Noaro Giulia, Cappon Giacomo, Vettoretti Martina, Sparacino Giovanni, Favero Simone Del, Facchinetti Andrea
IEEE Trans Biomed Eng. 2021 Jan;68(1):247-255. doi: 10.1109/TBME.2020.3004031. Epub 2020 Dec 21.
This paper aims at proposing a new machine-learning based model to improve the calculation of mealtime insulin boluses (MIB) in type 1 diabetes (T1D) therapy using continuous glucose monitoring (CGM) data. Indeed, MIB is still often computed through the standard formula (SF), which does not account for glucose rate-of-change ( ∆G), causing critical hypo/hyperglycemic episodes.
Four candidate models for MIB calculation, based on multiple linear regression (MLR) and least absolute shrinkage and selection operator (LASSO) are developed. The proposed models are assessed in silico, using the UVa/Padova T1D simulator, in different mealtime scenarios and compared to the SF and three ∆G-accounting variants proposed in the literature. An assessment on real data, by retrospectively analyzing 218 glycemic traces, is also performed.
All four tested models performed better than the existing techniques. LASSO regression with extended feature-set including quadratic terms (LASSO ) produced the best results. In silico, LASSO reduced the error in estimating the optimal bolus to only 0.86 U (1.45 U of SF and 1.36-1.44 U of literature methods), as well as hypoglycemia incidence (from 44.41% of SF and 44.60-45.01% of literature methods, to 35.93%). Results are confirmed by the retrospective application to real data.
New models to improve MIB calculation accounting for CGM- ∆G and easy-to-measure features can be developed within a machine learning framework. Particularly, in this paper, a new LASSO model was developed, which ensures better glycemic control than SF and other literature methods.
MIB dosage with the proposed LASSO model can potentially reduce the risk of adverse events in T1D therapy.
本文旨在提出一种基于机器学习的新模型，以利用连续血糖监测（CGM）数据改进1型糖尿病（T1D）治疗中餐时胰岛素大剂量（MIB）的计算。实际上，MIB目前仍常通过标准公式（SF）计算，该公式未考虑血糖变化率（∆G），会导致严重的低血糖/高血糖事件。
开发了基于多元线性回归（MLR）和最小绝对收缩和选择算子（LASSO）的四种用于MIB计算的候选模型。使用弗吉尼亚大学/帕多瓦T1D模拟器，在不同用餐场景下对所提出的模型进行计算机模拟评估，并与SF以及文献中提出的三种考虑∆G的变体进行比较。还通过回顾性分析218条血糖轨迹对真实数据进行了评估。
所有四个测试模型的表现均优于现有技术。包含二次项的扩展特征集的LASSO回归（LASSO ）产生了最佳结果。在计算机模拟中，LASSO 将估计最佳大剂量的误差降低至仅0.86单位（SF为1.45单位，文献方法为1.36 - 1.44单位），同时降低了低血糖发生率（从SF的44.41%和文献方法的44.60 - 45.01%降至35.93%）。对真实数据的回顾性应用证实了这些结果。
可以在机器学习框架内开发考虑CGM - ∆G和易于测量特征的改进MIB计算的新模型。特别是，本文开发了一种新的LASSO 模型，与SF和其他文献方法相比，该模型可确保更好的血糖控制。
使用所提出的LASSO 模型进行MIB给药可能会降低T1D治疗中不良事件的风险。
