Prognostic prediction model for esophageal cancer based on probability membrane systems

Esophageal squamous cell carcinoma (ESCC) is a clinically common heterogeneous malignant tumor of the digestive system and also one of the diseases with a high incidence rate in China. Selecting appropriate treatment methods for patients is the key to improving patient survival rates and quality of life. Therefore, accurate prognostic assessment for esophageal cancer patients is crucial. In this paper, we propose a multi-factor esophageal cancer prognosis prediction model (PMS) based on probabilistic membrane systems. First, we use receiver operating characteristic(ROC) analysis and Kaplan–Meier (KM) survival analysis to screen out the key factors that affect the survival status of the samples. Then, based on these key factors and probabilistic membrane systems, we construct a conceptual model for esophageal cancer prognosis prediction. We define the corresponding membrane structure and object set according to the conceptual model, and design relevant evolution rules considering the characteristics of esophageal cancer progression. In particular, we use MeCoSim software to simulate the PMS model and compare the prediction results of the four stages of esophageal cancer with the actual results. The relative error between the simulation results and the actual results does not exceed \(\pm 10\%\) $\pm 10\%$ . To further demonstrate the effectiveness of the model, we compare PMS with other algorithms. Compared with traditional machine learning methods such as support vector machines (SVM), backpropagation neural networks (BP), and XGBoost, the PMS model has certain advantages. The accuracy of this model reached \(92\%\) $92\%$ , the recall rate reached \(88\%\) $88\%$ , the F1 score reached 0.88, and the AUC reached 0.91.