Medical record data analysis method and device

Abstract

The invention relates to the technical field of computers, in particular to a medical record data analysis method and device. The method comprises the steps: obtaining an electronic medical record ofa user to be detected; extracting feature information related to a target disease according to the electronic medical record; and taking the feature information related to the target disease as an input parameter based on a trained disease risk assessment model and obtaining a risk assessment result of target disease occurrence of the user to be detected, wherein the disease risk assessment modelis obtained by performing iterative training according to a positive sample set and a negative sample set, the positive sample set being the electronic medical record of the target disease, and the negative sample set being the electronic medical record of other diseases which are not the target disease, so that based on the electronic medical record and the risk assessment result of the disease risk assessment model, active information collection is not needed, the cost is saved, the efficiency is improved, and the risk assessment accuracy is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a method and device for analyzing medical record data. Background technique [0002] At present, cardiovascular and cerebrovascular diseases, such as stroke, are common diseases that seriously threaten human health. It is very necessary to accurately predict and prevent them early. The risk assessment schemes for cardiovascular and cerebrovascular diseases in the prior art mainly rely on the active input of users. Information requires manual and active collection of user disease-related information, such as the improved Framingham Stroke Scale, pooled cohort equations, and stroke risk calculators. The models of these methods rely on simple scorecard forms. [0003] However, this method in the prior art requires manual and active collection of user information, which consumes a lot of manpower, material and financial resources, and has low efficiency. The number and di...

AI Technical Summary

Problems solved by technology

[0003] However, this method in the prior art requires manual active collection of user information, which consumes a lot of manpower, material and financial resources, and has low efficiency. The number and dimensions of collected user information are limited, and a simple linear statistical model is used. The process is limited by factors such as the accuracy of actively collected information, which reduces the accuracy of the final disease risk assessment

Images