Six pigeons were trained to detect cancer from looking at CT scans—now that work is the basis for training new AI medical tools.

Can AI revolutionize cancer detection?

Scientists have developed a tool to evaluate the risk of lung cancer, the most deadly form of the disease. Named "Sybil," this AI program was trained using CT scans with clear cancer signs, followed by scans where cancer wasn’t obvious. The tool is able to review CT scan data to predict a patient's of developing a lung cancer within six years. See how it works here.

Trials ongoing for a 99% accurate, AI-powered blood test

The UK's National Health Service has launched a trial for a blood test that can detect a dozen types of cancers with just ten drops of blood. An AI tool looks for genetic material known to be released by tumors, allowing for cancer detection before tumors are large enough to be imaged.

Using deep learning to analyze tumors

The explosive growth of life sciences data is driving artificial intelligence methods to gain traction in biology and medicine — including cancer research.

Two dogs were able to detect prostate cancer in 98% of patients in one study

In this small study published in 2015, two highly trained German Shepherd dogs sniffed hundreds of urine samples and were able to accurately detect prostate cancer—sniffing out certain volatile organic compounds—in almost every single case. One dog was correct 98% of the time and the other correctly identified patients 100% of the time. (Some users may encounter a paywall.)

How medical robots could cure cancer

Medical robots are on the verge of being able to be injected into the body, where they will be responsible for semi-autonomous behavior, such as detecting cancer cells and distributing medication. This six-minute video dives into the science of these nanorobots, which are smaller than blood cells. Applications of these nanobots could range from disease discovery and condition monitoring to tissue repair and artificial blood delivery.

Dogs' disease-sniffing skills were first identified in 1989

This capability, reported in the medical journal The Lancet, was discovered when a dog reportedly detected cancer in its handler. The dog repeatedly focused on a spot on the owner's leg where a malignant melanoma lesion was later found, helping lead to an early diagnosis.

How artificial intelligence, which detects patterns, can identify burnout

Researchers are training AI to detect stress-related symptoms, helping physicians and other medical workers recognize and reduce stress from overwork and potentially avoid burnout.

Artificial intelligence may improve organ donation systems—and even organ health

Mayo Clinic transplant experts suggest that artificial intelligence could potentially improve organ donation systems in several ways, including better identifying patients most at risk for organ rejection, enhancing donor-recipient matching, and helping to avoid organ transplant needs by identifying health issues earlier.

Help scientists at LIGO train AI to resolve glitches in observational data

Volunteers are provided with visual representations of signal abnormalities at various frequencies and tasked with categorizing them based on reference examples. Progressing through the tool unlocks more difficult images and additional features. Categorized images will be used to train machine learning algorithms for automated future classification.

Emergency room evaluations may be improved with AI algorithms

Emergency room care teams must make fast and crucial decisions. They must determine if patients need to be admitted or discharged and when to order more tests or not. Researchers have been exploring how often patients died in the week after they were sent home and evaluating how this and other aspects of emergency care decision-making could be improved with AI algorithms to assist decision-makers.

The potential promises and pitfalls of AI in medicine

Artificial intelligence (AI) is increasingly being integrated into healthcare, offering the potential to aid in diagnoses, answer patient queries, and streamline administrative processes. In a recent PBS interview, Dr. Isaac Kohane, editor-in-chief of the New England Journal of Medicine AI and chair of Harvard’s department of biomedical informatics, discusses the current state and future of AI in medicine.

AI can aid fertility treatments, from helping select egg candidates to laboratory automation

Reproductive AI technologies are already here, from processing vast amounts of data to helping clinicians identify the healthiest embryos for implantation. It could be a boon to the fertility industry, and help mitigate the shortage of experienced embryologists.

AI may enable smart cities to drastically improve public safety

By utilizing machine learning techniques to analyze real-time monitoring reports against facial recognition databases, artificial intelligence can enhance the identification of criminals and coordinate an appropriate emergency response across various scenarios.

Efforts to create disease-sniffing capabilities for phones still can't match dogs

In this video, a scientist explains why dogs remain leaders in olfactory capabilities, outpacing technology. Scientists have attempted to create artificial "e-noses" for phones to detect early signs of disease, but so far they have not been successful.

Some medical schools have phased out human cadavers for digital alternatives

AI-based anatomy tools and digital cadavers are increasingly used to teach students, bypassing the ethical and consent concerns around the use of real bodies. Digital cadavers have also become less expensive than real ones, though the tactile and sensory experiences of real dissection may be irreplaceable.

How birds are becoming research assistants

Through the creation of tiny sensors easily placed on their bodies, birds have served as research assistants for various scientists. With untold numbers of birds sending back data, researchers have achieved greater insights in long obscure areas of meteorology, ecology, and more. For example, weather scientists use high-flying birds to outline the height of the planetary boundary layer, while conservationists track gulls to protect migrating whales. Learn more here.

Searching for the history of cancer in ancient human bones

Nestled under archaeology lies bioarchaeology, which involves the study of bones, human or animal. This subfield recently birthed another field of study: paleo-oncology. Paleo-oncology looks for cancer and related biomarkers in bioarchaeological remains. This TED article explains how this nascent multidisciplinary field challenges the idea that cancer is modern.

Test your ability to identify AI-generated images

This interactive project from MIT challenges users to distinguish between AI-generated images and real ones.

A super-sniffer smelled her husband's Parkinson's disease years ahead of symptoms.

Chinese scientists transplanted a pig lung into a human being—but it had to be removed

In August 2025, Chinese scientists transplanted a pig lung into a brain-dead person, a common research step for this type of experimental work. Researchers used CRISPR technology to alter six proteins in the pig genes to make the organ seem less foreign to the human immune system. Within a day there were indications the organ wasn’t functioning well and that the person’s body was rejecting it. Scientists ended the experiment after nine days.

Computed tomography scans use X-rays to create 3D internal images

Just as shadows can reveal the shape of obstacles blocking visible light, the donut-shaped CT scanner measures how X-rays are blocked, revealing the shape of bones, organs, tissue, and other matter along a cross-section. As it rotates, the scanner combines these cross-sections to build a model of the internal structure.

Meet the investor running his life with AI

Daniel Ha is a venture capitalist who built a suite of AI agents to boost his productivity, both professionally and personally. At his VC firm, a troupe of agents gathers data on startups and analyzes it from competing perspectives to produce a confidence score. When his dad was diagnosed with cancer, Ha used an oncology-trained AI to help him understand the condition.

AI excels at assisting with structured tasks involving logistics and planning

Tools like ChatGPT, Gemini, and Perplexity can help organize chaotic calendars, troubleshoot bedtime routines, and assist with salary planning and moving. However, specific quotes, like insurance, and local cost comparisons can be flawed since AI draws from nonlocalized datasets.

Dinosaurs suffered from cancer, arthritis, and infections seen in modern animals

Using CT scans and advanced pathology techniques, paleopathologists have identified respiratory illnesses, malignant osteosarcoma, and other diseases in dinosaurs. The research has helped show how many of these ailments are not exclusively modern phenomena.

Using brain implants to restore vision

Several companies are attempting to create brain-computer interfaces that skip over retinas and optic nerves to allow visual input to go straight to the brain, potentially restoring some sight to the blind. Clinical trial findings suggest restored sight is sparse and manifests differently than a sighted person might expect, appearing as specks of "light" clusters called phosphenes to help differentiate one's surroundings.

When you complete a CAPTCHA on a website to prove you are human, you may be unknowingly training algorithms for self-driving cars, whose systems require training data to help identify crosswalks, bicycles, and other outdoor objects.

AI tools are trained on human-created data containing implicit and explicit biases

Because AI tools reflect patterns in their training data, their outputs may reinforce existing societal biases—especially racial ones—rather than offering neutral or fair ones. Adequate training is necessary to undermine these biases whenever new data is incorporated.

Medical imaging allows 3D printers to create patient-matched devices

With imaging data on a person's anatomy, external prostheses and implants, such as cranial plates or hip joints, can be custom-printed to better match a patient's body. Fabrication of porous structures can promote bone growth, leading to longer-lasting implants.

Scientists may have discovered why gene-edited pig kidneys are rejected in humans

In November 2025, researchers studying how a brain-dead donor’s body responded to the transplantation of a genetically engineered pig kidney, published that they’ve identified immune system reactions that may explain why these pig organs get rejected. What’s more, they were able to reverse the rejections with an already available drug combination and the kidney functioned well. They also pinpointed a way to detect a potential rejection up to five days sooner.

Explore the differences between healthy and cancerous cells using a DNA microarray

In this simulation, you will learn how scientists use microarrays to experiment on thousands of genes at the same time. By determining which genes are on or off, users can identify those that contribute to cancer formation.

Brain implants are restoring movement and communication in early human trials

Several companies developing brain-computer interfaces have begun testing on humans with promising results. These implants have helped reanimate paralyzed limbs and enable communication, though ethical concerns remain about data privacy.

A man with organ failure used AI to speed discovery of his miracle drug

David Fajgenbaum had a few months to live after a diagnosis with a rare form of Castleman's disease. By studying his blood, medical records, and broader literature, he was able to identify the cause of his condition and a treatment. He's been in total relapse for ten years.

Research suggests using AI for schoolwork may harm critical thinking skills

An MIT study finds lower brain engagement in students who used ChatGPT, resulting in consistent underperformance in neural, linguistic and behavioral levels. AI users struggled to recall their own essays, while the brain-only group showed the highest neural connectivity and satisfaction.

How is precision medicine is transforming healthcare?

As the medical sector moves toward more personalized care, healthcare systems are using technologies such as artificial intelligence (AI) and data analytics to pave the way for precision medicine. This analysis in HealthTech Magazine looks into the...

Using AI to restore speech 30 years after a stroke

Through a novel surgical procedure involving electrodes implanted in the brain, along with the help of artificial intelligence, a stroke patient is regaining her ability to speak. This technology converts her thoughts into speech through a digital avatar, allowing her to verbally express herself for the first time in decades.

Biotech is trying to boost drug production efficiency—using chicken eggs

A company called Neion Bio is genetically engineering birds in a bid to produce medical compounds, a herculean task that scientists have struggled with for decades. The US FDA has approved only one chicken-derived drug in the past—an expensive treatment for a rare liver disorder. (Some users may encounter a paywall.)

Medical professionals have experimented with using mixed reality headsets

Devices like the Apple Vision Pro have helped doctors develop surgical plans for hip and knee replacements using software that provides 3D models and other tools. Virtual screens displayed by mixed reality devices can provide information related to surgical progress, a patient's vitals, and more.