Hospitalization behavior prediction method and device based on time-varying attention improved Bi-LSTM

Abstract

The invention provides a hospitalization behavior prediction method and device based on time-varying attention improved Bi-LSTM. The hospitalization behavior prediction method comprises the steps of extracting features from massive medical insurance data, wherein the correlation degree between the features and hospitalization behaviors is greater than a preset correlation degree threshold; constructing Bi-LSTM by utilizing the extracted hospitalization behavior characteristics and the corresponding weights of the hospitalization behavior characteristics; updating a weight value of each hospitalization state prediction data in the Bi-LSTM by adopting hospital-disease attraction data pre-generated by an attention mechanism based on the hospitalization state prediction data obtained by the Bi-LSTM; constructing a time adjustment function; outputting a multi-period multi-state hospitalization state prediction vector; utilizing the hospitalization state prediction vector to construct a softmax prediction function; calculating a loss function of an output value of the softmax prediction function, training learning parameters of Bi-LSTM by adopting back propagation, and completing training of the model; and after model training is completed, outputting a prediction result of the experimental sample set, comparing the prediction result with an actual hospitalization behavior, and feeding back and updating a weight value of hospitalization state prediction data.

Description

technical field [0001] The disclosure belongs to the field of medical insurance information processing, and in particular relates to a time-varying attention-improved Bi-LSTM hospitalization behavior prediction method and device. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Medical-seeking behavior refers to the process in which an individual seeks medical help in order to relieve symptoms or cure the disease when symptoms appear. Due to the differences in medical technology levels and medical insurance reimbursement policies of various hospitals, individuals tend to seek medical treatment in hospitals with high medical standards and relatively favorable medical insurance reimbursement, which leads to problems such as high medical service load in some hospitals, uneven distribution of medical resources, and serious medical insurance fu...

AI Technical Summary

Problems solved by technology

However, RNNs cannot effectively solve the long-term dependent expression relationship between medical treatment sequences. For example, when the time interval of a patient's medical treatment sequence is too large, the prediction performance of the RNNs model will decline.

In addition, the inventor found that due to the special regularity of the behavior of seeking medical treatment, such as the specialties of each hospital have different attractiveness of the trend of seeking medical treatment, there are few medical records in a long period of time, or there are many medical records in a short period of time. At this time, the traditional The prediction method of hospitalization and medical treatment behavior ignores the influence of the hospital's special attention and time availability on medical treatment behavior, so it is difficult to achieve the prediction effectiveness of hospitalization and medical treatment behavior

Images