Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs)
Reliable continuous glucose monitoring (CGM) enables a variety of advanced technology for the treatment of type 1 diabetes. In addition to artificial pancreas algorithms that use CGM to automate continuous subcutaneous insulin infusion (CSII), CGM can also inform fault detection algorithms that aler...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/17/1/161 |
id |
doaj-29854c87b82d44cdaf0c90d057e0d467 |
---|---|
record_format |
Article |
spelling |
doaj-29854c87b82d44cdaf0c90d057e0d4672020-11-24T21:06:34ZengMDPI AGSensors1424-82202017-01-0117116110.3390/s17010161s17010161Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs)Daniel P. Howsmon0Faye Cameron1Nihat Baysal2Trang T. Ly3Gregory P. Forlenza4David M. Maahs5Bruce A. Buckingham6Juergen Hahn7B. Wayne Bequette8Department of Chemical & Biological Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USADepartment of Chemical & Biological Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USADepartment of Chemical & Biological Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USAStanford University School of Medicine, Stanford, CA 94305, USABarbara Davis Center for Childhood Diabetes, University of Colorado Denver, Aurora, CO 80045, USABarbara Davis Center for Childhood Diabetes, University of Colorado Denver, Aurora, CO 80045, USAStanford University School of Medicine, Stanford, CA 94305, USADepartment of Chemical & Biological Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USADepartment of Chemical & Biological Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USAReliable continuous glucose monitoring (CGM) enables a variety of advanced technology for the treatment of type 1 diabetes. In addition to artificial pancreas algorithms that use CGM to automate continuous subcutaneous insulin infusion (CSII), CGM can also inform fault detection algorithms that alert patients to problems in CGM or CSII. Losses in infusion set actuation (LISAs) can adversely affect clinical outcomes, resulting in hyperglycemia due to impaired insulin delivery. Prolonged hyperglycemia may lead to diabetic ketoacidosis—a serious metabolic complication in type 1 diabetes. Therefore, an algorithm for the detection of LISAs based on CGM and CSII signals was developed to improve patient safety. The LISA detection algorithm is trained retrospectively on data from 62 infusion set insertions from 20 patients. The algorithm collects glucose and insulin data, and computes relevant fault metrics over two different sliding windows; an alarm sounds when these fault metrics are exceeded. With the chosen algorithm parameters, the LISA detection strategy achieved a sensitivity of 71.8% and issued 0.28 false positives per day on the training data. Validation on two independent data sets confirmed that similar performance is seen on data that was not used for training. The developed algorithm is able to effectively alert patients to possible infusion set failures in open-loop scenarios, with limited evidence of its extension to closed-loop scenarios.http://www.mdpi.com/1424-8220/17/1/161type 1 diabetesfault detectioncontinuous subcutaneous insulin infusionsensor-augmented pump |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Daniel P. Howsmon Faye Cameron Nihat Baysal Trang T. Ly Gregory P. Forlenza David M. Maahs Bruce A. Buckingham Juergen Hahn B. Wayne Bequette |
spellingShingle |
Daniel P. Howsmon Faye Cameron Nihat Baysal Trang T. Ly Gregory P. Forlenza David M. Maahs Bruce A. Buckingham Juergen Hahn B. Wayne Bequette Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs) Sensors type 1 diabetes fault detection continuous subcutaneous insulin infusion sensor-augmented pump |
author_facet |
Daniel P. Howsmon Faye Cameron Nihat Baysal Trang T. Ly Gregory P. Forlenza David M. Maahs Bruce A. Buckingham Juergen Hahn B. Wayne Bequette |
author_sort |
Daniel P. Howsmon |
title |
Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs) |
title_short |
Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs) |
title_full |
Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs) |
title_fullStr |
Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs) |
title_full_unstemmed |
Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs) |
title_sort |
continuous glucose monitoring enables the detection of losses in infusion set actuation (lisas) |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2017-01-01 |
description |
Reliable continuous glucose monitoring (CGM) enables a variety of advanced technology for the treatment of type 1 diabetes. In addition to artificial pancreas algorithms that use CGM to automate continuous subcutaneous insulin infusion (CSII), CGM can also inform fault detection algorithms that alert patients to problems in CGM or CSII. Losses in infusion set actuation (LISAs) can adversely affect clinical outcomes, resulting in hyperglycemia due to impaired insulin delivery. Prolonged hyperglycemia may lead to diabetic ketoacidosis—a serious metabolic complication in type 1 diabetes. Therefore, an algorithm for the detection of LISAs based on CGM and CSII signals was developed to improve patient safety. The LISA detection algorithm is trained retrospectively on data from 62 infusion set insertions from 20 patients. The algorithm collects glucose and insulin data, and computes relevant fault metrics over two different sliding windows; an alarm sounds when these fault metrics are exceeded. With the chosen algorithm parameters, the LISA detection strategy achieved a sensitivity of 71.8% and issued 0.28 false positives per day on the training data. Validation on two independent data sets confirmed that similar performance is seen on data that was not used for training. The developed algorithm is able to effectively alert patients to possible infusion set failures in open-loop scenarios, with limited evidence of its extension to closed-loop scenarios. |
topic |
type 1 diabetes fault detection continuous subcutaneous insulin infusion sensor-augmented pump |
url |
http://www.mdpi.com/1424-8220/17/1/161 |
work_keys_str_mv |
AT danielphowsmon continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT fayecameron continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT nihatbaysal continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT trangtly continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT gregorypforlenza continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT davidmmaahs continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT bruceabuckingham continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT juergenhahn continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas AT bwaynebequette continuousglucosemonitoringenablesthedetectionoflossesininfusionsetactuationlisas |
_version_ |
1716765469207166976 |