Development of a Precise, Clinically Relevant, Digital Classification Schema for Cancer.

Area of Science:

• Oncology
• Health Informatics
• Bioinformatics

Background:

• Current healthcare transactions rely on digital codes for efficiency.
• The International Classification of Diseases (ICD) system, widely used, inadequately represents oncologic disease complexity.
• Missing prognostic factors like cancer stage and genomic markers limit ICD's utility for patient cohort definition and comparison.

Purpose of the Study:

• To address the limitations of existing digital classification systems in oncology.
• To develop a more precise, clinically relevant, and prognosis-based digital classification schema for cancer.
• To incorporate essential prognostic and predictive markers into a new classification system.

Main Methods:

• Collaboration with cancer disease-specific experts to develop a novel digital classification scheme.
• Introduction of the Cota Nodal Address (CNA) system, comprising six components.
• Integration of standard-of-care prognostic and predictive markers, including patient features, into the CNA system.

Main Results:

• The CNA system enables the creation of homogeneous patient groupings based on similar prognostic characteristics.
• Facilitation of big data analytics, including population health evaluations and treatment variation identification.
• Successful application of the CNA system to breast cancer patients, supporting value-based payment models.

Conclusions:

• The development and utility of a prognosis-based classification system are reviewed.
• The CNA system's enhanced precision over ICD coding allows for improved analysis of treatment, outcomes, and costs in cancer care.
• The schema holds significant potential for advancing cancer care management through more accurate data analysis.