Diagnosing cancer at an early stage increases the chance of performing effective treatment in many tumour groups. Key approaches include screening patients who are at risk but have no symptoms, and rapidly and appropriately investigating those who do. Machine learning, whereby computers learn complex data patterns to make predictions, has the potential to revolutionise early cancer diagnosis. Here, we provide an overview of how such algorithms can assist doctors through analyses of routine health records, medical images, biopsy samples and blood tests to improve risk stratification and early diagnosis. Such tools will be increasingly utilised in the coming years.
Chinese scientists have unveiled a groundbreaking bio-adhesive, popularly known as “Bone-02,” that can bond fractured bones within just three minutes. This innovation was inspired by the adhesive properties of oysters, which can attach firmly to wet surfaces, a concept now translated into medical science.
Unlike traditional implants such as metal plates or screws, the new bone glue is completely bioabsorbable. As the bone naturally heals, the adhesive is gradually absorbed by the body, effectively eliminating the need for secondary surgery to remove any hardware.
Reports from early clinical trials indicate that the glue provides an impressive bonding strength exceeding 400 pounds (around 180 kg) and achieves stable fixation even in wet, blood-rich surgical environments. This could revolutionize the way fractures are treated in orthopedic surgery.
Researchers have developed a way to predict how lung cancer cells will respond to different therapies, allowing people with the most common form of lung cancer to receive more effective individualized treatment.
The research, published Oct. 10 in Nature Genetics, was led by Thazin Aung, Ph.D., in the laboratory of Yale School of Medicine’s David Rimm, MD, Ph.D., in collaboration with scientists at the Frazer Institute at the University of Queensland. Researchers studied the tumors of 234 patients with non-small cell lung cancer (NSCLC) across three cohorts in Australia, the United States, and Europe.
“Using AI and spatial biology, we mapped NSCLC, cell-by-cell, to understand and predict its response to drug treatment,” Aung says. “This ‘Google Maps’ approach can pinpoint areas within tumors that are both responsive and resistant to therapies, which will be a gamechanger for lung cancer treatment. Rather than having to use a trial-and-error approach, oncologists will now know which treatments are most likely to work with new precision medicine tools.”
In a monumental leap for healthcare innovation, China has opened the world’s first fully AI-powered hospital, staffed by 14 artificial intelligence “doctors” capable of diagnosing, treating, and managing up to 10,000 virtual patients per day.
This revolutionary facility, developed by Tsinghua University, is called the Smart Hospital of the Future — and it may represent the most advanced experiment in AI-driven medicine the world has ever seen.
Designed as a testbed for AI medical systems, the hospital blends robotics, machine learning, natural language processing, and big data analytics to simulate full-spectrum care at lightning speed — with zero fatigue, no paperwork errors, and real-time updates from global medical databases.
USC engineers have developed an optical system that routes light autonomously using thermodynamic principles. Rather than relying on switches, light organizes itself much like particles in a gas reaching equilibrium. The discovery could simplify and speed up optical communications and computing. It reimagines chaotic optical behavior as a tool for design rather than a limitation.