Treatment-Specific CT Radiomics Models Predict Response to Neoadjuvant Therapy in Gastric Cancer

CT radiomics models tailored to neoadjuvant chemo or immunochemotherapy better predicted pathologic response in gastric cancer. The NAIC-specific model achieved AUC 0.753 vs 0.659 general; patients getting recommended treatment had higher response (e.g., 40.5% vs 19.4%).

• Treatment-specific models outperformed the general model in validation (NAIC-specific AUC 0.753, NAC-specific 0.770), but in the temporal test cohort, only the NAIC-specific model retained superiority (AUC 0.707 vs 0.626), while the NAC-specific model did not (0.563 vs 0.625).
• In a dual-score framework, patients who received the model-recommended treatment had significantly higher pathologic response rates: NAC-recommended 46.4% vs 23.3% (p=0.043); NAIC-recommended 40.5% vs 19.4% (p<0.0001).

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.