Establishment of Metabolomic-based Osteosarcoma Prognostic Model Using Non-Convex Kernel Models
Principal investigators: Kayvan Najarian, associate professor of computational medicine and bioinformatics, emergency medicine, and electrical engineering and computer science, U-M; Yingqi Hua, associate investigator, Shanghai General Hospital, SJTU
Summary: Osteosarcoma is the most common primary bone malignancy and most genomically complex cancer. Its five-year survival has remained unchanged in the past 30 years, and early occurrence of pulmonary metastasis is the main challenge for patients to be cured. This project aims at establishing a prognostic predictive model using machine learning in osteosarcoma metabolomics. This model will be potentially useful for providing adjuvant information to stratify osteosarcoma patients and subsequently to guide clinical decision.