HSBlox Uses Machine Learning

Standard Rules based edits are included in RevBlox™ as well

• WEDI/SNIP
• PTP (Procedure to Procedure)
• MUE (Medically Unlikely Edits)
• NCCI (National Correct Coding Initiative)

Rules-Based, with practice-configurable rules

Continuous, Adaptive, & Aware

Machine learning is continuous and auto-adaptive, uncovering changes prospectively, with complete awareness

Limited to, and relies on human awareness

Multi-Practice

Machine learning provides benefit to all practices of changes learned, detecting issues long before an individual practice can detect it. This learning approach is automatically part of the algorithm’s intelligence and does not require configuration.

Rules are practice-specific and do not benefit from the machine learning that is multi-practice. A given practice is only as good as its human detectors, who will miss or not be aware. If it is noticed, it is then configured by a human, which is also prone to error.

Multi-Specialty

Machine learning handles all specialties without the need for specific human knowledge of a given specialty.

Human configured rules require human knowledge across specialties, so it requires multiple humans.

Real-Time Awareness

Retrospective awareness---and limited to what a human has detected

Multi-Layered

RevBlox™ solution is not limited to Charge-posting accuracy. RevBlox™ is aware of charge-posting, eligibility, payer-provider contract, prior authorization, referral, coordination of benefits

Retrospective awareness---and limited to what a human has detected

Granular

The RevBlox™ solution is granular in its edits:

• Payer Level
• Member Plan Level
• Provider NPI Level
• Claim Level, and
• Service Line Level

Charge-posting within the practice

Dashboard & Workflow Routing

Complete workflow for routing of claims and remittance to specific users within the practice (or within a Central Billing Office)

Workflow is single-user centric