Time Series Analysis Of Emergency Visits With Acute Stroke In A Top Three Hospital

Objective:Using the emergency visits with acute stroke those are from a top hospital from 2010 to2015 to retrospectively analyze the characteristics of the number and distribution of he emergency visits with acute stroke.The time series analysis model is established to predict the incidence of acute stroke in recent years.Provide a reliable theoretical basis for the hospital managers to make a decision about allocating scientific and rational emergency medical personnel,making effective use of resources and improving the quality of medical services.Methods:Selected the emergency medical information of a top hospital from January 2010 to December 2015 to establish a database.The data included patient name,gender,age,treatment department,visit time,chief complaint,preliminary diagnosis.And used the data from January 2010 to December 2014 to establish the ARMA?1,1?model and experimentally predicted the number of emergency visits in the 12 months of2015.Evaluate the degree of fit of the predict model with the actual data of 2015 to further understand the time distribution characteristics of emergency acute stroke visits,and apply its predictive effect to clinical practice.Results:Finally,the ARMA?1,1?is the prediction model,the specific form is:X_t=189.4641?1-0.981891?+0.981891*X_t-1-0974909*X_t-2+?_t.And its 2015 forecast results was compared with real data and the relative error was less than 5%,which indicated that the model is well-fitted.Conclusion:The ARMA?1,1?model of emergency visits with acute stroke can predict the onset of the disease in recent years to further improve the management of stroke prevention and management.On the other hand,it can provide a basis for the management of high-efficiency medical institutions.