Machine Learning–Based Calibration of Commercial Continuous Glucose Monitoring Sensor in Nonserum Solutions: An In Vitro Validation Study

Abstract

Background

Continuous glucose monitoring (CGM) systems, such as the FreeStyle Libre Pro (Abbott Diabetes Care), offer noninvasive glucose measurement. However, their accuracy in cerebrospinal fluid (CSF) glucose monitoring remains unvalidated. This study evaluates the performance of the FreeStyle Libre sensor against a standard laboratory analyzer and proposes a regression-based calibration model to enhance measurement accuracy in neurotrauma ICU.

Materials and Methods

A FreeStyle Libre sensor was integrated into an experimental setup using an adapter. Sensor readings were recorded with glucose concentrations ranging from 50 to 275 mg/dL. A standard laboratory analyzer was used as the reference. A linear regression model was trained to correct sensor deviations, with interpolation (SciPy's interp1d) used for refined predictions. Real-time data acquisition was facilitated via Universal asynchronous receiver / transmitter (UART)-based serial communication, and adaptive learning enabled model retraining upon accumulating 10 sensor laboratory value pairs.

Results

Initial sensor readings exhibited significant deviations from laboratory values, particularly at lower glucose concentrations (mean absolute relative difference [MARD]: 30.45%). Postcalibration, the MARD was reduced to 8.92%, demonstrating improved accuracy. Interpolation further minimized deviations, correcting values such as 40 mg/dL (20% deviation) to 49.1 mg/dL (1.8% deviation) and 72 mg/dL (42.4% deviation) to 123.5 mg/dL (1.2% deviation). Adaptive learning progressively reduced the root mean square error (RMSE) from 23.7 to 9.8 mg/dL after 30 updates.

Conclusion

The calibration model makes the FreeStyle Libre sensor more accurate for CSF glucose measurements. This method might be promising for monitoring CSF glucose continuously of patients with external ventricular drainage, improving patient care in the neurotrauma ICU.

Keywords

biosensor - calibration model - glucose monitoring - external ventricular drainage - neurotrauma

Publikationsverlauf

Artikel online veröffentlicht:
09. April 2025

• References

• 1 Johnston L, Wang G, Hu K, Qian C, Liu G. Advances in biosensors for continuous glucose monitoring towards wearables. Front Bioeng Biotechnol 2021; 9: 733810
• 2 Cappon G, Vettoretti M, Sparacino G, Facchinetti A. Continuous glucose monitoring sensors for diabetes management: a review of technologies and applications. Diabetes Metab J 2019; 43 (04) 383-397
• 3 Acciaroli G, Vettoretti M, Facchinetti A, Sparacino G. Calibration of minimally invasive continuous glucose monitoring sensors: state-of-the-art and current perspectives. Biosensors (Basel) 2018; 8 (01) 24
• 4 Blum A. Freestyle Libre glucose monitoring system. Clin Diabetes 2018; 36 (02) 203-204
• 5 Huang Q, Chen J, Zhao Y, Huang J, Liu H. Advancements in electrochemical glucose sensors. Talanta 2025; 281: 126897
• 6 Pullano SA, Greco M, Bianco MG, Foti D, Brunetti A, Fiorillo AS. Glucose biosensors in clinical practice: principles, limits and perspectives of currently used devices. Theranostics 2022; 12 (02) 493-511
• 7 Reddy N, Verma N, Dungan K. Monitoring technologies: continuous glucose monitoring, mobile technology, biomarkers of glycemic control. In: Feingold KR, Anawalt B, Blackman MR. et al., eds. Endotext. South Dartmouth, MA: MDText.com, Inc.; 2000
• 8 Ida S, Goto H, Ida S. et al. Accuracy of a factory calibrated retrospective CGM device and the comparison to a conventionally calibrated retrospective CGM device: a pilot study. Biomed Sci 2019; 4 (04) 32-36
• 9 Murata T, Sakane N, Hirota Y. et al. Difference in the accuracy of the third-generation algorithm and the first-generation algorithm of FreeStyle Libre continuous glucose monitoring device. J Med Invest 2024; 71 (3.4): 225-231
• 10 Nakagawa Y, Hirota Y, Yamamoto A. et al. Accuracy of a professional continuous glucose monitoring device in individuals with type 2 diabetes mellitus. Kobe J Med Sci 2022; 68 (01) E5-E10
• 11 Wang C, He T, Zhou H, Zhang Z, Lee C. Artificial intelligence enhanced sensors: enabling technologies to next-generation healthcare and biomedical platform. Bioelectron Med 2023; 9 (01) 17
• 12 Hrishi AP, Sethuraman M. Cerebrospinal fluid (CSF) analysis and interpretation in neurocritical care for acute neurological conditions. Indian J Crit Care Med 2019; 23 (Suppl. 02) S115-S119
• 13 Hatami-Fard G, Anastasova-Ivanova S. Advancements in cerebrospinal fluid biosensors: bridging the gap from early diagnosis to the detection of rare diseases. Sensors (Basel) 2024; 24 (11) 3294
• 14 Fellinger E, Brandt T, Creutzburg J, Rommerskirchen T, Schmidt A. Analytical performance of the FreeStyle Libre 2 glucose sensor in healthy male adults. Sensors (Basel) 2024; 24 (17) 5769
• 15 Freckmann G, Nichols JH, Hinzmann R. et al. Standardization process of continuous glucose monitoring: traceability and performance. Clin Chim Acta 2021; 515: 5-12
• 16 Zhou J, Lv X, Mu Y. et al. The accuracy and efficacy of real-time continuous glucose monitoring sensor in Chinese diabetes patients: a multicenter study. Diabetes Technol Ther 2012; 14 (08) 710-718
• 17 Nashruddin SNABM, Salleh FHM, Yunus RM, Zaman HB. Artificial intelligence-powered electrochemical sensor: recent advances, challenges, and prospects. Heliyon 2024; 10 (18) e37964
• 18 Facchinetti A. Continuous glucose monitoring sensors: past, present and future algorithmic challenges. Sensors (Basel) 2016; 16 (12) E2093
• 19 van Doorn WPTM, Foreman YD, Schaper NC. et al. Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: the Maastricht study. PLoS One 2021; 16 (06) e0253125