Silvia Oviedo1, Ivan Contreras2, Carmen Quirós3, Marga Giménez4, Ignacio Conget5, Josep Vehi6. 1. Institut d'Informatica i Aplicacions. Universitat de Girona, Spain. Electronic address: silvia.oviedo@udg.edu. 2. Institut d'Informatica i Aplicacions. Universitat de Girona, Spain. Electronic address: ivancontrerasfd@gmail.com. 3. Servicio de Endocrinología y Nutrición. Hospital Universitari Mutua de Terrassa, Terrassa, Spain. Electronic address: cmquiros@clinic.cat. 4. Diabetes Unit. Endocrinology and Nutrition Dpt. IDIBAPS (Institut d'investigacions biomdiques August Pi I Sunyer), Barcelona, Spain; Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), Spain. Electronic address: gimenez@clinic.cat. 5. Diabetes Unit. Endocrinology and Nutrition Dpt. IDIBAPS (Institut d'investigacions biomdiques August Pi I Sunyer), Barcelona, Spain; Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), Spain. Electronic address: iconget@clinic.cat. 6. Institut d'Informatica i Aplicacions. Universitat de Girona, Spain; Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), Spain. Electronic address: josep.vehi@udg.edu.
Abstract
BACKGROUND: Predicting insulin-induced postprandial hypoglycemic events is critical for the safety of type 1 diabetes patients because an early warning of hypoglycemia facilitates correction of the insulin bolus before its administration. The postprandial hypoglycemic event counts can be lowered by reducing the size of the bolus based on a reliable prediction but at the cost of increasing the average blood glucose. METHODS: We developed a method for predicting postprandial hypoglycemia using machine learning techniques personalized to each patient. The proposed system enables on-line therapeutic decision making for patients using a sensor augmented pump therapy. Two risk-based approaches were developed for a window of 240 min after the meal/bolus, and they were tested based on real retrospective data from 10 patients using 70 mg/dL and 54 mg/dL as thresholds according to the consensus for Level 1 and Level 2 hypoglycemia, respectively. Due to the small size of the patient cohort, we trained personalized models for each patient. RESULTS: The median specificity and sensitivity were 79% and 71% for Level 1 hypoglycemia, respectively, and 81% and 77% for Level 2. CONCLUSIONS: The results demonstrated that it is feasible to anticipate hypoglycemic events with a reasonable false-positive rate. The accuracy of the results and the trade-off between performance metrics allow its use in decision support systems for patients who wear insulin pumps.
BACKGROUND: Predicting insulin-induced postprandial hypoglycemic events is critical for the safety of type 1 diabetespatients because an early warning of hypoglycemia facilitates correction of the insulin bolus before its administration. The postprandial hypoglycemic event counts can be lowered by reducing the size of the bolus based on a reliable prediction but at the cost of increasing the average blood glucose. METHODS: We developed a method for predicting postprandial hypoglycemia using machine learning techniques personalized to each patient. The proposed system enables on-line therapeutic decision making for patients using a sensor augmented pump therapy. Two risk-based approaches were developed for a window of 240 min after the meal/bolus, and they were tested based on real retrospective data from 10 patients using 70 mg/dL and 54 mg/dL as thresholds according to the consensus for Level 1 and Level 2 hypoglycemia, respectively. Due to the small size of the patient cohort, we trained personalized models for each patient. RESULTS: The median specificity and sensitivity were 79% and 71% for Level 1 hypoglycemia, respectively, and 81% and 77% for Level 2. CONCLUSIONS: The results demonstrated that it is feasible to anticipate hypoglycemic events with a reasonable false-positive rate. The accuracy of the results and the trade-off between performance metrics allow its use in decision support systems for patients who wear insulin pumps.
Authors: Omar Diouri; Monika Cigler; Martina Vettoretti; Julia K Mader; Pratik Choudhary; Eric Renard Journal: Diabetes Metab Res Rev Date: 2021-03-24 Impact factor: 4.876