news-medical.net

AIAI-generated summary Lab Thread launched a new Model Context Protocol server that allows scientists to connect assistants like ChatGPT and Claude directly to laboratory data. The company also released new artificial intelligence functions for generating experimental protocols, configuring storage, and transcribing handwritten notes.

AIAI-generated summary Researchers at the University of the Pacific School of Pharmacy published a study in Scientific Reports comparing the accuracy of five large language models on 227 infectious disease examination questions. ChatGPT-4o-mini achieved the highest accuracy at 91.2 percent, while the evaluation showed that model performance declined on questions containing images.

AIAI-generated summary The American College of Physicians and OpenEvidence announced a collaboration to bring evidence-based clinical content to physicians at the point of care. OpenEvidence will license published content from Annals of Internal Medicine and clinical guidance developed by the American College of Physicians.

AIAI-generated summary NYU Langone Health announced that its PREVIA ensemble analyzed emergency-department trauma narratives to estimate one-month post-traumatic stress disorder risk in a 145-patient study. The system utilizes Whisper, Llama, Mistral, DeepSeek, and NVIDIA A100 GPUs to process patient recordings and demographic data without adding intake time.

AIAI-generated summary Researchers developed an artificial intelligence e-nose device and a wearable release system called Scentronic to detect and analyze odors. Field testing showed that participants could identify individual odors about 73% of the time and paired scents about 71% of the time.

AIAI-generated summary A University of Cambridge and DIOSynVax Ltd team developed an artificial intelligence-guided bird flu vaccine that provided complete protection against diverse variants in animal trials. Published in Cell Reports Medicine, the study showed the new vaccine outperformed existing government-stockpiled vaccines that protected only about half of the tested animals.

AIAI-generated summary Scientists at Rensselaer Polytechnic Institute created the Quest2Dx framework to screen for early signs of Parkinson's disease using health questionnaires. The research team published details in Nature Aging describing how the model analyzes lengthy questionnaires to help doctors identify patients who may need early testing.

AIAI-generated summary Researchers developed a deep learning analysis technology named NONOS that separates rhythms from background signals in brain activity. DGIST says the technology achieved high accuracy in predicting movement steps in patients with Parkinson disease during testing.

AIAI-generated summary Weill Cornell Medicine researchers describe a conceptual framework called Laboratory Agentic Reasoning and Integrative Analytics designed to monitor laboratory quality and operations. Dr. He Sarina Yang states that the framework could help identify anomalies and trends before they trigger formal quality control violations or disrupt patient care.

AIAI-generated summary Mayo Clinic Platform launched a new Clinical Decision Support solution that brings Mayo Clinic knowledge and evidence-informed guidance directly into clinicians workflows. The artificial intelligence-enabled solution is available to healthcare professionals at organizations participating in Mayo Clinic Platform healthcare provider programs to support individualized patient care decisions.

AIAI-generated summary Researchers at the Translational Genomics Research Institute made available a new approach using AlphaFold3 to predict T cell receptor recognition of specific antigens from genetic sequences. John Altin says the method performs better than random chance and could help scientists more rapidly decode immune responses to infectious diseases and tumors.

AIAI-generated summary Researchers have released findings showing that artificial intelligence measurements of heart function from MRI scans more strongly predict patient survival than clinician measurements. The artificial intelligence tool analyzed scans in approximately two to three seconds compared to thirteen minutes for expert clinicians, potentially supporting faster clinical decision-making.

AIAI-generated summary Florida Atlantic University made available a study evaluating quantum machine learning approaches for lung cancer prediction using limited training data. D-Wave Quantum Inc. states that the research demonstrates the technology's capability to extract insights in data-constrained healthcare environments.