Sepsis treatment strategy optimization method and system, computer equipment and storage medium

Abstract

The invention provides a sepsis treatment strategy optimization method and system, computer equipment and a storage medium, and the method comprises the steps: building corresponding health state labeling medical record data according to obtained sepsis patient medical record data, and building a sepsis patient health state transfer model according to health state information and medication action information; obtaining a first treatment strategy of the sepsis patient through the health state transfer model, obtaining a second treatment strategy of the sepsis patient through a model-free deep reinforcement learning method according to the health state labeling medical record data, and carrying out strategy fusion on the first treatment strategy and the second treatment strategy to obtain a fusion treatment strategy. According to the method, the fusion treatment strategy is subjected to expected income evaluation through an off-strategy evaluation method, and the fusion treatment strategy is adjusted to obtain an optimal treatment strategy, so that a reasonable medication treatment strategy can be given according to different health states of sepsis patients, and a reliable reference basis is provided for sepsis treatment.

Description

technical field [0001] The invention relates to the technical field of medical reinforcement learning, in particular to a method, system, computer equipment and storage medium for optimizing a sepsis treatment strategy based on strategy fusion. Background technique [0002] Sepsis is a systemic inflammatory response syndrome caused by infection, which poses a serious threat to life safety and is one of the main causes of common high-risk complications and death in ICU patients. Therefore, the medication actions of patients with sepsis at each stage are very critical. If a rational drug treatment strategy can be given according to the different health states of sepsis patients at different stages, it will effectively reduce the mortality of sepsis patients. [0003] Existing machine learning for sepsis is limited to early prediction of patients' conditions, and does not involve machine learning research on treatment strategies for patients with sepsis. Clinical treatment stil...

AI Technical Summary

Problems solved by technology

[0003] Existing machine learning for sepsis is limited to early prediction of patients' conditions, and does not involve machine learning research on treatment strategies for patients with sepsis. Clinical treatment still mainly relies on experience accumulation and human decision-making by doctors. However, sepsis The clinical data of patients with the disease cannot be shared well, and each doctor's clinical experience is limited, which does not necessarily guarantee that a reasonable and effective medication strategy can be given at each stage of the patient's health status

Images