English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Sepsis is a leading cause of mortality in intensive care units (ICUs) andcosts hospitals billions annually. Treating a septic patient is highlychallenging, because individual patients respond very differently to medicalinterventions and there is no universally agreed-upon treatment for sepsis.Understanding more about a patient's physiological state at a given time couldhold the key to effective treatment policies. In this work, we propose a newapproach to deduce optimal treatment policies for septic patients by usingcontinuous state-space models and deep reinforcement learning. Learningtreatment policies over continuous spaces is important, because we retain moreof the patient's physiological information. Our model is able to learnclinically interpretable treatment policies, similar in important aspects tothe treatment policies of physicians. Evaluating our algorithm on past ICUpatient data, we find that our model could reduce patient mortality in thehospital by up to 3.6% over observed clinical policies, from a baselinemortality of 13.7%. The learned treatment policies could be used to aidintensive care clinicians in medical decision making and improve the likelihoodof patient survival.

Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach