In European journal of clinical investigation
Type 2 Diabetes (T2D) diagnosis is based solely on glycemia, even though it is an endpoint of numerous dysmetabolic pathways. T2D 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 as a promising tool to unravel Diabetes complexity. Herein, we aimed at scrutinizing and integrate the results obtained in most of the works up to date. We conclude that 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 i.e. the millieu. Ultimately the abovementioned 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. Fully profiling the individuals, considering genomic and environmental factors, and exposure time, will allow the drive to precision medicine and prevention of complications.
Pina Ana F, Meneses Maria João, Sousa-Lima Inês, Henriques Roberto, Raposo João F, Macedo M Paula
big data, cluster analysis, diabetes, machine learning