System for predicting prognosis of gastric cancer in subjects
A technology for subjects and gastric cancer, applied in medical data mining, pathological reference, instruments, etc., can solve the problems of great differences in clinical outcomes of patients
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0106] Example 1 Study population and sample collection
[0107]The samples used in the examples of this application were obtained from patients treated with radical gastrectomy for gastric cancer or gastroesophagogastric junction between January 2000 and December 2012 at Peking University Cancer Hospital. Samples with histological identification of adenocarcinoma and available paraffin-embedded tissues (FFPE tissues) were selected. According to the histopathological classification system adopted by the World Health Organization (WHO), all hematoxylin and eosin (H&E) slides were centrally examined at the Pathology Department of Peking University Cancer Hospital to confirm the tumor type and degree of differentiation. A representative area of each tissue sample was identified and carefully marked on the H&E-stained sections. Three representative core tissue samples (1 mm in diameter) were punched from corresponding single donor tissue blocks and rearranged in recipient block...
Embodiment 2
[0119] Embodiment 2 system model construction
[0120] Part of the clinical feature data, immune marker feature data, and protein expression data in the above-mentioned test samples were selected as the variables predicted by the present invention, and the gastric cancer prognosis risk value was used as the result to construct a system model.
[0121] Specifically, a system model was constructed for the above-mentioned clinical data, immune labeling characteristic data and protein expression data obtained in the training set in Example 1. In the process of building the model, the number and risk ratio of the selected feature data were studied, and it was found that the detection of 8 of the features was feasible under clinical conditions, and the risk ratio was equivalent to that of 8–12 features , so in order to balance the efficacy of the model and the convenience of testing clinical practice, 8 of the features were finally selected as the variables of the system model. The...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com