Mapping ICD-10 Codes for Oncology Diseases to OncoTree: Lessons Learned

Area of Science:

• Oncology
• Medical Informatics
• Bioinformatics

Background:

• The International Classification of Diseases, 10th Revision (ICD-10) is widely used for tumor classification in clinical practice.
• The OncoTree classification system offers a more granular, molecularly-informed tumor hierarchy essential for research and clinical trials.
• A discrepancy exists between the broadness of ICD-10 and the detailed nature of OncoTree, hindering data integration.

Purpose of the Study:

• To develop a robust mapping between the ICD-10 and OncoTree cancer classification systems.
• To facilitate improved data comparison and clinical trial enrollment using standardized cancer terminology.
• To address the need for a unified approach to cancer coding in research and clinical settings.

Main Methods:

• A mapping strategy was devised utilizing Systematized Nomenclature of Medicine — Clinical Terms (SNOMED CT) as an intermediary due to structural differences between ICD-10 and OncoTree.
• The mapping process involved aligning concepts from both coding systems through SNOMED CT.
• Challenges related to structural dissimilarities and mapping inaccuracies were identified and addressed during development.

Main Results:

• A mapping between ICD-10 and OncoTree was successfully developed.
• The mapping achieved a satisfactory accuracy rate of 86.18%.
• The developed mapping demonstrates the feasibility of integrating these distinct cancer classification systems.

Conclusions:

• The creation of an ICD-10 to OncoTree mapping is a significant step towards harmonizing cancer data.
• The achieved accuracy rate indicates the potential utility of this mapping in research and clinical applications.
• Further refinement of the mapping process is recommended for seamless integration into production systems and broader adoption.