Learn More
GP at hand Open in new tab

Artificial Intelligence

We're pioneering AI to make healthcare universally accessible and affordable.


Babylon is helping to solve an increasing range of healthcare challenges with artificial intelligence.

Our AI has been designed around a doctor’s brain to provide accessible healthcare for millions in the palm of their hands. It can understand and recognise the unique way that humans express their symptoms. Using this knowledge, combined with a patient’s medical history and current symptoms, it provides information on possible medical conditions and common treatments.

  • How our AI works

    A committed team of research scientists, engineers, doctors and epidemiologists are working together to develop and optimise Babylon's AI abilities. Much of the team’s work is on the development of cutting edge machine learning research; this is being driven through access to large volumes of data from the medical community, continual learning from our own users and through feedback from Babylon’s own experts.

  • The knowledge graph and user graph

    Babylon’s Knowledge Graph is one of the largest structured medical knowledge bases in the world. It captures human knowledge on modern medicine and is encoded for machines. We use this as the basis for Babylon’s intelligent components to speak to each other. The Knowledge Graph keeps track of the meaning behind medical terminology across different medical systems and different languages.

    While the Knowledge Graph provides the general knowledge about medicine, particular patient cases are kept in the User Graph. Coexistence of the Babylon Knowledge Graph and the User Graph allows for more discovery. We can match symptoms with information and outcomes, constantly improving the information we provide.

  • The inference engine

    Simply understanding how users express their symptoms and risk factors is not enough to provide information on possibly matching conditions. At the heart of Babylon’s AI is our inference engine, a powerful set of machine learning systems, capable of reasoning on a space of >100s of billions of combinations of symptoms, diseases and risk factors, per second, to help identify conditions which may match the information entered. The inference engine provides our AI with the ability to provide reasoning efficiently, at scale, to bring health information to millions.

  • Natural Language Processing (NLP)

    Our AI can’t provide information to patients if it can’t understand them, and patients won’t use our AI if they can’t understand it. To help bridge the gap, we use Natural Language Processing (NLP). NLP helps computers interpret, understand, and then use everyday human language and language patterns. It breaks both speech and text down into shorter components and interprets these more manageable blocks to understand what each individual component means and how it contributes to the overall meaning, linking the occurrence of medical terms to our Knowledge Graph. Through NLP our AI can transcribe consultations, summarise clinical records and chat with users in a more natural, human way.

  • Machine Learning research at Babylon

    Throughout the Babylon platform we use Machine Learning (ML) for a variety of tasks. In the inference engine we combine probabilistic models with deep learning techniques to speed up the inference process. In the Knowledge Graph we predict new relationships between medical concepts based on reading medical literature. In NLP we build language understanding models based on large-scale datasets of interactions with our users and data from the web. We use ML to teach our NLP system new languages.

    Babylon would not be feasible without the use of state of the art ML techniques, so we've invested significantly into building a world class research team in this field. Babylon is also keen to contribute back to the AI community through papers, blog posts, and by open sourcing some of our work for the benefit of all.

Babylon’s AI services provide health information only, and do not provide a diagnosis. The AI services respond to the information entered, and the information provided is based on risk factors and statistics, rather than a personalised assessment. The AI services are not a substitute for a doctor, and should not be used in a medical emergency.