المؤلفون: Fathi, Anas El, Pryor, Elliott, Breton, Marc D.

مصطلحات موضوعية: Quantitative Biology - Quantitative Methods, Computer Science - Artificial Intelligence

الوصف: Calculating mealtime insulin doses poses a significant challenge for individuals with Type 1 Diabetes (T1D). Doses should perfectly compensate for expected post-meal glucose excursions, requiring a profound understanding of the individual's insulin sensitivity and the meal macronutrients'. Usually, people rely on intuition and experience to develop this understanding. In this work, we demonstrate how a reinforcement learning agent, employing a self-attention encoder network, can effectively mimic and enhance this intuitive process. Trained on 80 virtual subjects from the FDA-approved UVA/Padova T1D adult cohort and tested on twenty, self-attention demonstrates superior performance compared to other network architectures. Results reveal a significant reduction in glycemic risk, from 16.5 to 9.6 in scenarios using sensor-augmented pump and from 9.1 to 6.7 in scenarios using automated insulin delivery. This new paradigm bypasses conventional therapy parameters, offering the potential to simplify treatment and promising improved quality of life and glycemic outcomes for people with T1D.
Comment: 6 pages, 4 figures, Biological and Medical Systems - 12th BMS 2024 - IFAC

الوصول الحر: http://arxiv.org/abs/2406.14579Test

المؤلفون: Fathi, Anas El, Ganji, Mohammadreza, Boiroux, Dimitri, Bengtsson, Henrik, Breton, Marc D.

مصطلحات موضوعية: Electrical Engineering and Systems Science - Systems and Control

الوصف: Around a third of type 2 diabetes patients (T2D) are escalated to basal insulin injections. Basal insulin dose is titrated to achieve a tight glycemic target without undue hypoglycemic risk. In the standard of care (SoC), titration is based on intermittent fasting blood glucose (FBG) measurements. Lack of adherence and the day-to-day variabilities in FBG measurements are limiting factors to the existing insulin titration procedure. We propose an adaptive receding horizon control strategy where a glucose-insulin fasting model is identified and used to predict the optimal basal insulin dose. This algorithm is evaluated in \textit{in-silico} experiments using the new UVA virtual lab (UVlab) and a set of T2D avatars matched to clinical data (NCT01336023). Compared to SoC, we show that this control strategy can achieve the same glucose targets faster (as soon as week 8) and safer (increased hypoglycemia protection and robustness to missing FBG measurements). Specifically, when insulin is titrated daily, a time-in-range (TIR, 70--180 mg/dL) of 71.4$\pm$20.0\% can be achieved at week eight and maintained at week 52 (72.6$\pm$19.6%) without an increased hypoglycemia risk as measured by time under 70 mg/dL (TBR, week 8: 1.3$\pm$1.9% and week 52: 1.2$\pm$1.9%), when compared to the SoC (TIR at week 8: 59.3$\pm$28.0% and week:52 72.1$\pm$22.3%, TBR at week 8: 0.5$\pm$1.3% and week 52: 2.8$\pm$3.4%). Such an approach can potentially reduce treatment inertia and prescription complexity, resulting in improved glycemic outcomes for T2D using basal insulin injections.
Comment: 6 pages, 2 figures, conference

الوصول الحر: http://arxiv.org/abs/2309.09132Test

المؤلفون: Fathi, Anas El, Breton, Marc D.

مصطلحات موضوعية: Computer Science - Artificial Intelligence

الوصف: People with type 1 diabetes (T1D) struggle to calculate the optimal insulin dose at mealtime, especially when under multiple daily injections (MDI) therapy. Effectively, they will not always perform rigorous and precise calculations, but occasionally, they might rely on intuition and previous experience. Reinforcement learning (RL) has shown outstanding results in outperforming humans on tasks requiring intuition and learning from experience. In this work, we propose an RL agent that recommends the optimal meal-accompanying insulin dose corresponding to a qualitative meal (QM) strategy that does not require precise carbohydrate counting (CC) (e.g., a usual meal at noon.). The agent is trained using the soft actor-critic approach and comprises long short-term memory (LSTM) neurons. For training, eighty virtual subjects (VS) of the FDA-accepted UVA/Padova T1D adult population were simulated using MDI therapy and QM strategy. For validation, the remaining twenty VS were examined in 26-week scenarios, including intra- and inter-day variabilities in glucose. \textit{In-silico} results showed that the proposed RL approach outperforms a baseline run-to-run approach and can replace the standard CC approach. Specifically, after 26 weeks, the time-in-range ($70-180$mg/dL) and time-in-hypoglycemia ($<70$mg/dL) were $73.1\pm11.6$% and $ 2.0\pm 1.8$% using the RL-optimized QM strategy compared to $70.6\pm14.8$% and $ 1.5\pm 1.5$% using CC. Such an approach can simplify diabetes treatment, resulting in improved quality of life and glycemic outcomes.
Comment: 6 pages, 4 figures, conference

الوصول الحر: http://arxiv.org/abs/2309.09125Test

المؤلفون: Fathi, Anas El, Kearney, Robert E., Palisaitis, Emilie, Boulet, Benoit, Haidar, Ahmad

المساهمون: Canadian Institutes of Health Research, Fonds de Recherche du Quebec - Nature et Technologies

المصدر: IEEE Transactions on Biomedical Engineering ; volume 68, issue 4, page 1208-1219 ; ISSN 0018-9294 1558-2531

مصطلحات موضوعية: Biomedical Engineering

الإتاحة: https://doi.org/10.1109/tbme.2020.3023555Test
http://xplorestaging.ieee.org/ielx7/10/9381734/09195161.pdf?arnumber=9195161Test

المؤلفون: Jafar, Adnan, Fathi, Anas El, Haidar, Ahmad

المساهمون: Canada Research Chairs

المصدر: Computer Methods and Programs in Biomedicine ; volume 200, page 105936 ; ISSN 0169-2607

مصطلحات موضوعية: Health Informatics, Computer Science Applications, Software

الإتاحة: https://doi.org/10.1016/j.cmpb.2021.105936Test
https://api.elsevier.com/content/article/PII:S0169260721000109?httpAccept=text/xmlTest
https://api.elsevier.com/content/article/PII:S0169260721000109?httpAccept=text/plainTest

المؤلفون: Tsoukas, Michael, Cohen, Elisa, Legault, Laurent, Oettingen, Julia Von, Yale, Jean-François, Vallis, Michael, Odabassian, Madison, Fathi, Anas El, Rutkowski, Joanna, Jafar, Adnan, Ghanbari, Milad, Gouchie-Provencher, Nikita, René, Jennifer, Palisaitis, Emilie, Haidar, Ahmad

المصدر: Canadian Journal of Diabetes ; volume 45, issue 7, page S29-S30 ; ISSN 1499-2671

مصطلحات موضوعية: Endocrinology, General Medicine, Endocrinology, Diabetes and Metabolism, Internal Medicine

الإتاحة: https://doi.org/10.1016/j.jcjd.2021.09.087Test
https://api.elsevier.com/content/article/PII:S1499267121003312?httpAccept=text/xmlTest
https://api.elsevier.com/content/article/PII:S1499267121003312?httpAccept=text/plainTest

المؤلفون: Fathi, Anas El, Breton, Marc D.

المصدر: IFAC-PapersOnLine; January 2023, Vol. 56 Issue: 2 p11539-11544, 6p

مستخلص: People with type 1 diabetes (T1D) struggle to calculate the optimal insulin dose at mealtime, especially when under multiple daily injections (MDI) therapy. Effectively, they will not always perform rigorous and precise calculations; but occasionally, they might rely on intuition and previous experience. Reinforcement learning (RL) has shown outstanding results in outperforming humans on tasks requiring intuition and learning from experience. In this work, we propose an RL agent that recommends the optimal meal-accompanying insulin dose corresponding to a qualitative meal (QM) strategy that does not require precise carbohydrate counting (CC) (e.g., a usual meal at noon.). The agent is trained using the soft actor-critic approach and comprises long short-term memory (LSTM) neurons. For training, eighty virtual subjects (VS) of the FDA-accepted UVA/Padova T1D adult population were simulated using MDI therapy and QM strategy. For validation, the remaining twenty VS were examined in 26-week scenarios, including intra- and inter-day variabilities in glucose. In-silicoresults showed that the proposed RL approach outperforms a baseline run-to-run approach and can replace the standard CC approach. Specifically, after 26 weeks, the time-in-range (70 - 180mg/dL) and time-in-hypoglycemia (< 70mg/dL) were 73.1 ± 11.6% and 2.0 ± 1.8% using the RL-optimized QM strategy compared to 70.6± 14.8% and 1.5± 1.5% using CC. Such an approach can simplify diabetes treatment resulting in improved quality of life and glycemic outcomes.

المؤلفون: Fathi, Anas El, Palisaitis, Emilie, Boulet, Benoit, Legault, Laurent, Haidar, Ahmad

المصدر: 2019 American Control Conference (ACC)

الإتاحة: https://doi.org/10.23919/acc.2019.8814932Test
http://xplorestaging.ieee.org/ielx7/8789884/8814292/08814932.pdf?arnumber=8814932Test

المؤلفون: Tsoukas, Michael A, Majdpour, Dorsa, Yale, Jean-François, Fathi, Anas El, Garfield, Natasha, Rutkowski, Joanna, Rene, Jennifer, Legault, Laurent, Haidar, Ahmad

المصدر: The Lancet Digital Health; November 2021, Vol. 3 Issue: 11 pe723-e732, 10p

مستخلص: For people with type 1 diabetes, there is currently no automated insulin delivery system that does not require meal input. We aimed to assess the efficacy of a novel faster-acting insulin aspart (Fiasp) plus pramlintide fully closed-loop system that does not require meal input.

المؤلفون: Kairy, Dahlia, Rushton, Paula W., Archambault, Philippe, Pituch, Evelina, Torkia, Caryne, Fathi, Anas El, Stone, Paula, Routhier, François, Forget, Robert, Demers, Louise, Pineau, Joelle, Gourdeau, Richard

المصدر: eScholarship@McGill: Discover theses, dissertations, articles, and more

مصطلحات موضوعية: hist, lang

العلاقة: 10670/1.yf1t87; https://escholarship.mcgill.ca/concern/articles/9k41zk168Test

الإتاحة: https://escholarship.mcgill.ca/concern/articles/9k41zk168Test