Delirium risk monitoring method and system based on delirium dynamic prediction model

Abstract

The invention relates to a delirium risk monitoring method based on a delirium dynamic prediction model. The delirium risk monitoring method at least comprises one or more of the following steps of carrying out delirium consciousness fuzzy quick evaluation of a to-be-evaluated object for at least one time; calling a dominant factor and a recessive factor related to the to-be-evaluated object in amedical information management system by a delirium factor processing module, and generating a label required by a delirium risk monitoring module according to the attribute of the dominant factor and / or the attribute of the recessive factor; based on the generated label, enabling the delirium risk monitoring module to obtain a plurality of case information groups matched with the to-be-evaluatedobject in a cloud platform in an information interaction mode with the cloud platform; and enabling the delirium risk monitoring module to perform calculation by using the delirium dynamic predictionmodel according to the obtained multiple case information groups to obtain delirium risk prediction of the to-be-evaluated object.

Description

technical field [0001] The invention relates to the technical field of delirium nursing, in particular to a delirium risk monitoring method and system based on a delirium dynamic prediction model. Background technique [0002] Delirium is a group of acute cognitive impairment syndromes characterized by attention deficit, confusion, confusion, and altered state of consciousness. It is an acute or subacute onset disease, usually changing within hours to days. , identification requires a brief cognitive screening and keen clinical observation, the main diagnostic features include acute onset and fluctuating altered state of consciousness, inattention, impaired level of consciousness, cognitive impairment (eg, disorientation, memory impairment ). Clinically, the delirium that occurs in patients in the Intensive Care Unit (ICU) is often referred to as ICU delirium. According to literature reports, 14% to 24% of hospitalized patients develop delirium during hospitalization, and t...

AI Technical Summary

Problems solved by technology

In this regard, the prior art proposes a solution to cluster and capture similar condition information in medical big data and perform risk prediction based on the captured data. However, since such solutions are aimed at Multiple related medical data are clustered and captured, without considering the important impact of the individual differences of the current subject to be evaluated on the risk of delirium, that is, a single medical data cannot reflect the current state and response of the subject to be evaluated; in addition, the The medical data objects captured by such solutions are all patients whose diseases have already been confirmed, resulting in the risk prediction results determined based on the medical data of the patients after diagnosis, which has extremely low reliability. Therefore, the solutions proposed by the existing technology The protocol is not suitable for delirium risk prediction, especially not for delirium risk prediction of subjects who have not yet experienced delirium

Images