Can AI support EMA-compliant medical translation? 

The life sciences sector is undergoing a significant shift as AI becomes increasingly embedded in multilingual content workflows. Tightening regulatory deadlines, expanding language coverage, and growing documentation requirements have prompted many clinical, regulatory, and quality teams to ask: 

Can AI-assisted translation be used responsibly for regulated medical content such as SmPCs, package leaflets, and other materials required under EMA or MDR/IVDR frameworks, including IFUs and patient communications? 

This article explores how AI can be used within the boundaries of regulatory compliance, and under what conditions it becomes a safe and effective solution for medical translation services. 

The role of AI in regulated medical translation 

AI-assisted translation has made substantial progress in the past two years. When used thoughtfully, it can improve speed, consistency, and scalability across a range of use cases, including: 

These benefits make AI an increasingly attractive option, especially for projects with high volume and short timelines. However, regulatory content requires more than speed, it demands precision, traceability, and full alignment with terminology and format expectations established by authorities such as the EMA, FDA, and national agencies. 

Why AI alone is not enough 

Despite its capabilities, AI still faces limitations in highly specialised domains like regulatory translation. These challenges may include: 

• Morphological complexity in languages like Hungarian or Finnish 

• Use of standardised terms such as MedDRA, EDQM, or EMA QRD templates 

• Sensitivity to phrasing and clarity, particularly in patient-facing materials 

Because of this, raw AI output is never suitable for regulatory submission. Quality, compliance, and patient safety can only be ensured when expert human review is embedded in the process. 

Human-in-the-loop: the cornerstone of safe AI translation 

AI can support translation workflows, but only under the close supervision of qualified human experts. In the context of regulated medical content, the role of human reviewers goes beyond basic post-editing: 

• They verify correct application of regulatory templates and terminology 

• They ensure alignment with product-specific references and previous submissions 

• They assess the readability and tone of patient communications 

• They provide the final layer of accountability required for compliance 

The “human-in-the-loop” approach ensures that AI improves productivity without compromising the regulatory integrity of the output. In this model, human reviewers are not simply editors, they are guardians of quality, safety, and consistency in healthcare translation services. 

Systems, not just tools: responsible AI implementation 

Effective use of AI in regulatory translation involves more than choosing the right tool. The entire system must be designed to support compliance and quality from the start. This includes: 

• Benchmarking AI models by language pair, content type, and domain to determine suitability 

• Integrating AI with existing translation memories, termbases, and client glossaries to ensure consistent terminology and phrasing 

• Establishing internal policies for when and how each tool can be used, based on content sensitivity 

This interconnected framework helps reduce post-editing effort while ensuring terminology accuracy and alignment with regulatory expectations. 

Aligning with EMA compliance and ISO standards 

While the EMA has not issued explicit guidance on the use of AI in translation, existing regulations and standards provide a clear framework for compliance. AI-assisted workflows are considered acceptable if they include proper human post-editing, transparent processes, and data protection safeguards. 

Industry standards that support responsible AI use include: 

• ISO 18587, for the post-editing of machine translation 

• ISO 13485, for quality management systems in medical device translation 

• MDR/IVDR requirements, particularly for readability and terminology consistency in IFUs and patient materials 

Organizations using AI responsibly incorporate these standards into their workflows, combining automated tools with expert human oversight and continuous quality evaluation. 

What do regulations say about AI use in translation? 

To date, no EU regulation prohibits the use of AI in medical translation workflows. The EMA and national agencies focus on the quality and compliance of the final output, regardless of the tools used. Key regulatory expectations include: 

• Human validation by qualified translators 

• Traceability of process and tool usage 

• Terminology alignment with approved reference materials 

• Transparency and data protection throughout the workflow 

When these principles are respected, AI-assisted translation can support regulatory compliance. 

Final thoughts 

AI is not a replacement for human expertise, it’s a tool that, when used responsibly, can improve the accuracy, consistency, and scalability of medical translation workflows. For regulated content, success lies in combining technological support with human accountability, robust quality systems, and standards-based validation. 

As the medical and pharmaceutical industries continue to evolve, AI will likely play an expanding role in multilingual content delivery. But for regulatory translation, one truth remains constant: compliance starts with processes, not with tools. 

La compasión en los negocios: cómo apoyar proyectos con propósito hace que el trabajo sea más gratificante 

En Novalins, creemos que los negocios van más allá de las transacciones: se trata de contribuir a algo más grande, alineándonos con valores que reflejan quiénes somos como equipo y como individuos. Esto cobra aún más sentido cuando colaboramos con clientes cuyo trabajo tiene un impacto positivo en la sociedad a través de servicios de traducción ética. 

El poder de los proyectos con propósito 

En los últimos meses, hemos tenido el privilegio de trabajar en proyectos de traducción para varias organizaciones dedicadas a promover la salud global, proteger el medio ambiente y generar cambio social. Nuestra experiencia en traducción médica y servicios de localización nos permite apoyar iniciativas verdaderamente significativas. 

Uno de estos proyectos consistió en traducir contenido para una organización internacional que trabaja incansablemente por mejorar el bienestar animal y erradicar prácticas crueles en la agricultura. Otro se centró en avanzar el diálogo sobre el manejo del dolor crónico en Europa, contribuyendo a una investigación médica vital que empodera tanto a pacientes como a profesionales sanitarios. 

También tuvimos la oportunidad única de colaborar con una empresa de tecnología médica (MedTech) que desarrolló un dispositivo para monitorear los patrones de sueño, tan innovador que fue utilizado en una misión espacial para estudiar el sueño en astronautas. Proyectos como estos nos recuerdan que, aunque no salvamos vidas directamente, formamos parte de algo más grande: una red de innovadores, investigadores y defensores que trabajan para crear un mundo mejor a través de la traducción en ciencias de la vida. 

Un sentimiento de orgullo y conexión 

Estos proyectos de traducción con impacto social alimentan nuestro sentido de orgullo y propósito en Novalins. Saber que nuestro trabajo apoya organizaciones cuyas misiones se alinean con nuestros valores, desde promover la salud y el bienestar hasta fomentar prácticas sostenibles, da más significado a cada proyecto. 

Nuestro equipo a menudo reflexiona sobre el hecho de que no solo traducimos palabras; amplificamos mensajes importantes, facilitamos investigaciones internacionales que podrían dar lugar a avances médicos, y hacemos que la información médica crítica sea accesible para más personas. 

Comentarios de los clientes: más que palabras 

Los comentarios que recibimos sobre estos proyectos de localización con impacto social refuerzan aún más nuestro compromiso. Escuchamos a organizaciones expresar su agradecimiento por nuestra flexibilidad frente a presupuestos ajustados, plazos urgentes y necesidades específicas. Nos ven como más que un proveedor de servicios lingüísticos: nos consideran un aliado en su misión de generar un impacto social positivo. 

Por qué es importante para nosotros 

Trabajar con clientes impulsados por una misión no solo es gratificante, sino esencial para nuestra identidad. En Novalins, somos un equipo guiado por la ética y un sentido compartido de responsabilidad. Este compromiso con una práctica empresarial responsable y sostenible nos ha llevado a rechazar proyectos que entran en conflicto con nuestros valores, incluso cuando podría haber sido financieramente beneficioso aceptarlos. 

Entre nuestros clientes se encuentran innovadores que desarrollan los primeros test de diagnóstico para la endometriosis, dispositivos de monitoreo remoto para pacientes oncológicos, y herramientas de detección para la ictericia neonatal. Cada proyecto de traducción médica nos recuerda que lo que hacemos importa, no solo para nuestros clientes, sino también para la salud global. 

Una reflexión final 

En Novalins, nos esforzamos por trabajar con clientes cuyo trabajo genera un impacto positivo en la sociedad. Aunque no salvamos vidas directamente, creemos que incluso la contribución más pequeña, ya sea asegurar la precisión del contenido médico o traducir investigaciones científicas que puedan conducir a descubrimientos, puede marcar una diferencia significativa. Gracias a una localización de calidad en ciencias de la vida y a prácticas de traducción ética, contribuimos a un mundo más saludable y compasivo. 

¿Cuál es el impacto de tu trabajo? ¿Y cómo podemos contribuir todos a proyectos que no solo impulsen el negocio, sino que también generen un impacto social positivo? 

Sigamos conversando. 

Referencias 

1. https://www.maddyness.com/2021/04/26/bandeau-dreem-sommeil-espace-thomas-pesquet/ 

Compassion in business: How supporting meaningful projects makes work more rewarding 

At Novalins, we believe that business is more than just transactions, it’s about contributing to something greater, aligning with values that reflect who we are as a team and as individuals. This is especially true when we partner with clients whose work makes a positive impact on society through ethical translation services. 

The power of purpose-driven projects 

In recent months, we’ve had the privilege of working on translation projects for several organisations dedicated to advancing global health, protecting the environment, and promoting social change. Our work in medical translation and localisation services allows us to support initiatives that truly matter. 

One such project involved translating content for an international organisation working tirelessly to improve animal welfare and end cruel practices in farming. Another focused on advancing the conversation around chronic pain management in Europe, contributing to vital medical research that empowers patients and healthcare providers alike. 

We also had the unique opportunity to support a MedTech company that developed a device to monitor sleep patterns, a device so impactful it was later used in a space mission to study sleep in astronauts. These life sciences translation projects remind us that while we may not be saving lives directly, we are part of something larger, a network of innovators, researchers, and advocates working to make the world a better place. 

A sense of pride and connection 

It’s these meaningful translation projects that fuel our sense of pride and purpose at Novalins. Knowing that our work supports organisations with missions that align with our values, from advancing health and wellness to championing sustainable practices, gives every project more meaning. 

Our team often reflects on the fact that we’re not just translating words; we’re amplifying important messages, facilitating international research that could lead to medical breakthroughs, and making life-saving healthcare information accessible to more people. 

Client feedback: more than just words 

The feedback we receive from clients on these purpose-driven localisation projects further reinforces our commitment. We hear from organisations expressing their gratitude for our flexibility in aligning with tight budgets, urgent timelines, and specific project needs. They see us as more than just a language service provider, they see us as a trusted partner in their mission to create social impact. 

Why it matters to us? 

Working with clients who are mission-driven isn’t just fulfilling, it’s essential to who we are as a company. At Novalins, we are a team of people driven by ethics and a shared sense of responsibility. This commitment to sustainable and responsible business practices has led us to turn down projects that conflict with our values, even when it might have been financially advantageous to take them on. 

Among our clients are innovators developing the first diagnostic tests to detect endometriosis, remote health monitoring devices for cancer patients, and newborn jaundice screening tools. Each medical translation project reminds us that what we do matters, not just to our clients but to global health and well-being. 

A closing reflection 

At Novalins, we work hard to align with clients whose work brings something positive to society. While we aren’t directly saving lives, we believe that even the smallest contribution, whether it’s ensuring the accuracy of medical content or translating scientific research that could lead to a breakthrough, can make a meaningful difference. Through high-quality life sciences localisation and ethical translation practices, we aim to support a healthier, more compassionate world. 

What kind of impact does your work have? And how can we all contribute to projects that not only drive business but also make a positive social impact? 

Let’s keep the conversation going. 

References 

1. https://www.maddyness.com/2021/04/26/bandeau-dreem-sommeil-espace-thomas-pesquet/ 

Precisión médica en la era de la IA: Por qué el contexto sigue siendo fundamental 

En el mundo de la traducción médica impulsada por inteligencia artificial, el auge de la IA ha sido verdaderamente revolucionario. Las herramientas de traducción automática ofrecen hoy una velocidad, eficiencia de costes y escalabilidad sin precedentes. Para las empresas farmacéuticas y de tecnología médica globales, esto significa una salida al mercado más rápida, flujos de localización más fluidos y la capacidad de gestionar docenas de idiomas al mismo tiempo. 

Pero por poderosa que sea la IA, tiene un punto ciego importante: el contexto. 

El peligro oculto de las cadenas aisladas 

A pesar de sus capacidades, la traducción automática en el ámbito sanitario presenta una limitación crítica: a menudo carece de comprensión contextual. 

La comunicación médica no trata solo de palabras. Se trata de significado, matices y claridad cultural. Incluso un solo término mal ubicado puede tener consecuencias reales en un entorno de atención médica. La IA, por más entrenamiento lingüístico que tenga, a menudo no puede distinguir entre homónimos, comprender el tono o interpretar la intención sin un contexto claro. 

Durante el último año, varios clientes se han acercado a nosotros con contenidos generados por motores de traducción automática para sus aplicaciones médicas. En cada caso, el contenido original estaba compuesto por cadenas aisladas —términos de interfaz, etiquetas, botones y mensajes de error—, a menudo almacenados en hojas de cálculo o repositorios de código, completamente desconectados de su uso real. 

A primera vista, traducir estas cadenas parece una tarea rápida. Pero pronto identificamos problemas importantes. 

Tomemos la palabra “lead”. En una app, se usaba en el sentido cardiológico (derivaciones de ECG). Pero la IA, sin conocer esto, la tradujo como el verbo “liderar” o el sustantivo relacionado con el liderazgo. ¿El resultado? Gramaticalmente correcto, pero completamente erróneo —y potencialmente confuso en un contexto médico. 

Otro problema recurrente: el término “control”. En investigación clínica, puede referirse a un grupo de control. Pero cuando se presenta solo, la IA lo traduce como un verbo (“controlar”) o como un elemento de interfaz (como un botón), según su entrenamiento. Sin pistas contextuales, la precisión se desmorona. 

Por qué el contexto es esencial en la traducción médica asistida por IA 

En interfaces de usuario, aplicaciones para pacientes y herramientas digitales de salud, las cadenas aisladas son la norma —pero eso no significa que puedan traducirse a ciegas. Especialmente en salud, incluso una frase corta puede tener un significado crítico. Sin contexto adicional, incluso la IA mejor entrenada (¡y hasta un lingüista humano!) puede cometer errores. 

Los clientes suelen asumir que al proporcionar solo los archivos fuente, el trabajo está casi terminado. Pero en realidad, la calidad del resultado depende en gran medida de la entrada: metadatos, notas de uso, capturas de pantalla, archivos de referencia y aclaraciones sobre el tono o el público hacen una gran diferencia. 

¿Cómo prevenir estos errores? 

En Novalins, hemos creado procesos para afrontar este desafío: 

• Solicitamos notas contextuales para cadenas aisladas. 

• Fomentamos el uso de herramientas que permiten etiquetar cadenas, añadir capturas de pantalla o comentarios de desarrolladores. 

• Nuestros lingüistas médicos están entrenados para detectar ambigüedades desde el principio y fomentar el diálogo en lugar de asumir. 

• Recomendamos crear y aprobar glosarios con el cliente antes de comenzar el proyecto. 

• Pedimos material de referencia, como traducciones anteriores o maquetas de diseño, para entender mejor la función del contenido. 

• Sugerimos involucrar a alguien del equipo interno del cliente que pueda ofrecer comentarios en tiempo real dentro de nuestro sistema de gestión de traducciones (TMS), para resolver problemas durante el proyecto —no solo después de la entrega. 

• Y lo más importante, enfatizamos la comunicación constante entre el cliente y nuestro equipo de proyecto para garantizar una alineación completa de principio a fin. 

La colaboración hace posible la calidad 

Ya sea que uses IA para pretraducir contenido o confíes en un equipo humano desde el inicio, la conclusión es clara: el contexto debe compartirse. Un proveedor de servicios lingüísticos (LSP) capacitado puede guiar el proceso, optimizar la documentación de cadenas y garantizar que el contenido de tu aplicación sea seguro, preciso y conforme. 

Cuando se trabaja con traducción automática, la velocidad y el ahorro de costos son reales. Pero también lo son los riesgos. Los mejores resultados provienen de la colaboración —combinando automatización con revisión experta, y contexto rico con juicio lingüístico. 

En el mundo vertiginoso de la salud digital, donde cada palabra puede afectar una decisión del usuario o un resultado regulatorio, el contexto no es solo útil: es fundamental. 

Así que si estás preparando contenido para una app, no envíes solo las cadenas. Envía la historia detrás de ellas. 

Referencias 

1. Genovese A, Borna S, Gomez-Cabello CA, Haider SA, Prabha S, Forte AJ, Veenstra BR. Artificial intelligence in clinical settings: a systematic review of its role in language translation and interpretation. Ann Transl Med. 2024 Dec 24;12(6):117. doi: 10.21037/atm-24-162. Epub 2024 Dec 17. PMID: 39817236; PMCID: PMC11729812. 

2. Delfani, J., Orasan, C., Saadany, H., Temizoz, O., Taylor-Stilgoe, E., Kanojia, D., Braun, S., & Schouten, B. (2024). Google Translate error analysis for mental healthcare information: Evaluating accuracy, comprehensibility, and implications for multilingual healthcare communication (arXiv:2402.04023). arXiv. https://doi.org/10.48550/arXiv.2402.04023 

Medical accuracy in the age of AI: Why context still reigns supreme 

In the world of AI-powered medical translation, the rise of artificial intelligence has been nothing short of revolutionary. AI-powered translation tools now offer unprecedented speed, cost-efficiency, and scalability. For global pharmaceutical and MedTech companies, this means faster time-to-market, smoother localisation workflows, and the ability to manage dozens of languages simultaneously. 

But as powerful as AI is, it has one significant blind spot: context. 

The hidden danger of isolated strings 

Despite its capabilities, machine translation for healthcare has a critical limitation: it often lacks contextual understanding.  

Medical communication is not just about words. It’s about meaning, nuance, and cultural clarity. Even a single misplaced term can have significant consequences in a healthcare setting. AI, for all its linguistic training, often lacks the ability to distinguish between homonyms, understand tone, or interpret intent without clear context. 

Over the past year, we’ve had multiple clients approach us with content generated by AI translation engines for their medical apps. In each case, the source content was composed of isolated strings — interface terms, labels, buttons, and error messages — often stored in spreadsheets or code repositories, completely detached from their real-world usage. 

At first glance, translating these strings seems like a quick task. But we quickly identified major issues. 

Take the word “lead”. In one app, it was used in the cardiology sense (ECG leads). But AI, unaware of this, translated it as the verb “to lead” or the noun referring to leadership. The result? Grammatically correct, but completely wrong — and potentially confusing in a medical context. 

Another recurring issue: the term “control”. In clinical research, this might refer to a control group. But when presented alone, the AI rendered it as a verb (“to control”) or as a UI element (like a button), depending on its training. Without contextual cues, accuracy fell apart. 

Why context is essential in AI-assisted medical translation 

In user interfaces, patient apps, and digital health tools, isolated strings are the norm — but that doesn’t mean they can be translated blindly. Especially in healthcare, even a short phrase can carry critical meaning. Without additional context, even the best-trained AI (and even a human linguist!) can make the wrong call. 

Clients often assume that by providing source files alone, the job is 90% done. But in reality, the quality of the output depends largely on the input: metadata, usage notes, screenshots, reference files, and clarification about tone or audience all make a massive difference. 

How to prevent these errors? 

At Novalins, we’ve built processes to handle this challenge: 

• We request contextual notes for isolated strings. 

• We encourage the use of tools that allow string tagging, screenshots, or developer comments. 

• Our medical linguists are trained to flag ambiguities early in the process, prompting dialogue instead of assumptions. 

• We recommend creating and approving glossaries with the client before the project begins. 

• We ask for reference material, such as previous translations or design mockups, to better understand the content’s function. 

• We suggest involving someone from the client’s internal team who can provide live feedback during the project, directly within our TMS, to resolve issues in real time — not just after delivery. 

• And most importantly, we emphasize constant communication between the client and our project team to ensure full alignment from start to finish. 

Collaboration makes quality possible 

Whether you’re using AI to pre-translate content or relying on a human team from the start, the takeaway is clear: context must be shared. A skilled LSP can help guide the process, optimize string documentation, and ensure that your app content is safe, accurate, and compliant. 

When working with AI translation, speed and cost savings are real. But so are the risks. The best results come from collaboration — combining automation with expert review, and rich context with linguistic judgment. 

In the fast-paced world of digital health, where every word can impact a user decision or a regulatory outcome, context isn’t just helpful — it’s critical. 

So if you’re preparing app content, don’t just send the strings. Send the story behind them. 

References 

1.  Genovese A, Borna S, Gomez-Cabello CA, Haider SA, Prabha S, Forte AJ, Veenstra BR. Artificial intelligence in clinical settings: a systematic review of its role in language translation and interpretation. Ann Transl Med. 2024 Dec 24;12(6):117. doi: 10.21037/atm-24-162. Epub 2024 Dec 17. PMID: 39817236; PMCID: PMC11729812. 

2. Delfani, J., Orasan, C., Saadany, H., Temizoz, O., Taylor-Stilgoe, E., Kanojia, D., Braun, S., & Schouten, B. (2024). Google Translate error analysis for mental healthcare information: Evaluating accuracy, comprehensibility, and implications for multilingual healthcare communication (arXiv:2402.04023). arXiv. https://doi.org/10.48550/arXiv.2402.04023 

From human to AI to multilingual content validation: the evolution of the role of medical translation agencies 

The language services industry is undergoing a rapid transformation. Just a few years ago, most companies relied exclusively on human translation to ensure accuracy, nuance, and cultural relevance. Then came the rise of machine translation (MT), which brought dramatic gains in speed and scale—but also raised new challenges around quality and reliability. 

Today, we are witnessing the next stage in this evolution: the integration of artificial intelligence (AI) translation tools, and a growing shift toward multilingual content validation. This shift is especially visible in the medical and healthcare sectors, where accuracy is non-negotiable and new content needs to be rolled out fast, across dozens of languages. 

As artificial intelligence (AI) becomes central to translation workflows, companies are rethinking how they ensure quality—especially in the context of high-risk content.  

The rise of AI and in-house translation workflows 

More and more tech companies are internalizing their translation processes by leveraging AI tools. This gives them significant advantages: 

• Faster turnaround times, 
• Reduced costs, 
• Greater control over their multilingual content pipelines. 

However, AI translation—no matter how advanced—still lacks the contextual understanding and domain-specific expertise that is especially critical for healthcare translation accuracy in regulated industries like healthcare. 

To compensate for this, companies are building hybrid workflows:
AI translation is followed by in-house post-editing, and then by external validation from specialised medical linguists. This new model signals a shift in how companies view language service providers—not just as executors, but as expert validators and consultants. 

An example from our own experience: a wellness app with a new approach 

A recent case we encountered perfectly illustrates this shift. A large tech company preparing to launch a wellness app reached out to us. They needed to translate the app content into a wide range of languages to support a global rollout. 

Instead of sending their source files to a language service provider (LSP) as they might have in the past, they chose to do things differently. They used AI internally to generate the translations and handled the post-editing themselves. But when it came to validating the medical terminology and ensuring consistency with health-related standards, they turned to us—a specialized medical translation provider. 

Their goal was to ensure that the final content would be safe, compliant, and accurate, especially in terms of the medical guidance and terminology used throughout the app. Our role shifted from traditional translation to a more strategic one: validating their content and advising them on the linguistic quality control process. 

Why this matters: a glimpse into the future of medical translation 

This case is not an exception—it’s a glimpse into the future of medical translation. 

We expect to see more companies adopting this hybrid model: using AI and internal teams for speed and scale, while relying on external experts for quality assurance and validation, particularly for high-risk or specialised content. 

Why AI alone isn’t enough in healthcare translation becomes especially clear in this context. Multilingual content validation is the cornerstone of trust. It’s no longer just about getting words into another language—it’s about ensuring that those words convey the right meaning, in the right context, with full accuracy. Especially in healthcare, there’s no margin for error. 

Conclusion: quality needs collaboration 

If a company has the capability to manage machine translation and post-editing internally, that’s absolutely fine. But when it comes to medical content, relying solely on internal processes is risky. 

Specialised validation by expert medical translators is essential to ensure that the final content is not only safe, accurate, and compliant with medical standards, but also culturally appropriate. In the medical field, where communication can directly impact patient safety and treatment outcomes, it’s crucial to work with professionals who combine deep scientific and medical knowledge with a strong awareness of cultural nuances. Medical translators bring not just linguistic accuracy, but the ability to adapt terminology, tone, and context to local expectations — ensuring clarity, trust, and compliance across languages and cultures. 

What’s more, a trusted LSP can act as a strategic consultant, advising internal teams on the necessary quality steps to reach the highest possible output. 

Looking ahead, future trends in AI and medical language services point toward deeper integration of AI-driven tools with expert human validation. Automation may improve speed and scalability, but true quality still depends on the expertise of certified professionals who understand both the language and the science behind it. 

In the fast-paced world of multilingual communication, LSPs are no longer just translation providers—they are partners in quality, guardians of accuracy, and key players in the future of global healthcare communication. 

At Novalins, we support companies at every stage of this evolving process. As validation partners, we help ensure that medical translations are accurate, consistent, and aligned with the highest standards—because in healthcare, quality is never optional. 

References 

1. Noll R, Frischen LS, Boeker M, Storf H, Schaaf J. Machine translation of standardised medical terminology using natural language processing: A scoping review. N Biotechnol. 2023 Nov 25;77:120-129. doi: 10.1016/j.nbt.2023.08.004. Epub 2023 Aug 29. PMID: 37652265.