AI

MIT researchers have identified a new antibiotic compound using a machine-learning algorithm.

In the laboratory tests, the drug killed many of the world’s most problematic disease-causing bacteria, including some strains that have been so far resistant to all known antibiotics. These included Acinetobacter baumannii and Enterobacteriaceae which are two of the three high-priority pathogens that the World Health Organization rank as critical for new antibiotics to target.

The FDA have given marketing approval for Caption Health’s Caption Guidance and its use in cardiac ultrasound images.

The technology allows healthcare providers with no previous ultrasound experience to capture quality diagnostic images. It is planned to be deployed initially in areas needing acute care including critical care units as well as emergency and anesthesiology departments and will later be expanded to other departments.

Exscientia has created a new OCD drug using artificial intelligence to sift through potential compounds, checking them against a huge database of parameters.

The drug, called DSP-1181, was created in collaboration with Sumitomo Dainippon Pharma, and cut the traditional drug development time from 4.5 years to just 12 months.

A recent study showed that Artificial Intelligence is more accurate than doctors in diagnosing breast cancer from mammograms.

The research was published in the journal Nature, and was conducted by a team that included researchers from Imperial College London and Google Health. They designed and trained a computer model on X-ray images from nearly 29,000 women and the algorithm outperformed six radiologists in reading mammograms.

Few in the NHS trust ‘big tech’ companies to handle patient data in a confidential manner, a recent YouGov poll found.

The survey of 1,027 healthcare professionals, carried out between 23 and 31 October 2019, found that just 17% would trust these multinational corporations with the data. Only 12% of NHS staff and private healthcare workers said they would be comfortable carrying out analysis of patient data to help find cures and treatments for diseases.

This week’s top story covered the scandal surrounding Novartis over its covering up of faulty data from the FDA. The Swiss firm’s integrity was called into question after it waited until it’s $2.1 million gene therapy had been approved before informing the US regulator of inaccuracies in its data.

A new study from the Mayo Clinic shows that artificial intelligence (AI) can detect signs of atrial fibrillation (AF) in an electrocardiogram (EKG), even if the heart is in a normal rhythm at the time of the test.