Model-Based Detection and Classification of Insulin Pump Faults and Missed Meal Announcements in Artificial Pancreas Systems for Type 1 Diabetes Therapy
Модельное обнаружение и классификация неисправностей инсулиновой помпы и пропущенных уведомлений о приёме пищи в системах искусственной поджелудочной железы для терапии сахарного диабета 1 типа
2020-06-22
SCID: 54.1/munhpsyx
Discuss with AI
artificial pancreasautoregressive moving-average modelcontinuous glucose monitoringinsulin pump faultsmissed meal announcements
Figures from the paper
Abstract (AI)
OBJECTIVE: The artificial pancreas (AP) is an innovative closed-loop system for type 1 diabetes therapy, in which insulin is infused by portable pumps and insulin dosage is modulated by a control algorithm on the basis of the measurements collected by continuous glucose monitoring (CGM) sensors. AP systems safety and effectiveness could be affected by several technological and user-related issues, among which insulin pump faults and missed meal announcements. This work proposes an algorithm to detect in real-time these two types of failure. METHODS: The algorithm works as follows. First, a personalized autoregressive moving-average model with exogenous inputs is identified using historical data of the patient. Second, the algorithm is used in real time to predict future CGM values. Then, alarms are triggered when the difference between predicted vs measured CGM values is higher than opportunely set thresholds. In addition, by using two different set of parameters, the algorithm is able to distinguish the two types of failures. The algorithm was developed and assessed in silico using the latest version of the FDA-approved Padova/UVa T1D simulator. RESULTS: The algorithm showed a sensitivity of ∼ 81.3% on average when detecting insulin pump faults with ∼ 0.15 false positives per day on average. Missed meal announcements were detected with a sensitivity of ∼ 86.8% and 0.15 FP/day. CONCLUSION: The presented method is able to detect insulin pump faults and missed meal announcements in silico, correctly distinguishing one from another. SIGNIFICANCE: The method increases the safety of AP systems by providing prompt alarms to the diabetic subject and effectively discriminating pump malfunctioning from user errors.
Key Findings
1
A personalized autoregressive moving-average model with exogenous inputs predicts future CGM values in real time from patient historical data.
2
In silico evaluation with the FDA-approved Padova/UVa T1D simulator achieved approximately 81.3% sensitivity for pump faults and 0.15 false positives per day.
3
Missed meal announcements were detected with approximately 86.8% sensitivity and 0.15 false positives per day, supporting improved artificial-pancreas safety.
4
Prediction errors exceeding defined thresholds trigger alarms for insulin pump faults or missed meal announcements.
5
Using separate parameter sets, the algorithm distinguishes insulin pump malfunctions from missed meal announcements.
Research Object
Artificial pancreas systems for type 1 diabetes therapy, including insulin pumps, continuous glucose monitoring sensors, and their closed-loop operation
Research Subject
Real-time detection and discrimination of insulin pump faults and missed meal announcements based on discrepancies between predicted and measured CGM values
Publication Details
Publication Date
2020-06-22
Journal
Publisher
ISSN
Cited by
38
Access Type
Author Information
Download PDF
Subscribe to digest