Drug efficacy optimization method and device based on blood drug concentration monitoring

Abstract

The embodiment of the invention provides a drug efficacy optimization method and device based on blood drug concentration monitoring. The method comprises the steps: establishing a drug efficacy optimization sample database based on blood drug concentration monitoring, and each sample in the drug efficacy optimization sample database includes medication order information in case of normal blood drug concentration and the test item data closest to the time before taking the drug; performing missing value processing and significance testing on the drug efficacy optimization sample database so asto obtain the pretreated drug efficacy optimization sample database; performing supervised learning by using the XGBoost algorithm according to the pretreated drug efficacy optimization sample database and constructing a drug efficacy optimization model; and inputting the test item data to be predicted to the drug efficacy optimization model to obtain the medication order information corresponding to the test item data to be predicted. The drug efficacy optimization scheme of higher practicality can be predicted according to the test result of the patient so as to solve the medication problemof the patient in the complex situation and realize individualized drug efficacy optimization.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of medical artificial intelligence, and more specifically, to a drug efficacy optimization method and device based on blood drug concentration monitoring. Background technique [0002] The current traditional drug administration methods include: firstly formulate the initial drug regimen, and the formulation methods include: 1) the pharmacist performs the initial drug administration according to the instructions; 2) the pharmacist performs the initial drug administration according to the traditional pharmacokinetic equation; medication. After the patient is treated according to the initial plan, blood drug concentration monitoring (TDM) is usually performed before multiple doses. According to the measured trough concentration, the pharmacist then adjusts the medication plan according to the general medication guidelines and personal experience. However, the individual differences in th...

AI Technical Summary

Problems solved by technology

[0004] However, the method described in "Acta Pharmaceutica Sinica 2018,53(1):104-110" may not be practical for patients with complex conditions when formulating medication regimens, and there are certain risks. For example, patients with multiple diseases belong to For different special populations, this method cannot give a corresponding MAPB estimation model for this type of population, and patients who use vancomycin generally have complex conditions

In addition, the medical definition of special populations is very broad. If each type of population needs to implement a MAPB estimation model, it will be difficult to implement

Images