The Identification of Diabetes Mellitus Subtypes Applying Cluster Analysis Techniques: A Systematic Review

Abstract

Diabetes Mellitus is a chronic and lifelong disease that incurs a huge burden to healthcare systems. Its prevalence is on the rise worldwide. Diabetes is more complex than the classification of Type 1 and 2 may suggest. The purpose of this systematic review was to identify the research studies that tried to find new sub-groups of diabetes patients by using unsupervised learning methods. The search was conducted on Pubmed and Medline databases by two independent researchers. All time publications on cluster analysis of diabetes patients were selected and analysed. Among fourteen studies that were included in the final review, five studies found five identical clusters: Severe Autoimmune Diabetes; Severe Insulin-Deficient Diabetes; Severe Insulin-Resistant Diabetes; Mild Obesity-Related Diabetes; and Mild Age-Related Diabetes. In addition, two studies found the same clusters, except Severe Autoimmune Diabetes cluster. Results of other studies differed from one to another and were less consistent. Cluster analysis enabled finding non-classic heterogeneity in diabetes, but there is still a necessity to explore and validate the capabilities of cluster analysis in more diverse and wider populations.

A novel diabetes typology: towards precision diabetology from pathogenesis to treatment

“…Reclassification methods From a methodological perspective, different clustering algorithms have been used to reclassify people with diabetes [20][21][22][23][24][25]. Topology-based analysis [21] and Bayesian non-negative matrix factorisation clustering [22] are widely applied procedures for discovering groups of related observations (e.g.…”

Characterisation of type 2 diabetes subgroups and their association with ethnicity and clinical outcomes: a UK real-world data study using the East London Database

“…A 2020 systematic review of cluster-based approaches to diabetes subtypes identified 14 studies, of which the majority found identical clusters. 16 First reported by Ahlqvist and colleagues in 2018, clusters related to T2DM included: ‘severe insulin deficient diabetes’, ‘severe insulin resistant diabetes’, MOD, and MARD. 4 These subgroups have been replicated across a number of settings including the Netherlands and Scotland, 7 Ukraine, 17 China, 18 and India.…”

Novel strategies for glycaemic control and preventing diabetic complications applying the clustering-based classification of adult-onset diabetes mellitus: A perspective

“…Although the relative contributions of both are largely non-uniform among patients [3][4][5][6], heterogeneity is rarely considered in clinical practice when deciding the class of antidiabetic agents [7][8][9][10]. Many international research groups are working on uniting the clinical, pathophysiological, and genetic characteristics to more precisely describe the subsets of diabetes currently categorised into T1DM versus T2DM with the aim of optimising the therapeutic strategy [11,12]. The application of sub-classification in therapeutic strategies has not been mentioned in clinical guidelines [7][8][9][10], perhaps because it is considered premature to discuss.…”