Need of global collaboration for the future of Artificial Intelligence in Traditional Medicine

Abstract

The global health landscape is undergoing a pivotal shift. Rising demand for personalized, affordable, and evidence-informed health care is driving renewed interest in integrating digital technologies with Traditional Medicine (TM) systems.[1] Advancements in Artificial Intelligence (AI), big data analytics, the Internet of Things (IoT), Telemedicine, and Electronic Health Records (EHRs) have reshaped the organization and governance of health services worldwide.[2] Among these, AI stands out for its ability to enhance diagnostics, forecast disease trends, and support individualized care planning. The convergence of AI and TM, therefore, offers a strategic opportunity to strengthen evidence generation and create new pathways for culturally grounded, person-centered care.[3] TM continues to play a central role in health and well-being worldwide and remains widely relied upon in primary care settings. Global momentum has grown to strengthen its evidence base and ensure its contributions to public health are recognized and effectively supported. Several international initiatives, including the establishment of the World Health Organization (WHO) Global Traditional Medicine Centre (GTMC), underscore the importance of enhancing research quality, creating shared knowledge platforms, and promoting cross-regional collaboration to fortify equitable health systems.[4] However, realizing the full potential of AI in TM requires more than technological innovation. It demands coordinated global collaboration connecting governments, knowledge systems, scientific institutions, private sector, and communities. Such cooperation is essential for aligning governance frameworks, mobilizing sustainable financing, harmonizing data and regulatory standards, and ensuring that digital health advances are ethical, inclusive, and responsive to local contexts.[2] The future of AI in TM will depend on the ability of the global community to work collectively to shape this transformation. INTERSECTION OF ARTIFICIAL INTELLIGENCE AND TRADITIONAL MEDICINE: BRIDGING KNOWLEDGE SYSTEMS AI and TM represent two complementary domains: One driven by data and computational analysis, and the other grounded in centuries of accumulated cultural practice and clinical experience. When aligned, they offer pathways to develop more inclusive and contextually relevant models of health.[1] AI applications, such as pattern recognition, network modeling, and clustering, are being used to model and analyze TM literature, identify therapeutic trends, and support drug discovery by pinpointing potential bioactive compounds. Machine Learning (ML) techniques are aiding in the investigation of the connections between constitutional types and genetic markers,[5] while AI-based analyses of clinical records[6] and reverse pharmacology data[7] are playing a role in the development of drugs based on evidence. Natural Language Processing (NLP) techniques[8] and ontology-based frameworks[9] enable the synthesis of large bodies of literature and fragmented knowledge sources, linking classical texts, patient data, and clinical outcomes across diverse TM systems. Predictive analytics and clinical decision support systems offer potential to guide individualized treatment planning, and data augmentation techniques support research in areas where clinical data are limited.[3] ML also supports biodiversity conservation by monitoring ecosystems vital to medicinal plants.[10] The key challenge is ensuring that these applications remain culturally grounded, ethically governed, and equitably accessible. Achieving this balance requires sustained global collaboration that aligns technical innovation with the social, clinical, and philosophical foundations of TM. MULTILATERAL ENGAGEMENT AND INSTITUTIONAL LEADERSHIP To advance AI in TM, it is crucial to have coordinated global leadership and strategic alliances. International cooperation is vital to align standards, develop shared infrastructures, and ensure that the digital transformation in health care remains fair and culturally sensitive. The establishment of the WHO GTMC in India marks a milestone in global health governance. As the first WHO out posted center dedicated to TM, it is dedicated to integrating traditional knowledge with contemporary scientific methods, supported by a USD 250 million investment from the Government of India. The initiative is structured around four fundamental pillars – governance, evidence, data, and innovation, thereby promoting the WHO’s vision of sustainable and evidence-based TM.[11] Complementing this, the Gujarat Declaration, adopted at the WHO TM Global Summit in 2023, outlines a collective commitment to integrating into national health systems in ways that uphold cultural heritage, biodiversity conservation, sustainability, digital transformation, and responsible AI.[12] The Global Initiative on AI for Health (GI-AI4H) establishes a platform for responsible and scalable AI deployment in health through its pillars of enable, facilitate, and implement, promoting normative guidance, fosters collaboration among governments, research institutions, and industry, and supports the translation of AI tools into practice.[13] The formation of the Topic Group on TM (TG-TM) within this initiative illustrates how coordinated action can strengthen shared learning, standard setting, and capacity building across regions in the TM ecosystem.[14] These multilateral efforts underscore that technological advancement alone is not sufficient; a strong governance framework is essential to ensure that AI in TM evolves in ways that are ethical, equitable, and aligned with public health priorities. WHO’s convening role is central to this process. By bringing together member states, scientific institutions, industry partners, and civil society, the WHO facilitates the development of shared standards and coordinated strategies that prevent fragmentation and uneven adoption.[5] Through global platforms such as the AI for Good Global Summit[15] and the GI-AI4H,[13] WHO provides structured spaces for dialogue, consensus building, and capacity development across diverse health systems. These convenings help translate high-level ethical principles into actionable guidance and operational frameworks that can be adapted to different national and cultural contexts. By linking the evidence-generation mandate of the GTMC, the governance frameworks of the GI-AI4H, and the policy dialogue enabled by global summits, WHO is shaping an integrated architecture for responsible and collaborative implementation of AI in health. This coordinated approach strengthens and supports country readiness and ensures that the benefits of digital transformation are shared equitably across populations, anchored in equity, shared value, and community participation. PARTNERSHIP ECOSYSTEMS: A MULTISECTORAL MODEL Building on this governance architecture, sustained progress in applying AI to TM requires a multisectoral partnership ecosystem grounded in shared purpose, pooled resources, and complementary expertise. Multilateral and institutional collaborations, such as those led through the GTMC and GI-AI4H, provide global alignment, normative guidance, and standards for responsible AI deployment across diverse health systems. Public–private–philanthropic alliances support the development and scaling of digital infrastructure and AI-driven tools for TM, with pooled financing mechanisms helping to ensure sustainability and accessibility. Academic and research networks contribute interdisciplinary knowledge, bridging data science, health research, and traditional knowledge. Initiatives such as the Virtual Health Library (VHL) on Traditional, Complementary, and Integrative Medicines (TCIM) in the Americas[16] and the WHO TM Global Library illustrate how AI can be used to organize, preserve, and connect large bodies of TM knowledge across regions.[17] Within this architecture, the GI-AI4H serves as the connecting hub, linking knowledge partners, implementation networks, and resource partners that underpin shared governance, coordinated action, and the equitable distribution of data, tools, and benefits. Building on this role, the GI-AI4H offers a practical foundation for partnership-driven collaboration. It brings together governments, medical institutions, AI research bodies, practitioner networks, civil society organizations, and industry partners within a shared governance structure that supports cocreation rather than parallel effort. By acting as a neutral convening platform with structured working groups, GI-AI4H enables partners to jointly set priorities, pool expertise, and codevelop normative guidelines that reflect diverse knowledge systems. Importantly, the initiative also provides a mechanism for mobilizing and aligning finances across government budgets, philanthropic funds, multilateral programs, and responsible private sector investment. This shared financing approach helps reduce fragmentation, supports long-term research and implementation continuity, and ensures that benefits are not limited to isolated pilot projects. By fostering trust, transparency, coownership, and sustainable resource flows, GI-AI4H can also become a strategic vehicle for scaling responsible AI innovation in TM, anchored in equity, shared value, and community participation. WAY FORWARD The next stage in advancing AI within TM should prioritize operational coordination, research convergence, capacity strengthening, and scalable implementation. Structured collaboration among the WHO GTMC, the GI-AI4H, TG-TM, national research institutions, and practitioner networks will facilitate joint planning, monitoring, and coordinated project delivery. Establishing multidisciplinary innovation clusters that connect AI laboratories, TM universities, clinical research centers, and practitioner groups can accelerate the codevelopment of decision-support tools, validated datasets, and integrative knowledge systems. Enhancing country-level implementation capacity through digital infrastructure development, workforce training, and service integration models will help translate pilot initiatives into sustainable practice. Promoting shared data standards and open-access knowledge platforms will enable cross-regional research collaboration and comparative evidence generation. To ensure long-term continuity and scale, sustainable and pooled financing must be mobilized through blended mechanisms that integrate government resources, philanthropic funding, and innovation-driven partnerships.

Ähnliche Arbeiten