A method and device for identifying doctors who prescribe drugs abnormally based on local outlier factors

Abstract

An embodiment of the invention provides a method and device for identifying doctors who prescribe drugs abnormally based on local outlier factors. The method comprises the steps: obtaining drug classdata of drug prescribed by each doctor; according to the drug class data, determining a feature vector of the drug prescribed by each doctor; preprocessing the feature vector, and calculating a localoutlier factor value of the doctor according to the preprocessed feature vector; and according to the local outlier factor value, identifying the doctors who prescribe the drugs abnormally. The methodis implemented by the device. According to the method and device for identifying the doctors who prescribe drugs abnormally based on the local outlier factors, by obtaining the drug class data of thedrug prescribed by each doctor, determining the feature vector of the drug prescribed by each doctor, preprocessing the feature vector and calculating the local outlier factor value of each doctor according to the preprocessed feature vector and identifying the doctors who prescribe the drugs abnormally, the doctors who prescribe the drugs abnormally can be identified accurately, simply and conveniently at low cost.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of medical behavior recognition, and in particular to a method and device for identifying doctors who prescribe abnormal drugs based on local outlier factors. Background technique [0002] Doctors or nurses in medical institutions may induce patients to take some expensive drugs that have little to do with the treatment of their own diseases, or a large amount of drugs, etc., which not only endangers the physical and mental health of patients, but also wastes the country's medical resources. Resources, doctors with these behaviors are defined as doctors who prescribe abnormal drugs, so it is particularly important to identify doctors who prescribe abnormal drugs. [0003] With the advent of the era of big data, more and more medical data (medical insurance data) are recorded in the medical information system. The existing technology uses methods such as data mining of the data in the me...

AI Technical Summary

Problems solved by technology

[0003] With the advent of the era of big data, more and more medical data (medical insurance data) are recorded in the medical information system. The existing technology uses methods such as data mining of the data in the medical information system to identify doctors who prescribe abnormal drugs. , however, the method used has the following defects: 1) Some supervised or hybrid methods for identifying abnormal cases require labeled data, and the cost of data labeling in reality is relatively high

2) The calculation process is complex, time-consuming, and not easy to understand

3) The characteristics of most methods are obtained after abstracting the original data, and the impact of all items in the original data on the identification results of doctors who prescribe abnormal drugs is not fully considered, that is, the identification results are not accurate enough

Images