Intel and Penn Medicine announced results of the largest medical federated learning study to date, leveraging OpenFL, an open source framework for training machine learning algorithms. The project demonstrated the ability to improve brain tumor detection by 33%, a significant leap in accuracy that could save lives. But the real innovation wasn’t just the results, it was how they got there.

Penn Medicine and 71 international healthcare and research institutions used Intel’s federated learning technology to improve detection of rare cancer boundaries by 33% compared to an initial AI model trained using public data. The challenge in medical AI has always been data access. Patient privacy laws and ethical concerns mean life-saving algorithms can’t access the data they need. Federated learning changed the game by keeping raw data inside hospitals while allowing the algorithm to learn from it. Privacy preserved, accuracy improved.

This was the largest medical federated learning study to date, with an unprecedented global dataset from 71 institutions across six continents. My role was translating this incredibly complex technical and medical breakthrough into visual storytelling that made sense to multiple audiences, from healthcare professionals to tech journalists to investors. The infographics, presentation materials, and supporting visuals needed to communicate both the scale of the collaboration and the precision of the results without losing people in jargon or oversimplifying the science.

Always with intention. Never just life-saving tech buried in jargon.