On the 10th, the reporter learned from the Hong Kong University of Science and Technology that an international research team led by the university has developed an artificial intelligence model that can predict the progress and outcomes of glioma patients after treatment, providing new directions for improving patient management strategies and implementing precise treatment. The relevant results were recently published in Science Translational Medicine. It is reported that the research team led by Wang Jiguang, Associate Professor of Life Sciences at the University of Science and Technology of Hong Kong, identified genome and transcriptome predictive factors for the evolution of different types of glioma by comprehensively analyzing tumor molecular samples and clinical data from 544 glioma patients (including 182 East Asian patients). Through big data analysis, the research team not only identified some early predictive factors related to temozolomide resistance and rapid deterioration of glioma, but also found significant differences in glioma gene mutations between East Asians and Caucasians. These research results confirm the importance of developing personalized treatment plans for patients with glioblastoma. "Wang Jiguang introduced," We believe that discovering early predictors of glioblastoma recurrence will help carry out precise treatment for this malignant tumor, especially for recurrent patients. "To better evaluate the progress and results of patients receiving treatment, The research team has developed an artificial intelligence model called "CELLO2" for evaluating patients' condition after initial diagnosis. At present, this model can accurately predict whether recurrent tumors will worsen under temozolomide chemotherapy and identify high-risk patients. Jiang Tao, a professor at Beijing Tiantan Hospital affiliated with Capital Medical University and director of the Beijing Institute of Neurosurgery, stated that "CELLO2" is the first effective tool that can predict whether the level of recurrent tumors is elevated or drug-resistant based on the molecular characteristics of primary tumors. It will provide important reference for clinical management of patients and predicting patient prognosis. It is also reported that in the future, the team will integrate more patient data, optimize machine learning models, study other molecular mechanisms that lead to drug resistance in brain tumors, and develop an artificial intelligence platform that integrates medical imaging and multi omics data to promote the development of precision neurooncology. (New News Agency)