Beyond Abstraction: Using AI to Support Follow-Up and Long-Term Patient Tracking (2026)
The presentation provides an in-depth exploration of how AI can transform follow-up operations and long-term patient tracking within the cancer registry. It focuses on what happens after the abstract is completed: maintaining lifetime contact with patients, updating vital status, tracking recurrence, and meeting follow-up compliance thresholds set by the CoC and SEER. Presenters will address one of the most resource-intensive and historically under-supported areas of registry work, demonstrating how AI can proactively identify patients at risk of being lost to follow-up, automate passive data linkage review, flag recurrence signals across clinical documentation, and reduce the manual burden that keeps registrars from higher-value quality and analytics work.
Learning Objectives:
- Explain the operational and compliance challenges of cancer registry follow-up, including CoC and SEER requirements, common causes of lost to follow-up, and the impact of manual processes on registry resources.
- Identify how AI can support proactive follow-up and long-term patient tracking, including risk-based prioritization, passive vital status confirmation, and automated identification of patients approaching delinquency thresholds.
- Describe the role of AI and NLP in detecting cancer recurrence and supporting outcomes research, including analysis of unstructured clinical documentation and integration of longitudinal data for improved survival and recurrence monitoring.
Credit Information
| Activity Number | Credit Amount | Accreditation Period |
|---|---|---|
| 2026-120 | 1 CE | August 11, 2026 - August 05, 2028 |