Prediction of Survival in Patients With Esophageal Cancer After Immunotherapy Based on Small-Size Follow-Up Data

Abstract

Esophageal cancer (EC) poses a significant health concern, particularly among the elderly, warranting effective treatment strategies. While immunotherapy holds promise in activating the immune response against tumors, its specific impact and associated reactions in EC patients remain uncertain. Precise prognosis prediction becomes crucial for guiding appropriate interventions. This study, based on data from the First Affiliated Hospital of Xiamen University (January 2017 to May 2021), focuses on 113 EC patients undergoing immunotherapy. The primary objectives are to elucidate the effectiveness of immunotherapy in EC treatment and to introduce a stacking ensemble learning method for predicting the survival of EC patients who have undergone immunotherapy, in the context of small sample sizes, addressing the imperative of supporting clinical decision-making for healthcare professionals. Our method incorporates five sub-learners and one meta-learner. Leveraging optimal features from the training dataset, this approach achieved compelling accuracy (89.13%) and AUC (88.83%) in predicting three-year survival status, surpassing conventional techniques. The model proves efficient in guiding clinical decisions, especially in scenarios with small-size follow-up data.

Keywords: Esophageal carcinoma; immunotherapy; machine learning; stacking ensemble learning; survival prediction.

Fig. 1.

Correlation heat map between the features. A heat map showing the value of the correlation coefficient between each possible pair of features.

Fig. 2.

Normalized correlation scores between the features and survival status.

Fig. 3.

Framework of the proposed prediction method.

Fig. 4.

Framework of the -fold cross-validation approach for each sub-learner.

Fig. 5.

Feature importance of the different tree-based models in the sub-learning module.

Fig. 6.

Framework of the meta-learning module.

Fig. 7.

Loss function on traning and texting datasets of the proposed prediction model.

Fig. 8.

Performance comparison of the mainstream traditional machine leaning-based prediction models.

Fig. 9.

Performance comparison of the different traditional single machine leaning-based prediction models.

Fig. 10.

Performance comparison of the different stacking ensemble learning mechanism-based prediction models.