Cerebral hemorrhage classification prediction device

Abstract

The invention relates to a cerebral hemorrhage classification prediction device, and the device comprises a data collection module which is used for collecting the treatment information of a patient; the classification prediction module is used for taking the treatment information of the patient as the input of a classification prediction model to obtain the possibility of future cerebral hemorrhage of the patient; wherein the classification prediction model is constructed by a model construction module, and the model construction module comprises a collection unit used for collecting longitudinal panel data of a patient; the preprocessing unit is used for carrying out independence test and statistic test on the longitudinal panel data; the classification unit is used for inputting the preprocessed longitudinal panel data into a plurality of trained classification models to obtain a classification result; the selection unit is used for selecting the classification model with the best classification effect from the classification results; and the adjustment unit is used for adjusting the classification model selected by the selection unit so that the accuracy, the precision and the recall rate of the classification model are balanced, and the adjusted classification model is used as a classification prediction model.

Description

technical field [0001] The invention relates to the technical field of computer-aided medical data analysis, in particular to a device for classifying and predicting cerebral hemorrhage. Background technique [0002] Cerebral hemorrhage is one of the main diseases that endanger human health. At present, in the research on the prediction of cerebral hemorrhage, there are many researches on the prediction of cerebral hematoma after cerebral hemorrhage and the prognosis of cerebral hemorrhage. However, the research on the prediction of cerebral hemorrhage in non-cerebral hemorrhage patients is relatively few. In the prior art, to predict the probability of cerebral hemorrhage in non-cerebral hemorrhage patients, a cerebral hemorrhage prediction model is usually established based on external factors such as external temperature and air pressure, and then the probability of cerebral hemorrhage in a group is analyzed and predicted. However, most of the objects predicted by this m...

AI Technical Summary

Problems solved by technology

However, most of the prediction objects of this method are groups, and the probability of cerebral hemorrhage in a certain patient cannot be effectively obtained. At the same time, this prediction method is not applied to the features that can directly predict cerebral hemorrhage, but the prediction features are variable weather and air pressure. Building predictive models, which also affects the accuracy of forecasts

Images