Medical record auditing method and device based on machine learning, equipment and storage medium

Abstract

The invention provides a medical record auditing method based on machine learning, and the method comprises the steps: obtaining medical record sample data, and carrying out the training of a preset medical record auditing model according to the medical record sample data till the convergence of the medical record auditing model; when a to-be-audited medical record text is monitored, determining adisease type probability value and a high risk value of the to-be-audited medical record text according to the to-be-audited medical record text and the medical record auditing model; and determininga medical record auditing result of the to-be-audited medical record text according to the medical record probability value and the high risk value. The invention further provides a medical record auditing device and equipment based on machine learning and a computer readable storage medium. According to the invention, the accuracy and efficiency of medical record risk auditing are effectively improved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, and in particular, to a method, device, device and storage medium for examining medical records based on machine learning. Background technique [0002] With the effective implementation of the national medical insurance, patients can use the national medical insurance to see a doctor and be hospitalized. The hospital usually charges by item, that is, charges by diagnosis and treatment items, such as urine routine and blood routine. The packaging and pricing of medical records are used as the payment standard of medical insurance, and medical insurance reimbursement expenses are related to the accuracy and standardization of medical records. Therefore, the risk review of medical records is an indispensable part of charging by disease. [0003] At present, the risk review method of medical records is mainly to adopt near-random screening of medical records, or to manually screen t...

AI Technical Summary

Problems solved by technology

[0003] At present, the risk review method of medical records is mainly to adopt near-random screening of medical records, or to manually screen medical records based on the experience of previous errors and illegal medical records to determine whether the medical records have high risk. However, the current medical records There is a lag in the risk review method, and the accuracy of the risk review of medical records is poor and the review efficiency is low.

Images