Health AI
AI has the potential to accelerate innovation and unlock new solutions to global health challenges, to help billions of people live longer, healthier lives.
AI has the potential to accelerate innovation and unlock new solutions to global health challenges, to help billions of people live longer, healthier lives.
Addressing critical healthcare challenges
From genomics and diagnostics to public health, we’re advancing AI research to address real-world healthcare challenges. Today’s powerful models and tools have the potential to make healthcare more personalized, diseases more detectable and treatable, and public health ecosystems more resilient.
Partnering with the ecosystem
We collaborate with world-class academic and scientific institutions, along with healthcare providers, to research cutting-edge AI solutions responsibly and ensure that our innovations are safe and helpful in clinical settings.
-
Conversational AI for clinicians and patientsAMIE (Articulate Medical Intelligence Explorer) is a research-grade AI system with diagnostic reasoning. It’s designed to act as a conversational partner capable of conducting complex medical interviews and clinical history-taking.
-
AI for cancer diagnosisEarly breast cancer detection can save lives. Our experimental research with Imperial College London and the UK’s National Health Service demonstrates AI’s potential to detect 25% of the interval cancers previously missed, and reduce radiologists’ workloads.
-
AI building blocks for developersOur Health AI Developer Foundations (HAI-DEF), including our open MedGemma models, provide a launchpad for developers to build and fine-tune AI-enabled, next generation healthcare applications.
-
Google Earth AI for public healthWe’re harnessing our advanced geospatial models to provide insights on population behaviors and environmental factors. This can empower the global public health community to predict outbreaks, identify local vulnerabilities, and deliver proactive care where it’s needed most.
-
Genomics research powered by AIOur deep learning tools in genomics are routinely run by scientists worldwide to accelerate scientific discovery and healthcare. Tools like DeepSomatic, DeepVariant, and DeepConsensus help the genomics community get the most out of their data.
Publications
Groundsource: A dataset of Flood Events from News
Rotem Mayo, Oleg Zlydenko, Moral Bootbool, Shmuel Fronman, Oren Gilon, Avinatan Hassidim, Frederik Kratzert, Gila Loike, Yossi Matias, Yonatan Nakar, Grey Nearing, Reuven Sayag, Amitay Sicherman, Ido Zemach, Deborah Cohen (2026)
AI learns to forecast global flood events from historical news
Oleg Zlydenko, Hadas Fester, Shmuel Fronman, Martin Gauch, Oren Gilon, Avinatan Hassidim, Gila Loike, Yossi Matias, Rotem Mayo, Grey Nearing, Aviel Niego, Reuven Sayag, Shruti Verma, Ido Zemach, Deborah Cohen (2026)
Efficacy of Scalable Airline-led Contrail Avoidance
Tharun Sankar, Thomas Dean, Tristan Abbott, Jill Blickstein, Alejandra Martín Frías, Mark Galyen, Rebecca Grenham, Paul Hodgson, Kevin McCloskey, Alan Pechman, Tyler Robarge, Dinesh Sanekommu, Aaron Sarna, Aaron Sonabend-W, Marc Stettler, Raimund Zopp, Scott Geraedts (2026)
An Operational Deep Learning System for Satellite-Based High-Resolution Global Nowcasting
Shreya Agrawal, Mohammed Alewi Hassen, Emmanuel Asiedu Brempong, Boris Babenko, Fred Zyda, Olivia Graham, Di Li, Samier Merchant, Santiago Hincapie Potes, Tyler Russell, Danny Cheresnick, Aditya Prakash Kakkirala, Stephan Rasp, Avinatan Hassidim, Yossi Matias, Nal Kalchbrenner, Pramod Gupta, Jason Hickey, Aaron Bell (2025)
Estimating high-resolution albedo for urban applications
David Fork, Elizabeth Jane Wesley, Salil Banerjee, Vishal Batchu, Aniruddh Chennapragada, Kevin Crossan, Bryce Cronkite-Ratcliff, Ellie Delich, Tristan Goulden, Mansi Kansal, Jonas Kemp, Eric Mackres, Yael Mayer, Becca Milman, John C. Platt, Shruthi Prabhakara, Gautam Prasad, Shravya Shetty, Charlotte Stanton, Wayne Sun, Lucy R. Hutyra (2025)
