Predictive Big Data Analytics using the UK Biobank Data

Abstract

The UK Biobank is a rich national health resource that provides enormous opportunities for international researchers to examine, model, and analyze census-like multisource healthcare data. The archive presents several challenges related to aggregation and harmonization of complex data elements, feature heterogeneity and salience, and health analytics. Using 7,614 imaging, clinical, and phenotypic features of 9,914 subjects we performed deep computed phenotyping using unsupervised clustering and derived two distinct sub-cohorts. Using parametric and nonparametric tests, we determined the top 20 most salient features contributing to the cluster separation. Our approach generated decision rules to predict the presence and progression of depression or other mental illnesses by jointly representing and modeling the significant clinical and demographic variables along with the derived salient neuroimaging features. We reported consistency and reliability measures of the derived computed phenotypes and the top salient imaging biomarkers that contributed to the unsupervised clustering. This clinical decision support system identified and utilized holistically the most critical biomarkers for predicting mental health, e.g., depression. External validation of this technique on different populations may lead to reducing healthcare expenses and improving the processes of diagnosis, forecasting, and tracking of normal and pathological aging.

Compressive Big Data Analytics: An ensemble meta-algorithm for high-dimensional multisource datasets

“…Similar to our previous study, for all the Binomial datasets, only 10 features are used to generate the binary outcome variable (these are what we call truly predictive features, see details below in the Binomial Datasets section). The real case-study represents a real biomedical dataset on aging and neurodegenerative disorders (UK Biobank) [5,6].…”

“…In this manuscript, we expand the CBDA method and test the new CBDA 2.0 technique on large synthetic datasets (e.g., ranging from 10,000-1,000,000 cases and 1,000-10,000 features). In addition, we validate CBDA 2.0 by applying it for detection and prediction of mood disorders (e.g., irritability) using a large population-based clinical survey, the UK Biobank [5,6] (see Datasets section for details).…”

Modernizing the Methods and Analytics Curricula for Health Science Doctoral Programs

“…As a proxy of the underlying complex biological, physiological, and medical conditions, such data are important to understand the causes of morbid conditions, model associations between factors, predict risks of treatments, and forecast clinically relevant outcomes. Examples of big biomedical datasets include the UK Biobank (UKBB) (28)(29)(30), the Human Connectome Project (HCP) (31,32), and the Alzheimer's Disease Neuroimaging Initiative (ADNI) (33,34). UKBB represents a survey of a large population-based cohort including about 500 K individuals Dinov Methods and Analytics Health Science Curriculum assessed at 22 UK medical centers in UK between 2006 and 2010.…”

Compressive Big Data Analytics: An Ensemble Meta-Algorithm for High-dimensional Multisource Datasets

“…In addition, we validate CBDA by directly applying it for detection and prediction of mood disorders (e.g., irritability) using a large population-based clinical survey. Specifically, we will validate the technique on heterogeneous and incongruent data from the UK Biobank [5,6] datasets (see the Datasets section for details). The CBDA protocol relies on model-based statistical computing methods and model-free data analytics [7].…”