Arturo LoAlza-Bonilla, Co-Founder and Chief Medical Officer at Massive Bio, shared a post on LinkedIn:
“If we want AI to transform oncology clinical trials, we need to get two things right:
- How AI retrieves and generates clinical knowledge
- Whether that knowledge is transparent and verifiable in the first place
Two new papers in AI in Precision Oncology this month having the privilege to co-author with my amazing friend Nikhil Thaker, MD and collaborators tackle each side of that equation:
Retrieval-Augmented Generation in Oncology: Promises, Pitfalls, and Early Applications
RAG is quickly becoming the default architecture for clinical AI systems that need to stay current with evidence. But the gap between a demo and a deployable system is enormous. We review where RAG delivers real value in oncology, where it breaks down, and what the field needs to get right before scaling these systems into practice.
From Clinical Trials and Publications to Verifiable Evidence: Data Transparency as Artificial Intelligence-Ready Infrastructure for Oncology Trials
AI can only be as good as the data it reasons over. This paper argues that data transparency isn’t just a regulatory ideal – it’s a prerequisite for building AI systems that can reliably interpret, audit, and act on clinical trial evidence. Without it, we’re building on sand.
These two papers are complementary: one asks how we retrieve and generate knowledge, the other asks whether that knowledge is trustworthy in the first place. The AI conversation in oncology is maturing. We’re past ‘Can AI help?’ and into ‘What does it actually take to deploy it responsibly?’
Proud of this work and grateful to all co-authors.”
Title: From Clinical Trials and Publications to Verifiable Evidence: Data Transparency as Artificial Intelligence-Ready Infrastructure for Oncology Trials
Authors: Nikhil G, Arturo Bonilla, Chadi Nabhan
Read the full article on Sage Journals

Title: Retrieval-Augmented Generation in Oncology: Promises, Pitfalls, and Early Applications
Authors: Nikhil Thaker, Wei Liu, Mark Waddle, Timothy Showalter, Federico Mastroleo, Join Luh, Chad Levitt, Matthew Ning, Arturo Loaiza-Bonilla, Julian Hong
Read the full article on Sage Journals

Other articles featuring Arturo LoAlza-Bonilla on OncoDaily.