Health Life

AI helps scientists understand brain activity behind thoughts

Credit: Pixabay/CC0 Public Domain

A team led by researchers at Baylor College of Medicine and Rice University has developed artificial intelligence (AI) models that help them better understand the brain computations that underlie thoughts. This is new, because until now there has been no method to measure thoughts. The researchers first developed a new model that can estimate thoughts by evaluating behavior, and then tested their model on a trained artificial brain where they found neural activity associated with those estimates of thoughts. The theoretical study appears in the Proceedings of the National Academy of Sciences.

“For centuries, neuroscientists have studied how the works by relating brain activity to inputs and outputs. For instance, when studying the neuroscience of movement, scientists measure muscle movements as well as neuronal activity, and then relate those two measurements,” said corresponding author Dr. Xaq Pitkow, assistant professor of neuroscience at Baylor and of electrical and computer engineering at Rice. “To study cognition in the brain, however, we don’t have anything to compare the measured to.”

To understand how the brain gives rise to , researchers first need to measure a thought. They developed a method called “Inverse Rational Control” that looks at a and infers the beliefs or thoughts that best explain that behavior.

Traditionally, researchers in this field have worked with the idea that animals solve tasks optimally, behaving in a way that maximizes their net benefits. But when scientists study animal behavior, they find that this is not always the case.

“Sometimes animals have ‘wrong’ beliefs or assumptions about what’s going on in their environment, but still they try to find the best long-term outcomes for their task, given what they believe is going on around them. This could account for why animals seem to behave suboptimally,”

Health Life

Algorithm accurately predicts COVID-19 patient outcomes

Credit: Rensselaer Polytechnic Institute

With communities across the nation experiencing a wave of COVID-19 infections, clinicians need effective tools that will enable them to aggressively and accurately treat each patient based on their specific disease presentation, health history, and medical risks.

In research recently published online in Medical Image Analysis, a team of engineers demonstrated how a new algorithm they developed was able to successfully predict whether or not a COVID-19 patient would need ICU intervention. This -based approach could be a valuable tool in determining a proper course of treatment for individual patients.

The research team, led by Pingkun Yan, an assistant professor of biomedical engineering at Rensselaer Polytechnic Institute, developed this method by combining chest computed tomography (CT) images that assess the severity of a patient’s with non-, such as demographic information, , and laboratory blood test results. By combining these data points, the algorithm is able to predict patient outcomes, specifically whether or not a patient will need ICU intervention.

The algorithm was tested on datasets collected from a total of 295 patients from three different hospitals—one in the United States, one in Iran, and one in Italy. Researchers were able to compare the algorithm’s predictions to what kind of treatment a patient actually ended up needing.

“As a practitioner of AI, I do believe in its power,” said Yan, who is a member of the Center for Biotechnology and Interdisciplinary Studies (CBIS) at Rensselaer. “It really enables us to analyze a large quantity of data and also extract the features that may not be that obvious to the human eye.”

This development is the result of research supported by a recent National Institutes of Health grant, which was awarded to provide solutions during this worldwide pandemic.

Health Life

Smartphone use offers tool to treat multiple sclerosis, other diseases

The way patients with multiple sclerosis or other degnerative diseases use cellphones could provide tools for their treatment. Credit: Daria Nepriakhina

Monitoring how patients with multiple sclerosis or other degenerative diseases use their smartphones could provide valuable information to help get them better treatment.

In an article published in Chaos, researchers used a to record the keystroke dynamics of a control group and those of subjects in various stages of multiple sclerosis treatment over the course of a year.

Keystroke dynamics show how quickly or slowly someone is typing on a , the amount of time between letters typed, the number of mistakes made and corrected while typing, and other behaviors. As part of the study, researchers at Amsterdam University Medical Center used a mobile app that tracks how a user is typing on their phone’s keyboard.

In doing so, they observed changes over time in the way people with MS typed that were not seen in subjects who did not have the .

“The clinically relevant changes in dynamics can be seen as early warning signals for changes in of the patient prior to the change occurring,” the authors wrote.

James Twose, one of the authors, called the study’s findings a “first promising step” toward using keystrokes to help diagnose changes in patients with chronic diseases like MS.

“The dream is prediction,” said Twose. “If there is some semblance of predictability, the joy would be to forecast the disease in a similar way you do with weather.”

Multiple sclerosis patients generally make clinical visits every 3-12 months, according to the authors, and MRIs are the best way to measure changes in damage to the brain from the disease.

If doctors were able to use something like keystrokes to monitor patients

Health Life

Study projects the number of COVID-19 contagions to reach its peak in Spain in late November

This transmission electron microscope image shows SARS-CoV-2 — also known as 2019-nCoV, the virus that causes COVID-19 — isolated from a patient in the US. Virus particles are shown emerging from the surface of cells cultured in the lab. The spikes on the outer edge of the virus particles give coronaviruses their name, crown-like. Credit: NIAID-RML

The number of infections from COVID-19 will continue increasing rapidly until November, reaching its peak near the third week of the month. Furthermore, the number of people hospitalized will increase until early December, reaching the peak in the first days of the month; and the number of deaths will continue rising until mid-January of 2021. This is the result of a study in which researchers from the Polytechnic University of Valencia (UPV) and the Spanish National Research Council (CSIC) have taken part, and which has been published by journal Chaos, Solitons & Fractals.

In the study, the researchers have developed a randomized computational network model to study the dynamics of the spreading of COVID-19 in Spain, using it afterwards for the simulation of several scenarios depending on the availability or lack thereof of universal antivirals in chemists. In the first scenario, the study simulates the incidence of the virus in the current situation, in which said antiviral is not available, and reveals ‘very concerning’ figures.

“We conducted these simulations in June and, unfortunately, reality is confirming the results that we obtained. And if the trend continues, the figures that the model gives for the last days of this month and the beginning of December are very concerning, with an incidence that could multiply the maximum figures of the first wave by seven. Hence the importance of insisting, from all fields, on the fact that it is the responsibility of everyone to not reach