Marzia Cescon

Eleonora Maria Aiello, Mehrad Jaloli, Marzia Cescon

We present the design and \textit{in-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 $\pm$ standard deviation percent time in the range 70-180 [mg/dL] was 74.99 $\pm$ 7.09 vs. 54.15 $\pm$ 14.89, the mean $\pm$ standard deviation percent time in the tighter range 70-140 [mg/dL] was 47.78$\pm$8.55 vs. 34.62 $\pm$9.04, while the mean $\pm$ standard deviation percent time in sever hypoglycemia, i.e., $<$ 54 [mg/dl] was 1.00$\pm$3.18 vs. 9.45$\pm$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.

Mehrad Jaloli, Marzia Cescon

This paper presents a novel multi-agent reinforcement learning (RL) approach for personalized glucose control in individuals with type 1 diabetes (T1D). The method employs a closed-loop system consisting of a blood glucose (BG) metabolic model and a multi-agent soft actor-critic RL model acting as the basal-bolus advisor. Performance evaluation is conducted in three scenarios, comparing the RL agents to conventional therapy. Evaluation metrics include glucose levels (minimum, maximum, and mean), time spent in different BG ranges, and average daily bolus and basal insulin dosages. Results demonstrate that the RL-based basal-bolus advisor significantly improves glucose control, reducing glycemic variability and increasing time spent within the target range (70-180 mg/dL). Hypoglycemia events are effectively prevented, and severe hyperglycemia events are reduced. The RL approach also leads to a statistically significant reduction in average daily basal insulin dosage compared to conventional therapy. These findings highlight the effectiveness of the multi-agent RL approach in achieving better glucose control and mitigating the risk of severe hyperglycemia in individuals with T1D.

Mehrad Jaloli, Divya Choudhary, Marzia Cescon

In this study we show that a Convolutional Neural Network (CNN) model is able to accuratelydiscriminate between 4 different phases of neurological status in a non-Electroencephalogram(EEG) dataset recorded in an experiment in which subjects are exposed to physical, cognitiveand emotional stress. We demonstrate that the proposed model is able to obtain 99.99% AreaUnder the Curve (AUC) of Receiver Operation characteristic (ROC) and 99.82% classificationaccuracy on the test dataset. Furthermore, for comparison, we show that our models outperformstraditional classification methods such as SVM, and RF. Finally, we show the advantage of CNN models, in comparison to other methods, in robustness to noise by 97.46% accuracy on a noisy dataset.