Advancing cancer detection and treatment using longitudinal routine clinical data.
Authors
Affiliations (27)
Affiliations (27)
- Clinical Data Science Institute, State Key Laboratory of Macromolecular Drugs and Large-scale Manufacturing, and The Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation, the First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China; Department of Urology, State Key Laboratory of Molecular Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China; Artificial Intelligence Cross Disciplinary Research Institute, Faculty of Medicine, Macau University of Science and Technology, Macau, China; Guangzhou National Laboratory, Guangzhou, China.
- Artificial Intelligence Cross Disciplinary Research Institute, Faculty of Medicine, Macau University of Science and Technology, Macau, China; State Key Laboratory of Eye Health, Eye Hospital, Wenzhou Medical University, Wenzhou, China.
- Clinical Data Science Institute, State Key Laboratory of Macromolecular Drugs and Large-scale Manufacturing, and The Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation, the First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China; State Key Laboratory of Eye Health, Eye Hospital, Wenzhou Medical University, Wenzhou, China.
- Clinical Data Science Institute, State Key Laboratory of Macromolecular Drugs and Large-scale Manufacturing, and The Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation, the First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China; Department of General Surgery, Department of Hepatobiliary Surgery, Zhejiang-Germany Interdisciplinary Joint Laboratory of Hepatobiliary-Pancreatic Tumor and Bioengineering, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
- Department of Radiology, The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, China; Key Laboratory of Intelligent Medical Imaging of Wenzhou, Healthcare Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
- Department of Orthopedics, Key Laboratory of Hepatosplenic Surgery of Ministry of Education, the First Affiliated Hospital, Harbin Medical University, Harbin, China.
- Department of Respiratory and Critical Care Medicine, Center for Big Data and Intelligent Medicine, the First Affiliated Hospital of Chongqing Medical University, Key Laboratory of Digital Health and Intelligent Medicine, Chongqing Municipal Health Commission, Chongqing Translational Medicine Center, Chongqing, China.
- Department of Health Management, Department of Infectious Diseases, Nanfang Hospital, Southern Medical University, Guangzhou, China.
- Department of Big Data and Biomedical AI, College of Future Technology, Peking University, Peking-Tsinghua Center for Life Sciences, Beijing, China.
- Artificial Intelligence Cross Disciplinary Research Institute, Faculty of Medicine, Macau University of Science and Technology, Macau, China; Guangzhou National Laboratory, Guangzhou, China.
- Artificial Intelligence Cross Disciplinary Research Institute, Faculty of Medicine, Macau University of Science and Technology, Macau, China.
- Departments of Medicine and Bioengineering, Moores Cancer Center, School of Medicine, UC San Diego, CA, USA.
- Division of Pulmonary Medicine, the First Affiliated Hospital, Wenzhou Medical University, Wenzhou Key Laboratory of Interdisciplinary and Translational Medicine, Wenzhou Key Laboratory of Heart and Lung, Wenzhou, Zhejiang, China.
- Nepean Hospital, Sydney, Australia.
- Key Laboratory of Intelligent Medical Imaging of Wenzhou, Healthcare Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
- Dongguan Hospital, Southern Medical University, Guangzhou, China.
- Conde S. Januario Hospital, Macau, China.
- Department of Internal Medicine, Mayo Clinic, Arizona, USA.
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK.
- Clinical Data Science Institute, State Key Laboratory of Macromolecular Drugs and Large-scale Manufacturing, and The Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation, the First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China; Faculty of Health and Wellness, Faculty of Business, City University of Macau, Taipa, Macau SAR, China.
- Division of Engineering in Medicine, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA; Gene and Cell Therapy Institute, Mass General Brigham, Cambridge, MA, USA.
- Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration, F-75015 Paris, France; Department of Kidney Transplantation, Assistance Publique - Hôpitaux de Paris, Paris, France.
- Artificial Intelligence Cross Disciplinary Research Institute, Faculty of Medicine, Macau University of Science and Technology, Macau, China; Biomedical Pioneering Innovation Center (BIOPIC), School of Life Sciences, Peking University, Beijing, China.
- Departments of Medicine and Bioengineering, Moores Cancer Center, School of Medicine, UC San Diego, CA, USA; Big Data Institute, Oxford University, Oxford, UK.
- Department of Medical Oncology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Guangzhou, China.
- Departments of Neurosurgery, Radiology, and Data Science, Neuroscience Institute, NYU Langone Medical Center, New York University, New York, NY, USA.
- Clinical Data Science Institute, State Key Laboratory of Macromolecular Drugs and Large-scale Manufacturing, and The Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation, the First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China; Artificial Intelligence Cross Disciplinary Research Institute, Faculty of Medicine, Macau University of Science and Technology, Macau, China; Guangzhou National Laboratory, Guangzhou, China; State Key Laboratory of Eye Health, Eye Hospital, Wenzhou Medical University, Wenzhou, China. Electronic address: [email protected].
Abstract
Cancer management remains fragmented across its continuum, from late-stage diagnosis and salvage therapies to non-personalized surveillance. Here, we present Oncoformer, a unified multimodal transformer model trained on the China Oncology Multimodal Prediction and Surveillance Study (COMPASS) cohort (3.67 million individuals, 17.7 million clinical visits) and validated on independent external cohorts, including the UK Biobank. Oncoformer integrates longitudinal electronic health records with chest X-ray imaging to address multiple clinical tasks: pan-cancer diagnosis (area under the receiver operating characteristic curve [AUROC] = 0.956), future cancer prediction up to 1 year before diagnosis (AUROC = 0.869), tumor stage inference (mean AUROC > 0.90), patient-specific treatment-response forecasting, and recurrence-free survival stratification across ten cancer types (all p < 0.01). Staging predictions were independently validated against postoperative pathological endpoints and shown to converge on core cancer genomic pathways. By translating routine clinical data into a dynamic view of cancer evolution, Oncoformer provides a framework for risk-informed cancer prediction and treatment stratification using routine clinical data.