Giles AI delivers 95% accuracy in data extraction with Vertex AI and Gemini
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.
Overview
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.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
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.
The 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.
Reported 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.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other healthcare entries in the register.
Less paperwork, more time for people: Azure OpenAI at Landsberg Hospital
Klinikum Landsberg am Lech, a German acute-care hospital, deployed an AI language solution built on Azure OpenAI with partner Pexon Consulting that transcribes doctor-patient consultations in real time via tablet, recognizes medical terms, structures the content, and transfers it directly into the hospital information system.
Novo Nordisk builds AI drug discovery platform on Azure with Microsoft Research
Novo Nordisk partnered with Microsoft Research to build an AI platform on Azure AI and data stacks spanning regulatory affairs, early research, drug discovery and trial design, using Azure OpenAI Service, Azure Cosmos DB and Azure Kubernetes Service, with Power BI and Power Apps for collaboration. The platform includes a copilot for researchers, shared reasoning-chain templates, and governance/auditing of how data and models are used. The teams published early results on predictive AI models for cardiovascular disease risk detection, including an algorithm that Novo Nordisk says predicts patients' cardiovascular risk better than the best clinical standards, drawing on more than 100 years of insulin research data.
Novo Nordisk· DenmarkAzure OpenAI Service · Azure Cosmos DB · Azure Kubernetes Service +2BAYADA Builds a Unified, AI-Ready Platform for Compassionate Care
BAYADA Home Health Care is consolidating three separate legacy data platforms (multiple practice management systems, an on-prem ODS, and Snowflake) and 65+ enterprise data sources into a single Databricks Lakehouse under its Data Modernization program, using medallion tiers, Lakeflow Jobs, Asset Bundles, and Unity Catalog governance. As part of the migration, BAYADA uses an LLM-powered code converter and Databricks Assistant to automate SQL and stored-procedure translation, and applies a machine learning-based data mastering accelerator to create golden Client, Payor, Candidate, and Referrer records. BAYADA reports roughly 30% better workload performance and cost efficiency versus its prior Snowflake environment, and is laying a governed foundation for AI agents supporting payroll validation, compliance monitoring, and operational insights, separately from its roadmap for AI-assisted chart review and risk prediction.
BAYADA Home Health CareDatabricks SQL · Lakeflow Jobs · Unity Catalog +1
Heidi Health fine-tunes NVIDIA Parakeet/Nemotron ASR, cutting clinical transcription latency 75% and costs 64%
Heidi Health, which processes 2.4 million clinical consultations weekly across 110 languages, fine-tuned the open NVIDIA Parakeet V2 speech recognition model on 1,500 hours of curated clinical audio using the NVIDIA NeMo framework and 8x H100 GPUs, replacing its closed-source vendor ASR. The in-house Nemotron-based ASR stack cut end-to-end transcription latency from about 3.0 seconds to 0.7 seconds (75%+ improvement), reduced word error rate from 13% to 9.4%, and cut operating costs by 64% by eliminating per-minute API pricing, while giving Heidi full ownership of model weights for data sovereignty.
Was this helpful?
Your feedback helps us improve our use case database