We are working to create new machine learning tools and discover opportunities to increase the availability and accuracy of healthcare globally.
About the team
Transformative healthcare technologies build upon translational research to realize long-term potential. Google Health embraces a model of embedded research and development where scientists work in tight integration with clinical, product, and engineering teams, collaborating with academic and clinical partners globally to conduct research into improving healthcare. Read about some of our recent efforts on the Google AI blog and Google Keyword blog.
Team focus summaries
Imaging and diagnostics
In partnership with healthcare organizations globally, we’re working to develop robust new ML-enabled tools designed to assist clinicians. Drawing from diverse datasets, high-quality labels, and state-of-the-art deep learning techniques, we hope to translate the promise of ML into better and more equitable care.
Sequencing genomes enables clinicians to identify variants in a person’s DNA that indicate genetic disorders such as an elevated risk for breast cancer. DeepVariant is an open-source variant caller that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
We are developing tools and resources for the broader public health community, epidemiologists, analysts and researchers working to understand and address the impacts of COVID-19 and other public health needs.
Publishing our work allows us to share ideas and work collaboratively to advance healthcare. This is a comprehensive view of our publications and associated blog posts.
We are exploring computer-aided diagnostic screening for diabetic retinopathy, one of the fastest growing causes of preventable vision loss globally, as in much of the world, there simply are not enough doctors available to support the volume of screening required for the population.
Our team is working with researchers in mammography and pathology to develop ML that might one day assist clinicians in screening and diagnosing breast cancer.
We are using deep learning models to make a broad set of predictions relevant to hospitalized patients using de-identified electronic health records and discovering how models can be used to render accurate predictions.
We develop models for understanding medical speech and conversations and make them available publicly via Google Speech APIs. We are also developing next generation tools for recognizing symptoms of speech disorders from medical audio.