Analysis of survival-related factors in patients with endometrial cancer using a Bayesian network model

Abstract

Background: In recent years, remarkable progress has been made in the use of machine learning, especially in analyzing prognosis survival data. Traditional prediction models cannot identify interrelationships between factors, and the predictive accuracy is lower. This study aimed to construct Bayesian network models using the tree augmented naïve algorithm in comparison with the Cox proportional hazards model.

Methods: A Bayesian network model and a Cox proportional hazards model were constructed to analyze the prognostic factors of endometrial cancer. In total, 618 original cases obtained from the Surveillance, Epidemiology, and End Results database were used to construct the Bayesian network model, which was compared with the traditional Cox proportional hazards model by analyzing prognostic factors. External validation was performed using a dataset from The First Affiliated Hospital of Shandong First Medical University.

Results: The predictive accuracy, area under the receiver operating characteristic curve, and concordance index for the Bayesian network model were 74.68%, 0.787, and 0.72, respectively, compared to 68.83%, 0.723, and 0.71, respectively, for the Cox proportional hazards model. Tumor size was the most important factor for predicting survival, followed by lymph node metastasis, distant metastasis, chemotherapy, lymph node resection, tumor stage, depth of invasion, tumor grade, histological type, age, primary tumor site, radiotherapy and surgical sequence, and radiotherapy.

Conclusion: The findings indicate that the Bayesian network model is preferable to the Cox proportional hazards model for predicting survival in patients with endometrial cancer.

Fig 1. ROC curve for validation of the Cox proportional hazard model.

The AUC of the Cox proportional hazards model was 0.723. AUC values range from 0 to 1, with values closer to 1 indicating better classifier performance.

Fig 2. Independent variable impact strength ranking.

These factors were ordered by their MMFV values as follows: tumor size, lymph node metastasis, distant metastasis, chemotherapy, lymph node resection, tumor stage, depth of invasion, tumor grade, histological type, age, primary tumor site, radiotherapy and surgical sequence, and radiotherapy.

Fig 3. Bayesian network model for prognostic factors.

The arrow is directional and represents cause-and-effect relationships as well as associations.

Fig 4. ROC curve for validation of the Bayesian network model.

The AUC of the Bayesian network model was 0.787. AUC values range from 0 to 1, with values closer to 1 indicating better classifier performance.

Fig 5. ROC curve for external validation of the Bayesian network model.

The AUC of the Bayesian network model was 0.849. Estimates of AUC values range from 0 to 1, with values closer to 1 indicating better performance of the classifier.

Fig 6. ROC curve for external validation of the Cox proportional hazards model.

The CPH model achieved an AUC of 0.786. AUC values range from 0 to 1, with scores closer to 1 indicating better classifier performance.