Medical News Observer

SynergyX: Multi-Modality Mutual Attention Network for Drug Combination Prediction

SynergyX is a multi-modality mutual attention network that dramatically improves the prediction of anti-tumor drug synergies by leveraging intricate biological interactions and multi-omic data integration. This advanced approach outshines the accuracy of existing models, providing critical insights into drug-gene interactions and enhancing the development of effective cancer treatments.
COMPASS Digital Cognitive Behavioral Therapy Program Enhancing Mental Health in Chronic Illness Patients

A study by King’s College London’s Institute of Psychiatry, Psychology & Neuroscience has found that the COMPASS digital cognitive behavioral therapy (CBT) program significantly reduces psychological distress in individuals with long-term physical conditions. This therapist-guided, interactive program offers tailored mental and physical health care, showing promise for scalable, effective management of anxiety and depression in…
EyeArt: AI-based Diabetic Retinopathy Detection software

EyeArt v2.2.0, developed by Eyenuk Inc., is an AI-powered Class II medical device designed to automatically detect signs of diabetic retinopathy in adult diabetic patients using high-resolution retinal images. This innovative software aims to improve early detection and treatment outcomes by providing healthcare providers with a tool for detecting more than mild diabetic retinopathy and…
Degree Of Linear Polarization: For Age-related Skin Change Assessment

A study from Aston University’s Institute of Photonic Technologies reveals how aging affects the polarization properties of human skin. It indicates distinct differences between aging and younger skin texture due to collagen depletion. Published in the Journal of Biomedical Optics, the findings emphasize the potential for noninvasive, light-based techniques for early detection of skin conditions.
Novel Memory Decoding Model And Neural Prosthetics To Enhance Memory

Researchers from Wake Forest University School of Medicine and the University of Southern California (USC) successfully enhanced memory using a memory decoding model based on individual brain patterns, improving memory recall in epileptic patients. This breakthrough paves the way for neural prosthetics to treat memory loss in conditions like Alzheimer’s and stroke.
Predicting Psychosis Using Machine Learning and MRI

An international consortium, including researchers from the University of Tokyo, has developed a machine-learning tool that uses MRI brain scans to predict the onset of psychosis, achieving up to 85% accuracy. This innovative approach, part of Japan’s Brain/MINDS Beyond project, marks a significant step forward in identifying individuals at high risk for psychosis, potentially enabling…
Wearable Ultrasound Elastography for Continuous Organ Monitoring

MIT engineers have created a groundbreaking wearable bioadhesive ultrasound device about the size of a postage stamp that can continuously monitor the stiffness of internal organs by emitting and receiving sound waves. Published in Science Advances, this sensor’s technology represents a significant advance in noninvasive medical monitoring, providing continuous data on organ health and the…
Novel In Vitro Model For Human Placental Barrier

Tokyo Medical and Dental University researchers have developed a trophoblast stem cell-based organoid model that closely mimics the human placental barrier. This model represents a significant improvement over traditional methods, enabling more accurate studies of the placenta’s protective functions and the transfer of substances between mother and fetus.
DrugAI: A Generative AI Model To Streamline Drug Discovery

At Chapman University’s Schmid College of Science and Technology, scientists have unveiled “DrugAI,” a cutting-edge generative artificial intelligence model designed for de novo drug design. By utilizing a comprehensive dataset and advanced algorithms, DrugAI generates unique molecular structures with high potential, accelerating the discovery of novel drug candidates.
Machine Learning Aids in Detecting Secondary Bacterial Infections in COVID-19 Patients

Using RNA sequencing and patient data, researchers at the University of Queensland have developed a machine-learning model that predicts the risk of secondary bacterial infections in hospitalized COVID-19 patients. This method aims to optimize antibiotic use, addressing the global challenge of antibiotic resistance and the emergence of superbugs.