Abstract
Studies on Type 2 Diabetes Mellitus (T2DM) have revealed heterogeneous sub-populations in terms of underlying pathologies. However, identification of subpopulations in epidemiological datasets remain unexplored. We here focus on the detection of T2DM clusters in epidemiological data, specifically analysing the National Family Health Survey-4 (NFHS-4) dataset containing a wide spectrum of features, including medical history, dietary and addiction habits, socio-economic and lifestyle patterns of 10,125 T2DM patients. Epidemiological data provide challenges for analysis due to the diverse types of features in it. In this case, applying the state-of-the-art dimension reduction tool UMAP conventionally was found to be ineffective for the NFHS-4 dataset, which contains continuous, ordinal and nominal feature types. Continuous features, although smaller in numbers, had a overpowering effect on the distribution of clusters. To address this problem, we implemented a distributed clustering workflow combining different similarity measure settings of UMAP, for clustering continuous, ordinal and nominal features separately. We integrated the reduced dimensions from each feature-type-distributed clustering to obtain interpretable and unbiased clustering of the data. Our analysis reveals four significant clusters, with two of them comprising mainly of non-obese T2DM patients. These non-obese clusters has lower mean age and majorly comprises of rural residents. Surprisingly, one of the obese clusters had 90% of the T2DM patients practising non-vegetarian diet though they did not show an increased intake of plant-based protein-rich foods. Our findings demonstrate the presence of a heterogeneity among T2DM patients with regard to socio-demography and dietary pattern. These results support the development of demography-specific screening criteria for T2DM as well as a demography-specific lifestyle modification guide-lines.
All Related Versions

This publication has 27 references indexed in Scilit: