Title : Integration of the WHO International Classification of Health Interventions, standardized research documentation, and artificial intelligence in traditional medicine for global healthcare systems
Abstract:
Background: The integration of traditional medicine within modern healthcare systems requires internationally standardized frameworks for classification, documentation, research, and interoperability. The World Health Organization’s International Classification of Health Interventions (ICHI) provides a global structure for coding and reporting health interventions across diagnostic, therapeutic, preventive, rehabilitative, public health, and traditional medicine services. Importantly, ICHI includes interventions performed across the full scope of health systems, including traditional medicine. Simultaneously, advances in artificial intelligence (AI) offer new opportunities to enhance data capture, clinical decision support, outcome prediction, and integration of Traditional Medicine 1 (TM1) and Traditional Medicine 2 (TM2) frameworks into evidence-based healthcare delivery worldwide. WHO has also recently highlighted AI’s growing role in traditional medicine mapping and system integration.
Objective: This abstract aims to examine how ICHI-based intervention coding, structured clinical documentation for research data collection, and AI enabled analytics can support the integration of TM1 and TM2 into national and international healthcare systems.
Methods: A conceptual framework was developed through review of WHO classification standards, current medical documentation methodologies, and published literature on AI applications in healthcare and traditional medicine. The framework emphasizes:
• Standardized intervention coding using ICHI
• Structured documentation fields for clinical and research data collection
• AI-assisted natural language processing of clinical records
• Predictive analytics for patient outcomes
• Treatment pattern recognition within TM1 and TM2 systems
• Interoperability with electronic health records (EHRs) and public health databases
This model supports harmonized data collection for multicenter clinical studies, regulatory reporting, health services research, and policy development.
Results: The proposed integration model demonstrates that standardized coding through ICHI can improve international comparability of traditional medicine interventions while strengthening research quality and reproducibility. AI applications support automated classification of interventions, syndrome pattern recognition, outcome tracking, and evidence synthesis from large datasets. This enables TM1 and TM2 interventions to systematically be evaluated alongside biomedical services within national health systems. Recent WHO initiatives further support the formal inclusion of traditional medicine modalities into global intervention classification systems.
Conclusion: The convergence of WHO ICHI standards, robust research documentation systems, and AI technologies provides a scalable pathway for integrating traditional medicine into global healthcare infrastructures. This framework can strengthen regulatory harmonization, evidence generation, reimbursement models, and whole-person health strategies across countries, supporting equitable and culturally inclusive healthcare systems worldwide.

