AI-powered diagnostics: How the tools are developing to help doctors

AI-powered diagnostics: How the tools are developing to help doctors

AI tools are becoming more prevalent in back office operations, but they are also making inroads on the diagnostic side.

Six years ago, artificial intelligence was tested in traumatology at the emergency room of the Ospedale clinic for radio analysis. A successful experiment was found, so that the facility extended to help him establish orthopaedic measurements. And she is currently testing it for mammography. On the radio, with the naked eye, there is a white trait that crosses the bottom of the tibia. The radiologist is also formal, the AI: "fracture," she suspe…

Some doctors increasingly using artificial intelligence to take notes during appointments

CHICAGO — It was easy to miss Dr. Robert Gray’s quick movements, tapping the screen of his smartphone at the beginning and end of patient visits on a recent day.

Scientists from the University at Buffalo have made a significant step forward in the application of artificial intelligence in medicine. Their approach, known as Semantic Clinical Artificial Intelligence (SCAI), has significantly improved the performance of language models on the USMLE exam, a standardized test for medical licensing in the United States. An important element of this technology is the RAG mechanism, which enriches the model with…

AI video analysis tool helps clinicians assess Parkinson’s symptoms

A new open-source software called VisionMD may help doctors assess motor symptoms of Parkinson’s disease and other movement disorders with artificial intelligence (AI)-enabled video analysis, a study reports. Analyzing videos of patients tapping their fingers and doing other clinical tests can help clinicians understand disease progress and treatment response, said the software’s developer, Diego Guarin, PhD, an assistant professor of applied ph…

New AI Tool Outperforms Most Human Physicians on U.S. Medical Licensing Examination

A new clinical AI tool developed by biomedical informatics researchers at the University of Buffalo (UB) has shown that it can outperform most human physicians, as well as all previously tested AI models, on the U.S. Medical Licensing Examination (USMLE), a benchmark of clinical competence. This tool, called Semantic Clinical Artificial Intelligence (SCAI), could support doctors in clinical decision-making by offering medically reasoned response…