Reading an LLM-generated recap to get the gist of a scientific publication? Not a good idea, a new study finds: Most leading chatbots exaggerate the findings – prompting for more accuracy even makes things worse.
Researchers evaluated the clinical value of using ChatGPT to interpret seizure semiology in order to predict which brain areas to remove to achieve seizure freedom in epilepsy patients.
Generative AI can detect and quantify cognitive biases of human caregivers during medical emergency situations. This way, LLMs could help reduce the impact of bias based on gender, age, or ethnicity.
In the world of theatre, the ‘deus ex machina’, the god from the machine, is a dramaturgical trick to resolve seemingly unsolvable conflicts. Can artificial intelligence (AI) also be such a universal problem solver for internal medicine? At the Annual Congress of the German Society of Internal Medicine (DGIM), Dr Isabella Wiest explored the potential – and limitations – of AI helpers.
A new study investigating the impact of AI in healthcare shows that using LLMs to process thousands of patient records daily across multiple hospitals could lead to substantial resource consumption.
Imitation learning could open a new frontier in medical robotics: Researchers 'taught' a robot to mimic a surgical procedure by watching the surgeons' performance.
Telesurgical procedures, new resection techniques, robot-assisted surgery: The sixth Semi-Live conference at University Hospital Heidelberg looked at how surgical approaches have evolved in the last few decades driven by technical advances in the ongoing quest for precision and excellence in patient care.
ChatGPT has brought generative AI to the mainstream – and into many GP practices as well, a new study suggests. The work points out the risk of doctors using AI without clear guidance or policies.
Enter symptoms into ChatGPT, receive an accurate diagnosis? Research reveals that LLM AI models are not quite there yet, struggling to identify genetic conditions from patient-written descriptions.
New research shows that the AI large language model ChatGPT can be tailored to provide accurate responses to questions about digital pathology and compile detailed results.
Chatbots like ChatGPT generally deliver servicable results when asked for healthcare advice. However, new research suggests that the LLM's accuracy drops when languages other than English are used.
As AI is playing an increasingly crucial role in the fields of pharmacy and medicine, Pharmaceutical Automation and Digitalisation Congress (AUTOMA+ 2024) welcomes the entire industry value chain to join the roundtable discussion on the innovative strategies that are navigating the future of pharma. The Congress takes place in Zurich, Switzerland, on 18-19 November 2024.
‘Computer, why did the doctor take that MRI scan of my leg? And what did it show?’: Popularized by OpenAI’s ChatGPT, generative artificial intelligence (AI) is already beginning to see practical applications in medical settings. The technology holds immense potential, with benefits for patients, clinicians, and even hospital administration, according to Shez Partovi, MD.
Large language models like ChatGPT have become a go-to point for health information. However, a new study uncovers a vital weakness: The AI gets confused when faced with actual scientific evidence.
Can generative AI reduce the administrative burden on healthcare professionals? In a new study, chatbot model ChatGPT shows high aptitude in producing medical record notes.
Pulse oximeters delivering poorer results in people with darker skin tones, underdiagnosis of cardiac conditions in women: some medical devices are not as fair as the ought to be, a new review finds.
Digital leaders and major players of the whole value chain gather at Pharmaceutical Automation and Digitalisation Congress (AUTOMA+ 2024) to share professional opinion on trends and latest solutions for the pharma digital transformation. Following the long-standing tradition, the Congress is held in the heart of the pharmaceutical industry, Zurich, Switzerland, on 18-19 November 2024.
Can AI help better evaluate images of brain tumours? A publication from German researchers on this topic presented at this years' ICIS conference won the Best Paper Award.
Researchers explored the potential of two generative AI models for answering clinical questions and literature selection for medical research – one fared signifcantly better than the other.
Machine learning and AI are playing an increasingly important role in medicine and healthcare, and not just since ChatGPT. This is especially true in data-intensive specialties such as radiology, pathology or intensive care. The quality of diagnostics and decision-making via AI, however, does not only depend on a sophisticated algorithm but – crucially – on the quality of the training data.
Hardly a day passes without new headlines about ChatGPT, the AI-powered large language model, and its potential applications in healthcare. First results have been somewhat sobering after the initial hype, with the AI’s “hallucinations” often replacing scientific truth. Still, Professor Philip Moons is convinced that the chatbot might bring actual benefits to nursing and health science…
A new artificial intelligence (AI) model combines imaging information with clinical patient data to improve diagnostic performance on chest X-rays, a new study finds.
Experts from Brigham and Women’s Hospital have tasked ChatGPT to generate recommendations for cancer treatment – with some promise, but ultimately inadequate results.
When faced with an unfamiliar task, many people rely on the voice assistants in their smartphone to help them out. However, when it comes to CPR, these AI companions cannot always be counted on.
LLM-based generative chat tools such as ChatGPT or Google’s MedPaLM have great medical potential, but there are inherent risks associated with their unregulated use in healthcare.
Chatbots are increasingly becoming a part of health care around the world, but do they encourage bias? New research from the University of Colorado School of Medicine hints at this possibility.
AI, as used in ChatGPT, can generate credible medical information in response to common patient questions, a research team from Taiwan and the US found. However, some critical pitfalls remain.
The latest version of ChatGPT passed a radiology board-style exam, highlighting the potential of large language models (LLM) but also revealing limitations that hinder reliability, new research shows.
Doctors across all disciplines, with assistance from artificial intelligence, may soon have the ability to quickly consult a patient's entire medical file against the backdrop of all medical health care data and every published piece of medical literature online.
As ChatGPT becomes more popular among those seeking health advice, researchers try to find out whether the information provided by the AI chatbot is reliable and accurate.
Chatbots become popular resources for cancer information - but are their results accurate? Researchers evaluated the reliability of ChatGPT’s cancer information.
Researchers from the University of Liverpool have tested whether the AI-powered chatbot ChatGPT could be used to make decisions about prescribing patients with antibiotics.