Drug risk grading method based on naive random oversampling and support vector machine

Abstract

The invention discloses a drug risk grading method based on naive random oversampling and a support vector machine, and the method comprises the steps: constructing risk indexes I1, I2 and I3 based on adverse drug reaction risk factors, processing adverse drug reaction spontaneous report data, calculating three risk index values, taking a drug as an object, taking the risk indexes as features, constructing a drug risk matrix, inquiring national basic drug catalogs, marking drug categories, expanding non-prescription drug data by using naive oversampling, realizing the balance of prescription drug and non-prescription drug sample sizes, establishing a classification model and verifying by using a dichotomy support vector machine, and realizing intelligent management of drug risk classification. According to the method, unbalanced sampling is carried out on processed data, then binary classification of drugs is realized by using the support vector machine, and finally, the function of automatic classification according to adverse reactions of different drugs is realized.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a drug risk classification method based on naive random oversampling and support vector machines. Background technique [0002] With the rapid advancement of science and technology and its wide application in medicine, it has provided important tools for relieving patients' pain and curing various diseases, greatly improving the health level of patients, not only improving the quality of life of patients, but also effectively prolonging the life expectancy of patients. Longevity has brought a lot of convenience to our life. Because of the unpredictable adverse drug reaction (Adverse Drug Reaction, ADR) of drugs after marketing, it poses a threat to human health. [0003] Adverse drug reaction spontaneous reporting system plays an important role in timely detection of adverse reactions, timely assessment of drug safety risks, and ensuring drug safety. [000...

AI Technical Summary

Problems solved by technology

RX and OTC can be transformed into each other under certain conditions. At present, this kind of transformation is mainly through the application of pharmaceutical companies and the approval of the state. The approval process is mainly expert investigation, mainly manual, and lacks the method of automatic decision-making based on machine learning.

Images