A computational technique to predict the level of glucose of a diabetic patient with uncertainty in the short term. Issue 2 (21st November 2019)

• Record Type: Journal Article
• Authors: Burgos Simón, Clara; Cervigón, Carlos; Hidalgo, José‐Ignacio; Villanueva, Rafael‐J.
• Is Part Of: Computational and mathematical methods. Volume 2:Issue 2(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-11-21
• Subjects: glucose mathematical model -- model prediction -- uncertainty quantification; Mathematics -- Data processing -- Periodicals; Numerical analysis -- Periodicals; Numerical analysis; Mathematics -- Data processing; Periodicals; 004.0151
• DOI: 10.1002/cmm4.1064
• Languages: English
• ISSNs: 2577-7408

Abstract

Abstract : On advanced stages of the disease, diabetic patients have to inject insulin doses to maintain blood glucose levels inside of a healthy range. The decision of how much insulin is injected implies somehow to predict the level of glucose they will have after a certain time. Due to the sudden changes in the glucose levels, their estimation is a very difficult task. If we were able to give reliable estimations in advance, it would facilitate the process of taking therapeutic decisions to control the disease and improve the health of the patient. In this work, we present a technique to estimate the glucose level of a diabetic patient, capturing the measurement errors produced by continuous glucose monitoring systems (CGMSs), smart devices that measure glucose levels. To do that, we will use a model of glucose dynamics and we calibrate it with the aim to capture the glucose level data of the patient in a time interval of 30 minutes and the uncertainty given by the glucose measurement. Then, we use the calibrated parameters to predict the levels of glucose over the next 15 minutes. Repeating this procedure every 15 minutes, we are able to give short‐term accurate predictions.