The Artificial Pancreas: How Sweet Engineering Will Solve Bitter Problems

Klonoff, David C.

doi:10.1177/193229680700100112

Cited by 69 publications

(38 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In brief, an artificial pancreas consists of three components: an insulin pump; a continuous glucose monitoring system; and a closed loop control algorithm to tie them together, so that insulin flow can be continuously adjusted to meet patient needs [14], [15]. Some control algorithms are of the traditional proportional-integral-derivative (PID) variety, in which case, no blood glucose modeling is used.…”

Section: Related Workmentioning

confidence: 99%

Blood Glucose Level Prediction Using Physiological Models and Support Vector Regression

Bunescu

Struble

Marling

et al. 2013

2013 12th International Conference on Machine Learning and Applications

View full text Add to dashboard Cite

Abstract-Patients with diabetes must continually monitor their blood glucose levels and adjust insulin doses, striving to keep blood glucose levels as close to normal as possible. Blood glucose levels that deviate from the normal range can lead to serious short-term and long-term complications. An automatic prediction model that warned people of imminent changes in their blood glucose levels would enable them to take preventive action. Modeling inter-patient differences and the combined effects of insulin and life events on blood glucose have been particularly challenging in the design of accurate blood glucose forecasting systems. In this paper, we describe a solution that uses a generic physiological model of blood glucose dynamics to generate informative features for a Support Vector Regression model that is trained on patient specific data. Experimental results show that the new prediction model outperforms all three diabetes experts involved in the study, thus demonstrating the utility of using the generic physiological features in machine learning models that are individually trained for every patient.

show abstract

Section: Related Workmentioning

confidence: 99%

Blood Glucose Level Prediction Using Physiological Models and Support Vector Regression

Bunescu

Struble

Marling

et al. 2013

2013 12th International Conference on Machine Learning and Applications

View full text Add to dashboard Cite

show abstract

“…Several studies have documented the benefits of CGM [4][5][6][7] and charted guidelines for its clinical use 8,9 and for its future as a base for closed-loop control. 10,11 Physiology and CGM errors…”

Section: Introductionmentioning

confidence: 99%

Assessing Sensor Accuracy for Non-Adjunct Use of Continuous Glucose Monitoring

Kovatchev

Patek

Ortiz

et al. 2015

Diabetes Technology & Therapeutics

184

154

View full text Add to dashboard Cite

Background: The level of continuous glucose monitoring (CGM) accuracy needed for insulin dosing using sensor values (i.e., the level of accuracy permitting non-adjunct CGM use) is a topic of ongoing debate. Assessment of this level in clinical experiments is virtually impossible because the magnitude of CGM errors cannot be manipulated and related prospectively to clinical outcomes. Materials and Methods: A combination of archival data (parallel CGM, insulin pump, self-monitoring of blood glucose [SMBG] records, and meals for 56 pump users with type 1 diabetes) and in silico experiments was used to ''replay'' real-life treatment scenarios and relate sensor error to glycemic outcomes. Nominal blood glucose (BG) traces were extracted using a mathematical model, yielding 2,082 BG segments each initiated by insulin bolus and confirmed by SMBG. These segments were replayed at seven sensor accuracy levels (mean absolute relative differences [MARDs] of 3-22%) testing six scenarios: insulin dosing using sensor values, threshold, and predictive alarms, each without or with considering CGM trend arrows. Results: In all six scenarios, the occurrence of hypoglycemia (frequency of BG levels £ 50 mg/dL and BG levels £ 39 mg/dL) increased with sensor error, displaying an abrupt slope change at MARD = 10%. Similarly, hyperglycemia (frequency of BG levels ‡ 250 mg/dL and BG levels ‡ 400 mg/dL) increased and displayed an abrupt slope change at MARD = 10%. When added to insulin dosing decisions, information from CGM trend arrows, threshold, and predictive alarms resulted in improvement in average glycemia by 1.86, 8.17, and 8.88 mg/dL, respectively. Conclusions: Using CGM for insulin dosing decisions is feasible below a certain level of sensor error, estimated in silico at MARD = 10%. In our experiments, further accuracy improvement did not contribute substantively to better glycemic outcomes.

show abstract

“…During experiments 2-3 (days [1][2][3][4][5][6][7][8][9][10][11][12][13][14], the run-to-run procedure attains a good glycemic regulation within a few days. The subsequent meal perturbations during experiment 4 (days 15-24) produce some excursions that are, however, kept under control.…”

Section: Assessment Of Performancementioning

confidence: 99%

“…[1][2][3] Thanks to the availability of innovative sensors and actuators, the possibility to successfully maintain normoglycemia has significantly improved, so that automatic control experts are faced with new technological challenges.…”

Section: Introductionmentioning

confidence: 99%