With the help of artificial intelligence, computers are to simulate human thought processes. Machine learning is intended to support almost all medical specialties. But what is going on inside an AI algorithm, what are its decisions based on? Can you even entrust a medical diagnosis to a machine? Clarifying these questions remains a central aspect of AI research and development.
"Let's book you in": AI chatbots are generally seen as a welcome tool for managing medical screening appointments. However, too much of a good thing can backfire, a new study finds.
Improved detection of clinical errors and time-saving on the one hand, inadequate training on the other: the latest Future Health Index points out benefits and challenges of medical AI integration.
A new AI model enables more efficient analysis of tissue samples taken from colorectal cancer tumours. This can help shorten diagnosis times, reduce costs, and improve diagnostic accuracy.
A new AI-based method can reduce the time required for certain MRI brain scans by up to 90% while maintaining a high level of accuracy, paving the way for more efficient and accessible neuroimaging.
A team of researchers has developed an AI system capable of interpreting some of the most complex heart scans in medicine, cardiac MRI, without the need for manually labeled training data.
Researchers have discovered that teaching Large Language Models (LLMs) to mimic human intuition and reasoning significantly improves their ability to provide accurate medical care-seeking advice.
Discussion at the Pharmaceutical Automation and Digitalisation Congress (AUTOMA+) 2026 recognises that artificial intelligence is an important part of clinical innovation, positioning it as a practical tool for improving speed, decision accuracy and transparency in drug development. Industry attention is increasingly shifting towards AI-driven data ecosystems, advanced analytics and intelligent…
A new study using a “digital twin” AI model has found that factors such as loneliness, insomnia and poor mental health substantially raise a person’s future risk of developing type 2 diabetes.
AI models can generate more complete summaries of complex cancer pathology reports than physicians, according to a new study that tested six models developed by Meta, Google, DeepSeek and Mistral AI.
To improve lung cancer detection, researchers have developed a new AI system that employs a dual approach to analyse CT scans – seeing both detail and context at the same time.
Researchers are developing a portable AI-powered scanning slit-light device, designed to make ophthalmic care more accessible, so patients can be assessed any place, and any time.
AI-enabled ambient documentation shows great promise for reducing doctors' workload – but how big is their impact on burnout prevention really? A new study reveals modest time-saving effects.
Researchers have developed an AI model showing that it is possible to detect different neurodegenerative diseases - for example, Alzheimer’s and Lewy body disease - from a single blood sample.
One phishing email sends an entire county’s health service back into the age of pen and paper for months. A hidden prompt is buried within an abdominal CT image: At ECR 2026 in Vienna, cybersecurity experts presented real-world cases that read like ghost stories: tales that exemplify new vulnerabilities in modern AI-driven radiology systems – and how to avoid them.
Digital spatial profiling (DSP) is emerging as a powerful technology in helping specialists investigate complex kidney disease, according to a leading expert. Professor Renate Kain believes spatial profiling adds significantly to systems biology approaches that will transform diagnostic histopathology. However, she warns that the adoption and effective utilization of the technique is critically…
"Why did the computer conclude this?": Patients increasingly scrutinize the impact of AI on medical diagnostics. A new article explores the tension between transparency and legal frameworks.
New treatments for neurodegenerative diseases like Alzheimer’s, Parkinson’s, and motor neurone disease (MND) could be unlocked thanks to microscopic medicines called intrabodies.
Imaging left ventricular function is challenging for patients who cannot hold their breath for long. A new AI-enhanced MRI technique captures the entire cardiac cycle in a single shot.
Neither radiologists nor multimodal large language models (LLMs) are able to easily distinguish AI-generated “deepfake” X-ray images from authentic ones, according to a new study.
