Facilitating risk assessment by linking a dynamic predictive modeling system to clinical decision support. Clinical data and the results of biomarker analyses (left) are collected from a cohort of people (top) and stored in disease model libraries, and models are developed from them (middle). Other populations can be used to verify the data (top right). The models can be used to identify risk prediction factors for particular diseases or events and can be compared against an individual's profile to determine their risk, or to diagnose disease progression (right). Data from each patient can then be fed back into the model, in order to improve it. Abbreviations: EEG, electroencephalogram; EKG, electrocardiogram; fMRI, functional magnetic resonance imaging; GIS, geographic information systems; MALDI-TOF, matrix-assisted laser desorption ionization time-of-flight mass spectrometry; MEG, magnetoencephalogram; MS/MS, tandem mass spectrometry; SNPs, single-nucleotide polymorphisms.