👉This Drug Was Designed by AI—and It Works: Issue # 57

In partnership with

AIHealthTech Insider: Issue #57

July 14, 2025

This week, AI doesn’t just assist—it leads. From Google’s open-source MedGemma models fueling global health innovation to Johns Hopkins' robot matching human surgeons in real surgery, we’re witnessing the future of medicine unfold. Plus: an AI-discovered lung drug enters human trials, Merck and UCLA reimagine medical data access. Let’s dive into what’s shaping AI-powered healthcare this week.

Google’s Open-Source MedGemma AI Models Empower Healthcare Developers

Google announced the release of MedGemma 27B Multimodal and MedSigLIP, two open-source AI models designed for healthcare applications. Unlike proprietary systems, these models are freely available to developers, enabling advancements in diagnostics, medical imaging, and personalized care.

By democratizing access to cutting-edge AI, Google is accelerating innovation in digital health, particularly for resource-constrained providers.

Source 👉: MedGemma Technical Report

AI Surgical Robot Matches Human Surgeons in Realistic Trial

The SRT-H robot, developed at Johns Hopkins, has autonomously performed a full phase of gallbladder surgery on a lifelike patient, without human hands-on controls. Trained using surgical videos and guided by voice commands, it responded to changes in anatomy and unexpected challenges with expert precision.

Powered by the same architecture behind ChatGPT, SRT-H uses language-conditioned imitation learning to understand and adapt during procedures. The success marks a major step toward fully autonomous surgery where robots don’t just follow steps, they perform like surgeons.

Source 👉: Robot performs first realistic surgery without human help | Hub

AI-Discovered Drug for Lung Disease Shows Promise in Human Trials

Rentosertib (formerly ISM001-055), the first AI-generated TNIK inhibitor, has entered and successfully completed a Phase 2a randomized trial for idiopathic pulmonary fibrosis (IPF). This marks one of the earliest generative AI-designed drugs to advance to human testing.

The study showed Rentosertib was safe, well tolerated, and improved lung function in patients with this incurable condition signaling a major leap for AI in drug discovery and development.

Source 👉: A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial | Nature Medicine

FROM THE RUNDOWN AI

Stay up-to-date with AI

The Rundown is the most trusted AI newsletter in the world, with 1,000,000+ readers and exclusive interviews with AI leaders like Mark Zuckerberg, Demis Hassibis, Mustafa Suleyman, and more.

Their expert research team spends all day learning what’s new in AI and talking with industry experts, then distills the most important developments into one free email every morning.

Plus, complete the quiz after signing up and they’ll recommend the best AI tools, guides, and courses – tailored to your needs.

Sign up to start learning.

Merck Manuals Unveils AI-Powered Search Tool for Faster, Trusted Medical Answers

Merck Manuals has unveiled an AI-powered search tool that helps users quickly access reliable medical information powered by Google Cloud’s Vertex AI Search and trained on decades of expert-reviewed content.

By integrating AI into its global health platform, Merck is bridging technology and trust—offering users accurate, readable answers to health questions like “how to treat a bee sting” or “signs of COVID,” in multiple languages.

Source 👉:Merck Manuals Launches AI-powered Search Tool, Providing Enhanced Access to Trusted Medical Information and Resources

UCLA Health Builds AI to Make EHRs Easier to Read

UCLA Health has created a new AI model that transforms complex electronic health record (EHR) data into easy-to-read clinical-style text, improving emergency care decisions and AI usability in hospitals.

The Multimodal Embedding Model converts tabular EHR data into “pseudonotes,” allowing advanced language models and clinicians to better interpret patient records. More adaptable than traditional AI systems, the tool could be a game-changer for hospitals using varied data formats.

Source 👉: Clinical decision support using pseudo-notes from multiple streams of EHR data | npj Digital Medicine

Just for Fun: What Kind of AI Health Hero Are You?

Take this quiz to find out how you'd survive in the AI-powered healthcare future.

Stay Ahead: AI Healthcare News!

This is just a glimpse of the AI healthcare revolution. Subscribe for exclusive updates on medicine’s future!