Diabetes Technol Ther. 2016 Oct;18(10):616-624. doi: 10.1089/dia.2015.0266. Epub 2016 Oct 05.
Physiology-Invariant Meal Detection for Type 1 Diabetes.
Diabetes technology & therapeutics
James Weimer, Sanjian Chen, Amy Peleckis, Michael R Rickels, Insup Lee
Affiliations
Affiliations
- 1 Department of Computer and Information Science, University of Pennsylvania , Philadelphia, Pennsylvania.
- 2 Division of Endocrinology, Diabetes and Metabolism, Perelman School of Medicine, University of Pennsylvania , Philadelphia, Pennsylvania.
PMID: 27704875
PMCID: PMC6528748 DOI: 10.1089/dia.2015.0266
Abstract
BACKGROUND: Fully automated artificial pancreas systems require meal detectors to supplement blood glucose level regulation, where false meal detections can cause unnecessary insulin delivery with potentially fatal consequences, and missed detections may cause the patient to experience extreme hyperglycemia. Most existing meal detectors monitor various measures of glucose rate-of-change to detect meals where varying physiology and meal content complicate balancing detector sensitivity versus specificity.
METHODS: We developed a novel meal detector based on a minimal glucose-insulin metabolism model and show that the detector is, by design, invariant to patient-specific physiological parameters in the minimal model. Our physiological parameter-invariant (PAIN) detector achieves a near-constant false alarm rate across all individuals and is evaluated against three other major existing meal detectors on a clinical type 1 diabetes data set.
RESULTS: In the clinical evaluation, the PAIN-based detector achieves an 86.9% sensitivity for an average false alarm rate of two alarms per day. In addition, for all false alarm rates, the PAIN-based detector performance is significantly better than three other existing meal detectors. In addition, the evaluation results show that the PAIN-based detector uniquely (as compared with the other meal detectors) has low variance in detection and false alarm rates across all patients, without patient-specific personalization.
CONCLUSIONS: The PAIN-based meal detector has demonstrated better detection performance than existing meal detectors, and it has the unique strength of achieving a consistent performance across a population with varying physiology without any individual-level parameter tuning or training.
References
- Comput Methods Programs Biomed. 2000 Jul;62(3):249-57 - PubMed
- Stroke. 2001 Oct;32(10):2426-32 - PubMed
- Diabetes Care. 2005 Jun;28(6):1289-94 - PubMed
- Diabetes Care. 2008 Feb;31(2):295-300 - PubMed
- J Diabetes Sci Technol. 2009 Jan;3(1):44-55 - PubMed
- J Diabetes Sci Technol. 2007 Nov;1(6):804-12 - PubMed
- J Diabetes Sci Technol. 2007 Nov;1(6):825-33 - PubMed
- J Diabetes Sci Technol. 2009 May 01;3(3):536-44 - PubMed
- J Diabetes Sci Technol. 2009 Sep 01;3(5):1014-21 - PubMed
- J Diabetes Sci Technol. 2009 Sep 01;3(5):1022-30 - PubMed
- J Diabetes Sci Technol. 2009 Sep 01;3(5):1082-90 - PubMed
- IEEE Rev Biomed Eng. 2009 Jan 1;2:54-96 - PubMed
- Diabetes. 2011 Nov;60(11):2672-82 - PubMed
- J Diabetes Sci Technol. 2014 Jan 1;8(1):26-34 - PubMed
- J Diabetes Sci Technol. 2014 Mar 13;8(2):307-320 - PubMed
- IEEE J Biomed Health Inform. 2016 Jan;20(1):47-54 - PubMed
- Conf Proc IEEE Eng Med Biol Soc. 2015 Aug;2015:1504-7 - PubMed
- Am J Physiol. 1979 Jun;236(6):E667-77 - PubMed
- Diabetes. 1983 Apr;32(4):331-6 - PubMed
- Diabetes Care. 1995 Feb;18(2):258-68 - PubMed
- N Engl J Med. 1993 Jul 29;329(5):304-9 - PubMed
- J Nutr. 1996 Nov;126(11):2807-12 - PubMed
Publication Types
Grant support