MAX™ Architecture

MAX drives precision-targeted personalized interventions that maximize financial ROI while optimizing clinical outcomes. MAX can uniquely integrate very large and diverse data sets, including medical and pharmacy claims, lab results, EHR, intervention engagement and outreach, survey, socio-economic and genomic data to construct highly accurate predictions of intervention outcomes.



MAX employs an industry-unique MeasureBase, a member-focused data warehouse. MeasureBase models the large and diverse data in MAX as multidimensional observations about people over time.

MeasureBase provides powerful and intuitive capabilities to population health analysts through its Measure Language. With Measure Language, analysts specify what they want to measure, on which people, over what time periods in simple terms without writing SQL or database queries. A comprehensive code manager holds the definition of standard terms such as “antihypertensive drugs.”

REFS™ Analytics Engine

REFS (Reverse Engineering and Forward Simulation) is GNS Healthcare’s patented scalable, massively parallel computing framework for discovering new knowledge from real world data. REFS automates the extraction of causal network models directly from observational data and uses high-throughput simulations to generate new knowledge. REFS discovers knowledge at scale for today’s most pressing healthcare problems.

GNS has successfully deployed REFS  to address a variety of different large-scale healthcare issues, employing divergent data drawn from across the healthcare spectrum, including:

  • Risk of adverse events & medication adherence (claims, consumer data)
  • Progression to metabolic syndrome (claims, clinical & HRA data)
  • Adverse drug events (encrypted claims data)
  • Preterm births (genomic, claims, EMR data)
  • Progression to Type 2 Diabetes (EMR data)
  • CHF readmissions & adverse drug events (EMR data)
  • Drug switching for Multiple Sclerosis (claims data)
  • Individual risk for Type 2 Diabetes (EMR data)
  • Optimal drug regimens for Rheumatoid Arthritis (registry data)
  • Progression in Rheumatoid Arthritis (clinical trial data)

Analytics & Models

The MeasureBase, REFS and other machine learning platforms drive the creation of analytic models.  MAX deploys these in a massively-parallel cloud-based computing environment.  GNS models include:

  • Risk: Predicts risk of negative outcomes, including adverse events, sub-optimal outcomes and progression to disease states
  • Efficacy: Quantifies risk reduction resulting from behavior and clinical behavior changes
  • Engagement: The GNS IEScore™ identifies people likely to participate in interventions
  • Intervention: Quantifies how interventions drive changes in behavior
  • ROI: Determines the best intervention match for each individual.

MAX Architecture: Unmatched Speed to Value

The MAX Architecture delivers unmatched speed to value by integrating easily into business processes, scaling to support huge and diverse data sets, providing precision selection predictions, and measuring and improving the effectiveness of intervention programs.

Learn More