DEL FAVERO, Simone,MENEGHETTI, Lorenzo,TERZI, Matteo,SUSTO, Gian Antonio,COBELLI, Claudio
申请号：
IBIB2019/054470
公开号：
WO2019/229686A1
申请日:
2019.05.30
申请国别(地区):
IB
年份:
2019
代理人:
摘要：
The present invention involves a system (11) for detecting malfunctions in devices (1) for the administration of insulin, comprising a data processing unit (111) adapted to receive measurements of the glucose concentration from a sensor (21) of glucose monitoring and measurements of the amount of insulin infused by an infusion pump (31), a data input unit (311) operatively connected to the data processing unit (111) and adapted to receive estimates of assumed carbohydrates from a user, a storage unit (211) operatively connected to the data processing unit (111) and adapted to store the glucose concentration measurements, the measurements of the amount of infused insulin, the measurements of the amount of carbohydrates taken； in which the data processing unit (111) is able to calculate the value of a DCOB variable (t) called "weighted glucose variation": in which the data processing unit (111) is further adapted to calculate an ICOB variable (t) named "weighted residual insulin": wherein IOB(t) is the variable which describes the estimate of the residual insulin in the blood over time, γ and δ are two positive constants, and wherein the data processing unit (111) is able to execute at least one anomaly detection algorithm of the unsupervised type configured for assigning an anomaly score to data in a patient data set, based on at least one criterion selected among: - "Density-based"； - "Isolation-based"； - "Statistics-based", and - "hypersurface-based", wherein each patient data in said set, at a given time, comprises at least a triad of values, said triad of values being constituted by a value of the variable DCOB(t) at a given time, a value of the variable ICOB(t) in said given time, and a measurement of glucose concentration by said sensor (21) at said given time, and wherein said data processing unit (111) is able to generate an alert signal if said algorithm detects at least one anomaly within the patient data set, said data processing unit (111) detecting at le
