Experts in Health AI
Delivering change
In collaboration with the AI Centre for Value Based Healthcare, we have built and deployed the software behind an innovative federated learning & deployment platform that transforms AI implementation and value delivery in healthcare. With numerous active clinical deployments and extensive practical expertise, Answer can expedite and enhance the outcomes of your AI deployment.
Our comprehensive range of services includes architecture design, source system integration, data harmonisation, cutting-edge AI model deployment, data and clinical governance, and ongoing support; all leveraging our deep and extensive domain experience as designers, builders, and integrators of AI solutions in healthcare.
The open AI platform for healthcare
We deliver a single, intelligent AI platform that allows healthcare providers to deploy AI models safely, effectively, and efficiently into clinical workflows without the installation of additional hardware and software. A comprehensive system, it encompasses administrative and clinical tasks as well as regulatory compliance. Our deployment engine and federated learning platforms are poised to make a significant impact on the field of healthcare, opening new avenues for the integration of AI applications into clinical pathways.
Incredible feedback
Marc Farr, East Kent Hospitals University NHS Foundation Trust
Clinical AI is the future of healthcare – AIDE will enable us to transition to healthcare where AI acts as a complementary tool for our clinicians.
Haris Shuaib, AI Centre for Value Based Healthcare
I am confident that with AIDE as an AI enterprise platform we can achieve AI transformation at scale.
The technology
Working with the AI Centre, Answer have architected and developed two platforms, AIDE and FLIP, which provide access to high-quality health data for the purpose of development and deployment of AI Technology. They will enable NHS trusts to test and deploy AI in clinical practice and share data in a way that is safe and secure.
As a key contributor to the Medical Open Network for AI (MONAI) we are creating tools that will drive innovation in healthcare and allow for the fundamental redesign of clinical pathways improving outcomes and reducing costs.
AI Deployment Engine (AIDE)
The AI Deployment Engine (AIDE), allows healthcare providers to deploy AI models safely, effectively, and efficiently by enabling the integration of AI models into clinical workflows.
AIDE accelerates the deployment of AI applications in hospital settings and is now deployed in 10 NHS Trusts, with tools to support NHS clinicians improve direct patient care in Breast, Prostate and Lung Cancer as well as Stroke and Coronary Artery Disease.
How it works
Deploying AI often involves installing separate hardware and bespoke connectivity for each algorithm. In comparison, AIDE provides a unified hardware and software solution that facilitates the deployment and use of any AI application. Through connection to a live stream of clinical data, clinicians can access real-time AI analysis within seconds.
How AIDE adds value
AIDE’s unified infrastructure allows multiple algorithms to run simultaneously through bespoke Application Programming Interfaces (APIs). This provides NHS Trusts with the capability to run multiple AI solutions on a single platform for day-to-day clinical care. AIDE lowers the barrier to deploying clinical AI allowing individual Trusts to speed up the AI transformation of patient pathways.
Federated Learning Interoperability Platform (FLIP)
The Federated Learning Interoperability Platform (FLIP) helps to link data from multiple NHS Trusts to enable AI at scale.
Our federated learning approach brings algorithms to the data within each NHS Trust’s secure enclave, without the need to share information outside the organisation or break local governance rules.
How it works
AI algorithms need to train on diverse clinical datasets from multiple sources to ensure the resulting model is both reliable and generalisable. Algorithmic models are sent to multiple Trusts and trained on local data before being securely combined to achieve consensus. The model is then applied within each secure enclave, where it learns from the data, is updated again, and the process repeated until an improved consensus model is created. To achieve convergence, the process of learning and combining is reiterated, until each locally applied model reaches the same conclusion, indicating that the model is generalizable and can be consistently applied.
How FLIP adds value
Our Federated Learning Interoperability Platform (FLIP) ensures a high level of fidelity in AI output models compared to traditional aggregative data strategies because the data it trains on does not need to be anonymized before use. FLIP also allows us to adhere to each Trust’s governance and data privacy regulations whilst ensuring that AI models are scalable.
Secure Enclaves
We are building dedicated secure data storage for processing and analysis within each Trust, a secure enclave within the firewall that keeps sensitive patient data inside the Trust. Data from across the Trusts’ patient records systems will be transferred into the secure enclave for curating and aggregation, unifying medical imaging and other electronic health data. The platform can process data from multiple sources and applies Natural Language Processing to make sense of unstructured data and extract data from semantic information. A secure enclave has been created at partner sites including King’s College Hospital Foundation Trust and Guy’s and St Thomas’ NHS Foundation Trust.
Federated learning
AI algorithms need to train on diverse clinical datasets from multiple sources to ensure the resulting model is both reliable and generalizable. Our federated learning approach brings AI algorithms to the data within each NHS Trust’s secure enclave, without needing to share information outside the secure firewall or break local governance rules. Algorithmic models are sent to multiple Trusts and trained on local data before being securely combined to achieve consensus.
Open source
One of the unique features of AIDE and FLIP is that they were designed by the community, for the community, and will be released as open-source solutions. Answer have also been a key contributor to the Medical Open Network for AI (MONAI), a set of open-source, freely available collaborative frameworks built for accelerating research and clinical collaboration in Medical Imaging.
Are you looking for a partner in the AI space?
We're here to help, reach out and let's have a conversation.