Page 8 - Nature Machine Intelligence News Today

Scientists harness the power of AI to shed light on different types of Parkinson’s diseaseResearchers at the Francis Crick Institute and UCL Queen Square Institute of Neurology, working with technology company Faculty AI, have shown that machine learning can accurately predict subtypes of Parkinson’s dis...

Scientists have created an AI tool that can classify subtypes of Parkinson's with up to 95% accuracy, raising hopes of personalised care.

The findings could pave the way for personalised medicine and targeted drug discovery, researchers have said.

The findings could pave the way for personalised medicine and targeted drug discovery, researchers have said.

Highlights from Inverse, CalMatters, the Los Angeles Times and others.

Deep-learning technology developed by a team of Johns Hopkins engineers and cancer researchers can accurately predict cancer-related protein fragments that may trigger an immune system response.

Recent developments in AI have left legislators scrambling to prevent worst-case scenarios from becoming realities in the near future.

It uses a competitive learning approach against unlabelled data.

Compiled by the MLCommons group that benchmarks AI chips, MedPerf allows clinicians to keep patient information private while letting algorithm developers test their programs on real-world data.

Sean Ekins and Fabio Urbina, two Collaborations scientists, decided to tweak their drug discovery platform to see what results they might produce. The platform was reprogramed to generate VX, one of the deadliest and fastest-acting chemical warfare nerve agents.