Dataset Information

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.

SUBMITTER: Capobianco E

PROVIDER: S-EPMC5526830 | biostudies-other | 2017 Dec

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:Type 1 diabetes (T1D) remains a devastating disease that requires much effort to control. Life-long daily insulin injections or an insulin pump are required to avoid severe complications. With many factors contributing to disease onset, T1D is a complex disease to cure. In this review, the risk factors, pathophysiology and defect pathways are discussed. Results from (pre)clinical studies are highlighted that explore restoration of insulin production and reduction of autoimmunity. It has become clear that treatment responsiveness depends on certain pathophysiological or genetic characteristics that differ between patients. For instance, age at disease manifestation associated with efficacy of immune intervention therapies, such as depleting islet-specific effector T cells or memory B cells and increasing immune regulation. The new challenge is to determine in whom to apply which intervention strategy. Within patients with high rates of insulitis in early T1D onset, therapy depleting T cells or targeting B lymphocytes may have a benefit, whereas slow progressing T1D in adults may be better served with more sophisticated, precise and specific disease modifying therapies. Genetic barcoding and immune profiling may help determining from which new T1D endotypes patients suffer. Furthermore, progressed T1D needs replenishment of insulin production besides autoimmunity reversal, as too many beta cells are already lost or defect. Recurrent islet autoimmunity and allograft rejection or necrosis seem to be the most challenging obstacles. Since beta cells are highly immunogenic under stress, treatment might be more effective with stress reducing agents such as glucagon-like peptide 1 (GLP-1) analogs. Moreover, genetic editing by CRISPR-Cas9 allows to create hypoimmunogenic beta cells with modified human leukocyte antigen (HLA) expression that secrete immune regulating molecules. Given the differences in T1D between patients, stratification of endotypes in clinical trials seems essential for precision medicines and clinical decision making.

Project description:ObjectivePrecision medicine requires reliable identification of variation in patient-level outcomes with different available treatments, often termed treatment effect heterogeneity. We aimed to evaluate the comparative utility of individualized treatment selection strategies based on predicted individual-level treatment effects from a causal forest machine learning algorithm and a penalized regression model.MethodsCohort study characterizing individual-level glucose-lowering response (6 month reduction in HbA1c) in people with type 2 diabetes initiating SGLT2-inhibitor or DPP4-inhibitor therapy. Model development set comprised 1,428 participants in the CANTATA-D and CANTATA-D2 randomised clinical trials of SGLT2-inhibitors versus DPP4-inhibitors. For external validation, calibration of observed versus predicted differences in HbA1c in patient strata defined by size of predicted HbA1c benefit was evaluated in 18,741 patients in UK primary care (Clinical Practice Research Datalink).ResultsHeterogeneity in treatment effects was detected in clinical trial participants with both approaches (proportion predicted to have a benefit on SGLT2-inhibitor therapy over DPP4-inhibitor therapy: causal forest: 98.6%; penalized regression: 81.7%). In validation, calibration was good with penalized regression but sub-optimal with causal forest. A strata with an HbA1c benefit > 10 mmol/mol with SGLT2-inhibitors (3.7% of patients, observed benefit 11.0 mmol/mol [95%CI 8.0-14.0]) was identified using penalized regression but not causal forest, and a much larger strata with an HbA1c benefit 5-10 mmol with SGLT2-inhibitors was identified with penalized regression (regression: 20.9% of patients, observed benefit 7.8 mmol/mol (95%CI 6.7-8.9); causal forest 11.6%, observed benefit 8.7 mmol/mol (95%CI 7.4-10.1).ConclusionsConsistent with recent results for outcome prediction with clinical data, when evaluating treatment effect heterogeneity researchers should not rely on causal forest or other similar machine learning algorithms alone, and must compare outputs with standard regression, which in this evaluation was superior.

Dataset Information

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets