Automatic classification method for eye refraction correction multi-source data based on XGBoost

Abstract

The invention relates to an automatic classification method for eye refraction correction multi-source data based on XGBoost, and the method comprises the steps: selecting an attribute feature relatedto eye refraction data classification as the most original feature for training by adopoting a scheme of combining the clinical experience of an ophthalmologist with a statistical strategy; based onthe screened data, utilizing an XGBoost algorithm to further perform feature screening according to the feature importance, and selecting related attribute features most related to the target; and based on the selected training samples, considering the problem of sample imbalance, giving different weights to each sample and avoiding setting corresponding early stop functions by training over-fitting, and training an XGBoost model to classify the samples. According to the method, the accuracy of multi-source data classification can be effectively improved, manual intervention is not needed in the training process, the training time is shortened, and the training efficiency is improved.

Description

technical field [0001] The invention belongs to the field of machine learning algorithms applied to medical data processing, and relates to machine learning technology, in particular to an algorithm scheme for automatically classifying multi-source data of corneal refraction correction in ophthalmology by using an integrated learning method based on an XGBoost model. Background technique [0002] Myopia has become the leading cause of visual impairment in the world. It has not only become one of the focus medical issues of global concern, but also an important social issue. Every year, a large number of people need myopia correction, so it is necessary to find a safe, effective and accurate correction method. At present, corneal refractive surgery is the main method for correcting myopia among young people. In China, more than one million people receive refractive surgery every year. Corneal refractive surgery includes a variety of surgical methods. The selection of differe...

AI Technical Summary

Problems solved by technology

The difficulty of applying this scheme is that the sample size of each data type is seriously unbalanced, and the data types include characters, numbers and other types that need to be unified; the earlystopping strategy in the process of training the model needs to be measured by indicators that doctors care about clinically

Images