In this study, the enhanced HbA1c NIBG deep learning model (blood glucose level predicted from PPG and HbA1c) is trained with 1494 measurements, and we replaced the HbA1c measurement (explicit HbA1c) with “implicit HbA1c” which is reversely derived from pretested PPG and finger pricked blood glucose level. The implicit HbA1c is then evaluated across intervals up to 90 days since the pretest, achieving an impressive 87% accuracy, while the remaining 13% falls near the CEG zone A boundary. The Implicit HbA1c approach exhibits a remarkable 16% improvement over the Explicit HbA1c method by covering personal correction items automatically. This improvement not only refines the accuracy of the model but also enhances the practicality of the previously proposed model that relied on an HbA1c input.
1. High accuracy of Non-Invasive Blood Glucose Prediction
2. Real time for Non-Invasive Blood Glucose Prediction
3. Easy to use

Figure1. The sequential workflow, starting from the pretest phase to derive the implicit HbA1c, followed by its application during testing to generate the final blood glucose level prediction.
26A-1121017
Patent filing
1. Non-Invasive Blood Glucose Prediction
2. Personalized medicine
3. Precision medicine
Fu-Liang Yang
If you are interested in this technology, please fill in the information on the webpage under the manufacturer option (Request for Technology Licensing, Material Transfer, or Sponsored Research) on the website of this office

Non-Invasive Blood Glucose Prediction by Deep Learning System with Implicit HbA1c