Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
Giles AI delivers 95% accuracy in data extraction with Vertex AI and Gemini
…extraction with Vertex AI and Gemini Get started for free Google Cloud Results 95% accuracy in medical research data extraction 85% reduction in time required for clinical research tasks Full healthcare comp…
Description
London-based Giles AI built its giles research assistant on Google Cloud's Vertex AI and Gemini, using Document AI to parse medical literature, achieving 95% accuracy in data extraction, an 85% reduction in time required for clinical research tasks, and a 98% agreement rate between the AI and human researchers.
…illions of complex documents with the accuracy the healthcare industry demands. By using Document AI to parse unstructured data, combined with the reasoning capabilities of Gemini Pro , giles® has achieved a 95% accuracy rate in data extraction. Importantly, if t…
…for free Google Cloud Results 95% accuracy in medical research data extraction 85% reduction in time required for clinical research tasks Full healthcare compliance out of the box with Google Cloud Giles AI uses the i…
Company
Giles AI
…p us build a platform capable of transforming data into life-saving knowledge." Giles AI is a London-based AI research assistant that helps healthcare organizations quickly extract and summarize key data from fragmented literature, accelerating evidence generation. Industry: Healthcare and Life Sciences Locat…
Country
United Kingdom
…ature, accelerating evidence generation. Industry: Healthcare and Life Sciences Location: UK Products: Google Cloud , Cloud Run , Document AI , Gemini , Gemini Live , Gemin…
Industry
Healthcare
…ummarize key data from fragmented literature, accelerating evidence generation. Industry: Healthcare and Life Sciences Location: UK Products: Google Cloud , Cloud Run , Document AI , Gemini , Gemini…
Problem
Bringing a new drug to market takes 10-12 years, a third spent on research, with scientists forced to trawl through over 40 million PubMed articles to find insights; healthcare professionals also distrust large language models that hallucinate answers, and Giles AI's prior multi-cloud, third-party-model architecture made healthcare compliance like HIPAA and SOC2 harder to achieve.
…an inaccurate one can have potentially life-changing consequences for patients. The healthcare industry is, therefore, wary of certain large language models hallucinating responses when they can't find the correct information. Initially built using third-party AI models, Giles AI wanted to overcome this t…
Solution
Giles AI migrated to Google Cloud with partner Insight managing the infrastructure landing platform, and built its giles® research assistant on Vertex AI and Gemini, using Document AI to parse unstructured medical literature and Gemini Pro's reasoning to extract and summarize data, admitting when data isn't available rather than hallucinating, with Model Garden letting the team swap in models like Gemma for clients needing data residency, and GKE/Cloud Run reducing latency for features like text-to-speech.
…rse unstructured data, combined with the reasoning capabilities of Gemini Pro , giles® has achieved a 95% accuracy rate in data extraction. Importantly, if the data isn't available, the AI admits this, rather than simp…
Business value
Giles AI achieves 95% accuracy in medical research data extraction, a 98% agreement rate between its AI and human researchers, and one customer saw an 85% reduction in time required for clinical research tasks; the company is also exploring multimodal features (Gemini Live, MedGemma, TxGemma) to expand into image analysis and real-time meeting insights.
…build trust with medical professionals and ensure the integrity of their work. Thanks to Google Cloud, one customer achieved an 85% reduction in the time required for clinical research. The combination of Document AI and Gemini has also led to a 98% agreement rate…
AI capabilities
Document Intelligence, Generative AI
…illions of complex documents with the accuracy the healthcare industry demands. By using Document AI to parse unstructured data, combined with the reasoning capabilities of Gemini Pro , giles® has achieved a 95% accuracy rate in data extraction. Importantly, if t…
Technology
Vertex AI, Gemini, Gemini Pro, Document AI, Model Garden on Vertex AI, Gemma, Google Kubernetes Engine (GKE), Cloud Run
…rating evidence generation. Industry: Healthcare and Life Sciences Location: UK Products: Google Cloud , Cloud Run , Document AI , Gemini , Gemini Live , Gemini Pro , Gemma , Google Cloud Marketplace , Google Kubernetes Engine (GKE) , MedGemma , Model Garden on Vertex AI , TxGemma , Vertex AI About Google Cloud partner - Insight SADA , an Insight company, helps organizat…
Deployment model
cloud
…s dependability as a robust engine for accelerating scientific decision-making. At the heart of this transformation are Vertex AI and Gemini , which allow the platform to ingest, parse, and analyze millions of complex do…
Headline outcome
…extraction with Vertex AI and Gemini Get started for free Google Cloud Results 95% accuracy in medical research data extraction 85% reduction in time required for clinical research tasks Full healthcare comp…
Use case type
Document processing
…illions of complex documents with the accuracy the healthcare industry demands. By using Document AI to parse unstructured data, combined with the reasoning capabilities of Gemini Pro , giles® has achieved a 95% accuracy rate in data extraction. Importantly, if t…
