What question did this study set out to answer?

This research aims to develop a deep learning model to predict overall survival in gastric cancer patients and compare it to traditional Cox regression.

December 10, 2025Clinical Cancer Research

Abstract A012: A Deep Learning Framework for Predicting Survival in Gastric Cancer: A Comparative Analysis with Traditional Cox Regression

View Full Paper

Ask AI

Bookmark

This research aims to develop a deep learning model to predict overall survival in gastric cancer patients and compare it to traditional Cox regression.
Conducted a retrospective cohort study of 200 gastric adenocarcinoma patients.
Implemented a neural network using TensorFlow and Keras with two hidden layers and dropout regularization.
Evaluated model performance using concordance index and compared with Cox proportional hazards model.
Interpreted feature importance with SHAP values.
The deep learning model achieved a C-index of 0.69, showing moderate predictive accuracy for survival.
The traditional Cox model yielded a C-index of 0.67, indicating comparable performance.
Key prognostic factors identified included surgical non-resection, advanced cancer stage, and male gender.
Kaplan-Meier analysis confirmed significant risk stratification among grouped patients.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Retrospective cohort reveals deep learning accurately predicts survival in gastric cancer, indicating new prognostic factors.

Cite This Study

Ahmed M Badheeb (2025) studied this question.

synapsesocial.com/papers/69401d472d562116f28f8544 https://doi.org/10.1158/1557-3265.earlyonsetca25-a012

View Full Paper

Ask AI

Bookmark

Abstract A012: A Deep Learning Framework for Predicting Survival in Gastric Cancer: A Comparative Analysis with Traditional Cox Regression

Key Points

Discussion

Implication

Cite This Study

Abstract A012: A Deep Learning Framework for Predicting Survival in Gastric Cancer: A Comparative Analysis with Traditional Cox Regression

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider