Big data and machine learning to tackle diabetes management

Abstract

Background: Type 2 Diabetes (T2D) diagnosis is based solely on glycaemia, even though it is an endpoint of numerous dysmetabolic pathways. Type 2 Diabetes complexity is challenging in a real-world scenario; thus, dissecting T2D heterogeneity is a priority. Cluster analysis, which identifies natural clusters within multidimensional data based on similarity measures, poses a promising tool to unravel Diabetes complexity.

Methods: In this review, we scrutinize and integrate the results obtained in most of the works up to date on cluster analysis and T2D.

Results: To correctly stratify subjects and to differentiate and individualize a preventive or therapeutic approach to Diabetes management, cluster analysis should be informed with more parameters than the traditional ones, such as etiological factors, pathophysiological mechanisms, other dysmetabolic co-morbidities, and biochemical factors, that is the millieu. Ultimately, the above-mentioned factors may impact on Diabetes and its complications. Lastly, we propose another theoretical model, which we named the Integrative Model. We differentiate three types of components: etiological factors, mechanisms and millieu. Each component encompasses several factors to be projected in separate 2D planes allowing an holistic interpretation of the individual pathology.

Conclusion: Fully profiling the individuals, considering genomic and environmental factors, and exposure time, will allow the drive to precision medicine and prevention of complications.

Keywords: big data; cluster analysis; diabetes; machine learning.

FIGURE 1

Cluster analysis scheme. A heterogenous population regarding characteristics of interest is stratified by a chosen algorithm that places them in a hyperplane, differentiating natural homogenous groups.

FIGURE 2

Integrative model of diabetes. (A) Subjects are deeply characterized regarding aetiological factors (including genes, lifestyle and environmental factors), underlying physiopathological mechanisms and metabolic and haemodynamic factors that they are exposed to. They are placed correspondingly onto the aetiology, mechanisms and milieu plan. The location of a subject in each plan can be predicted by knowing their position in the others. Ultimately, aetiology, mechanisms and milieu project the subject onto the metabolic phenotype plan where its health condition is assessed also considering diabetes complications as nephropathy, retinopathy and cardiovascular complications. Each subject path through time in the metabolic phenotype plan can be analysed but also predicted, leveraging therapeutic and preventive strategies. (B) Aetiology, mechanisms and milieu for each subject can be summarized and more easily visible on a radarplot.

FIGURE 3

From the palette model to the proposed integrative model. The integrative model that we propose was based on the McCarthys' palette model but differs essentially in the path and in the component planes of the model.