arxiv arXiv cs.CL · 15h ago · research

TrialGPT 2.0 improves clinical trial matching efficiency and access in multicenter evaluation

from English

The authors present TrialGPT 2.0, an AI-assisted clinical trial recommendation system designed for real-world deployment that assesses which trials warrant consideration based on patient needs and workflow priorities.

In retrospective multicenter cohorts of 288 cases, the system retrieved at least one clinician-recommended trial in its top 10 recommendations for approximately 91% of cases.
The system reduced clinician screening time by 55.0% in the retrospective evaluation.
In a six-month prospective evaluation within an active precision oncology tumor board, TrialGPT 2.0 expanded patient access to clinical trial participation by 90.9%.
The authors introduce NIH-TrialBench, a clinician-authored dataset comprising 126 diverse synthetic patient vignettes and matching scenarios from 11 NIH Institutes and Centers.

These results support the value of AI in assisting clinical trial matching by improving clinician efficiency and identifying frequently overlooked trial opportunities to accelerate accrual.

Importance 2/3 New harness with differentiators arXiv cs.CL Retrieval & RAG Training data

Related articles

arxiv arXiv cs.CL · 52d ago

Study evaluates NLP approaches for extracting keywords from crowdsourced collections

A project using the University of Oxford's "Their Finest Hour Online Archive" evaluated three Natural Language Processing approaches—Named Entity Recognition, Keyword Extraction, and Topic Modelling—to automate keyword extraction at scale. The study tested these methods across techniques ranging from traditional statistical models to modern generative AI neural networks.

arxiv arXiv cs.CL · 57d ago

Automated extraction of Italian tax-court judgments with citation-hallucination control

The authors present an automated pipeline that decomposes approximately 330,000 Italian tax-court judgments into individual legal issues and extracts structured XML representations grounded in the IRAC framework. The system uses DeepSeek V3 for cost-efficient processing and couples extraction with a hallucination-detection filter that compares model-generated references against those identified by the Linkoln parser.

media Hugging Face Forums · 62d ago · 1 view

How to publish my research in HuggingFace?

A user on the Hugging Face forum seeks guidance on how to properly publish their research project, TIS (Token Importance Scoring), along with its associated code and documentation.

lab OpenAI News · 1d ago · 3 views

OpenAI adds Epic EHR integration and Healthcare Public Data plugin to ChatGPT

OpenAI has introduced a new integration allowing healthcare organizations to connect authorized patient context from Epic electronic health records into ChatGPT for Healthcare, alongside a Healthcare Public Data plugin providing structured access to official datasets.

media Hugging Face Forums · 2d ago · 3 views

HF Agent OS: multi-agent system for Hugging Face Hub lifecycle

A new project called HF Agent OS provides a multi-agent platform for managing the full Hugging Face Hub lifecycle through natural language. Built on smolagents, it utilizes a Planner and Orchestrator to route requests to specialized sub-agents for datasets, models, and deployments.