Journal article Open Access

Mathematical Models of Meal Amount and Timing Variability With Implementation in the Type-1 Diabetes Patient Decision Simulator

Camerlingo Nunzio; Vettoretti Martina; Del Favero Simone; Facchinetti Andrea; Sparacino Giovanni


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>Background:</p>\n\n<p>In type 1 diabetes (T1D) research, in-silico clinical trials (ISCTs) have proven effective in accelerating the development of new therapies. However, published simulators lack a realistic description of some aspects of patient lifestyle which can remarkably affect glucose control. In this paper, we develop a mathematical description of meal carbohydrates (CHO) amount and timing, with the aim to improve the meal generation module in the T1D Patient Decision Simulator (T1D-PDS) published in Vettoretti et al.</p>\n\n<p>&nbsp;</p>\n\n<p>Methods:</p>\n\n<p>Data of 32 T1D subjects under free-living conditions for 4874&thinsp;days were used. Univariate probability density function (PDF) parametric models with different candidate shapes were fitted, individually, against sample distributions of: CHO amounts of breakfast (CHO<sub>B</sub>), lunch (CHO<sub>L</sub>), dinner (CHO<sub>D</sub>), and snack (CHO<sub>S</sub>); breakfast timing (T<sub>B</sub>); and time between breakfast-lunch (T<sub>BL</sub>) and between lunch-dinner (T<sub>LD</sub>). Furthermore, a support vector machine (SVM) classifier was developed to predict the occurrence of a snack in future fixed-length time windows. Once embedded inside the T1D-PDS, an ISCT was performed.</p>\n\n<p>&nbsp;</p>\n\n<p>Results:</p>\n\n<p>Resulting PDF models were: gamma (CHO<sub>B</sub>, CHO<sub>S</sub>), lognormal (CHO<sub>L</sub>, T<sub>B</sub>), loglogistic (CHO<sub>D</sub>), and generalized-extreme-values (T<sub>BL</sub>, T<sub>LD</sub>). The SVM showed a classification accuracy of 0.8 over the test set. The distributions of simulated meal data were not statistically different from the distributions of the real data used to develop the models (&alpha;&thinsp;=&amp;thinsp;0.05).</p>\n\n<p>&nbsp;</p>\n\n<p>Conclusions:</p>\n\n<p>The models of meal amount and timing variability developed are suitable for describing real data. Their inclusion in modules that describe patient behavior in the T1D-PDS can permit investigators to perform more realistic, reliable, and insightful ISCTs.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "University of Padova", 
      "@id": "https://orcid.org/0000-0003-3222-2479", 
      "@type": "Person", 
      "name": "Camerlingo Nunzio"
    }, 
    {
      "affiliation": "University of Padova", 
      "@type": "Person", 
      "name": "Vettoretti Martina"
    }, 
    {
      "affiliation": "University of Padova", 
      "@id": "https://orcid.org/0000-0002-8214-2752", 
      "@type": "Person", 
      "name": "Del Favero Simone"
    }, 
    {
      "affiliation": "University of Padova", 
      "@type": "Person", 
      "name": "Facchinetti Andrea"
    }, 
    {
      "affiliation": "University of Padova", 
      "@id": "https://orcid.org/0000-0002-3248-1393", 
      "@type": "Person", 
      "name": "Sparacino Giovanni"
    }
  ], 
  "headline": "Mathematical Models of Meal Amount and Timing Variability With Implementation in the Type-1 Diabetes Patient Decision Simulator", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2020-09-17", 
  "url": "https://zenodo.org/record/4139754", 
  "version": "Final published version", 
  "keywords": [
    "in-silico clinical trials", 
    "maximum absolute difference", 
    "parametric modelling", 
    "machine learning", 
    "support vector machine"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1177/1932296820952123", 
  "@id": "https://doi.org/10.1177/1932296820952123", 
  "@type": "ScholarlyArticle", 
  "name": "Mathematical Models of Meal Amount and Timing Variability With Implementation in the Type-1 Diabetes Patient Decision Simulator"
}
57
55
views
downloads
Views 57
Downloads 55
Data volume 148.0 MB
Unique views 53
Unique downloads 54

Share

Cite as