PROSPECTS: Optimism as study to determine whether artificial intelligence (AI) could accurately locate damage to the brain after stroke based on a person’s health history, produces positive results…

By Own Correspondent

MINNEAPOLIS, US – Artificial intelligence may serve as a future tool for neurologists to help locate where in the brain a stroke occurred.

Thanks to a new study, which used AI to process information from a person’s health history and a neurologic exam to locate lesions in the brain, and produced positive results. Cases of 46 people who had a stroke were used in the study conducted by Dr Jung-Hyun Lee of State University of New York (SUNY) Downstate Health Sciences University in Brooklyn (US).

The study, which looked specifically at the large language model called generative pre-trained transformer 4 (GPT-4), is to be published on March 27, online issue of Neurology® Clinical Practice, an official journal of the American Academy of Neurology, the world’s largest association of neurologists and neuroscience professionals, with over 40 000 members.

A stroke can cause long-term disability or even death. A stroke, sometimes called a brain attack, occurs when something blocks blood supply to part of the brain or when a blood vessel in the brain bursts. In either case, parts of the brain become damaged or die. A stroke can cause lasting brain damage, long-term disability, or even death.

 Knowing where a stroke has occurred in the brain can help predict long-term effects such as problems with speech and language or a person’s ability to move part of their body. It can also help determine the best treatment and a person’s overall prognosis.

A neurologic exam can help locate lesions, which are defined as damage to the brain tissue from stroke, when paired with a review of a person’s health history. The exam involves symptom evaluation and thinking and memory tests. People with stroke often have brain scans to locate lesions.

“Not everyone with stroke has access to brain scans or neurologists, so we wanted to determine whether GPT-4 could accurately locate brain lesions after stroke based on a person’s health history and a neurologic exam,” said Lee.

Using 46 published cases of people who had stroke, Lee and his team of researchers gathered information from health histories and neurologic exams of these individuals. The raw text was fed into GPT-4.

Researchers asked it to answer three questions: whether a participant had one or more lesions; on which side of the brain lesions were located; and in which region of the brain the lesions were found. They repeated these questions for each participant three times. Results from GPT-4 were then compared to brain scans for each participant.

Researchers found that GPT-4 processed the text from the health histories and neurologic exams to locate lesions in many participants’ brains, identifying which side of the brain the lesion was on, as well as the specific brain region, with the exception of lesions in the cerebellum and spinal cord.

“For the majority of people, GPT-4 was able to identify on which side of the brain lesions were found with a sensitivity of 74% and a specificity of 87%. Sensitivity is the percentage of actual positives that are correctly identified as positive. Specificity is the percentage of negatives that are correctly identified. It also identified the brain region with a sensitivity of 85% and a specificity of 94%,” Lee said.

When looking at how often the three tests had the same result for each participant, the results showed that GPT-4 was consistent for 76% of participants regarding the number of brain lesions. It was also consistent for 83% of participants for the side of the brain, and for 87% of participants regarding the brain regions.

However, when combining its responses to all three questions across all three times, the researchers found that GPT-4 provided accurate answers for 41% of participants.

“While not yet ready for use in the clinic, large language models such as generative pre-trained transformers have the potential not only to assist in locating lesions after stroke, they may also reduce health care disparities because they can function across different languages,” said Lee. “The potential for use is encouraging, especially due to the great need for improved health care in underserved areas across multiple countries where access to neurologic care is limited.”

A limitation of the study is that the accuracy of GPT-4 depends on the quality of the information it is provided, Lee said.

While researchers had detailed health histories and neurologic exam information for each participant, such information was not always available for everyone who had a stroke.

Cancer vaccines ready within three years  – Russian scientist

BREAKTHROUGH: Most remaining obstacles appear to be regulatory, according to Vasily Lazarev of Russia’s Federal Medical-Biological Agency

By WSAM Correspondent

Russian medical researchers could be able to roll out oncological vaccines within the next couple of years, given adequate funding and support from lawmakers, a high-ranking official at the Federal Medical-Biological Agency (FMBA) said on Thursday.

The comments come after President Vladimir Putin said last month that the country was “one step away” from developing vaccines against cancer.

“If financial support is provided, I think that in two or three years existing organizations will be able to put oncology vaccines into practice,” Vasily Lazarev, deputy director of the Lopukhin Federal Scientific and Clinical Center for Physical and Chemical Medicine, told the outlet RTVI. Domestic private investors will also be attracted to the technology “after regulatory pressure eases,” he added.

Lazarev did not bring up any medical or technological challenges, choosing instead to highlight the legal constraints facing vaccine development.

“I don’t know how quickly by-laws will be developed, it could take a year to resolve all the regulatory issues,” he said. “We have the tools, the production facilities, I think it’s not difficult to organize.”

 Russia close to ‘cancer vaccines’ – Putin  Amendments proposed by the FMBA, which would allow for the production and use of “variable composition” medication, will go into effect in September. They also require the drugs to be produced at the same institution that holds the patent, however.

“Organizing such production at home will be quite expensive, although it is feasible,” Lazarev said. “Most likely, these will be regional centers and maybe specialized oncological institutions.”

There are currently only a handful of facilities that could handle the production requirements, such as the Blokhin Cancer Center or the FMBA’s Federal Center for Brain and Neurotechnology, both located in Moscow.

Variable-composition neoantigens, which vaccine developers have focused on, don’t quite fit the current Russian legal framework and could not be used in treatments at all until very recently.

Putin revealed the development of cancer vaccines at the Future Technologies Forum in Moscow last month. The Russian president mentioned them among the developing medical technologies that he described as approaching science fiction. – Source: RT