Multimodal fusion model for prognostic prediction and radiotherapy response assessment in head and neck squamous cell carcinoma
Accurate prediction of prognosis and postoperative radiotherapy response is critical for personalized treatment in head and neck squamous cell carcinoma (HNSCC). We developed a multimodal deep learning model (MDLM) integrating computed tomography, whole-slide images, and clinical features from 1087 HNSCC patients across multiple centers. The MDLM exhibited good performance in predicting overall survival (OS) and disease-free survival in external test cohorts. Additionally, the MDLM outperformed unimodal models. Patients with a high-risk score who underwent postoperative radiotherapy exhibited prolonged OS compared to those who did not (P = 0.016), whereas no significant improvement in OS was observed among patients with a low-risk score (P = 0.898). Biological exploration indicated that the model may be related to changes in the cytochrome P450 metabolic pathway, tumor microenvironment, and myeloid-derived cell subpopulations. Overall, the MDLM effectively predicts prognosis and postoperative radiotherapy response, offering a promising tool for personalized HNSCC therapy.
Authors
- Ting Yuan (ORCID: https://orcid.org/0000-0002-9895-1677)
- Fengsu Hou (ORCID: https://orcid.org/0000-0001-5869-4365)
- Yisong Yao (ORCID: https://orcid.org/0009-0000-7593-6979)
- Pengyi Yu
- Y.-Z. Chen
- Haicheng Zhang (ORCID: https://orcid.org/0000-0002-5357-6332)
- Dexin Yu (ORCID: https://orcid.org/0000-0002-3430-4817)
- Anning Li (ORCID: https://orcid.org/0000-0001-6683-943X)
- Guohua Yu (ORCID: https://orcid.org/0000-0002-3260-3178)
- Ning Mao (ORCID: https://orcid.org/0000-0001-7097-5530)
- J. Li (ORCID: https://orcid.org/0009-0004-9955-3576)
- Ruxian Tian
- Zhonglu Liu (ORCID: https://orcid.org/0000-0001-7250-7968)
- Huaiqing Lv (ORCID: https://orcid.org/0009-0000-7554-4094)
- Xi Chen (ORCID: https://orcid.org/0000-0003-3843-6478)
- Ping Yang (ORCID: https://orcid.org/0000-0003-2904-8916)
- Yan Hao (ORCID: https://orcid.org/0000-0002-1868-3087)
- Fang Han (ORCID: https://orcid.org/0000-0003-4130-3625)
- Xicheng Song (ORCID: https://orcid.org/0000-0002-9789-1318)
- Hongfei Zhao (ORCID: https://orcid.org/0000-0001-9691-519X)
- Hongxia Cheng
- Liling Song
Institutions
- Qingdao University (CN)
- Shandong University of Traditional Chinese Medicine (CN)
- Binzhou Medical University (CN)
- Shandong University of Aeronautics (CN)
- Yuhuangding Hospital (CN)
- Affiliated Hospital of Qingdao University (CN)
- Qilu Hospital of Shandong University (CN)
- Xi'an Jiaotong University (CN)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-05-23
- DOI
- https://doi.org/10.1038/s41746-025-01712-0
- Citations
- 9
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 12.24
Funders
- National Natural Science Foundation of China
- Taishan Scholar Project of Shandong Province