KAMLN can effectively utilize prior knowledge between different complications to achieve more accurate and fine-grained complication prediction.