New method improves cancer prediction accuracy

The tumor molecular information and data mining methods can predict whether early non-small cell lung cancer will die within 5 years. The overall accuracy of this prediction reaches 87.2%. The research results are published in the Journal of Clinical Oncology, and the impact factor of the magazine reaches 15.484.

Lung cancer is mainly divided into small cell lung cancer and non-small cell lung cancer. Among the two main types of lung cancer, non-small cell lung cancer accounts for about 75%, which is the main cause of lung cancer-related deaths. At present, even the early non-small cell lung cancer patients with good surgical outcomes have a 5-year survival rate of only 40% to 70%, meaning that 30% to 60% of patients will relapse locally or distant within 5 years. Transfer. The pTNM staging system, which is widely used in the medical industry today, is difficult to accurately predict the prognosis of patients with non-small cell lung cancer, and it is even helpless to predict individualized prognosis.

The academic team led by Professor Rong Tiehua began to explore new methods in 1996. They used tissue chips and immunohistochemistry to detect more than 30 molecular markers that may be related to prognosis in a large sample of early-stage lung cancer, combined with the clinicopathological characteristics and prognostic information of the patient, and worked with data mining experts at the University of Science and Technology of China Cooperate, use the support vector machine method to select and construct three early lung cancer individualized prognosis prediction models, and verify the three models. Immunohistochemistry method has strong stability and repeatability, the requirements for specimen processing are relatively low, and the cost of the experiment is relatively low. At present, this research achievement has been initially recognized by international counterparts.

It is reported that the reason why the research results are recognized by domestic and foreign counterparts is mainly because similar genetic detection methods for predicting cancer are very expensive. For example, the cost of 70 genetic tests for breast cancer clinically applied in the United States reaches $ 4,200. The Chinese are different; Professor Rong Tiehua's research group used to predict the prognosis of early non-small cell lung cancer, the cost is only a few hundred yuan, which is conducive to the promotion and application of this technology.

Once the technology is mature, each lung cancer patient will be able to predict his 5-year survival after surgery. If the prognosis is good, there is no need to do radiotherapy and chemotherapy to reduce pain and burden; patients with poor prognosis should study and supplement chemotherapy, radiotherapy or biological therapy in time. And the cost of testing is far cheaper than genetic testing abroad.

Modern Clear Tea Table

Modern Clear Tea Table,Modern Tea Table,Modern Coffee Table,Clear Glass Top Tea Table