What happened
Google Research and Google for Health have developed AI-based tools to interpret chest radiographs (CXRs) with the accuracy of an expert radiologist for TB screening. They have partnered with Nexus AI to translate their chest X-ray algorithms into a certified clinical diagnostic tool. The tool is being deployed in approximately 40 healthcare facilities across six countries, reducing turnaround times from weeks to under 45 seconds. The collaboration has also led to the development of open, adaptable foundations that allow developers and health ministries to create solutions tailored to local needs.
Google Research and Google for Health have developed AI-based tools to interpret chest radiographs (CXRs) with the accuracy of an expert radiologist for TB screening.
They have partnered with Nexus AI to translate their chest X-ray algorithms into a certified clinical diagnostic tool.
The tool is being deployed in approximately 40 healthcare facilities across six countries, reducing turnaround times from weeks to under 45 seconds.
The collaboration has also led to the development of open, adaptable foundations that allow developers and health ministries to create solutions tailored to local needs.
The open foundations include MedGemma, a family of open- multimodal models, and MedSigLIP, a lightweight vision-language model trained to align medical images with clinical language.
Source details: research.google ↗
Why it matters
The development of AI-based tools for TB screening has the potential to democratize access to healthcare, particularly in high-burden settings where radiologists are scarce. The open, adaptable foundations developed by Google Research and Google for Health can help enable public health systems to build sovereign solutions that protect patient privacy.
The development of AI-based tools for TB screening has the potential to democratize access to healthcare, particularly in high-burden settings where radiologists are scarce.
The open, adaptable foundations developed by Google Research and Google for Health can help enable public health systems to build sovereign solutions that protect patient privacy.
The collaboration has also led to the development of Health Acoustic Representations (HeAR), a non-invasive acoustic screening tool that enables communities to screen for TB using cough sounds recorded on a standard smartphone microphone.
The deployment of AI-based tools for TB screening in high-burden settings has the potential to reduce the number of undiagnosed cases and improve treatment outcomes.
The development of open, adaptable foundations can help enable public health systems to build sovereign solutions that protect patient privacy and meet local needs.
Interactive Mechanism: How It Actually Works
Explore the underlying technology behind this development interactively.
A route planner searches possible journeys using explicit rules. What does this illustrate about AI?
What to watch next
The deployment of AI-based tools for TB screening in high-burden settings, the development of open, adaptable foundations, and the potential for public health systems to build sovereign solutions that protect patient privacy.
The deployment of AI-based tools for TB screening in high-burden settings.
The development of open, adaptable foundations that allow developers and health ministries to create solutions tailored to local needs.
The potential for public health systems to build sovereign solutions that protect patient privacy.
The development of Health Acoustic Representations (HeAR), a non-invasive acoustic screening tool.
The collaboration between Google Research and Google for Health, Nexus AI, and other partners to develop and deploy AI-based tools for TB screening.