April 21st 2025

Author

Max Gray
April 21, 2025

The Daily Innovation Newsletter

Enjoying this newsletter? Know someone who would too? Forward this email to them!

April 21st 2025

💻 Technology

A team from Shanghai Jiao Tong University has created a wearable AI device that helps blind and visually impaired individuals navigate independently by combining real-time visual analysis with audio and tactile feedback. Published in Nature Machine Intelligence, the system uses a camera and AI to detect obstacles and guide users through bone-conduction audio and vibrating wrist patches. Early trials showed significant improvements in obstacle avoidance, offering a promising, non-invasive tool to enhance mobility and independence for millions with vision loss.

Researchers at Ohio State University have created wearable smart insoles that monitor walking, running, and standing in real time to help detect conditions like plantar fasciitis and Parkinson’s disease. Powered by shoe-mounted solar panels and embedded with 22 pressure sensors, the device transmits gait data via Bluetooth and uses AI to classify motion and identify abnormalities. Published in Science Advances, the system’s durability and precision make it a promising tool for posture correction, injury prevention, and personalized health monitoring.

🌎 Sustainability

British researchers have launched SeaCURE, a pilot project on England’s south coast that uses solar-powered technology to remove carbon dioxide from seawater, allowing the ocean to absorb more CO₂ from the air. The process involves extracting CO₂ using acidity changes and renewable energy, then restoring seawater balance before returning it to the sea. Backed by £3 million from the UK government and published findings, the project could eventually scale to remove up to 14 billion tons of CO₂ annually—offering a promising solution for climate mitigation.

💊 Healthcare

Researchers at EPFL have developed a soft, flexible auditory brainstem implant (ABI) that conforms to the brainstem's curved surface, providing high-resolution hearing without the side effects of rigid implants. Tested successfully in macaques and published in Nature, the thin-film device uses micrometer-scale platinum electrodes in silicone to improve signal precision and reduce unwanted nerve activation. This breakthrough offers new hope for patients with damaged cochlear nerves who cannot benefit from cochlear implants.

A study led by the Whole Health Oncology Institute used AI to analyze over 10,000 scientific papers, finding that cannabis is widely supported as both a symptom-relief aid and potential anticancer agent. Published in Frontiers in Oncology, the meta-analysis showed that studies were over 30 times more likely to favor cannabis than oppose it, especially for reducing pain, nausea, and possibly inhibiting tumor growth. This large-scale review offers a powerful data-driven case for rethinking cannabis in medical oncology.

Scientists at Children’s Hospital of Philadelphia and Penn Medicine have used a deep learning algorithm called PRINT to identify potential disease-causing mutations in the noncoding regions of the human genome. These regions, which do not produce proteins but regulate gene expression, have been difficult to study until now. Published in The American Journal of Human Genetics, the method accurately detects DNA-protein binding "footprints" that can pinpoint which noncoding variants may contribute to diseases, offering new avenues for diagnosis and treatment.

That’s all for today, please reply to this email if you have any comments or feedback, we’d love to hear from you about what we can do better!

Have you enjoyed this email? Make sure to share it with your friends and colleagues.

See you soon,

Max