Jiangdian Song

Loading metrics Open Access Peer-reviewed Research Article Citation: Song J, Nie Q, Wang S, An T, Li X, Liu Y, et al. (2026) Clinician-deployable deep hypergraph model integrating clinical and CT radiomics predicts immunotherapy outcomes in NSCLC. PLOS Digit Health 5(4): e0001361.

Abstract Although neoadjuvant chemotherapy (NACT) is commonly used for advanced ovarian cancer, patient outcomes vary substantially. We developed a graph convolutional network (GCN) that integrates patient-specific baseline clinical variables and computed tomography–derived radiomic features while modeling inter-patient relationships to improve outcome prediction beyond standard models.

Keywords GPT lung nodule large language model deep learning computed tomography lung cancer feature detection malignancy follow-up diagnosis Introduction Large language models (LLMs), such as Chat generative pre-trained transformer (GPT) and Gemini, have stimulated the surge of natural language processing techniques that allow text comprehension and human-like response generation.1 Prior LLMs have shown the potential to interpret radiological images, thus aiding in the detection of anomalies...