Method of dynamically predicting middle and short term area pediatric outpatient amount based on time sequence

Abstract

The invention discloses a method of dynamically predicting a middle and short term area pediatric outpatient amount based on a time sequence. A middle and short term pediatric outpatient amount in an area is dynamically predicted accurately so that a scientific basis is provided for solving problems of area health resource programming, optimization configuration and the like. Simultaneously, through introducing different disease outpatient amount distribution, abnormal states, such as sudden infectious diseases and the like, can be determined so that spreading of the infectious diseases in groups can be rapidly prejudged. The method is realized based on a time sequence prediction model. The method comprises the following steps of step1, sequence smoothness inspection and processing; step2, event variable identification; step3, parameter estimation and inspection; step4, optimal sequence length identification; and step5, dynamic prediction. The above steps are mainly used for selecting an optimal sequence prediction model, a time variation influence is eliminated, problems of overfitting of time sequence prediction and a poor extrapolation effect are effectively overcome and accurate prediction is performed.

Description

technical field [0001] The invention relates to a method for predicting the number of outpatient visits, in particular to a method for dynamically predicting the number of pediatric outpatient visits in a short-term and medium-term region based on time series. Background technique [0002] Under the current situation, quantitatively understanding the medical and health service needs of residents in the region has significant practical significance for rationally formulating regional health planning, optimizing the allocation of medical and health resources, and improving the quality and efficiency of medical and health services. The number of outpatient visits is an important indicator that reflects residents' medical treatment. It can accurately predict the number of outpatient visits in the next cycle (day, week, month) in the region, and provide an important basis for the planning and optimal allocation of regional health resources. [0003] The number of pediatric outpat...

AI Technical Summary

Problems solved by technology

[0005] Some scholars have used time series to predict the number of outpatients, and compared with the actual number of outpatients, they have achieved good prediction results, but there are also obvious limitations: 1) The selection bias is more biased towards large hospitals when visiting a doctor, so These forecasts of outpatient visits for all departments of a tertiary hospital can grasp the short-term fluctuations in the outpatient volume of the hospital as a whole, but the reference value for specific optimization of which department outpatient resources in the hospital is limited; 2) A children's hospital uses the ARIMA model to predict short-term, The number of outpatient visits in the mid-term provides a basis for the hospital to rationally arrange outpatient medical resources and improve hospital management. However, it is not feasible to infer the demand for pediatric medical treatment in the entire region if the sample is used; The department’s annual summary of visits can be carried out on the scale of visits, which can grasp the growth trend of hospital visits in my country in recent decades as a whole, but there is limited basis for health management departments to carry out specific regional health planning and resource allocation; 4) Static forecasting in the near future ( 3 months, 4 weeks) outpatient visits, no dynamic time series prediction was attempted

Images