System and method for predicting recurrence of prostatic cancer based on characteristic value

Abstract

The invention relates to a system and method for predicting recurrence of a prostatic cancer. The system comprises a doctor work station and a server, wherein the doctor work station is used for receiving input information and displaying a predicting result; the server comprises an information obtaining module, a preprocessing module, a model training module, an information receiving module and a prostatic cancer recurrence predictor. The information obtaining module obtains a training set; the preprocessing module extracts feature information, preprocesses the feature information, generates a characteristic word set and generates a characteristic value for the characteristic word; the model training module trains a clustering analysis model to obtain the prostatic cancer recurrence predictor; the information receiving module receives information input by a user and transmits the information to the preprocessing module; the trained prostatic cancer recurrence predictor obtains a predicting result of the recurrence of the prostatic cancer according to the characteristic value of the information input by the user. According to the method, the problems that an existing method consumes manpower, depends on subjective judgment of a doctor and lacks a unified standard, and misdiagnosis is easily caused are solved.

Description

technical field [0001] The present invention relates to the technical field of disease prediction, in particular to a system and method for predicting recurrence of prostate cancer based on eigenvalues. Background technique [0002] At present, we are in the era of big data, and all walks of life have large-scale data volumes, and the simple rule processing in the existing technology is difficult to maximize the value of these data. The rapid development of hardware provides conditions for the analysis and application of big data. High-performance computing greatly reduces the data learning time and data processing cost based on large-scale data; large-scale data storage makes it possible to process large-scale data faster and at a lower cost. Due to the development of hardware and algorithms, after using machine learning to solve data analysis problems, more lucrative benefits can be obtained. [0003] Existing machine learning technologies are mainly applied to Internet ...

AI Technical Summary

Problems solved by technology

[0004] In view of the above analysis, the present invention aims to provide a system and method for predicting the recurrence of prostate cancer based on eigenvalues, to solve the problems that the existing methods are labor-intensive, rely on the subjective judgment of doctors, lack uniform standards, and easily cause misdiagnosis

Images