About the Customer
Eolas Medical is a leading healthcare technology company dedicated to streamlining access to medical knowledge right at the point of care. Founded by Dr. Declan Kelly, an emergency medicine physician by background, Eolas translates to “knowledge” or “information” in Irish, reflecting the company’s mission to empower clinicians with rapid, reliable access to clinical guidelines, policies, and standard operating procedures. Today, the Eolas platform is utilized by over 400 medical centers worldwide, including renowned institutions such as Stanford Hospital, Massachusetts General Hospital, and more than 80% of all acute hospitals within the UK’s National Health Service (NHS).
Customer Challenge
Clinicians at major hospitals face a persistent challenge: efficiently locating critical information within the vast repositories of clinical guidelines and documents available on their platforms. For example, a physician searching for guidance on outpatient management of a pulmonary embolism must not only know that a specific diagram exists within a guideline, but also manually scroll through lengthy documents to find it. This process is time-consuming and prone to oversight, especially when important information is embedded in diagrams, tables, or text boxes rather than plain text.
The inability to quickly access and validate clinical information at the point of care introduces significant risks:
- Patient care delays are due to the time spent searching for answers.
- Increased likelihood of error if visual or tabular data is overlooked.
- Reduced trust in digital tools if answers cannot be reliably traced back to their original source.
If left unaddressed, these challenges could compromise patient safety and limit the effectiveness of digital knowledge management systems in clinical settings.
LandingAI Solution
To address these challenges, LandingAI partnered with Eolas Medical to integrate its Agentic Document Extraction (ADE) API into the Eolas platform, leveraging the scalability and reliability of AWS infrastructure. The solution begins with intelligent indexing of all clinical documents. Using layout-aware parsing and visual grounding, ADE extracts and tags text, diagrams, tables, and visual elements using LandingAI’s proprietary foundation models running on AWS GPUs, and a mix of LLMs.
When a clinician queries the Eolas’ platform (e.g., “When should I consider outpatient management of a pulmonary embolism?”), the system uses a Retrieval-Augmented Generation (RAG) architecture. Then it does a vector-based retrieval, identifying relevant guidelines. The enriched content feeds into generative AI models, which synthesize concise answers. Pinpoint sourcing by ADE includes references to original diagrams/tables, with clinicians able to verify sources directly.
A key innovation is the pinpoint sourcing enabled by ADE. Every answer generated by the system includes direct references to the specific diagrams, tables, or sections from which the information was derived. Clinicians can click on these references to view the original source, providing transparency and building trust in the AI-generated answers.
The entire solution was deployed without the need for custom training or data collection, making it both scalable and easy to implement across Eolas’s diverse client base.
Results and Benefits
The integration of LandingAI’s ADE API has transformed the way clinicians access and interact with clinical knowledge on the Eolas platform. Information retrieval is now significantly faster, with clinicians able to find precise answers in seconds—a 90% improvement over previous manual search times. Every answer is accompanied by clear, clickable references to the original source, whether it be a diagram, table, or section of a guideline.
This level of transparency has led to a dramatic increase in clinician confidence, with a 78% rise in trust reported during deployments. The platform’s ability to accurately pinpoint and reference visual elements has also reduced the risk of oversight and error, directly supporting safer, more efficient patient care.
Key metrics include:
- 90% reduction in time spent searching for clinical information
- 100% source attribution for all answers
- 78% increase in clinician confidence and trust in digital tools
- 87% of clinicians stated that a healthcare-specific engine like Ask Eolas is superior to general AI tools like ChatGPT
- Zero configuration required for deployment across 400+ sites
About LandingAI
LandingAI is an AWS Partner, specializing in AI-powered solutions for processing images and documents. The company’s Agentic Document Extraction API enables organizations to convert complex, unstructured documents into structured, LLM-ready data at scale, leveraging the robust and secure infrastructure of AWS. LandingAI’s solutions are trusted by enterprises across industries to drive efficiency, accuracy, and innovation in document-intensive workflows.
