Connect with us
[adrotate group="1"]

Science & Health

Alzheimer’s: Researchers create model to predict decline

Researchers from the Massachusetts Institute of Technology have developed a machine-learning model that could predict the rate of Alzheimer’s-related cognitive decline for up to 2 years in the future. MIT researchers have developed a machine-learning model that they say could accurately predict cognitive decline. Alzheimer’s disease affects millions of people worldwide, yet scientists still do…

Published

on

Researchers from the Massachusetts Institute of Technology have developed a machine-learning model that could predict the rate of Alzheimer’s-related cognitive decline for up to 2 years in the future.
MIT researchers have developed a machine-learning model that they say could accurately predict cognitive decline.

Alzheimer’s disease affects millions of people worldwide, yet scientists still do not know what causes it.

For this reason, prevention strategies can be hit and miss. Moreover, healthcare professionals have no clear way of determining a person’s rate of cognitive decline once a doctor has diagnosed them with Alzheimer’s.

Now, researchers from the Massachusetts Institute of Technology (MIT) in Cambridge — in collaboration with specialists from other institutions — have developed a machine-learning model that could allow specialists to predict how much a person’s cognitive functioning will change up to 2 years in advance of this decline becoming established.

The team — made of Ognjen Rudovic, Yuria Utsumi, Kelly Peterson, Ricardo Guerrero, Daniel Rueckert, and Prof. Rosalind Picard — will present their project later this week at the Machine Learning for Healthcare conference. This year’s conference will take place in Ann Arbor, MI.

“Accurate prediction of cognitive decline from 6 to 24 months is critical to designing clinical trials,” Rudovic explains. This, he adds, is because “[b]eing able to accurately predict future cognitive changes can reduce the number of visits the participant has to make, which can be expensive and time consuming.”

“Apart from helping develop a useful drug,” the researcher continues, “the goal is to help reduce the costs of clinical trials to make them more affordable and done on larger scales.”

Using meta learning to predict decline

In order to develop their new model, the team used data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), which is the largest Alzheimer’s disease clinical trial dataset in the world.

Through ADNI, the researchers were able to access the data of approximately 1,700 people — some with and some without Alzheimer’s disease — collected over 10 years.

The team had access to clinical information, including participants’ cognitive functioning assessments, brain scans, data regarding individuals’ DNA makeup, and cerebrospinal fluid measurements, which reveal Alzheimer’s disease biomarkers.

As a first step, the researchers developed and tested their machine-learning model using data from a subgroup of 100 participants. However, there were a lot of missing data about this cohort. So, the investigators decided to use a different statistic approach to analyze the cohort’s available data in a way that would make the analysis more accurate.

Still, the new model did not reach the level of accuracy that its developers had expected. To render it even more accurate, the researchers used data from another subcohort of ADNI participants.

This time, however, the team decided against applying the same model to everyone. Instead, they personalized the model to fit each participant, taking in new data as they became available after each new clinical assessment.

With this approach, the researchers found that the model led to a significantly lower error rate in its predictions. Moreover, it performed better than existing machine-learning models applied to clinical data.

Still, the researchers went a step further to make sure that their approach left room for as little error as possible. They went on do devise a “meta learning” model that can pick the best approach to predict cognitive outcomes in each participant.

This model automatically chooses between the overall population and the personalized approach, calculating which one will most likely offer the best prediction for any given individual at a particular point in time.

The researchers found that this approach reduced the error rate for predictions by as much as an additional 50%.

“We couldn’t find a single model or fixed combination of models that could give us the best prediction,” explains Rudovic.

“So we wanted to learn how to learn with this meta learning scheme. It’s like a model on top of a model that acts as a selector, trained using meta knowledge to decide which model is better to deploy.”

Ognjen Rudovic

Going forward, the team aims to form a partnership with a pharmaceutical company to test this model in an ongoing Alzheimer’s disease trial.
Read More

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

*

code

Science & Health

Video gaming as a child related to improvements in memory

A new study exploring the link between video games and cognition finds that playing video games as a child can improve a person’s working memory years later on specific tasks.Video games can be a contentious topic, particularly among parents or caregivers who may be concerned about the effects of spending hours in front of the…

Published

on

By

Video gaming as a child related to improvements in memory

A new study exploring the link between video games and cognition finds that playing video games as a child can improve a person’s working memory years later on specific tasks.Video games can be a contentious topic, particularly among parents or caregivers who may be concerned about the effects of spending hours in front of the console.Yet, it seems that some video gaming could actually be beneficial. Recent studies have shown that playing video games could improve learning and may even protect against dementia in older adults.The authors of a recent review of the evidence on video games concluded that gaming could have benefits for both cognitive and emotional skills.In a new study, which features in the journal Frontiers in Human Neuroscience, researchers from the Universitat Oberta de Catalunya in Barcelona trained volunteers to play “Super Mario 64” — a game that researchers have previously shown to induce structural changes in parts of the brain associated with executive function and spatial memory.The new study found that people who played video games as children showed greater improvements in their working memory than those who did not, suggesting that video games can have long lasting benefits for cognition.This study combined video game playing with transcranial magnetic stimulation (TMS), a noninvasive form of brain stimulation that scientists have studied as a treatment for mood disorders. In 2008, the Food and Drug Administration (FDA) approved its use for the treatment of major depression when other approaches have failed.Studies have also shown TMS to boost cognitive performance under some conditions, with more than 60 studies reporting that the treatment led to significant improvements in cognition, including in working memory (holding and manipulating information over a short period).The researchers behind the new study wanted to find out whether combining video game training and TMS could enhance cognitive function more than either element alone.They asked 27 healthy volunteers, with an average age of 29 years, to take part in 10 video game training sessions, during each of which they played “Super Mario 64” for an hour and a half.At the end of each session, the researchers applied TMS to part of the prefrontal cortex, which is at the front of the brain and is important for complex cognitive functions, such as working memory and reasoning. The researchers assessed the cognitive function of the participants before the study started, at the end of the 10 sessions, and 15 days after this.They assessed a range of cognitive functions, including reaction time, working memory, attention span, visuospatial skills, and problem-solving.Although the results overall showed very limited changes in cognitive ability, which seemed to result only from the video game training and not the TMS, the researchers did find that participants with early experience of video gaming had improved working memory.“People who were avid gamers before adolescence, despite no longer playing, performed better with the working memory tasks, which require mentally holding and manipulating information to get a result,” explains lead author of the study Dr. Marc Palaus, Ph.D.People with prior experience of playing video games (but not the actual game in the study) also showed improvements in processing and were better able to focus on relevant stimuli during the tasks.“People who played regularly as children performed better from the outset in processing 3D objects, although these differences were mitigated after the period of training in video gaming, when both groups showed similar levels,” adds Dr. Palaus.The results suggest that video games may induce cognitive changes that last for years after people have stopped playing.Dr. Palaus says that video games that provide motivation — making the player want to keep on playing — and also get more difficult to stay challenging require intensive use of brain resources, which makes them ideal for boosting cognitive ability.“Video games are a perfect recipe for strengthening our cognitive skills, almost without our noticing.”– Dr. Marc Palaus, Ph.D. It is important to note that this study included a small number of participants who were all healthy, young, and highly educated, meaning that the findings might not be more widely applicable.Talking about the findings of their study, Dr. Palaus stressed that these improvements only have a limited effect on the performance of other activities not linked to video gaming, as is the case with most cognitive training.
Read More

Continue Reading

Science & Health

Lax gun laws in neighboring states may increase firearm deaths

A US study suggests strong gun control regulations reduce a state’s firearm deaths, but having neighbors with more lenient laws undermines their effect.Share on PinterestNew research suggests that one state’s lax gun laws could undo the effects of its neighbor’s stricter firearm regulations.In 2017, 39,773 people died from gun-related injuries in the United States, according…

Published

on

By

Lax gun laws in neighboring states may increase firearm deaths

A US study suggests strong gun control regulations reduce a state’s firearm deaths, but having neighbors with more lenient laws undermines their effect.Share on PinterestNew research suggests that one state’s lax gun laws could undo the effects of its neighbor’s stricter firearm regulations.In 2017, 39,773 people died from gun-related injuries in the United States, according to the National Center for Injury Prevention and Control.Overall, research indicates that stronger state laws governing the sale and ownership of firearms reduce firearm-related deaths. However, some states have relatively high rates of gun deaths despite strict regulations. To investigate why this might be the case, scientists at the University of Alabama at Birmingham, and the Boston University School of Public Health at Boston, MA, looked into the effects of firearm laws in neighboring states.They used the Web-based Injury Statistics Query and Reporting System to obtain figures for firearm-related deaths in the 48 adjacent U.S. states from 2000 to 2017. There were 578,022 firearm deaths in total, including homicides and suicides, but excluding deaths due to shootings by police or other law enforcement agents. The scientists also searched the State Firearm Laws Database for laws in each state regarding:background checksgun dealer regulationsbuyer regulationsgun-trafficking lawsThe team used the number of these laws as a proxy for gun control strength in each state.If you would like to check your registration status or register to vote, we have added some useful links at the bottom of this article.Overall, stronger state gun laws were associated with reduced firearm deaths, but having a neighboring state with more permissive laws undermined this protective effect.Larger policy differences across state borders were associated with increased gun-related deaths, suicides, and homicides, though the results were statistically stronger for suicide than homicide.The authors conclude:“This study adds to the growing literature emphasizing the role played by neighboring states’ firearm regulations in addition to own-state firearm regulations in firearm deaths. Failing to account for neighboring states with weaker laws, in some instances, can make a state’s own regulations appear less effective in reducing firearm deaths.”The scientists calculate that, on average, failure to account for weaker firearm laws in neighboring states make it appear as though a state’s laws were about 20% less effective at reducing deaths than they really were.They report their findings in the American Journal of Preventive Medicine.The researchers write that higher prices and strong marketing regulations can lead consumers to purchase firearms in adjacent, relatively unregulated markets. They say these are a frequent source of the guns used in crimes.They believe their work supports the case for more cooperative legislation between neighboring states and at the federal level.“I think the main message of this study is that to solve a nationwide problem we need to think of a nationwide or at least a regional-level (i.e. multistate) approach, like we may also need for the COVID-19 pandemic,” says Dr. Ye Liu, who is a doctoral student in the Department of Health Care Organization and Policy at the University of Alabama and the first author of the study. “An ‘each state on its own’ approach is ultimately inadequate to address one of the biggest public health challenges in this country,” Dr. Liu adds.The authors acknowledge the number of gun-control laws may not perfectly reflect the strictness of a state’s regulations. In addition, they note states may vary in how diligently they enforce these laws.They call for further studies that might use alternative measures of regulatory strength, focus on specific categories of law, or explore the effects of regulations in more distant states. To check your voter registration status, click here to visit VoteAmerica, a nonprofit, nonpartisan organization dedicated to increasing voter turnout. They can also help you register to vote, vote by mail, request an absentee ballot, or find your polling place.
Read More

Continue Reading

Science & Health

COVID-19 will eventually become seasonal, researchers predict

A new study argues that COVID-19 is likely to become a seasonal disease similar to influenza — but not before a vaccine and greater herd immunity are achieved.Share on PinterestResearchers warn that COVID-19 outbreaks may become a seasonal occurrence.New research published in the journal Frontiers in Public Health suggests that SARS-CoV-2 is likely to be…

Published

on

By

COVID-19 will eventually become seasonal, researchers predict

A new study argues that COVID-19 is likely to become a seasonal disease similar to influenza — but not before a vaccine and greater herd immunity are achieved.Share on PinterestResearchers warn that COVID-19 outbreaks may become a seasonal occurrence.New research published in the journal Frontiers in Public Health suggests that SARS-CoV-2 is likely to be affected by the changing seasons in a way similar to other human coronaviruses and influenza.In temperate regions, this would mean reduced infections in the summer and peaks in the winter. However, this seasonality is only likely to occur once a vaccine is developed and greater herd immunity is achieved.Stay informed with live updates on the current COVID-19 outbreak and visit our coronavirus hub for more advice on prevention and treatment.The sudden emergence and rapid spread of SARS-CoV-2 and the disease it causes, COVID-19, have left scientists urgently attempting to develop vaccines to combat the virus and treatments for its disease.Another key area of research is how the virus is transmitted from one person to another.Understanding how the virus spreads is crucial, as it allows governments to enact policies that effectively limit viral transmission.While policies have varied from country to country, they have generally involved maintaining social distance, washing the hands regularly, and wearing face masks.This is because the virus can be transmitted on surfaces, through direct human contact, and via droplets expelled when a person sneezes, coughs, or talks.In addition to transmitting through droplets from the respiratory tract, the virus may also spread through aerosols: very small droplets that are expelled alongside larger ones or that form when larger droplets evaporate.Determining precisely how the virus transmits requires time and research. However, given the lethality of COVID-19, policy decisions need to be made urgently, based on the best evidence currently available. Making the best suggestions requires scientists to analyze emerging research on COVID-19 and past studies that have looked at similar viruses.Doing so may also allow researchers to better predict how the virus will react in the future.In the present study, the team pooled the latest research on COVID-19 and compared it with information about other viruses that affect the respiratory tract. They did this to predict whether the novel coronavirus is likely to become seasonal — particularly severe in the winter in temperate regions — or whether it will circulate throughout the year.The researchers noted that many other human coronaviruses are more prevalent in winter than in summer, as is the influenza virus thought to react to temperature similarly to SARS-CoV-2.They argue that this seasonal pattern will likely develop in SARS-CoV-2, due to the effects of the climate on the virus and on humans.First, the researchers point out, the climate can affect the stability of the virus. Previous research has suggested that enveloped viruses, including SARS-CoV-2, become more stable in cold weather. This means that they are able to survive for longer periods between hosts.Cold weather may also allow the virus to travel through the air more easily, while higher levels of ultraviolet radiation in the summer may be more likely to kill the virus.Second, cold weather may affect our physiology, making it easier for the virus to infect us. People also generally get less vitamin D in the winter, when sunlight is less intense, which has been linked to a weakened immune response to respiratory infections. In addition, people are more likely to stay indoors during the winter months, increasing the risk of viral transmission at home, work, and school, for example.While cold weather may increase the rate of transmission of SARS-CoV-2, the prevalence of the virus in countries with significant heat and high levels of moisture suggest that climatic conditions alone are not enough to make the virus seasonal.Instead, the researchers argue that seasonality is only likely once an effective vaccine has been developed and deployed, and once a greater level of herd immunity comes about as more people develop the infection.That means that, in the meantime, emergency measures remain crucial for limiting the spread of the virus — no matter the time of year.As study co-author Hadi Yassine, an assistant professor of infectious diseases at Qatar University, in Doha, notes: “The highest global COVID-19 infection rate per capita was recorded in the Gulf states, regardless of the hot summer season. Although this is majorly attributed to the rapid virus spread in closed communities, it affirms the need for rigorous control measures to limit virus spread until herd immunity is achieved.”As senior study author Hassan Zaraket, an assistant professor of virology at the American University of Beirut, in Lebanon, observes, “COVID-19 is here to stay, and it will continue to cause outbreaks year-round until herd immunity is achieved.”“Therefore, the public will need to learn to live with it and continue practicing the best prevention measures, including wearing of masks, physical distancing, hand hygiene, and avoidance of gatherings,” he adds.The authors stress that their study is a “best guess” at how SARS-CoV-2 may react to changing weather conditions. Although it can behave similarly to previous viruses, the new virus is unique and may react in unexpected ways.“This remains a novel virus, and despite the fast-growing body of science about it, there are still things that are unknown. Whether our predictions hold true or not remains to be seen in the future. But we think it’s highly likely, given what we know so far, [that] COVID-19 will eventually become seasonal, like other coronaviruses.”– Hassan Zaraket, Ph.D.For live updates on the latest developments regarding the novel coronavirus and COVID-19, click here.
Read More

Continue Reading
error: Content is protected !!