Dr. Subarna Roy, Director, ICMR National Institute of Traditional Medicine, Belagavi, India, and Sanjay H Deshpande, Regional Centre for Biotechnology, Department of Biotechnology, Govt of India under auspices of UNESCO, Faridabad, India

Introduction

Artificial intelligence (AI) has emerged as a transformative force across various fields, including healthcare, in recent times. The scope for AI applications lies in its ability to augment traditional knowledge systems, specifically in health and well-being (Chu et al., 2022). Having a rich history and a wide range of repositories of herbal remedies, holistic practices, and Indigenous knowledge, traditional medicine has provided many effective health solutions across diverse cultures (Saini & Parashar, 2024). Integrating traditional knowledge with modern healthcare practices is highly challenging due to the immense complexity of the data involved. AI offers a unique opportunity that bridges the gap and enables the systematic analysis, preservation, and application of traditional medicinal knowledge (Al Kuwaiti et al., 2023). Using natural language processing (NLP), Deep learning, Predictive Analytics and Machine learning (ML), AI can sift through extensive historical texts, folk remedies, and anecdotal evidence to identify patterns, validate efficacy, and suggest novel applications (Arowosegbe & Oyelade, 2023). AI-based databases can collate and analyse the available ethnobotanical resources, mining bioactive compounds in traditional remedies that have therapeutic potential (E. Zhou et al., 2024).

AI can assist in formalising treatments using traditional methods for individual needs by integrating data generated from genomics, metabolic, and environmental factors, which help create personalised health solutions. This personalised approach, or precision medicine, is increasingly gaining traction as AI facilitates the integration of traditional medicinal practices with cutting-edge genomic research (Johnson et al., 2021). By mapping genetic markers to the efficacy of traditional remedies, AI can guide the development of treatments more aligned with an individual’s genetic makeup, enhancing their effectiveness while minimising adverse effects. AI technologies like deep learning can support digitising and preserving traditional knowledge, ensuring that ancient wisdom is not lost to time but adapted to modern contexts. For example, AI algorithms can transcribe and translate ancient manuscripts, making them accessible to researchers and practitioners worldwide (Münster et al., 2024). Additionally, AI can enable the creation of knowledge graphs that connect traditional medical practices with contemporary scientific findings, facilitating a more integrated approach to health and well-being. By leveraging AI, the potential of traditional medicine can be unlocked, making it more accessible, adaptable, and effective in addressing contemporary health challenges (E. Zhou et al., 2024). The connection between AI and traditional medicine has great potential to transform healthcare globally and in knowledge-rich countries like India, providing culturally relevant and scientifically validated solutions that are sustainable and scalable (Das et al., 2024).

Understanding Traditional Knowledge

Traditional knowledge is a vast repository of wisdom, beliefs, and practices accumulated and passed down through generations within indigenous and local communities. The knowledge is deeply rooted in the communities with cultural heritage and empirical knowledge, which offers a holistic approach to health and well-being, often overlooked by modern medicine. Traditional knowledge is not static; it evolves over time as communities adapt to changing environments and societal conditions.

Herbal Medicine

One of the most well-known aspects of traditional knowledge is its extensive use of herbal medicine. Indigenous communities have long relied on the medicinal properties of plants to treat various ailments, ranging from common colds to chronic diseases. This knowledge is often based on centuries of trial and error, observation, and a deep understanding of local biodiversity (Pan et al., 2014). For example, using the Artemisia annua plant in traditional Chinese medicine to treat malaria led to the discovery of the artemisinin drug. This compound is now a cornerstone of modern antimalarial therapy (Tu, 2011).

Herbal medicine, in traditional knowledge, is not just about using plants for healing but also understanding how they should be prepared and administered to achieve optimal results. The knowledge of when to harvest, how to process, and how to combine various herbs is intricately tied to the cultural practices of these communities. Such practices often emphasise sustainability and respect for nature, ensuring that the natural resources used in healing are not depleted (Chaachouay & Zidane, 2024).

Spiritual Healing

Traditional knowledge also encompasses spiritual healing practices that are integral to the well-being of individuals and communities. Spiritual healing in traditional medicine is based on the belief that health is a state of harmony between an individual’s physical, mental, and spiritual aspects. Illness is often viewed as a disruption of this balance, which can be restored through rituals, prayers, and the involvement of spiritual healers or shamans (Dein, 2020).

The following traditional practices show the connection between health and spirituality, in which healing is seen as a process that addresses physical symptoms and nurtures the soul and mind. For example, in many Native American cultures, the “medicine wheel” symbolises the holistic approach to healing, where physical, emotional, mental, and spiritual well-being are all interconnected and must be balanced for proper health (Gall et al., 2021; Montour, 2000).

Lifestyle Practices

Lifestyle practices are another critical component of traditional knowledge. These include dietary guidelines, exercise routines, and daily habits that promote long-term health and prevent illness. Traditional diets, for instance, are often based on locally available foods that are seasonally consumed and prepared in ways that enhance their nutritional value (Singh et al., 2020). The diet in the Mediterranean region is full of fresh greens, fruits, vegetables, whole grains, and olive oil, a prime example of traditional dietary knowledge that has gained recognition for its health benefits (Bach-Faig et al., 2011).

In addition to diet, traditional knowledge includes long-term physical activities like Yoga, Tai Chi, and various other forms of physical activity that are deeply embedded in cultural rituals and daily routines (Varambally & Gangadhar, 2020). The cultural physical practices are not just limited to physical exercises but are also meant to cultivate mental clarity, emotional balance, and spiritual growth, contributing to overall well-being (Ramos-Jiménez et al., 2015).

Community-Based Healthcare Systems

Community-based healthcare systems are central to traditional knowledge, where healthcare is a collective responsibility. In these systems, the knowledge of healing practices is often shared within the community, and healthcare providers such as midwives, herbalists, and spiritual healers play essential roles. These systems emphasise the importance of community solidarity and mutual aid, where the well-being of one individual is seen as interconnected with the entire community’s well-being (Krah et al., 2018).

For example, in many African societies, community-based approaches to healthcare are prevalent, where traditional birth attendants and herbalists are highly respected for their roles in maintaining the community’s health. These systems are often more accessible and culturally relevant than formal healthcare services, especially in remote or underserved areas (Abrahams et al., 2001).

Interconnectedness with the Environment

A fundamental aspect of traditional knowledge is that it emphasises the interconnectedness between individuals and their environment. Indigenous communities often profoundly understand their ecosystems, recognising that human health is closely linked to environmental health. This understanding is reflected in practices such as sustainable agriculture, the conservation of medicinal plants, and rituals that honour natural cycles (Jakes, 2024).

For example, agroforestry in many indigenous communities involves cultivating trees alongside crops, supporting biodiversity, enhancing soil fertility, and providing medicinal resources. This practice is a testament to the profound ecological knowledge embedded in traditional systems, where maintaining environmental balance is essential for human health (González & Kröger, 2020; Pan et al., 2014).

Traditional knowledge, therefore, offers valuable insights into how health and healthy well-being can be achieved through a holistic approach that integrates physical, mental, spiritual, and environmental dimensions. Modern healthcare systems can benefit from a more comprehensive and culturally inclusive approach to health by understanding and respecting traditional knowledge (Nanda, 2023; Payyappallimana, 2013).

The Role of AI in Health

Artificial Intelligence (AI) has revolutionised the integration of traditional medicine by analysing vast datasets, identifying patterns, and providing insights for decision-making. Traditional medicine encompasses a wealth of knowledge and practices passed down through generations. However, this knowledge is often fragmented, localised, and encoded in various languages and formats, making it challenging to analyse and integrate with modern healthcare systematically. The ability of AI to process and analyse vast datasets can bridge this gap by organising and interpreting traditional medical knowledge in ways that are accessible and useful to healthcare providers and researchers (Al Kuwaiti et al., 2023; Alowais et al., 2023; Bajwa et al., 2021).

AI can analyse extensive collections of ethnobotanical data, ancient medical texts, and clinical records of traditional medicine practices to identify patterns and correlations. For example, AI algorithms can map the therapeutic uses of specific herbs across different cultures, enabling a deeper understanding of their potential applications. Additionally, AI can integrate traditional knowledge with modern clinical data to validate traditional remedies, identify possible drug interactions, and optimise treatment protocols. By creating databases that combine traditional medicine with modern clinical data, AI can support evidence-based integration of traditional practices into mainstream healthcare, ensuring that valuable traditional knowledge is preserved and utilised effectively (Chu et al., 2022; Saini & Parashar, 2024)

AI applications in traditional medicine include discovering new herbal treatments, personalised traditional medicine plans, and predictive analytics for wellness and prevention.

Discovery of New Herbal Treatments

AI has the potential to revolutionise the discovery of new herbal treatments by mining traditional medicine databases and identifying compounds that can be repurposed for modern therapeutic uses (Ma et al., 2023; Patwardhan & Vaidya, 2010). Traditional medicine systems, such as Ayurveda, Traditional Chinese Medicine (TCM), and African traditional medicine, have documented the use of thousands of plants and herbs for various ailments (Ranade, 2024; H. Zhang et al., 2020). AI can sift through this vast knowledge base, identifying active compounds that may be effective against modern diseases.

For example, AI can analyse the chemical composition of herbs used in traditional medicine and predict their biological activities using machine learning models (Y. Zhang & Wang, 2023). This approach can lead to identifying new drug candidates, which can be tested in laboratory settings. AI has already been used to discover potential antiviral compounds from traditional medicinal plants, accelerating drug discovery and validating traditional remedies (Wu et al., 2022).

Personalised Traditional Medicine Plans

Personalised medicine, which tailors treatments to individual characteristics, can also be applied to traditional medicine with the help of AI. Traditional medicine often emphasises individualised treatment approaches, considering a person’s unique constitution, lifestyle, and environment. AI can enhance this personalisation by integrating traditional diagnostic methods with modern data, such as genetic information, to create customised treatment plans (Ng et al., 2024).

For example, AI can help analyse a patient’s genetic signatures, health history, and lifestyle with the diagnostic tools used in traditional medicine, like pulse diagnosis in Ayurveda or tongue diagnosis in Traditional Chinese Medicine. The combination of the latest and traditional approaches with integration can help provide accurate diagnoses and person-specific treatment strategies rooted in traditional medicine but enhanced by modern science (Nashwan & Rao, 2024; H. Zhang et al., 2020).

Predictive Analytics for Wellness and Prevention

AI’s predictive analytics capabilities can be applied to traditional medicine to promote wellness and disease prevention. Traditional medicine strongly emphasises preventive care, with practices designed to maintain balance and harmony within the body (Jansen et al., 2021). AI can analyse data from traditional health practices, such as dietary habits, herbal use, and lifestyle routines, to identify patterns that contribute to long-term health (Amabie et al., 2024).

For instance, AI can predict the onset of chronic conditions based on traditional medicine principles, allowing for early interventions that align with conventional practices. AI-driven wellness apps can also incorporate traditional knowledge, offering personalised recommendations for diet, exercise, and herbal supplements based on an individual’s constitution and health goals (Williamson, 2001).

Integration of AI with Traditional Knowledge

AI technologies like natural language processing (NLP) and Machine learning (ML) can serve as crucial tools in preserving and utilising traditional medicine knowledge by analysing unstructured data. Much of traditional medicine knowledge is embedded in ancient texts, oral traditions, and environmental observations, which are often not digitised or structured in a way that is easily accessible to modern science. Integrating AI technologies with traditional knowledge presents a unique opportunity to bridge the gap between ancient wisdom and modern healthcare. Traditional medicine, rich with centuries of empirical knowledge, often faces documentation, preservation, and validation challenges. AI offers powerful tools to address these challenges, ensuring that valuable traditional practices are preserved and systematically integrated with contemporary healthcare approaches.

Analysing Ancient Texts with NLP

Natural language processing (NLP) can be used to digitise and analyse ancient medical texts, often written in classical languages and containing valuable insights into traditional medical practices. NLP allows researchers to uncover patterns, correlations, and treatment protocols used for centuries by converting these texts into structured data (Gayathri & Kannan, 2020; Tonja et al., 2024).

For instance, NLP can be applied to ancient Ayurvedic texts to extract information about herbal formulations and their uses. This information can be cross-referenced with modern scientific research to validate traditional treatments’ efficacy or identify potential new therapies. Similarly, NLP can be used to analyse Traditional Chinese Medicine texts to identify the therapeutic properties of herbs and their interactions (Wijaya et al., 2023; L. Zhou et al., 2021).

Machine Learning for Environmental Data Analysis

Traditional medicine is deeply connected to the environment, with many practices based on locally available plants, animals, and minerals (Alves & Rosa, 2007; Kala, 2022). Machine learning can analyse environmental data, such as climate patterns, soil composition, and biodiversity, to support the sustainable use of traditional medicine resources (Roopashree et al., 2024).

For example, ML can predict the availability of medicinal plants based on environmental conditions, helping to ensure their sustainable harvest and use. ML can also assist in identifying regions where  traditional medicine practices are at risk due to the degradation of the environment by guiding conservation efforts that help preserve both the natural resources and the traditional knowledge associated with them (Kavitha et al., 2023).

Sensor Data Analysis for Traditional Health Practices

AI can also be applied to analyse sensor data from traditional health practices, such as pulse diagnosis in Ayurveda or acupuncture in TCM. By collecting data from sensors that measure physiological parameters, AI can help validate and refine traditional diagnostic methods, making them more consistent and reliable (Fatangare & Bhingarkar, 2024).

For example, AI-powered devices can analyse pulse data to provide more accurate and reproducible diagnoses, enhancing the precision of traditional medicine practices. Integrating AI with traditional diagnostic tools can help to bridge the gap between traditional and modern medicine, providing a more holistic approach to healthcare (Amabie et al., 2024; Lu et al., 2020).

Documenting and Conserving Traditional Knowledge

Traditional healing practices are primarily transmitted from generation to generation within communities without formal documentation, which may lead to the risk of knowledge being lost with time. AI can play a critical role in documenting and preserving these practices by creating digital repositories of traditional medical knowledge. Through AI-driven data collection and storage, recording of oral traditions, categorisation, and stored in formats that are easily accessible and analysable (Marques et al., 2021; E. Zhou et al., 2024).

Moreover, AI can facilitate the digitisation of traditional medicine practices, transforming them into structured databases that can be used as a reference for future research and clinical applications. This may help preserve the cultural heritage associated with traditional medicine and make knowledge more accessible to a broader audience, including healthcare professionals and researchers (Lauricella & Pêgo-Fernandes, 2022).

Validating and Enhancing Traditional Healing Practices

One of the significant challenges of integrating traditional medicine into modern healthcare is the validation of its efficacy. AI can assist in analysing patterns in the usage and outcomes of traditional remedies, helping to identify which practices are most effective. By leveraging large datasets, AI can uncover correlations and causal relationships that may not be immediately apparent, thereby validating traditional treatments scientifically (Alowais et al., 2023).

For instance, machine learning algorithms can analyse patient outcomes associated with traditional medicine practices, helping to identify treatments that are particularly effective for specific conditions. This validation can enhance the credibility of traditional medicine and facilitate its integration into mainstream healthcare systems, ensuring that patients benefit from a holistic approach to health and well-being (Ng et al., 2024).

Translating and Digitising Traditional Texts

Natural Language Processing (NLP) algorithms offer a powerful tool for translating and digitising traditional medical texts, many written in ancient or indigenous languages. These texts often contain a wealth of knowledge about traditional healing practices, but language barriers and the lack of digital versions limit their accessibility (Piotrowski, 2012).

AI-driven NLP can automatically translate these texts into modern languages and convert them into digital formats, making them available for analysis and application in healthcare settings. It preserves the knowledge in these texts and makes it easier for researchers and practitioners to study and apply traditional medicine principles in their work (Névéol et al., 2018).

AI-Driven Decision Support for Traditional Healers

AI-driven decision support systems can empower traditional healers by providing evidence-based recommendations that enhance their practices. These systems can integrate traditional knowledge with the latest scientific research, offering traditional healers insights grounded in their cultural practices and informed by modern medical science. The application of AI to facilitate the connection between traditional healers and modern healthcare practitioners can benefit both contrasting worlds of traditional medicine and modern medicine (Zeng & Jia, 2024). For example, AI can supply traditional healers with details of potential interactions between traditional therapies and modern remedies, helping to ensure patient safety and improve therapeutic outcomes with safety. The collaborative approach can lead to a more integrative healthcare system that appreciates and leverages the strengths of both traditional and modern medicine (Münster et al., 2024).

Examples of AI-Traditional Knowledge Integration

AI offers significant potential to enhance and complement traditional knowledge systems in healthcare, creating opportunities to innovate in areas like herbal medicine discovery, community health monitoring, and culturally sensitive healthcare delivery.

1. Herbal Medicine Discovery

Traditional knowledge often includes the use of medicinal plants to treat various ailments. These remedies, passed down through generations, provide valuable insights into the therapeutic properties of plants. AI can revolutionise the discovery and validation of herbal medicines by analysing both traditional knowledge and modern scientific data to predict the therapeutic potential of medicinal plants (Rustandi et al., 2023).

AI algorithms, particularly machine learning models, can analyse large datasets containing information about the chemical composition of plants and their historical usage in traditional medicine. Established on the grounds of cross-referencing this data with scientific evidence from biomedical research, AI can predict which plant compounds will likely have specific therapeutic properties, such as anti-inflammatory, antioxidant, or antimicrobial effects. This approach accelerates the discovery of new medicinal uses for traditional plants and helps validate their efficacy (Paul et al., 2021).

For example, AI can predict plant-derived compounds’ bioactivity by mining data from traditional medical systems like Ayurveda, Traditional Chinese Medicine (TCM), or African herbal medicine. By applying AI algorithms to vast databases of phytochemicals, researchers can identify plants with potential for new drug development based on patterns and correlations observed in traditional usage. It reduces the need for costly and time-consuming laboratory experiments by prioritising plants more likely to show promising results (Azadnia et al., 2022).

Moreover, AI can assist in identifying synergistic combinations of plant-based compounds that work together to enhance therapeutic effects, a concept widely recognised in traditional medicine. By analysing the interactions between multiple compounds, AI can suggest optimised herbal formulations that may provide more effective treatments than isolated compounds (Ma et al., 2023).

2. Community Health Monitoring

For communities practicing traditional medicine, AI-driven health monitoring can align with existing practices of holistic health assessment. In the Traditional Chinese medicine (TCM) technique, the balance of Yin and Yang is considered crucial for maintaining health. AI-based tools can monitor lifestyle habits that may influence this balance. This way, wearable technology and AI can track physiological and environmental factors, providing personalised feedback based on traditional healing concepts (Lu et al., 2024; Nahavandi et al., 2022).

AI-based platforms can also facilitate community health initiatives by aggregating individual data and identifying trends that may suggest emerging health risks. In remote or underserved communities where traditional healthcare is the primary or the only source of medical treatment, introducing AI-driven systems can alert traditional healers and community leaders about potential health concerns, enabling early interventions that align with their cultural approaches to disease prevention and treatment.

For example, an AI-based app can monitor the health outcomes of individuals taking herbal remedies, correlating those outcomes with lifestyle factors and traditional healing practices, thus providing evidence-based insights that can be shared with traditional healers and modern healthcare providers (Alowais et al., 2023).

3. Cultural Sensitivity in Healthcare

Traditional knowledge systems are deeply embedded in the Indigenous communities’ cultures and belief systems, and effective healthcare delivery must be sensitive to these cultural contexts. AI-driven language translation tools can facilitate communication between healthcare providers and patients from diverse cultural backgrounds, ensuring that traditional beliefs and practices are followed during diagnosis and treatment (Marques et al., 2021).

Natural language processing (NLP) tools can be developed and implemented to translate indigenous languages or culturally specific medical terminologies into the language used by healthcare providers, allowing for more accurate communication and fostering a better understanding of patient needs, which can be particularly valuable in regions where patients primarily rely on traditional healers or community-based healthcare systems. By translating the terminology used in traditional medicine into modern medical language, healthcare providers can better understand the cultural context of a patient’s symptoms and treatment preferences.

For instance, in many traditional medicine systems, health may be associated with balance, spirituality, or harmony with nature – concepts that may not easily translate into Western medical terminology. AI-driven translation tools can help bridge this gap, ensuring that healthcare providers are aware of these cultural nuances and can tailor their treatments accordingly (Mohamed et al., 2024).

Additionally, AI can assist healthcare providers in learning about cultural practices that influence patient care. Machine learning algorithms can analyse cultural practices and preferences from patient records, enabling healthcare providers to offer treatment options that align with a patient’s traditional beliefs. This cultural sensitivity improves patient satisfaction and trust. It can improve health outcomes by ensuring patients are more likely to adhere to treatments that respect their cultural norms.

Challenges and Considerations

While integrating Artificial Intelligence (AI) with traditional knowledge presents exciting opportunities for healthcare, it also brings forth several challenges and ethical considerations. These include respecting the intellectual property rights of indigenous communities, cultural sensitivity, and ensuring data privacy and security. Addressing these concerns is essential for building equitable, respectful, and effective AI-traditional knowledge collaborations.

Ethical Considerations: Intellectual Property Rights and Equitable Partnerships

One of the primary ethical challenges in using AI to harness traditional knowledge is the protection of intellectual property rights (IPR) for indigenous communities. Traditional knowledge is often maintained or practised collectively and passed down through generations within communities. Many communities have not historically participated in formalised intellectual property regimes and agree with government policies, making it challenging to ensure their knowledge is recognised, respected, and fairly compensated in the modern world (Wagner & de Clippele, 2023). In AI-traditional knowledge collaborations, it is crucial to develop frameworks that protect the rights of indigenous communities. This involves creating equitable partnerships where these communities retain control over their knowledge and benefit from commercialising or using their traditional remedies and practices (Timmermans, 2003). Misappropriation or exploitation of traditional knowledge for profit, without proper consent or benefit-sharing, has been a persistent issue, and AI applications must not exacerbate this.

A solution to this challenge lies in adopting frameworks like the Nagoya Protocol, which emphasises access to genetic resources and traditional knowledge with prior informed consent and equitable sharing of benefits (Heinrich et al., 2020). AI developers and healthcare organisations must engage in ethical agreements with indigenous communities, ensuring they actively participate in decision-making. This will ensure that their knowledge is not exploited but is leveraged in a way that honours their cultural heritage.

Cultural Sensitivity: Avoiding Western-Centric Perspectives in AI Applications

Traditional knowledge systems are practiced mainly by indigenous people from different cultures, races, traditions, and locations. However, AI technologies are often developed based on Western-centric models of knowledge and healthcare, which may need to align with traditional medicine’s holistic and community-based approaches (Mazzocchi, 2006).

AI applications designed to work with traditional knowledge must be culturally sensitive and avoid imposing any particular scientific frameworks that may not be relevant to the context. For instance, traditional medicine often emphasises the balance between the body, mind, spirit, and environment, a concept that may only sometimes be easily quantifiable through AI models. To respect diversity and traditions, AI systems should be adaptable and able to integrate traditional knowledge on its terms rather than forcing it to fit into a pre-defined mould.

Moreover, developers of AI systems must engage directly with Indigenous communities to ensure that their cultural values and healing practices are accurately represented. This collaboration should involve Indigenous healers and practitioners in the design and development, ensuring that AI systems reflect traditional medicine systems’ cultural richness and nuances (Silano, 2024).

Data Privacy and Security: Safeguarding Sensitive Information

Incorporating AI into traditional medicine often involves collecting, storing, and analysing sensitive health and cultural data from indigenous populations. This raises significant concerns about data privacy and security, particularly in light of past abuses where Indigenous communities were exploited for research without their consent or knowledge (Murdoch, 2021).

AI-driven healthcare technologies must ensure that Indigenous communities retain control over their data and that data collection is conducted with complete transparency and informed consent. This is especially important as traditional knowledge is often viewed as sacred or proprietary, and sharing this knowledge outside the community without proper safeguards can lead to exploitation or misrepresentation.

In addition, AI systems must be mandated to implement robust security measures that not only protect the interest of the people using it but also protect the collected data from unauthorised access, breaches, or misuse (Kaur et al., 2023). Given that healthcare data is susceptible, AI systems should comply with global privacy regulations, such as the General Data Protection Regulation (GDPR) and country-specific rules, while ensuring that community-specific ethical considerations are considered. Indigenous communities should be fully informed about how their data will be used and be able to withdraw consent or access their data at any point (Reddy, 2023).

AI developers must also build trust by ensuring transparency in how AI models are trained, their data sources, and the outcomes they generate. This transparency is critical in avoiding the misuse of sensitive cultural or health-related data and ensuring that AI tools are accepted and trusted by the communities they aim to serve (Balasubramaniam et al., 2023).

Conclusion

Integrating Artificial Intelligence (AI) with traditional knowledge offers a promising pathway to enhance health and well-being in diverse communities. Combining the deep-rooted wisdom of traditional healing systems with the analytical power of AI, we can create more inclusive and culturally sensitive healthcare solutions. AI can be a great tool that will be used to document, preserve, and validate traditional practices followed over centuries while identifying new insight that bridges the gap between ancient remedies and modern scientific methods. By honoring and respecting the traditional knowledge passed down through generations, the integration of AI with traditional medicine will be a game changer that will pave the way for innovative approaches to global healthcare.

To fully realise the potential, fostering collaboration between scientists, technologists, and traditional healers is crucial, ensuring each plays an active role in shaping AI applications. Such partnerships can help navigate ethical considerations, respect cultural sensitivities, and safeguard indigenous knowledge. Together, we can develop healthcare systems that embrace the wisdom of the past while harnessing the possibilities of the future, leading to more holistic, equitable, and effective health solutions for all.

 

Acknowledgement

SR is thankful to the Indian Council of Medical Research, Department of Health Research and the Government of India for permission to deliver an invited lecture on this paper at the Plenary Session of the Pontifical Academy of Sciences, 23-26 September 2024, Casina Pio IV, Vatican City.

References

Abrahams, N., Jewkes, R., & Mvo, Z. (2001). Health Care – Seeking Practices of Pregnant Women and the Role of the Midwife in Cape Town, South Africa. Journal of Midwifery & Women’s Health, 46(4), 240–247. https://doi.org/10.1016/S1526-9523(01)00138-6

Al Kuwaiti, A., Nazer, K., Al-Reedy, A., Al-Shehri, S., Al-Muhanna, A., Subbarayalu, A.V., Al Muhanna, D., & Al-Muhanna, F.A. (2023). A Review of the Role of Artificial Intelligence in Healthcare. Journal of Personalized Medicine, 13(6), 951. https://doi.org/10.3390/jpm13060951

Alowais, S.A., Alghamdi, S.S., Alsuhebany, N., Alqahtani, T., Alshaya, A.I., Almohareb, S.N., Aldairem, A., Alrashed, M., Bin Saleh, K., Badreldin, H.A., Al Yami, M.S., Al Harbi, S., & Albekairy, A.M. (2023). Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Medical Education, 23(1), 689. https://doi.org/10.1186/s12909-023-04698-z

Alves, R.R., & Rosa, I.M. (2007). Biodiversity, traditional medicine and public health: where do they meet? Journal of Ethnobiology and Ethnomedicine, 3(1), 14. https://doi.org/10.1186/1746-4269-3-14

Amabie, T., Izah, S.C., Ogwu, M.C., & Hait, M. (2024). Harmonizing Tradition and Technology: The Synergy of Artificial Intelligence in Traditional Medicine (pp. 2103–2125). https://doi.org/10.1007/978-3-031-43199-9_70

Arowosegbe, A., & Oyelade, T. (2023). Application of Natural Language Processing (NLP) in Detecting and Preventing Suicide Ideation: A Systematic Review. International Journal of Environmental Research and Public Health, 20(2), 1514. https://doi.org/10.3390/ijerph20021514

Azadnia, R., Al-Amidi, M.M., Mohammadi, H., Cifci, M.A., Daryab, A., & Cavallo, E. (2022). An AI-Based Approach for Medicinal Plant Identification Using Deep CNN Based on Global Average Pooling. Agronomy, 12(11), 2723. https://doi.org/10.3390/agronomy12112723

Bach-Faig, A., Berry, E.M., Lairon, D., Reguant, J., Trichopoulou, A., Dernini, S., Medina, F.X., Battino, M., Belahsen, R., Miranda, G., & Serra-Majem, L. (2011). Mediterranean diet pyramid today. Science and cultural updates. Public Health Nutrition, 14(12A), 2274–2284. https://doi.org/10.1017/S1368980011002515

Bajwa, J., Munir, U., Nori, A., & Williams, B. (2021). Artificial intelligence in healthcare: transforming the practice of medicine. Future Healthcare Journal, 8(2), e188–e194. https://doi.org/10.7861/fhj.2021-0095

Balasubramaniam, N., Kauppinen, M., Rannisto, A., Hiekkanen, K., & Kujala, S. (2023). Transparency and explainability of AI systems: From ethical guidelines to requirements. Information and Software Technology, 159, 107197. https://doi.org/10.1016/j.infsof.2023.107197

Chaachouay, N., & Zidane, L. (2024). Plant-Derived Natural Products: A Source for Drug Discovery and Development. Drugs and Drug Candidates, 3(1), 184–207. https://doi.org/10.3390/ddc3010011

Chu, H., Moon, S., Park, J., Bak, S., Ko, Y., & Youn, B.-Y. (2022). The Use of Artificial Intelligence in Complementary and Alternative Medicine: A Systematic Scoping Review. Frontiers in Pharmacology, 13. https://doi.org/10.3389/fphar.2022.826044

Das, S.K., Dasgupta, R.K., Roy, S.D., & Shil, D. (2024). AI in Indian healthcare: From roadmap to reality. Intelligent Pharmacy, 2(3), 329–334. https://doi.org/10.1016/j.ipha.2024.02.005

Dein, S. (2020). Traditional Healers and Global Mental Health. In Innovations in Global Mental Health (pp. 1–11). Springer International Publishing. https://doi.org/10.1007/978-3-319-70134-9_132-1

Fatangare, M., & Bhingarkar, S. (2024). A comprehensive review on technological advancements for sensor-based Nadi Pariksha: An ancient Indian science for human health diagnosis. Journal of Ayurveda and Integrative Medicine, 15(3), 100958. https://doi.org/10.1016/j.jaim.2024.100958

Gall, A., Anderson, K., Howard, K., Diaz, A., King, A., Willing, E., Connolly, M., Lindsay, D., & Garvey, G. (2021). Wellbeing of Indigenous Peoples in Canada, Aotearoa (New Zealand) and the United States: A Systematic Review. International Journal of Environmental Research and Public Health, 18(11), 5832. https://doi.org/10.3390/ijerph18115832

Gayathri, M., & Kannan, R.J. (2020). Ontology based Concept Extraction and Classification of Ayurvedic Documents. Procedia Computer Science, 172, 511–516. https://doi.org/10.1016/j.procs.2020.05.061

González, N.C., & Kröger, M. (2020). The potential of Amazon indigenous agroforestry practices and ontologies for rethinking global forest governance. Forest Policy and Economics, 118, 102257. https://doi.org/10.1016/j.forpol.2020.102257

Heinrich, M., Scotti, F., Andrade-Cetto, A., Berger-Gonzalez, M., Echeverría, J., Friso, F., Garcia-Cardona, F., Hesketh, A., Hitziger, M., Maake, C., Politi, M., Spadafora, C., & Spadafora, R. (2020). Access and Benefit Sharing Under the Nagoya Protocol – Quo Vadis? Six Latin American Case Studies Assessing Opportunities and Risk. Frontiers in Pharmacology, 11. https://doi.org/10.3389/fphar.2020.00765

Jakes, V. (2024). The Role of Traditional Knowledge in Sustainable Development. International Journal of Humanity and Social Sciences, 3(2), 40–55. https://doi.org/10.47941/ijhss.2079

Jansen, C., Baker, J.D., Kodaira, E., Ang, L., Bacani, A.J., Aldan, J.T., Shimoda, L.M.N., Salameh, M., Small-Howard, A.L., Stokes, A.J., Turner, H., & Adra, C.N. (2021). Medicine in motion: Opportunities, challenges and data analytics-based solutions for traditional medicine integration into western medical practice. Journal of Ethnopharmacology, 267, 113477. https://doi.org/10.1016/j.jep.2020.113477

Johnson, K.B., Wei, W., Weeraratne, D., Frisse, M.E., Misulis, K., Rhee, K., Zhao, J., & Snowdon, J.L. (2021). Precision Medicine, AI, and the Future of Personalized Health Care. Clinical and Translational Science, 14(1), 86–93. https://doi.org/10.1111/cts.12884

Kala, C.P. (2022). Traditional Ecological Knowledge of Tribal Communities and Sustainability of Nature and Natural Resources in Pachmarhi Biosphere Reserve in India. International Journal of Ecology, 2022, 1–13. https://doi.org/10.1155/2022/5979024

Kaur, R., Gabrijelčič, D., & Klobučar, T. (2023). Artificial intelligence for cybersecurity: Literature review and future research directions. Information Fusion, 97, 101804. https://doi.org/10.1016/j.inffus.2023.101804

Kavitha, S., Kumar, T.S., Naresh, E., Kalmani, V.H., Bamane, K.D., & Pareek, P.K. (2023). Medicinal Plant Identification in Real-Time Using Deep Learning Model. SN Computer Science, 5(1), 73. https://doi.org/10.1007/s42979-023-02398-5

Krah, E., de Kruijf, J., & Ragno, L. (2018). Integrating Traditional Healers into the Health Care System: Challenges and Opportunities in Rural Northern Ghana. Journal of Community Health, 43(1), 157–163. https://doi.org/10.1007/s10900-017-0398-4

Lauricella, L.L., & Pêgo-Fernandes, P.M. (2022). Databases, big data and artificial intelligence: what healthcare professionals need to know about them. Sao Paulo Medical Journal, 140(6), 737–738. https://doi.org/10.1590/1516-3180.2022.140611082022

Lu, L., Lu, T., Tian, C., & Zhang, X. (2024). AI: Bridging Ancient Wisdom and Modern Innovation in Traditional Chinese Medicine. JMIR Medical Informatics, 12, e58491. https://doi.org/10.2196/58491

Lu, L., Zhang, J., Xie, Y., Gao, F., Xu, S., Wu, X., & Ye, Z. (2020). Wearable Health Devices in Health Care: Narrative Systematic Review. JMIR MHealth and UHealth, 8(11), e18907. https://doi.org/10.2196/18907

Ma, S., Liu, J., Li, W., Liu, Y., Hui, X., Qu, P., Jiang, Z., Li, J., & Wang, J. (2023). Machine learning in TCM with natural products and molecules: current status and future perspectives. Chinese Medicine, 18(1), 43. https://doi.org/10.1186/s13020-023-00741-9

Marques, B., Freeman, C., & Carter, L. (2021). Adapting Traditional Healing Values and Beliefs into Therapeutic Cultural Environments for Health and Well-Being. International Journal of Environmental Research and Public Health, 19(1), 426. https://doi.org/10.3390/ijerph19010426

Mazzocchi, F. (2006). Western science and traditional knowledge. EMBO Reports, 7(5), 463–466. https://doi.org/10.1038/sj.embor.7400693

Mohamed, Y.A., Khanan, A., Bashir, M., Mohamed, A.H.H.M., Adiel, M.A.E., & Elsadig, M.A. (2024). The Impact of Artificial Intelligence on Language Translation: A Review. IEEE Access, 12, 25553–25579. https://doi.org/10.1109/ACCESS.2024.3366802

Montour, L. (2000). The Medicine Wheel: Understanding “Problem” Patients in Primary Care. The Permanente Journal, 4(1). https://doi.org/10.7812/TPP/00.996

Münster, S., Maiwald, F., di Lenardo, I., Henriksson, J., Isaac, A., Graf, M.M., Beck, C., & Oomen, J. (2024). Artificial Intelligence for Digital Heritage Innovation: Setting up a R&D Agenda for Europe. Heritage, 7(2), 794–816. https://doi.org/10.3390/heritage7020038

Murdoch, B. (2021). Privacy and artificial intelligence: challenges for protecting health information in a new era. BMC Medical Ethics, 22(1), 122. https://doi.org/10.1186/s12910-021-00687-3

Nahavandi, D., Alizadehsani, R., Khosravi, A., & Acharya, U.R. (2022). Application of artificial intelligence in wearable devices: Opportunities and challenges. Computer Methods and Programs in Biomedicine, 213, 106541. https://doi.org/10.1016/j.cmpb.2021.106541

Nanda, S. (2023). Integrating Traditional and Contemporary Systems for Health and Well-being. Annals of Neurosciences, 30(2), 77–78. https://doi.org/10.1177/09727531231185648

Nashwan, A.J., & Rao, A.G. (2024). Integrating Traditional Chinese Medicine and Artificial Intelligence for insomnia: A promising frontier. Brain Behavior and Immunity Integrative, 7, 100071. https://doi.org/10.1016/j.bbii.2024.100071

Névéol, A., Dalianis, H., Velupillai, S., Savova, G., & Zweigenbaum, P. (2018). Clinical Natural Language Processing in languages other than English: opportunities and challenges. Journal of Biomedical Semantics, 9(1), 12. https://doi.org/10.1186/s13326-018-0179-8

Ng, J.Y., Cramer, H., Lee, M.S., & Moher, D. (2024). Traditional, complementary, and integrative medicine and artificial intelligence: Novel opportunities in healthcare. Integrative Medicine Research, 13(1), 101024. https://doi.org/10.1016/j.imr.2024.101024

Pan, S.-Y., Litscher, G., Gao, S.-H., Zhou, S.-F., Yu, Z.-L., Chen, H.-Q., Zhang, S.-F., Tang, M.-K., Sun, J.-N., & Ko, K.-M. (2014). Historical Perspective of Traditional Indigenous Medical Practices: The Current Renaissance and Conservation of Herbal Resources. Evidence-Based Complementary and Alternative Medicine, 2014(1). https://doi.org/10.1155/2014/525340

Patwardhan, B., & Vaidya, A.D.B. (2010). Natural products drug discovery: accelerating the clinical candidate development using reverse pharmacology approaches. Indian Journal of Experimental Biology, 48(3), 220–227. http://www.ncbi.nlm.nih.gov/pubmed/21046974

Paul, D., Sanap, G., Shenoy, S., Kalyane, D., Kalia, K., & Tekade, R.K. (2021). Artificial intelligence in drug discovery and development. Drug Discovery Today, 26(1), 80–93. https://doi.org/10.1016/j.drudis.2020.10.010

Payyappallimana, U. (2013). Health and Well-being in Indian Local Health Traditions (pp. 99–112). https://doi.org/10.1007/978-94-007-6689-1_7

Piotrowski, M. (2012). Natural Language Processing for Historical Texts. Synthesis Lectures on Human Language Technologies, 5(2), 1–157. https://doi.org/10.2200/S00436ED1V01Y201207HLT017

Ramos-Jiménez, A., Wall-Medrano, A., Corona-Hernández, R., & Hernández-Torres, R. (2015). Yoga, bioenergetics and eating behaviors: A conceptual review. International Journal of Yoga, 8(2), 89. https://doi.org/10.4103/0973-6131.158469

Ranade, M. (2024). Artificial intelligence in Ayurveda: Current concepts and prospects. Journal of Indian System of Medicine, 12(1), 53–59. https://doi.org/10.4103/jism.jism_60_23

Reddy, S. (2023). Navigating the AI Revolution: The Case for Precise Regulation in Health Care. Journal of Medical Internet Research, 25, e49989. https://doi.org/10.2196/49989

Roopashree, S., Anitha, J., Challa, S., Mahesh, T.R., Venkatesan, V.K., & Guluwadi, S. (2024). Mapping of soil suitability for medicinal plants using machine learning methods. Scientific Reports, 14(1), 3741. https://doi.org/10.1038/s41598-024-54465-3

Rustandi, T., Prihandiwati, E., Nugroho, F., Hayati, F., Afriani, N., Alfian, R., Aisyah, N., Niah, R., Rahim, A., & As-Shiddiq, H. (2023). Application of artificial intelligence in the development of Jamu “traditional Indonesian medicine” as a more effective drug. Frontiers in Artificial Intelligence, 6. https://doi.org/10.3389/frai.2023.1274975

Saini, P., & Parashar, D. (2024). Scope of Artificial Intelligence in Spectrum of Ayurveda. International Journal of Advanced Research, 12(05), 543–547. https://doi.org/10.21474/IJAR01/18747

Silano, J.A. (2024). Towards abundant intelligences: Considerations for Indigenous perspectives in adopting artificial intelligence technology. Healthcare Management Forum, 37(5), 329–333. https://doi.org/10.1177/08404704241257144

Singh, A., Banerjee, P., Anas, M., Singh, N., & Qamar, I. (2020). Traditional Nutritional and Health Practices Targeting Lifestyle Behavioral Changes in Humans. Journal of Lifestyle Medicine, 10(2), 67–73. https://doi.org/10.15280/jlm.2020.10.2.67

Timmermans, K. (2003). Intellectual property rights and traditional medicine: policy dilemmas at the interface. Social Science & Medicine, 57(4), 745–756. https://doi.org/10.1016/S0277-9536(02)00425-2

Tonja, A., Balouchzahi, F., Butt, S., Kolesnikova, O., Ceballos, H., Gelbukh, A., & Solorio, T. (2024). NLP Progress in Indigenous Latin American Languages. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 6972–6987. https://doi.org/10.18653/v1/2024.naacl-long.385

Tu, Y. (2011). The discovery of artemisinin (qinghaosu) and gifts from Chinese medicine. Nature Medicine, 17(10), 1217–1220. https://doi.org/10.1038/nm.2471

Varambally, S., & Gangadhar, B.N. (2020). Yoga and Traditional Healing Methods in Mental Health (pp. 297–326). https://doi.org/10.1007/978-981-10-2345-3_20

Wagner, A., & de Clippele, M.-S. (2023). Safeguarding Cultural Heritage in the Digital Era – A Critical Challenge. International Journal for the Semiotics of Law – Revue Internationale de Sémiotique Juridique, 36(5), 1915–1923. https://doi.org/10.1007/s11196-023-10040-z

Wijaya, S.H., Nasution, A.K., Batubara, I., Gao, P., Huang, M., Ono, N., Kanaya, S., & Altaf-Ul-Amin, M. (2023). Deep Learning Approach for Predicting the Therapeutic Usages of Unani Formulas towards Finding Essential Compounds. Life, 13(2), 439. https://doi.org/10.3390/life13020439

Williamson, E. (2001). Synergy and other interactions in phytomedicines. Phytomedicine, 8(5), 401–409. https://doi.org/10.1078/0944-7113-00060

Wu, C., Chen, J., Lai-Han Leung, E., Chang, H., & Wang, X. (2022). Editorial: Artificial Intelligence in Traditional Medicine. Frontiers in Pharmacology, 13. https://doi.org/10.3389/fphar.2022.933133

Zeng, J., & Jia, X. (2024). Systems Theory-Driven Framework for AI Integration into the Holistic Material Basis Research of Traditional Chinese Medicine. Engineering, 40, 28–50. https://doi.org/10.1016/j.eng.2024.04.009

Zhang, H., Ni, W., Li, J., & Zhang, J. (2020). Artificial Intelligence–Based Traditional Chinese Medicine Assistive Diagnostic System: Validation Study. JMIR Medical Informatics, 8(6), e17608. https://doi.org/10.2196/17608

Zhang, Y., & Wang, Y. (2023). Recent trends of machine learning applied to multi-source data of medicinal plants. Journal of Pharmaceutical Analysis, 13(12), 1388–1407. https://doi.org/10.1016/j.jpha.2023.07.012

Zhou, E., Shen, Q., & Hou, Y. (2024). Integrating artificial intelligence into the modernization of traditional Chinese medicine industry: a review. Frontiers in Pharmacology, 15. https://doi.org/10.3389/fphar.2024.1181183

Zhou, L., Liu, S., Li, C., Sun, Y., Zhang, Y., Li, Y., Yuan, H., Sun, Y., Xu, F., & Li, Y. (2021). Natural Language Processing Algorithms for Normalizing Expressions of Synonymous Symptoms in Traditional Chinese Medicine. Evidence-Based Complementary and Alternative Medicine, 2021, 1–12. https://doi.org/10.1155/2021/6676607