Skip to main content

Cancer Registry

The Cancer Registry automates cancer case finding, staging, treatment tracking, and outcomes monitoring in compliance with NAACCR standards and state/national registry requirements. NAACCR-Compliant Cancer Registry Automation Reduce manual abstraction time by 80% with AI-powered case finding, automated staging, and regulatory-ready reporting.

Accelerate NAACCR-Compliant Cancer Registry Abstraction​

Cancer registry abstraction traditionally requires an average of 2 hours per case of manual chart review by certified tumor registrars, though this varies by complexity. For a health system with 2,000 new cancer cases annually, this represents 4,000 hours of specialized labor. At the national level, with approximately 2.1 million new cancer diagnoses projected in 2026, the United States requires roughly 4.2 million hours of manual cancer registry abstraction annually.

The Cancer Registry module transforms this labor-intensive process into an automated, audit-ready workflow. The system continuously monitors your electronic health records for new cancer cases, identifying them both from structured diagnosis codes in the EHR and by automatically analyzing clinical note content where diagnoses may be documented before formal coding occurs. Once a case is detected, the platform extracts all relevant NAACCR-reportable data elements specific to that cancer site—from primary site and histology to staging variables, treatment details, and outcomes—pulling information from pathology reports, operative notes, oncology documentation, and diagnostic imaging.

Rather than replacing human expertise, the system optimizes it through intelligent human-in-the-loop review workflows. Certified tumor registrars focus their time on validating AI-extracted data and resolving ambiguous cases instead of manually searching through charts and transcribing information. Every extraction is tracked with complete provenance: which document the data came from, what confidence score the AI assigned, and whether a human reviewer validated or modified the value. This creates a comprehensive audit trail that documents not just what data was abstracted, but how it was obtained and who verified it.

When cases are ready for submission, the system generates NAACCR-compliant export files formatted for direct submission to state and national cancer registries, ensuring all required fields are populated and validated against registry specifications.

Key Features​

🔍

Automated Case Finding

Multi-Source Detection

  • ICD-O-3 diagnosis codes
  • Pathology report screening
  • Radiology findings (CT, MRI, PET)
  • Treatment indication analysis
  • Death certificate review
📊

Staging & Classification

Automated AJCC Staging

  • AJCC 8th Edition TNM staging
  • Histology and grade extraction
  • Biomarker identification (ER, PR, HER2, PD-L1)
  • Lymph node involvement
  • Metastasis detection
💊

Treatment Tracking

Comprehensive Treatment Extraction

  • Surgical procedures and margins
  • Chemotherapy regimens and cycles
  • Radiation therapy doses and sites
  • Immunotherapy and targeted therapy
  • Clinical trial participation
📈

Outcomes Monitoring

Longitudinal Follow-Up

  • Disease progression tracking
  • Recurrence detection
  • Metastasis identification
  • Survival status updates
  • Quality of life indicators
📋

NAACCR Compliance

Regulatory Reporting

  • NAACCR v23 format export
  • State registry submissions
  • SEER reporting
  • CoC accreditation support
  • Quality metric calculation
👨‍⚕️

Registrar Review

Human-in-the-Loop Validation

  • Structured review interface
  • Side-by-side source documents
  • Confidence scoring display
  • One-click corrections
  • Audit trail maintenance

Supported Cancer Types​

Thorax

Male Genital Organs

Head and Neck

Bone

Urinary Tract

Upper Gastrointestinal Tract

Soft Tissue Sarcoma

Ophthalmic Sites

Lower Gastrointestinal Tract

Skin

Central Nervous System

Hepatobiliary System

Breast

Endocrine System

Neuroendocrine Tumors

Female Reproductive Organs

Hematologic Malignancies

Cancer Registry Workflow​

1

Define Your Data Sources

Connect your EHR systems, pathology databases, and clinical documentation repositories to enable automated case finding and data extraction.

↓

2

Create Registry Project

Select the cancer site you are interested in, specify the state where you are reporting, and choose the NAACCR version you want to use for compliance.

↓

3

Define Registrar Team

Assign certified tumor registrars who will validate the automatic abstraction, ensuring human expertise guides the final data quality.

↓

4

Start Automation

Launch the automated abstraction process. Once complete, registrars will see patients in the project dashboard and can begin validating extracted data.

↓

5

Report to State/National Registry

Generate NAACCR-compliant export files for validated cases and submit directly to your state or national cancer registry.

Comprehensive NAACCR Data Extraction​

400+ Automatically Extracted NAACCR Data Items

The Cancer Registry automatically extracts, codes, and validates all required NAACCR data items from your clinical documentation—covering patient identification, cancer characteristics, staging, treatment, and outcomes.

👤 Patient Identification & Demographics

  • Name, Address, Social Security Number
  • Date of Birth, Sex, Race, Ethnicity
  • Spanish/Hispanic Origin
  • Insurance Status, Marital Status
  • Usual Occupation and Industry

🔬 Cancer Identification

  • Primary Site (ICD-O-3 topography)
  • Histology (ICD-O-3 morphology)
  • Behavior Code (in situ, invasive, benign)
  • Laterality (left, right, bilateral)
  • Date of Diagnosis

📊 Stage of Disease at Diagnosis

  • Clinical TNM (cT, cN, cM)
  • Pathologic TNM (pT, pN, pM)
  • AJCC TNM Stage Group
  • SEER Summary Stage
  • Mets at Diagnosis (bone, brain, liver, lung)

🧬 Tumor Characteristics & Grade

  • Grade (G1-G4), Differentiation
  • Tumor Size, Extension
  • Lymph Node Involvement
  • Site-Specific Data Items (SSDI)
  • Biomarkers (ER, PR, HER2, Ki-67, etc.)

💊 Treatment Information

  • Date of First Treatment
  • Surgical Procedures and Scope
  • Radiation Therapy (modality, dose, site)
  • Systemic Therapy (chemo, hormone, immuno)
  • Reason for No Treatment

📈 Outcome Information

  • Vital Status, Date of Last Contact
  • Survival Time in Months
  • Recurrence Date and Type
  • Cause of Death (COD)
  • Autopsy Performed

AI-Powered Extraction Examples​

Pathology Report Processing​

Input: Free-text surgical pathology report

DIAGNOSIS: LEFT BREAST, LUMPECTOMY:
- Invasive ductal carcinoma, Grade 2
- Tumor size: 1.8 cm in greatest dimension
- Margins: All margins negative, closest margin 0.3 cm
- Lymphovascular invasion: Present
- ER: Positive (90%, strong)
- PR: Positive (70%, moderate)
- HER2: Negative (IHC 1+)
- Ki-67: 25%

Extracted Data:

  • Primary Site: C50.9 (Breast, NOS)
  • Histology: 8500/3 (Infiltrating duct carcinoma)
  • Grade: 2 (Moderately differentiated)
  • Tumor Size: 18 mm
  • ER Status: Positive
  • PR Status: Positive
  • HER2 Status: Negative
  • CS Extension: 310 (Confined to breast)

Radiology Report Processing​

Input: PET/CT report

IMPRESSION:
1. Hypermetabolic right upper lobe mass (SUV 8.2), suspicious for primary lung malignancy
2. FDG-avid right hilar and mediastinal lymph nodes (SUV 4.5-6.1)
3. No evidence of distant metastatic disease

Extracted Data:

  • Primary Site Confirmed: C34.1 (Upper lobe, lung)
  • Regional Lymph Nodes: Positive (hilar + mediastinal)
  • Distant Metastasis: M0 (No distant mets)
  • Clinical Stage: At least Stage IIIA

Registrar Validation & Review

Automated extraction provides the foundation, but cancer registry standards demand certified expertise. The Cancer Registry module provides structured validation workflows where certified tumor registrars review AI-extracted data, ensuring every case meets NAACCR standards and state reporting requirements. This human-in-the-loop validation transforms automated abstractions into audit-ready registry data.

Registry Project Workflow​

Cancer registry work is organized into Registry Projects—focused collections of cases for a specific cancer site, reporting period, or facility. Each project has its own configuration, assigned registrar team, and validation workflow.

Project Assignment​

When you create a registry project, you define which certified tumor registrars will validate the automated abstractions. Projects can be assigned based on cancer site expertise (e.g., breast cancer specialists handle breast cases), facility coverage (registrars cover specific hospitals), or workload distribution to balance case volume across your team.

The project dashboard shows each registrar which cases require their review, preventing duplicate work and ensuring complete coverage of all cases.

Patient Dashboard for Validation​

Once automation completes, registrars see all patients in the project dashboard with key information at a glance: patient demographics, cancer site and histology, date of diagnosis, abstraction completion status, and fields flagged for review.

Registrars can filter by completion status, cancer type, or time period to prioritize their work and track progress through the validation queue.

Field-Level Validation with Evidence​

For each patient case, registrars review a structured form presenting all NAACCR data items extracted by the AI. Each field shows:

Extracted Value: The data element extracted by AI (e.g., "pT3" for pathologic T stage)

Source Attribution: Whether the value came from AI extraction or manual entry, with confidence scores for AI-extracted values

Evidence Trail: Direct links to source documents—pathology reports, operative notes, clinical notes, radiology reports, or structured EHR data—with the specific text or data element that supports the extracted value highlighted

Validation Actions: Registrars can accept the AI-extracted value as correct, edit the value if the extraction was incorrect or incomplete, or flag the field for discussion if clinical judgment is needed

This evidence-based validation ensures registrars spend their time verifying accuracy rather than hunting through charts for information.

Source Documentation Access​

Every extracted value includes direct access to its source evidence. When reviewing primary site, the system shows the pathology report text describing the tumor location. For staging, it displays the relevant portions of pathology, imaging, and clinical notes that establish T, N, and M categories. Treatment data links to operative notes, chemotherapy orders, and radiation planning documents.

This immediate evidence access accelerates validation—registrars don't search through the EHR manually; they review the AI's work with supporting documentation already presented.

Complete Audit Trail​

Every interaction with the registry data is logged with full provenance:

  • AI Extractions: When was the value extracted, the confidence, and source document reference
  • Registrar Edits: Who modified which fields, what the original and new values were, when the change occurred, and optional notes explaining the rationale
  • Validation Status: Which registrars reviewed which cases, validation timestamps, and approval status
  • Source Attribution: Whether each data element came from structured EHR data, clinical notes (with NLP extraction), pathology reports, or manual registrar entry

This comprehensive audit trail satisfies regulatory requirements, supports quality audits, and provides complete transparency for how every data element was obtained and validated.

Quality Assurance Features​

The Cancer Registry module provides tools to maintain data quality throughout the validation process:

Pre-built Edit Checks: NAACCR-compliant edit checks run automatically, flagging impossible or unlikely value combinations (e.g., prostate cancer in female patients, dates out of sequence) before submission

Inter-Rater Review: Cases can be assigned to multiple registrars for dual review, with the system tracking agreement rates and flagging discrepancies for discussion

Supervisor Review: Senior registrars can conduct final quality reviews before cases are marked complete, ensuring consistent interpretation across the registry

Completion Tracking: The dashboard shows validation progress at both individual registrar and overall project levels, helping you manage workload and meet reporting deadlines

The AI-Registrar Partnership​

The Cancer Registry workflow embodies the principle that AI and certified expertise work best together. Automated extraction handles the time-consuming chart review—reading thousands of pages of clinical documentation to find relevant NAACCR data items. Certified tumor registrars provide the clinical judgment—validating complex staging scenarios, resolving ambiguous documentation, ensuring coding accuracy, and applying registry standards consistently.

This partnership reduces abstraction time from 2 hours per case to 20-30 minutes of focused validation, letting your registrar team maintain more cases without sacrificing quality or falling behind on reporting deadlines.

Impact on Registry Operations​

⏱️ 80% Time Reduction

Reduce abstraction time from hours to minutes per case through AI-assisted extraction

✓ Improved Accuracy

Reduce coding errors and improve inter-rater reliability through standardized AI extraction

📈 100% Case Capture

Ensure no reportable cases are missed through comprehensive automated screening

⏰ Faster Reporting

Meet CoC timeliness standards with automated workflows and real-time case identification

💰 Cost Savings

Reduce registrar FTE requirements or reallocate staff to quality improvement initiatives

Launch Your Cancer Registry Project​

Implementation Timeline

Typical cancer registry deployment: 8-12 weeks

  • Weeks 1-2: Data source integration and historical case identification
  • Weeks 3-4: NLP model validation on sample pathology/radiology reports
  • Weeks 5-6: Registrar training and review workflow configuration
  • Weeks 7-8: Pilot with 100 cases, accuracy validation
  • Weeks 9-12: Full production rollout and continuous monitoring
Last updated on