# Model Predictive Control (MPC) of an Artificial Pancreas with Data-Driven Learning of Multi-Step-Ahead Blood Glucose Predictors

arXiv: https://arxiv.org/abs/2307.12015 · HTML: https://mlsanity.com/paper/2307.12015/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 45 references that are in the map.
- First posted on arXiv 22 Jul 2023.

## Builds on (most cited first, 1 of 1)

- [LSTM: A Search Space Odyssey](https://mlsanity.com/paper/1503.04069/) (2015)

## Built on by (most cited first, 1 of 1)

- [MetaboNet: The Largest Publicly Available Consolidated Dataset for Type 1 Diabetes Management](https://mlsanity.com/paper/2601.11505/) (2026)

## Abstract (arXiv)

We present the design and textitin-silico evaluation of a closed-loop insulin delivery algorithm to treat type 1 diabetes (T1D) consisting in a data-driven multi-step-ahead blood glucose (BG) predictor integrated into a Linear Time-Varying (LTV) Model Predictive Control (MPC) framework. Instead of identifying an open-loop model of the glucoregulatory system from available data, we propose to directly fit the entire BG prediction over a predefined prediction horizon to be used in the MPC, as a nonlinear function of past input-ouput data and an affine function of future insulin control inputs. For the nonlinear part, a Long Short-Term Memory (LSTM) network is proposed, while for the affine component a linear regression model is chosen. To assess benefits and drawbacks when compared to a traditional linear MPC based on an auto-regressive with exogenous (ARX) input model identified from data, we evaluated the proposed LSTM-MPC controller in three simulation scenarios: a nominal case with 3 meals per day, a random meal disturbances case where meals were generated with a recently published meal generator, and a case with 25% decrease in the insulin sensitivity. Further, in all the scenarios, no feedforward meal bolus was administered. For the more challenging random meal generation scenario, the mean ± standard deviation percent time in the range 70-180 [mg/dL] was 74.99 ± 7.09 vs. 54.15 ± 14.89, the mean ± standard deviation percent time in the tighter range 70-140 [mg/dL] was 47.78±8.55 vs. 34.62 ±9.04, while the mean ± standard deviation percent time in sever hypoglycemia, i.e., < 54 [mg/dl] was 1.00±3.18 vs. 9.45±11.71, for our proposed LSTM-MPC controller and the traditional ARX-MPC, respectively. Our approach provided accurate predictions of future glucose concentrations and good closed-loop performances of the overall MPC controller.