Abstract A012: A Deep Learning Framework for Predicting Survival in Gastric Cancer: A Comparative Analysis with Traditional Cox Regression
Bibliographic record
Abstract
Abstract Introduction: Gastric cancer remains a leading cause of cancer-related mortality worldwide, with prognosis heavily dependent on a complex interplay of clinical and pathological factors. Traditional statistical models like Cox proportional hazards regression have limitations in capturing non-linear relationships and complex interactions between variables. This study aims to develop and validate a deep learning model for predicting overall survival in gastric cancer patients and compare its performance to a conventional Cox model. Methods: We conducted a retrospective cohort study of 200 patients diagnosed with gastric or gastroesophageal junction adenocarcinoma. A deep learning neural network was implemented using TensorFlow and Keras, with an architecture consisting of two hidden layers (64 and 32 neurons) and dropout regularization. The model was trained on clinical variables including age, gender, body mass index, symptoms, cancer stage, H. pylori status, and surgical resection. Model performance was evaluated using Harrell's concordance index (C-index) and compared against a traditional Cox proportional hazards model. Feature importance was interpreted using SHapley Additive exPlanations (SHAP) values. Results: The deep learning model achieved a C-index of 0.69 (95% CI: 0.62-0.75) on the test set, demonstrating moderate predictive accuracy for survival. This performance was comparable to the traditional Cox model, which yielded a C-index of 0.67 (95% CI: 0.60-0.73). SHAP analysis identified surgical non-resection, advanced cancer stage (III and IV), and male gender as the most important predictors of poor survival. Kaplan-Meier analysis confirmed significant stratification between low, medium, and high-risk groups defined by the model's output (log-rank p < 0.0001). Conclusion: A deep learning approach can predict survival in gastric cancer patients with accuracy comparable to traditional statistical methods. The model effectively identified key prognostic factors and stratified patients into distinct risk categories. This analytical framework holds promise for enhancing prognostic precision and could potentially inform personalized clinical decision-making. The most significant predictors of poor survival were the inability to perform surgical resection and advanced disease stage. Citation Format: Ahmed M. Badheeb. A Deep Learning Framework for Predicting Survival in Gastric Cancer: A Comparative Analysis with Traditional Cox Regression [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: The Rise in Early-Onset Cancers—Knowledge Gaps and Research Opportunities; 2025 Dec 10-13; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(23_Suppl):Abstract nr A012.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.004 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".