PMID- 27381030
OWN - NLM
STAT- MEDLINE
DCOM- 20171113
LR  - 20181113
IS  - 1932-2968 (Electronic)
IS  - 1932-2968 (Linking)
VI  - 10
IP  - 5
DP  - 2016 Sep
TI  - How Much Is Short-Term Glucose Prediction in Type 1 Diabetes Improved by Adding 
      Insulin Delivery and Meal Content Information to CGM Data? A Proof-of-Concept 
      Study.
PG  - 1149-60
LID - 10.1177/1932296816654161 [doi]
AB  - BACKGROUND: In type 1 diabetes (T1D) management, short-term glucose prediction 
      can allow to anticipate therapeutic decisions when hypo/hyperglycemia is 
      imminent. Literature prediction methods mainly use past continuous glucose 
      monitoring (CGM) readings. Sophisticated algorithms can use information on 
      insulin delivered and meal carbohydrate (CHO) content. The quantification of how 
      much insulin and CHO information improves glucose prediction is missing in the 
      literature and is investigated, in an open-loop setting, in this proof-of-concept 
      study. METHODS: We adopted a versatile literature prediction methodology able to 
      utilize a variety of inputs. We compared predictors that use (1) CGM; (2) CGM and 
      insulin; (3) CGM and CHO; and (4) CGM, insulin, and CHO. Data of 15 T1D subjects 
      in open-loop setup were used. Prediction was evaluated via absolute error and 
      temporal gain focusing on meal/night periods. The relative importance of each 
      individual input of the predictor was evaluated with a sensitivity analysis. 
      RESULTS: For a prediction horizon (PH) >/= 30 minutes, insulin and CHO information 
      improves prediction accuracy of 10% and double the temporal gain during the 2 
      hours following the meal. During the night the 4 methods did not give 
      statistically different results. When PH >/= 45 minutes, the influence of CHO 
      information on prediction is 5-fold that of insulin. CONCLUSIONS: In an open-loop 
      setting, with PH >/= 30 minutes, information on CHO and insulin improves short-term 
      glucose prediction in the 2-hour time window following a meal, but not during the 
      night. CHO information improves prediction significantly more than insulin.
CI  - (c) 2016 Diabetes Technology Society.
FAU - Zecchin, Chiara
AU  - Zecchin C
AD  - Department of Information Engineering, University of Padova, Padova, Italy.
FAU - Facchinetti, Andrea
AU  - Facchinetti A
AD  - Department of Information Engineering, University of Padova, Padova, Italy.
FAU - Sparacino, Giovanni
AU  - Sparacino G
AD  - Department of Information Engineering, University of Padova, Padova, Italy.
FAU - Cobelli, Claudio
AU  - Cobelli C
AD  - Department of Information Engineering, University of Padova, Padova, Italy 
      cobelli@dei.unipd.it.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20160822
PL  - United States
TA  - J Diabetes Sci Technol
JT  - Journal of diabetes science and technology
JID - 101306166
RN  - 0 (Blood Glucose)
RN  - 0 (Hypoglycemic Agents)
RN  - 0 (Insulin)
SB  - IM
MH  - *Algorithms
MH  - Blood Glucose/*analysis
MH  - Blood Glucose Self-Monitoring
MH  - Diabetes Mellitus, Type 1/*blood/drug therapy
MH  - Humans
MH  - Hypoglycemic Agents/*therapeutic use
MH  - Insulin/*therapeutic use
MH  - Insulin Infusion Systems
MH  - Meals
PMC - PMC5032963
OTO - NOTNLM
OT  - continuous glucose monitoring
OT  - neural network
OT  - nonlinear modeling
OT  - sensitivity analysis
OT  - signal processing
COIS- The author(s) declared no potential conflicts of interest with respect to the 
      research, authorship, and/or publication of this article.
EDAT- 2016/07/07 06:00
MHDA- 2017/11/14 06:00
PMCR- 2017/07/04
CRDT- 2016/07/07 06:00
PHST- 2016/07/07 06:00 [entrez]
PHST- 2016/07/07 06:00 [pubmed]
PHST- 2017/11/14 06:00 [medline]
PHST- 2017/07/04 00:00 [pmc-release]
AID - 1932296816654161 [pii]
AID - 10.1177_1932296816654161 [pii]
AID - 10.1177/1932296816654161 [doi]
PST - epublish
SO  - J Diabetes Sci Technol. 2016 Aug 22;10(5):1149-60. doi: 10.1177/1932296816654161. 
      Print 2016 Sep.