TrialMatch: Why Precision Matters When Lives Are on the Line
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built A few months ago, a friend’s aunt was diagnosed with advanced non-small cell lung cancer. First-line platinum chemotherapy had stopped working. The oncologist said something that stuck with me: "Our best shot right now is an experimental targeted trial. Go home, search ClinicalTrials.gov,…
A woman in her late fifties with advanced non-small cell lung cancer faced a dire situation when her chemotherapy stopped working. Her oncologist suggested an experimental targeted trial, urging her to search ClinicalTrials.gov for potential options. The registry contained over 450,000 studies written in dense clinical language, making it overwhelming for laypeople to navigate.
AI tools were tested on the patient's pathology summary, with one returning fabricated clinical trial identifiers, highlighting the risk of relying on unstructured prompts. A standard keyword search yielded 69 relevant trials, but 31 were disqualified due to prior systemic chemotherapy restrictions. This led to the development of TrialMatch, an open-source clinical trial discovery and safety verification agent.
TrialMatch utilizes Sanity Context MCP and deterministic GROQ queries to anchor the agent to a structured content lake, ensuring accurate trial selection based on strict Boolean rules, exact allele variants, and line-of-therapy sequences. The web application allows users to input patient profiles or select pre-configured clinical presets, comparing the results of TrialMatch against traditional keyword searches. This comparison highlights the critical importance of precision when lives are on the line.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
