Using AI to give doctors a 48-hour head start on life-threatening illness
In this research, we demonstrated how artificial intelligence could accurately predict Acute Kidney Injuries in patients up to 48 hours earlier than it is currently diagnosed. Learn more.
A promising step forward for predicting lung cancer
This research showed how artificial intelligence was used to detect 5% more cancer cases while reducing false-positive exams by more than 11% compared to unassisted radiologists. Learn more.
Using AI to help doctors address eye disease
Our research on Automated Retinal Disease Assessment (ARDA) showed how an AI algorithm is helping doctors to quickly spot diabetic retinopathy. Our research on optical coherence tomography (OCT) scans shows that our AI system can quickly interpret eye scans from routine clinical practice and correctly recommend how patients should be referred for treatment for over 50 sight-threatening eye diseases as accurately as world-leading expert doctors. Learn more about ARDA and OCT.
Deep learning for electronic health records
In this research, we showed how a deep learning model could be used to render an accurate prediction 24 hours after a patient was admitted to the hospital. Learn more.
Applying artificial intelligence to breast cancer detection
In our mammography research, we showed how our AI model identified breast cancer in de-identified screening mammograms with greater accuracy, fewer false positives, and fewer false negatives than experts. In our pathology research, we showed how a proof-of-concept assistance tool (LYNA) could use deep learning to help pathologists more accurately diagnose metastatic breast cancer. Learn more about LYNA and Mammography.
Highly accurate genomes with deep neural networks
Our genomics research and open source release of DeepVariant transformed the task of variant calling into an image classification problem, reducing the error rate by more than 50%. Learn more.