Early-Stage NSCLC Patients’ Prognostic Prediction with Multi-information Using Transformer and Graph Neural Network Model
Abstract
Background
We proposed a population graph with Transformer-generated and clinical features for the purpose of predicting overall survival and recurrence-free survival for patients with early-stage NSCLC and to compare this model with traditional models.
Methods
The study included 1705 patients with lung cancer (stage I and II), and a public dataset for external validation (n=127). We proposed a graph with edges representing non-imaging patient characteristics and nodes representing imaging tumour region characteristics generated by a pretrained Vision Transformer. The model was compared with a TNM model and a ResNet-Graph model. To evaluate the models’ performance, the area under the receiver operator characteristic curve (ROC-AUC) was calculated for both overall survival (OS) and recurrence-free survival (RFS) prediction. The Kaplan–Meier method was used to generate prognostic and survival estimates for low- and high-risk groups, along with net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA). An additional subanalysis was conducted to examine the relationship between clinical data and imaging features associated with risk prediction.
Results
Our model achieved AUC values of 0·785 (95 % CI:0·716 - 0·855) and 0·695 (95 % CI:0·603 - 0·787) on the testing and external datasets for OS prediction, and 0·726 (95 % CI:0·653 - 0·800) and 0·700 (95 % CI:0·615 - 0·785) for RFS prediction. Additional survival analyses indicated that our model outperformed the present TNM and ResNet-Graph models in terms of net benefit for survival prediction.
Conclusion
Our Transformer-Graph model was effective at predicting survival in patients with early-stage lung cancer, which was constructed using both imaging and non-imaging clinical features. Some high-risk patients were distinguishable by using a similarity score function defined by non-imaging characteristics such as age, gender, histology type, and tumour location, while Transformer-generated features demonstrated additional benefits for patients whose non-imaging characteristics were non-discriminatory for survival outcomes.
Funding
There was no funding source for this study.
Related articles
Related articles are currently not available for this article.