A method and system for classifying distant metastasis of abnormal cells based on non-equilibrium learning

Abstract

The invention provides an unbalanced learning-based abnormal cell remote transfer classification method and system, and the method comprises the steps: obtaining a plurality of data sequences with a certain cell remote transfer and a plurality of data sequences without a certain cell remote transfer, dividing the data set into a training set and a test set, enabling the training set to be used fortraining a model, and enabling the test set to be used for testing the model; firstly, a training set is input into a feature selection algorithm to be compared with a classification result of an original situation data set, and p features with the best result are selected; Using an oversampling algorithm to obtain a training set of which the ratio of positive and negative samples is 1: 1, respectively inputting the training set into a classification algorithm, testing by using a data sequence of a test set, and selecting to obtain an oversampling algorithm i of a training set Pi with an optimal evaluation result; By adjusting the proportion of the positive and negative samples, the training set is input into an oversampling algorithm for obtaining a training set Pi, the proportion of thepositive and negative samples is gradually increased to a set proportion, and the optimal proportion of the positive and negative samples is classified and evaluated. According to the technical scheme, an oversampling algorithm is used for attempting to increase the proportion of the positive samples, and better model evaluation indexes and the recall rate of a few positive samples are obtained.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning and data mining, in particular to a method and system for classifying distant metastasis of abnormal cells based on non-equilibrium learning. Background technique [0002] Esophageal squamous cell carcinoma is one of the most common malignant tumors in the world, but its early symptoms are not obvious, and the changes in the body are easy to be ignored. Once the body can't bear it, it is usually in the middle and late stage. In the clinic, doctors use imaging, or even puncture and surgery to diagnose whether the cancer cells in patients with esophageal squamous cell carcinoma have distant metastasis. These three methods not only increase the cost of treatment for patients, but also take a long time. With the advent of the era of big data, in order to solve this problem, it is proposed to use blood cell analysis to predict whether a patient's cancer cells have metastasized. Afte...

Images