Healthcare payer proof of concept: Enabling value-based care analytics & AI applications

A seamless integration of type 2 diabetes member data HULFT

A Proof of Concept Pilot Engagement for Payers

POC Scenario & Goals

Meaningful integration of member data for a population that is clinically diagnosed with diabetes to control costs and improve quality of care.

  • Deploy a platform that can handle complexity of health data, seamlessly collect, move, aggregate and meaningfully integrate data.
  • 800+ discrete fields for patient level clinical data set; 20-30 fields for financial transactions.

POC Overview Leverage

HULFT to build a limited purpose integrated environment from disparate data sources and disconnected systems.

  • Claims Processing System
  • PBM system/ Prescription Data
  • Claims payment
  • Provider directory
  • Provider contract system
  • Eligibility Verification System
  • Medical case management
  • Referral management system
  • EHR systems in provider networks
  • Call center management
  • EMPI

POC Outcome

Identify care gaps and generate select reports:

  • Who did not have a retinal or dilated eye exam
  • Who did not have a nephropathy test
  • Who did not have an HbA1c test
  • With no blood pressure record

Identify member leakage due to out-of-network referrals, generate select reports:

  • Percentage of out-of-network claims by zip codes
  • Percentage of distribution of cause of the leakage (ie, seeking second opinion, lack of cost transparency, appointment scheduling frustrations, communication breakdowns)

Go-Forward Engagement

HULFT offers a low-code/no-code integration platform that enables payers to:

  • Engage members
  • Optimize risk adjustment and quality
  • Accelerate speed to market
  • Prevent fraud
  • Establish environment for analytics and AI applications
  • Uniquely suitable to feed PHM applications
  • Can build layers of bucket, payers can apply ML and AI tools to develop models for multiple analysis: More precise phenotyping of member populations; predictive models to identify patients at various levels of risk; models for unsupervised learning to generate hypotheses

HULFT helps healthcare payers automate, orchestrate, and accelerate their data at scale.

This website uses cookies for analytics, personalisation and optimized performance. Click here to learn more or change your cookie settings. By using this website, you agree to our use of cookies.