Gastric cancer is the fifth most common cancer type worldwide and one of the most frequently diagnosed cancers in South Korea. In this study, we propose DeepPrevention, which comprises a prediction module to predict the possibility of progression from atrophic gastritis to gastric cancer and an explanation module to identify risk factors for progression from atrophic gastritis to gastric cancer, to identify patients with atrophic gastritis who are at high risk of gastric cancer. The data set used in this study was South Korea National Health Insurance Service (NHIS) medical checkup data for atrophic gastritis patients from 2002 to 2013. Our experimental results showed that the most influential predictors of gastric cancer development were sex, smoking duration, and current smoking status. In addition, we found that the average age of gastric cancer diagnosis in a group of high-risk patients was 57, and income, BMI, regular exercise, and the number of endoscopic screenings did not show any significant difference between groups. At the individual level, we identified that there were relatively strong associations between gastric cancer and smoking duration and smoking status.

Gastric cancer is a significant health concern in East Asia, where early risk prediction is critical for prevention. However, the scarcity of single-hospital electronic health records (EHRs) data limits the applicability and generalizability of machine learning models. To address this challenge, we propose an ensemble transfer learning framework for gastric cancer prediction using structured EHRs in a data-scarce single-hospital setting. Three base models, Support Vector Machine (SVM), Random Forest, and Deep Neural Network (DNN), were pretrained on a large-scale national dataset from the Republic of Korean National Health Insurance Service (NHIS) and fine-tuned on a smaller institutional dataset from Kangdong Sacred Heart Hospital (KSHH). These fine-tuned models were combined via stacking ensemble learning with logistic regression as a meta-learner. The proposed model achieved strong performance with precision 0.78, recall 0.92, F1-score 0.83, accuracy 0.91, and AUC 0.93. For interpretability, permutation feature importance and Shapley Additive Explanations (SHAP) were applied. Smoking status, gender, and hypertensive disorder were identified as key predictors consistent with previous studies. This study demonstrates the successful application of transfer learning to overcome data scarcity in single-hospital structured EHRs. Furthermore, our stacking ensemble strategy outperformed the individual fine-tuned models, offering a generalizable framework for gastric cancer prediction in data-scarce clinical settings.

This study addresses cross-domain recommendation when source-domain users and target-domain items are structurally disjoint. We propose an adaptive framework that embeds source behavior and target-item information in a shared semantic space. Its shared core combines semantic similarity, keyword mapping, preference compatibility, similar-user retrieval, and behavior transfer, while a domain-aware adaptive layer activates scenario-specific signals only when the user supplies the corresponding preference. Post-ranking explanations are generated by a separate language model. The framework was evaluated in hobby-to-volunteer and consumption-to-travel scenarios using human and LLM-based relevance judgments and eight baselines, including content-based hybrids with and without transfer and a direct LLM ranker. In Case A, the revised cold-start score outperformed the earlier content hybrid with transfer (Precision@10: 0.420 vs. 0.258; Holm-adjusted p < 0.001; Cohen’s dz = 0.90) but did not differ significantly from semantic similarity alone. The transfer term did not yield a statistically detectable incremental ranking gain in either scenario. In Case B, a two-by-two factorial analysis identified the adaptive layer as the main source of improvement (+0.363 Precision@10; p < 0.001; dz = 1.04), while a control without the adaptive layer showed that part of the association between active signals and performance reflected profile specificity. An exploratory Case A control found no significant explanation-associated change in automated scores. Human–LLM agreement was positive but limited, supporting automated evaluation as a scalable complement rather than a replacement for human judgment.

Baseline transcriptomes can predict anticancer drug response, but their high dimensionality complicates pathway-level interpretation. We developed a probabilistic representation learning framework using a reusable variational autoencoder (VAE) latent space to prioritize response-associated factors by aggregate importance and drug preferentiality. Across five reference drugs, leakage-free repeated cross-validation showed that gene-level Ridge regression performed best, whereas 64-dimensional latent representations retained predictive signal after compression. In a separate interpretation VAE fitted to 939 cancer cell lines, six aggregate-importance candidates were bootstrap-robust within the fixed representation and were associated with immune/inflammatory, oncogenic, cell-cycle, stress-response, and cellular-processing programs. Drug-preferential candidates lacked factor-level bootstrap robustness, although several pathway associations remained supported after lineage adjustment. Five independent VAE refits showed partial gene-program concordance but seed-sensitive axes, while a principal component analysis baseline supported stable factor selection and pathway annotation. As an exploratory application, baseline transcriptomes from 15 QAL333-tested cell lines were projected into the fixed VAE without encoder retraining. QAL333-prioritized factors were associated with inflammatory, oncogenic, cellular-processing, and microenvironment-related pathways. The two-model zebrafish xenograft comparison remained descriptive and hypothesis-generating. These findings support reusable, stability-aware latent-space analysis as a framework for pathway-level hypothesis generation from high-dimensional transcriptomic drug-response data.

Objective: Although several chemopreventive drugs against gastric cancer have been proposed, their effects have not been fully evaluated. We examined the impacts of aspirin, metformin, and statin use on gastric cancer development in a population-based cohort in Korea, where gastric cancer is prevalent.Design: We analyzed the association between potential chemopreventive drugs—aspirin, metformin, and statin—and gastric cancer through the Observational Medical Outcomes Partnership Common Data Model-based Korean nationwide cohort. To summarize the current evidence, we further performed a systematic review and meta-analysis of the impact of aspirin, metformin, and statin on gastric cancer development.Results: After propensity-score matching, 66,166, 15,962, and 33,408 subjects were observed for medians of 5.8, 5.3, and 5.3 years for aspirin, metformin, and statin, respectively. Use of aspirin or statin was associated with lower risks of gastric cancer compared to their non-use, respectively (hazard ratio [HR] [95% confidence interval [CI]]: aspirin, 0.84 [0.72–0.97]; statin, 0.66 [0.52–0.82]). However, no association was observed between metformin use and gastric cancer development (HR [95% CI]: 1.00 [0.74–1.34]). A subgroup of subjects with diabetes mellitus showed a lower risk of gastric cancer development with statin use. The meta-analysis showed the highest effect size on gastric cancer development for statin, followed by aspirin and metformin.Conclusion: Statin and aspirin use were associated with significantly reduced risks of gastric cancer development, while the use of metformin was not. The protective effect of statin against gastric cancer was also significant in patients with diabetes mellitus.Funding Statement: This research was supported by a grant from the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: HI19C0143).Declaration of Interests: None.Ethics Approval Statement: The protocol of the current study was approved by the InstitutionalReview Board of Kangdong Sacred Heart Hospital (IRB no. 2019-05-014).