Author: Edith Ballard, MHA (2025)
Primary advisor: Susan Fenton, PhD
Committee members: Angela Ross, DNP and Debora Simmons, PhD
DHI Translational Project, McWilliams School of Biomedical Informatics at UTHealth Houston
ABSTRACT
Background: The recruitment, development, and retention of skilled medical coding staff has become increasingly challenging for healthcare providers. To alleviate staffing burdens, Epic Systems’ electronic health record (EHR) introduced the Simple Visit Coding (SVC) work queue, designed to evaluate hospital patient encounters and automatically assign International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) diagnosis codes. However, the current SVC work queue evaluation rule at a prominent academic Oncology Care Organization (OCO) in the South does not utilize autonomous, generative, or computer-assisted coding (CAC) technologies. The work queue evaluation rule uses a simple rule-based program logic that relies on diagnosis codes entered by clinical healthcare providers (e.g., physicians, advanced practice nurses, etc.) who are not continuously trained in medical diagnosis abstraction and coding guidelines. Therefore, the SVC evaluation rule frequently produced medical claim denials, which decreased financial reimbursement and increased the administrative workload burden.
Objective: The aim of this translational project was to reduce claim denials generated by the SVC evaluation rule logic for the first hour of chemotherapy or immunotherapy administration services, current procedural terminology (CPT) code 96413 that was performed in the hospital ambulatory/outpatient setting. CPT code 96413 was selected due to its high denial rates, which directly impacted reimbursement and medical coder workload.
Methods: A comprehensive literature review was conducted using PubMed, ScienceDirect, American Health Information Management Association, the Health Management Financial Association, Healthcare Information and Management Systems Society, and American Medical Informatics Association databases. Sources included peer-reviewed articles and professional publications on the modification of Epic’s SVC Evaluation Rule in an outpatient academic and nonacademic hospital setting. Additionally, the Iowa model and institutional data from the Epic SlicerDicer report were used to identify the problem trigger and assess the pre- and post-implementation impact of the SVC evaluation rule modification.
Results: The modification of Epic’s SVC work queue evaluation rule led to a 98.85% reduction in medical denials for CPT code 96413. Additionally, the medical coders’ workflow process significantly decreased by 37.50% by eliminating three steps between coding and billing teams and reducing the administrative burden from 34.8 hours to 0.4 hours. These results highlighted the effectiveness of data-driven interventions in optimizing revenue cycle performance and reducing unnecessary administrative workload.
Conclusion: The project findings suggest that integrating CAC and artificial intelligence (AI)-driven solutions in oncology coding automation can further enhance efficiency, reduce administrative workload burdens, and improve financial outcomes for healthcare institutions managing high-complexity treatments. Therefore, future project implementations should consider exploring the integration of CAC and AI-driven solutions to further enhance coding automation and financial performance. This project established an evidence-based framework for future innovations, offering a scalable model for improving coding accuracy, operational efficiency, and financial sustainability in oncology medical coding.