Application of Machine Learning to Assess Interindividual Variability in Rapid-Acting Insulin Responses After Subcutaneous Injection in People With Type 1 Diabetes

• Published in: Canadian journal of diabetes 2022-04, Vol.46 (3), p.225-232.e2
• Main Authors: Coales, Eleanor M., Ajjan, Ramzi A., Pearson, Sam M., O’Mahoney, Lauren L., Kietsiriroje, Noppadol, Brož, Jan, Holmes, Mel, Campbell, Matthew D.
• Format: Article
• Language: English
• Subjects: apprentissage automatique; Blood Glucose - analysis; Diabetes Mellitus, Type 1 - complications; diabète de type 1; Fibrinogen - therapeutic use; Humans; Hypoglycemic Agents - pharmacology; Hypoglycemic Agents - therapeutic use; Injections, Subcutaneous; Insulin - therapeutic use; insulin pharmacokinetics; Insulin Resistance; Insulin, Short-Acting - therapeutic use; interpersonal variability; Machine Learning; pharmacocinétique de l’insuline; Plasminogen Activator Inhibitor 1 - therapeutic use; Postprandial Period; type 1 diabetes; variabilité interpersonnelle
• ISSN: 1499-2671; 2352-3840
• DOI: 10.1016/j.jcjd.2021.09.002

Circulating insulin concentrations mediate vascular-inflammatory and prothrombotic factors. However, it is unknown whether interindividual differences in circulating insulin levels are associated with different inflammatory and prothrombotic profiles in type 1 diabetes (T1D). We applied an unsupervised machine-learning approach to determine whether interindividual differences in rapid-acting insulin levels associate with parameters of vascular health in patients with T1D. We re-analyzed baseline pretreatment meal-tolerance test data from 2 randomized controlled trials in which 32 patients consumed a mixed-macronutrient meal and self-administered a single dose of rapid-acting insulin individualized by carbohydrate counting. Postprandial serum insulin, tumour necrosis factor (TNF)-alpha, plasma fibrinogen, human tissue factor (HTF) activity and plasminogen activator inhibitor-1 (PAI-1) were measured. Two-step clustering categorized individuals based on shared clinical characteristics. For analyses, insulin pharmacokinetic summary statistics were normalized, allowing standardized intraindividual comparisons. Despite standardization of insulin dose, individuals exhibited marked interpersonal variability in peak insulin concentrations (48.63%), time to peak (64.95%) and insulin incremental area under the curve (60.34%). Two clusters were computed: cluster 1 (n=14), representing increased serum insulin concentrations; and cluster 2 (n=18), representing reduced serum insulin concentrations (cluster 1: 389.50±177.10 pmol/L/IU h−1; cluster 2: 164.29±41.91 pmol/L/IU h−1; p