Wearable blood glucose detection method and system based on data enhancement and storage medium

Abstract

The invention discloses a wearable blood glucose detection method and system based on data enhancement and a storage medium. The wearable blood glucose detection method comprises the steps that a random forest model is built by collecting a blood glucose true value and a corresponding feature matrix in a fixed time period as a training set; inputting a newly added feature matrix of daily noninvasive detection into the random forest model to obtain corresponding N blood glucose predicted values, taking the N blood glucose predicted values as true values, combining the N blood glucose predicted values with an originally collected feature matrix, and supplementing the N blood glucose predicted values as new training data into an original data set so as to continuously enlarge the number of training samples; constructing a blood glucose prediction model through an RNN model according to the new training sample; according to the method, the features obtained by collecting the signals each time when the user actually uses the wearable device to conduct noninvasive detection are input into the blood glucose prediction model, the blood glucose prediction result is obtained, the robustness of the model is improved through data enhancement, and the prediction accuracy is effectively improved.

Description

technical field [0001] The invention relates to the technical field of blood sugar detection, and more particularly, to a wearable blood sugar detection method, system and storage medium based on data enhancement. Background technique [0002] As one of the four major chronic diseases, diabetes has long become a major disease that threatens people's physical and mental health. According to the current level of medical technology, diabetes cannot be completely cured. Moreover, diabetes will not only bring the pain and suffering of complications, but also affect people's diet and living habits for a long time, bring about psychological distress, and constantly endanger people's physical and mental health. Therefore, people should form the concept of "early prevention", "early detection" and "early treatment" of diabetes, among which measuring blood sugar is an essential step. In the traditional method of detecting blood sugar, the blood sugar value is detected by a biochemica...

AI Technical Summary

Problems solved by technology

The realization of wearable non-invasive blood glucose detection requires the collection of the user’s actual blood glucose data in the early stage, and then predicts the blood glucose value through the algorithm model based on the collected user characteristics. However, the original intention of non-invasive detection is to reduce the pain of patients, so it can only be collected in the early stage. Invasive detection data, and the key problem is - less data will lead to low accuracy of prediction results

Images