Cancer recurrence prediction system based on multidimensional Gaussian distribution Bayesian classification

Abstract

The invention relates to a cancer recurrence prediction system based on multidimensional Gaussian distribution Bayesian classification. The system includes a preprocessing module, a training module and a Bayesian classifier; the preprocessing module performs data cleaning on the training set and generates class vector data set; the training module first calculates the prior probability of two class attributes, and then uses the pearson correlation coefficient to divide the data attributes into a class data attribute set with a close correlation with the class attribute and a class II data attribute set with a sparse correlation with the class attribute. The data attribute set uses the multidimensional Gaussian distribution and the one-dimensional Gaussian distribution to calculate the corresponding probability; the Bayesian classifier combines the two probabilities and the prior probability of the category as the probability that the data belongs to each category, and judges cancer accordingly classification test results. The invention improves the prediction accuracy rate of whether the cancer recurs.

Description

technical field [0001] The invention belongs to the technical field of data mining, and relates to a multidimensional Gaussian distribution Bayesian classification system based on attribute selection, in particular to a cancer recurrence prediction system based on multidimensional Gaussian distribution Bayesian classification. The system has universal applicability to the general classification of continuous data satisfying Gaussian distribution. Background technique [0002] Classification method is a method to solve classification problems, and it is an important research field in data mining, machine learning and pattern recognition. The classification method finds classification rules by analyzing the training set of known categories, so as to predict the category of new data. Classification methods are used in a wide range of applications, such as risk assessment in banking, customer category classification, text retrieval and search engine classification, intrusion de...

AI Technical Summary

Problems solved by technology

Once breast cancer recurs or metastasizes, the difficulty of treatment will increase, which is far more difficult than the first treatment, and it is likely to directly threaten the patient's life

Images