Transformative AI: Unlocking the Future of Point-of-Care Ultrasound

Qure.ai has received a multimillion-dollar grant from the Gates Foundation to support the development of a large, open-source, multi-modal database aimed at advancing prevention and early identification innovations in lung health.

The initiative is aligned with WHO lung-health diagnostic pathways and is intended to enable researchers and innovators worldwide to develop, validate, and refine new artificial intelligence models.

The grant will support the aggregation of non-identifiable clinical history alongside diverse data modalities, including chest X-rays, thoracic ultrasound, high-resolution CT scans, cough and lung sound recordings, and laboratory or biological markers. By bringing these datasets together in an open-source framework, the project seeks to strengthen the evidence base for AI development across tuberculosis, pneumonia, and broader lung-health priorities, particularly in low- and middle-income countries.

As part of this effort, the funding will also allow Qure.ai to develop AI-enabled point-of-care ultrasound algorithms as a tool for the early detection of tuberculosis and pneumonia. These diseases remain among the leading causes of death globally, despite being curable when diagnosed early. Tuberculosis is associated with approximately 1.23 million deaths annually, while pneumonia causes an estimated 2 million deaths each year, including around 700,000 children under the age of five.

Qure.ai’s leadership emphasizes that the grant builds on more than a decade of experience deploying AI-enabled imaging technologies in resource-limited and remote settings. Previous efforts have demonstrated the potential of AI-supported diagnostics to reduce delays in tuberculosis diagnosis, including in settings without on-site clinicians. The current grant extends this work by focusing on data infrastructure and innovation that can support future advances in lung-health diagnostics.

The initiative brings together tuberculosis, pneumonia, and broader lung-health priorities with a stated focus on improving outcomes for children and underserved populations. By expanding access to high-quality, multimodal data and supporting AI innovation, the grant aims to address persistent diagnostic gaps and contribute to more equitable access to care globally.

Key Takeaways:

• What’s new? Grant accelerates targeted AI features for bedside ultrasound and related lung-health diagnostics.
• Who’s affected? Frontline and rural clinicians, emergency triage systems, and health systems planning procurement.
• What changes next? Expect field pilots, device firmware updates with embedded algorithms, and a need for local validation and training.