Connect with us

News

Using Personal Data To Predict Blood Pressure

Published

on

Engineers at UC San Diego used wearable off-the-shelf technology and machine learning to predict, for the first time, an individual’s blood pressure and provide personalized recommendations to lower it based on this data.

Their work earned the title of Best Paper at IEEE Healthcom 2018. To the researchers’ knowledge, this is the first work investigating daily blood pressure prediction and its relationship to health behavior data collected by wearables.

When doctors tell their patients to make a lot of significant lifestyle changes — exercise more, sleep better, lower their salt intake etc. — it can be overwhelming, and compliance is not very high, said Sujit Dey, co-author of the paper and Director of the Center for Wireless Communications at UC San Diego’s Jacobs School of Engineering where he’s a professor in the Department of Electrical and Computer Engineering.

“What if we could pinpoint the one health behavior that most impacts an individual’s blood pressure, and have them focus on that one goal, instead,” Dey asked.

Dey and co-author Po-Han Chiang, a graduate student in the Mobile Systems Design Lab in the Department of Electrical and Computer Engineering at UC San Diego’s Jacobs School of Engineering, collected sleep, exercise and blood pressure data from eight patients over 90 days using a FitBit Charge HR and Omron Evolv wireless blood pressure monitor. Using machine learning and this data from existing wearable devices, they developed an algorithm to predict the users’ blood pressure and show which particular health behaviors affected it most.

This study affirmed the importance of personalized data over generalized information. While many health databases add large amounts of patient data into one model, considering all patients together to make health suggestions, the personalized information in this study was more effective. For example, one subject’s blood pressure was most affected by the number of minutes they were sedentary throughout the day. Changing that one factor had a significant impact, lowering their average systolic blood pressure by 15.4 percent and their diastolic blood pressure by 14.2 percent in one week. For another subject, the time they went to bed was the most important factor in lowering their blood pressure based on their historical data. When this subject went to bed a total of 58 minutes earlier over the week prior, they experienced a 3.6 percent drop systolic blood pressure and 6.6 percent decrease in their average diastolic blood pressure from the previous week.

“This research shows that using wireless wearables and other devices to collect and analyze personal data can help transition patients from reactive to continuous care,” said Dey.

“Instead of saying ‘My blood pressure is high therefore I’ll go to the doctor to get medicine,’ giving patients and doctors access to this type of system can allow them to manage their symptoms on a continuous basis.”

Dey and Chiang have recently teamed up with clinicians at UC San Diego Health and are working to test their predictive model on a larger sample size, provide one day ahead prediction, and study the long-term effect of health behaviors on blood pressure.

News

Do You Know The Carbon Footprint Of Your Food Choices?

Published

on

Shoppers greatly underestimate the difference their food choices can make to climate change, but they’ll favour items with a lower carbon footprint if they’re given clear information on the label, according to new research from the University of Technology Sydney and Duke University.

Between 19% and 29% of global greenhouse gas emissions come from food production, with beef and lamb the biggest contributors, so shifting diets towards greater fruit and vegetable intake is a promising strategy for reducing climate change.

Lead author Dr Adrian Camilleri wanted to know how well consumers understood the carbon consequences of their food choices, as previous research had shown people significantly underestimate the carbon emissions from electrical appliances.

“With an appliance such as a heater you can feel the energy used and see an electricity bill at the end of the month, so the impact is quite salient, whereas the impact of food production is largely invisible,” says Dr Camilleri.

The study, published in the journal Nature Climate Change, asked more than 1000 people to estimate the energy embedded in 19 foods and 18 appliances, and the amount of greenhouse gas emissions associated with those appliances and foods.

The researchers found participants significantly underestimated energy consumption and greenhouse gas emissions for both electrical appliances and foods – but food was more severely underestimated.

“If you ask people to guess the difference between items such as beef and vegetable soup on the environment they assume there is not much difference, but beef soup creates more than 10 times the amount of greenhouse gases than vegetable soup,” says Dr Camilleri.

“This is a bit of a blind spot because if someone wants to reduce their greenhouse gas emissions, they might think to turn off the heater, drive less or fly less. Very few people think to eat less beef.”

The researchers also looked at whether they could improve people’s perception of the environmental impact of their food choices through the use of labelling, in the same way that a five-star rating system for electrical appliances conveys energy use.

They presented 120 participants with a choice of soups to buy. When the soups had a carbon footprint label, participants bought fewer beef soups and more vegetable soups than when there was no label provided.

The research suggests that the introduction of carbon footprint labels on food items could be a simple intervention to increase understanding of energy use and greenhouse gas emissions from food production, and so reduce environmental impacts.

Greenhouse gases emerging from beef and lamb production include those created in the production of fertiliser for feed, methane emitted from the animals, livestock transportation and the loss of trees to clear land for pasture.

A vegan diet based on fruits, vegetables and grains has the least impact on the environment, with pork, chicken and fish creating a moderate impact, and beef and lamb the greatest impact.

“The choices we make at the dinner table can have a significant impact on global challenges such as climate change, and our research shows consumers are keen to make that choice,” says Dr Camilleri.g

Continue Reading

News

How A Personality Trait Puts You At Risk For Cybercrime

Published

on

Impulse online shopping, downloading music and compulsive email use are all signs of a certain personality trait that make you a target for malware attacks. New research from Michigan State University examines the behaviors – both obvious and subtle – that lead someone to fall victim to cybercrime involving Trojans, viruses and malware.

“People who show signs of low self-control are the ones we found more susceptible to malware attacks,” said Tomas Holt, professor of criminal justice and lead author of the research.

“An individual’s characteristics are critical in studying how cybercrime perseveres, particularly the person’s impulsiveness and the activities that they engage in while online that have the greatest impact on their risk.”

Low self-control, Holt explained, comes in many forms. This type of person shows signs of short-sightedness, negligence, physical versus verbal behavior and an inability to delay gratification.

“Self-control is an idea that’s been looked at heavily in criminology in terms of its connection to committing crimes,” Holt said.

“But we find a correlation between low self-control and victimization; people with this trait put themselves in situations where they are near others who are motivated to break the law.”

The research, published in Social Science Computer Review, assessed the self-control of nearly 6,000 survey participants, as well as their computers’ behavior that could indicate malware and infection. To measure victimization, Holt and his team asked participants a series of questions about how they might react in certain situations. For computer behavior, they asked about their computer having slower processing, crashing, unexpected pop-ups and the homepage changing on their web browser.

“The internet has omnipresent risks,” Holt said.

“In an online space, there is constant opportunity for people with low self-control to get what they want, whether that is pirated movies or deals on consumer goods.”

As Holt explained, hackers and cybercriminals know that people with low self-control are the ones who will be scouring the internet for what they want – or think they want – which is how they know what sites, files or methods to attack.

Understanding the psychological side of self-control and the types of people whose computers become infected with malware – and who likely spread it to others – is critical in fighting cybercrime, Holt said. What people do online matters, and the behavioral factors at play are entirely related to risks.

Computer scientists, Holt said, approach malware prevention and education from a technical standpoint; they look for new software solutions to block infections or messaging about the infections themselves. This is important, but it is also essential to address the psychological side of messaging to those with low self-control and impulsive behaviors.

“There are human aspects of cybercrime that we don’t touch because we focus on the technical side to fix it,” he said.

“But if we can understand the human side, we might find solutions that are more effective for policy and intervention.”

Looking ahead, Holt hopes to help break the silos between computer and social sciences to think holistically about fighting cybercrime.

“If we can identify risk factors, we can work in tandem with technical fields to develop strategies that then reduce the risk factors for infection,” Holt said.

“It’s a pernicious issue we’re facing, so if we can attack from both fronts, we can pinpoint the risk factors and technical strategies to find solutions that improve protection for everyone.”

Continue Reading

News

Unrelated Events Are Linked in Memory When They Happen Close Together

Published

on

When two events occur within a brief window of time they become linked in memory, such that calling forth memory of one helps retrieve memory for the other event, according to research published in Psychological Science, a journal of the Association for Psychological Science. This happens even when temporal proximity is the only feature that the two events share.

“Our research shows that people are constantly recording information about the order in which events happen, even if those events are unrelated. They can then use the order to help search memory,” explains psychological scientist M. Karl Healey of Michigan State University.

Memory scientists have long been interested in determining whether temporal proximity acts as a tether of sorts that connects memories for different events. In most studies, researchers have tried to examine the phenomenon by asking people to memorize lists of words in the lab, but it is unclear how well this lab-based approach translates to memory for real-world events.

“In the fall of 2016, I was obsessing over US election coverage and it occurred to me that many other people probably were, too. This provided the opportunity for a more naturalistic test—we could ask people to remember news stories rather than word lists,” Healey explains.

In one online study, Healey and coauthor Mitchell G.Uitvlugt collected and analyzed data following Election Day in 2016. The study participants had 7 minutes to recall as many election-related news stories as they could – for each story, they also drafted a short newspaper-style headline.

Healey and Uitvlugt identified actual news stories that corresponded with the headlines generated by the participants, noting the date that the stories appeared. For their analyses, the researchers did not include stories that were not associated with specific election-related events. This process yielded 7,759 headlines from 855 participants.

The researchers then calculated a lag score that measured the transition, in days, from one headline in a participant’s story sequence to the next.

The results showed that participants tended to recall stories in time-based clusters: Short transitions between stories (0 to 10 days) were much more common than would be expected according to chance. Furthermore, long transitions of more than 50 days were less frequent than one would expect by chance. The analyses showed that what participants remembered wasn’t due to news events naturally clustering close together in time but rather the clustering of stories together in memory.

This pattern held even after the researchers accounted for similarity between events. And a second online study, in which a separate group of 561 participants recalled news stories from the previous 4 months, showed similar results.

“I was surprised at how well these real-world data agreed with lab data,” says Healey.

“Although remembering world events you’ve read about over the course of months seems different than memorizing a list of random words presented over the course of minutes, at a fundamental level it seems both are governed by the same principles.”

Uitvlugt and Healey point out that the participants could not have prepared for the memory task, which rules out the possibility that participants used specific strategies when the events occurred to aid subsequent recall. Instead, the findings suggest that our memories are tagged with time-correlated information as we encode them, and that this information can be used when we search memory later on.

“This research tells us something about memory in general. It suggests we all have a tendency to bind events together in memory when they occur near together in time,” Healey says.

Continue Reading

Like Us on Facebook

Trending Posts

News19 hours ago

Do You Know The Carbon Footprint Of Your Food Choices?

Shoppers greatly underestimate the difference their food choices can make to climate change, but they’ll favour items with a lower...

News19 hours ago

How A Personality Trait Puts You At Risk For Cybercrime

Impulse online shopping, downloading music and compulsive email use are all signs of a certain personality trait that make you...

News19 hours ago

Unrelated Events Are Linked in Memory When They Happen Close Together

When two events occur within a brief window of time they become linked in memory, such that calling forth memory...

News19 hours ago

Gently Stroking Babies Before Medical Procedures May Reduce Pain Processing

Researchers found that gently stroking a baby seems to reduce activity in the infant brain associated with painful experiences. Their...

News19 hours ago

Depression, Anxiety May Take Same Toll on Health as Smoking and Obesity

An annual physical typically involves a weight check and questions about unhealthy habits like smoking, but a new study from...

News2 days ago

How Your Colleague’s Rudeness Affects Your and Your Partner’s Sleep

Rudeness. Sarcastic comments. Demeaning language. Interrupting or talking over someone in a meeting. Workplace incivilities such as these are becoming...

News2 days ago

Study Shows Magnesium Optimizes Vitamin D Status

A randomized trial by Vanderbilt-Ingram Cancer Center researchers indicates that magnesium optimizes vitamin D status, raising it in people with...

Trending