HCC Analytics.
An API-first HCC suspecting engine that surfaces evidence-backed risk adjustment opportunities from structured and unstructured clinical data — without requiring EHR integration.
// suspected HCCs returned per patient { "patient_id": "p_4421998", "suspects": [ { "icd10": "N18.4", "hcc": "HCC 137", "category": "CKD, stage 4", "evidence": [ { "source": "CCDA", "snippet": "eGFR 22 mL/min/1.73…" }, { "source": "PDF p.3", "snippet": "nephrology consult, stage 4 CKD" } ] } ] }
HCC Analytics acts as a backend intelligence layer for risk adjustment. Send patient records — CCDAs, PDFs, embedded clinical documents — and receive suspected HCC conditions paired with the clinical evidence that triggered each finding. Designed for technology partners, risk adjustment teams, and organizations that need scalable HCC suspecting without a new EHR deployment.
Five steps from raw chart data to operational suspects.
Send records via API
CCDAs, PDFs, or embedded clinical documents submitted on a per-patient basis.
Parse and extract
NLP and document extraction surface clinically relevant facts from structured and unstructured content.
Apply clinical rules engine
Inferscience rules-based logic maps clinical signals to suspected HCC conditions and coding categories.
Return evidence-backed results
Structured JSON output includes suspected HCCs, diagnosis codes, categories, and supporting evidence.
Operationalize in your workflow
Display in your platform, build coder worklists, feed dashboards, or route opportunities to your teams.
Built for partners who need an engine, not another platform.
Evidence transparency on every suspect.
Every suspect includes the clinical data elements that triggered the finding — not just the resulting code. Reviewers see the "why" immediately, without re-reading the chart.
Handles real-world clinical data.
Processes messy, real-world records: CCDAs, scanned PDFs, faxed charts, and unstructured documents embedded inside CCDAs — not just clean structured feeds.
Not a black box.
Grounded in Inferscience clinical logic and NLP — not generative AI guesswork. Outputs are explainable and defensible.
No EHR integration required.
Skip lengthy EHR integration cycles. Send data, receive results, and plug findings into your existing workflow on your timeline.
JSON wherever you need it.
Results power dashboards, coder worklists, partner UIs, or internal analytics — wherever your team works.
Where teams put HCC Analytics to work.
Add HCC suspecting to your platform.
Technology vendors embed HCC intelligence into existing products without building the engine themselves.
Coder review workflows.
Surface prioritized HCC opportunities with supporting evidence so coders review and validate — not manually search.
Vendor evaluation pilots.
Send a defined chart set to benchmark detection quality before committing to a full implementation.
Unstructured document mining.
Extract HCC evidence buried in PDFs, scanned records, and embedded files that traditional tools miss.
Pre-visit and post-visit analytics.
Identify documentation gaps prospectively before an encounter, or validate coding after encounters close.
Population risk programs.
Run patient-level analysis at scale to support ACO, payer, and risk-bearing entity programs.
Teams that need HCC intelligence, on their own terms.
From vendors embedding suspecting into a product, to risk teams running their own pilots — HCC Analytics meets you where your data and workflows already live.
Ready to evaluate? Run a chart pilot.
Send a defined chart set, benchmark detection quality, and see evidence-backed suspects before committing to a full implementation.