Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence
Abstract We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glu...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-03-01
|
Series: | npj Digital Medicine |
Online Access: | https://doi.org/10.1038/s41746-023-00783-1 |
_version_ | 1797430078213193728 |
---|---|
author | Clara Mosquera-Lopez Leah M. Wilson Joseph El Youssef Wade Hilts Joseph Leitschuh Deborah Branigan Virginia Gabo Jae H. Eom Jessica R. Castle Peter G. Jacobs |
author_facet | Clara Mosquera-Lopez Leah M. Wilson Joseph El Youssef Wade Hilts Joseph Leitschuh Deborah Branigan Virginia Gabo Jae H. Eom Jessica R. Castle Peter G. Jacobs |
author_sort | Clara Mosquera-Lopez |
collection | DOAJ |
description | Abstract We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glucose control in the four hours following unannounced meals using a hybrid model predictive control (MPC) algorithm and the RAP system. The RAP system includes a neural network model to automatically detect meals and deliver a recommended meal insulin dose. The meal detection algorithm has a sensitivity of 83.3%, false discovery rate of 16.6%, and mean detection time of 25.9 minutes. While there is no significant difference in incremental area under the curve of glucose, RAP significantly reduces time above range (glucose >180 mg/dL) by 10.8% (P = 0.04) and trends toward increasing time in range (70–180 mg/dL) by 9.1% compared with MPC. Time below range (glucose <70 mg/dL) is not significantly different between RAP and MPC. |
first_indexed | 2024-03-09T09:23:21Z |
format | Article |
id | doaj.art-b0f5bb3f9c5748318fc161e25ae08e3a |
institution | Directory Open Access Journal |
issn | 2398-6352 |
language | English |
last_indexed | 2024-03-09T09:23:21Z |
publishDate | 2023-03-01 |
publisher | Nature Portfolio |
record_format | Article |
series | npj Digital Medicine |
spelling | doaj.art-b0f5bb3f9c5748318fc161e25ae08e3a2023-12-02T06:56:31ZengNature Portfolionpj Digital Medicine2398-63522023-03-01611710.1038/s41746-023-00783-1Enabling fully automated insulin delivery through meal detection and size estimation using Artificial IntelligenceClara Mosquera-Lopez0Leah M. Wilson1Joseph El Youssef2Wade Hilts3Joseph Leitschuh4Deborah Branigan5Virginia Gabo6Jae H. Eom7Jessica R. Castle8Peter G. Jacobs9Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science UniversityHarold Schnitzer Diabetes Health Center, Oregon Health & Science UniversityHarold Schnitzer Diabetes Health Center, Oregon Health & Science UniversityArtificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science UniversityArtificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science UniversityHarold Schnitzer Diabetes Health Center, Oregon Health & Science UniversityHarold Schnitzer Diabetes Health Center, Oregon Health & Science UniversityHarold Schnitzer Diabetes Health Center, Oregon Health & Science UniversityHarold Schnitzer Diabetes Health Center, Oregon Health & Science UniversityArtificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science UniversityAbstract We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glucose control in the four hours following unannounced meals using a hybrid model predictive control (MPC) algorithm and the RAP system. The RAP system includes a neural network model to automatically detect meals and deliver a recommended meal insulin dose. The meal detection algorithm has a sensitivity of 83.3%, false discovery rate of 16.6%, and mean detection time of 25.9 minutes. While there is no significant difference in incremental area under the curve of glucose, RAP significantly reduces time above range (glucose >180 mg/dL) by 10.8% (P = 0.04) and trends toward increasing time in range (70–180 mg/dL) by 9.1% compared with MPC. Time below range (glucose <70 mg/dL) is not significantly different between RAP and MPC.https://doi.org/10.1038/s41746-023-00783-1 |
spellingShingle | Clara Mosquera-Lopez Leah M. Wilson Joseph El Youssef Wade Hilts Joseph Leitschuh Deborah Branigan Virginia Gabo Jae H. Eom Jessica R. Castle Peter G. Jacobs Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence npj Digital Medicine |
title | Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence |
title_full | Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence |
title_fullStr | Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence |
title_full_unstemmed | Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence |
title_short | Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence |
title_sort | enabling fully automated insulin delivery through meal detection and size estimation using artificial intelligence |
url | https://doi.org/10.1038/s41746-023-00783-1 |
work_keys_str_mv | AT claramosqueralopez enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT leahmwilson enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT josephelyoussef enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT wadehilts enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT josephleitschuh enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT deborahbranigan enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT virginiagabo enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT jaeheom enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT jessicarcastle enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence AT petergjacobs enablingfullyautomatedinsulindeliverythroughmealdetectionandsizeestimationusingartificialintelligence |