Machine learning models fail to detect key health deteriorations in the ICU: a new study reveals that 66% of critical injuries in hospitals would go unnoticed if the current AI models were put to use.
To suppress tremors, such as those from Parkinson's disease, scientists equipped a biorobotic arm with artificial muscles, which compensate for the back-and-forth movement of the tremor.
The work of a nurse is becoming increasingly digital. A new study shows that nurses need to expand their professional competencies beyond their traditional skills to adapt to these changes.
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.
A pacemaker designed for babies could fill an unmet need for newborns with congenital heart defects and other heart conditions, finds a new study.
Playing video games to recover hand and wrist mobility? A new system of exergames demonstrates the potential for rehabilitation while providing therapists with data to analyse patients’ progress.
A newly-developed robot can detect medication side-effects in patients after heart arrhythmia treatment faster than a human doctor, while reducing the number of follow-up tests.
It takes one to know one: Researchers have developed an AI-based evaluation tool to assess how well clinical AI tools perform in the hospital.
Researchers developed a smart patch capable of real-time biometric signal monitoring and drug delivery. Potential applications include glucose management, pain relief, and chronic disease treatment.
A sensor, similar to glucose monitoring devices, detects lung cancer biomarkers from a blood sample in just 40 minutes. The technology has potential to identify at-risk patients and tailor treatments.
“A turning point in neuroscience,” say developers about a holographic endoscope that peers deep into the brain through an optical fiber – minimally invasive and with subcellular resolution.
Patient-specific 3D printed surgical guides could provide a clear visual aid that helps cardiac surgeons locate key treatment areas on the heart, such as the optimal location to build the bypass vein.
Less than a millimetre: the world's smallest biomedical robot is designed for imaging, sampling, drug delivery, and laser ablation. The developers highlight potential new clinical applications.
A survey found that many Americans use a device to monitor their heart, but few share that data with their doctor. Cardiologists explain when findings should be discussed with a medical professional.
Promising technology for patients with spinal cord injuries: A new study paves the way for complex touch sensation through brain stimulation, using an extracorporeal bionic limb.
Anyone who has exchanged a few lines of dialogue with a large language model (LLM), will probably agree that generative AI is an impressive new breed of technology. LLMs show great potential in addressing some of the most urgent challenges in healthcare. At the Medica tradefair, several expert sessions were dedicated to generative AI, its potential medical applications and current caveats.
New insights on the degradation of implantable chips in the body could lead to enhanced longevity of the chips and better treatments for patients with Parkinson's or clinical depression.
Researchers have developed an AI-based model to better predict whether cancer patients will benefit from immunotherapy — using only routine blood tests and clinical data.
Can an AI determine whether or not a person drinks beer by looking at their knee X-rays? It can't – but the claim shows why “shortcut learning” is such a dangerous mechanism in medical AI.
US engineers turned to the world of parasites as inspiration to affix small-scale medical devices to the GI tract or other soft tissues for sensing, sample collection, and extended drug release.
Large language models (LLM) show promise in detecting hospital patients at risk of committing suicide. This could help warn medical staff in time while maintaining the patients' privacy.
Opposing views on new implantable cardiac devices were aired in a Great Debate session at the European Society of Cardiology’s annual 2024 congress in London. Experts discussed emerging techniques and technologies and debated whether they are actually ready for clinical application. At the core of the session was the issue of whether conduction system pacing (CSP) should replace cardiac…
Precise segmentation of anatomical structures greatly benefits cancer diagnosis. Using AI and deep learning methods, researchers are developing a high-precision 3D viewer software for medical image data.
To advance the transition of AI from research to clinical application, Nvidia announced that Siemens Healthineers has adopted MONAI, an open-source medical imaging framework.
Detection of patient falls, unauthorized intrusions on hospital premises, and more: A new suite of AI tools is designed to enhance healthcare security and patient safety surveillance.
