GPT Automates Radiomics Modeling for Response Prediction in Head and Neck Cancer

In head and neck squamous cell carcinoma, GPT-assisted MRI radiomics predicted pathological complete response to chemoimmunotherapy with AUC 0.741 (validation) and 0.706 (multicenter prospective), comparable to manual models (0.714 and 0.700).

• Fused radiomic and deep learning features from pretreatment T2-weighted MRI yielded the highest predictive performance for pathological complete response.
• GPT-assisted logistic regression models achieved AUCs of 0.741 in internal validation and 0.706 in a prospective multicenter cohort, comparable to manual models.
• Repeated GPT-assisted runs showed minimal variability (AUC standard deviation 0.001–0.019).

Automated summary

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