Scientists have developed an artificial intelligence (AI) tool that can classify four subtypes of Parkinson’s disease with up to 95% accuracy. Researchers from the Francis Crick Institute and the UCL Queen Square Institute of Neurology in London “trained” a computer program to recognise the subtypes of the condition using images of stem cells from patients. The team said their work, published in the journal Nature Machine Intelligence, could pave the way for personalised medicine and targeted drug discovery. Sonia Gandhi, assistant research director and group leader of the Neurodegeneration Biology Laboratory at the Crick, said: “We understand many of the processes that are causing Parkinson’s in people’s brains. The hope is that one day this could lead to fundamental changes in how we deliver personalised medicine Sonia Gandhi, Francis Crick Institute “But, while they are alive, we have no way of knowing which mechanism is happening, and therefore can’t give precise treatments. “We don’t currently have treatments which make a huge difference in the progression of Parkinson’s disease. “Using a model of the patient’s own neurons, and combining this with large numbers of images, we generated an algorithm to classify certain subtypes – a powerful approach that could open the door to identifying disease subtypes in life. “Taking this one step further, our platform would allow us to first test drugs in stem cell models, and predict whether a patient’s brain cells would be likely to respond to a drug, before enrolling into clinical trials. “The hope is that one day this could lead to fundamental changes in how we deliver personalised medicine.” Parkinson’s is a condition in which parts of the brain become progressively damaged over many years. Symptoms include involuntary shaking of particular parts of the body, slow movement, and stiff and inflexible muscles. But there is also a wide range of other physical and psychological symptoms such as depression and anxiety, problems sleeping, and memory problems. These vary from person to person due to differences in the underlying mechanisms causing the disease. The researchers said that until now, there was no way to accurately differentiate Parkinson’s subtypes. It means people are given nonspecific diagnoses and do not always have access to targeted treatments, support or care, the team added. For the study, the researchers generated stem cells, which have the ability to develop into specialised cell types in the body, from patients’ own cells. The team then used those cells to chemically create four different subtypes of Parkinson’s: two involving pathways leading to toxic build-up of a protein called alpha-synuclein and two involving pathways associated with dysfunctional mitochondria, the cell’s battery packs. Working with the British technology company Faculty AI, the team developed machine-learning algorithms which were able to accurately predict the Parkinson’s subtype when presented with images it had not seen before. James Evans, a PhD student at the Crick and UCL, and first co-author of the study, said: “Now that we use more advanced image techniques, we generate vast quantities of data, much of which is discarded when we manually select a few features of interest. “Using AI in this study enabled us to evaluate a larger number of cell features, and assess the importance of these features in discerning (the) disease subtype. “Using deep learning, we were able to extract much more information from our images than with conventional image analysis. “We now hope to expand this approach to understand how these cellular mechanisms contribute to other subtypes of Parkinson’s.” Read More Charity boss speaks out over ‘traumatic’ encounter with royal aide Ukraine war’s heaviest fight rages in east - follow live Oxford scientists find no evidence to suggest Facebook not good for wellbeing Many adults would struggle to understand video-sharing platforms’ rules – Ofcom Ozzy Osbourne PlayStation tweet which failed to reveal link to Sony banned

MIAMI--(BUSINESS WIRE)--Aug 15, 2023--

An unknown source has been sending radio blasts towards Earth since at least 1988, scientists say. The researchers do not know what object is sending the radio waves towards Earth. The nature of the waves is such that they do not conform with any models that attempt to explain it. For 35 years, the source has been sending out regular 20-minute blasts of energy that vary considerably in their brightness, researchers say. The emissions appear something like the blasts that come out of pulsars or fast radio bursts, which last for milliseconds to several seconds. But the newly discovered source sends radio signals that pulsate on a period of 21 minutes – something previously thought impossible by expected explanations. Pulsars are neutron stars that spin around quickly, throwing out radio blasts as they do. When one crosses Earth, the emissions can be picked up very briefly and brightly, like being in the path of the light from a rotating lighthouse. Scientists believe that process can only work if the magnetic field of the pulsar is strong, and it is rotating quickly enough – if not, there would not be enough energy to see the pulsar from Earth. That has led to the development of the “pulsar death line”, which suggests that sources must be spinning fast and strong enough to be detected. The newly discovered object named GPMJ1839-10, however, is way beyond that death line. If it is a pulsar, then it seems to be operating in ways that scientists thought impossible. It could also be a highly magnetised white dwarf or magnetar, an extra kind of neutron star with incredibly strong magnetic fields. But they do not tend to send out emissions of this kind, researchers believe. The signals have been detected on Earth since at least 1988, scientists found by going through old records, but they had gone unnoticed by those collecting that data. After the source was detected, researchers checked radio archives and found that the source has been repeating for at least 35 years. Yet more discoveries may be made in this way in the future, said Victoria M Kaspi, a professor of physics at McGill University who did not work on the study. “Only time will tell what else lurks in these data, and what observations across many astronomical timescales will reveal,” she wrote in an accompanying article. That might include some explanation of how unusual the newly discovered source is. By examining whether there are is a similar collection of other objects in the data, researchers might be able to understand the mechanisms behind the newly discovered emissions. The findings are reported in a new paper, ‘A long-period radio transient active for three decades’, published in the journal Nature. Read More Scientists invent self-healing solar panels with ‘miracle material’ Powerful solar flare to disrupt communications, Russians warn New technique represents major breakthrough in search for aliens, scientists say

The UK was falling behind Europe in developing green industries, even before backsliding by Rishi Sunak’s government on

As the auto industry grapples with how to make affordable EVs, the task may get easier by one

NASA has lifted the lid on its first findings about the Bennu sample, one of the "most hazardous known asteroids". The highly-anticipated sample from the OSIRIS-REx’s mission took seven years to complete and finally made a safe landing on Sunday 24 September. Scientists audibly gasped upon opening the capsule. They kept details to a minimum and maintained a slow pace in progress for "good reason," as they received more material than expected. "The abundance of material found when the science canister lid was removed earlier this week has meant that the process of disassembling the TAGSAM (Touch-and-Go Sample Acquisition Mechanism) head – which holds the bulk of material from the asteroid – is off to a methodical start," they said a the time. That was until now... On Wednesday 11 October, the space agency shared details for the first time from NASA experts and the University of Arizona. NASA said there were signs of water and carbon on the sample through hydrated clay minerals that contain carbon. "At nearly 5% carbon by weight, carbon being the central element of life, far exceeding our goal of 60g, this is the biggest carbon-rich asteroid sample ever returned to earth," Administrator Bill Nelson said, adding that it was "exactly the kind of material that we wanted to find." He went on to suggest that "they are going to help us determine the origin of elements that could have led to life" and provide a greater understanding of how to protect Earth from asteroids. Scientists also revealed that the sample contained space dust from 4.5-billion-year-old asteroid Bennu. NASA showed the audience the sample on a video to protect the sample and to prevent contamination. Speaking about working through a glove box to analyse the sample, Francis McCubbin, astronomical curator at NASA's Johnson Space Centre said: "[It is] "hard, challenging work, and it does not go quickly, but we need to do this right". The samples will be preserved so that "scientists that aren't even born yet are going to have the opportunity to answer questions about our universe with these samples using technology that has not even been invented." Sign up for our free Indy100 weekly newsletter Have your say in our news democracy. Click the upvote icon at the top of the page to help raise this article through the indy100 rankings.

After a bruising few months, Chancellor Olaf Scholz and senior members of his ruling coalition were relaxing at

Andrew Tate tells his supporters he will 'force' himself 'to breathe' when the time comes

When Occidental Petroleum Corp.’s Vicki Hollub introduced the idea of “net zero oil” two years ago, few outside

There’s one ESG fund category that’s outgrowing most others in the US, and it’s dedicated to investing in

PREORDER: The new Nintendo Switch OLED Model - Mario Red Edition will be released on

California Governor Gavin Newsom unveiled legislation Friday to speed up construction of power lines, water works, bridges and