Systems and precision medicine approaches to diabetes heterogeneity: a Big Data perspective

Abstract

Big Data, and in particular Electronic Health Records, provide the medical community with a great opportunity to analyze multiple pathological conditions at an unprecedented depth for many complex diseases, including diabetes. How can we infer on diabetes from large heterogeneous datasets? A possible solution is provided by invoking next‐generation computational methods and data analytics tools within systems medicine approaches. By deciphering the multi‐faceted complexity of biological systems, the potential of emerging diagnostic tools and therapeutic functions can be ultimately revealed. In diabetes, a multidimensional approach to data analysis is needed to better understand the disease conditions, trajectories and the associated comorbidities. Elucidation of multidimensionality comes from the analysis of factors such as disease phenotypes, marker types, and biological motifs while seeking to make use of multiple levels of information including genetics, omics, clinical data, and environmental and lifestyle factors. Examining the synergy between multiple dimensions represents a challenge. In such regard, the role of Big Data fuels the rise of Precision Medicine by allowing an increasing number of descriptions to be captured from individuals. Thus, data curations and analyses should be designed to deliver highly accurate predicted risk profiles and treatment recommendations. It is important to establish linkages between systems and precision medicine in order to translate their principles into clinical practice. Equivalently, to realize their full potential, the involved multiple dimensions must be able to process information ensuring inter‐exchange, reducing ambiguities and redundancies, and ultimately improving health care solutions by introducing clinical decision support systems focused on reclassified phenotypes (or digital biomarkers) and community‐driven patient stratifications.

Healthcare Driven by Big Data Analytics

“…It is also key to establish linkages between systems and precision medicine to translate its principles into clinical practice for practitioners. A high-genomic content in Electronic Health Records (EHRs) could be very useful to uncovering existing knowledge discrepancies in diabetes data analyses (Capobianco, 2017). Some current applications of Big Data analytics in precision medicine include (Wu et al, 2017):…”

Big Data Processing System for Diabetes Prediction using Machine Learning Technique

“…This work utilizes Hadoop and MapReduce environment to predict the presence of diabetes and the type is classified. Systems and precision medicine approaches to diabetes heterogeneity is explained on the perspectives of big data in [16]. This work claims that multidimensional data analysis proves better functionality for disease prediction system and big data based prediction system is presented.…”

High-dimensionality Data Analysis of Pharmacological Systems Associated with Complex Diseases

“…This methodology allowed existing machine-learning predictors to effectively and efficiently capture the potential of textual predictors for cardiac disease, especially those based on short texts. Unsurprisingly, given the global incidence of glycometabolic disorders, the application of EMD analytics to diabetes diagnosis and treatment now represents a major computational tool in the endocrinological field (Chen et al, 2016;Zheng et al, 2016;Capobianco, 2017). The implementation of multiple forms of informatic interrogation (e.g., artificial neural networks, semantic analyses and machine learning) of EMD sources was shown recently to enhance phenotype description (Anderson et al, 2016;Gabert et al, 2016;Hall et al, 2018), disease trajectory progression (Jensen et al, 2014;Oh et al, 2016), diabetic comorbidities (Petrasek, 2008;Sancho-Mestre et al, 2016;Li et al, 2018), and eventual therapeutic efficacies (Ozery-Flato et al, 2016;Vashisht et al, 2016;Kang, 2018).…”