Mealtime blood glucose classifier based on fuzzy logic for the DIABTel telemedicine system
The accurate interpretation of Blood Glucose (BG) values is essential for diabetes care. However, BG monitoring data does not provide complete information about associated meal and moment of measurement, unless patients fulfil it manually. An automatic classification of incomplete BG data helps to a more accurate interpretation, contributing to Knowledge Management (KM) tools that support decision-making in a telemedicine system. This work presents a fuzzy rule-based classifier integrated in a KM agent of the DIABTel telemedicine architecture, to automatically classify BG measurements into meal intervals and moments of measurement. Fuzzy Logic (FL) tackles with the incompleteness of BG measurements and provides a semantic expressivity quite close to natural language used by physicians, what makes easier the system output interpretation. The best mealtime classifier provides an accuracy of 77.26% and does not increase significantly the KM analysis times. Results of classification are used to extract anomalous trends in the patient's data.
keywords: Classification, Diabetes, Fuzzy Logic, Telemedicine
Publication: Congress
1624015052237
June 18, 2021
/research/publications/mealtime-blood-glucose-classifier-based-on-fuzzy-logic-for-the-diabtel-telemedicine-system
The accurate interpretation of Blood Glucose (BG) values is essential for diabetes care. However, BG monitoring data does not provide complete information about associated meal and moment of measurement, unless patients fulfil it manually. An automatic classification of incomplete BG data helps to a more accurate interpretation, contributing to Knowledge Management (KM) tools that support decision-making in a telemedicine system. This work presents a fuzzy rule-based classifier integrated in a KM agent of the DIABTel telemedicine architecture, to automatically classify BG measurements into meal intervals and moments of measurement. Fuzzy Logic (FL) tackles with the incompleteness of BG measurements and provides a semantic expressivity quite close to natural language used by physicians, what makes easier the system output interpretation. The best mealtime classifier provides an accuracy of 77.26% and does not increase significantly the KM analysis times. Results of classification are used to extract anomalous trends in the patient's data. - García-Sáez G., Alonso J., Molero J., Rigla M., Martínez-Sarriegui I., De Leiva A., Gómez E., Hernando M. - 10.1007/978-3-642-02976-9_42
publications_en