‘AI doctor’ could boost survival in sepsis patients

Agencies
October 23, 2018

London, Oct 23: Scientists have created an artificial intelligence (AI) system that could help treat patients with sepsis by predicting the best treatment strategy. The system developed by researchers from Imperial College London in the UK analysed the records of about 100,000 hospital patients in intensive care units and every single doctor’s decisions affecting them. The findings, published in the journal Nature Medicine, showed the AI system made more reliable treatment decisions than human doctors.

The system, called AI Clinician, could be used alongside medical professionals, to help doctors decide the best treatment strategy for patients, researchers said. Sepsis can cause a drastic drop in blood pressure which can leave organs deprived of blood flow and oxygen, and can ultimately lead to multiple organ failure and death. To raise blood pressure and keep the heart pumping, doctors give extra fluids, usually in the form of a salt solution, as well as medication that tightens blood vessels and raises blood pressure, called vasopressors.

Researchers looked back at US patient records from 130 intensive care units over a 15 year period to explore whether the AI system’s recommendations might have been able to improve patient outcomes, compared with standard care. The researchers now hope to trial the system in intensive care units in the UK. “Sepsis claims six million lives worldwide — so we desperately need new tools at our disposal to help patients,” said Aldo Faisal from Imperial College London.

“Our new AI system was able to analyse a patient’s data –such as blood pressure and heart rate — and decide the best treatment strategy. We found that when the doctor’s treatment decision matched what the AI system recommended, they had a better chance of survival,” Faisal said. To help doctors decide which approach would boost a patient’s chance of survival, the research team created an AI system that would assess a patient’s vital signs and recommend the best treatment approach. The system analysed the medical records of 96,000 US patients with sepsis in intensive care units.

Using a process called reinforcement learning — where robots learn how to make decisions and solve a problem — the AI Clinician went through each patient’s case and worked out the best strategy of keeping a patient alive. The system calculated 48 variables including age, vital signs and pre-existing conditions. It then predicted the best treatment strategy for each patient with sepsis. The results revealed that 98 per cent of the time, the AI system matched or was better than the human doctors’ decision, researchers said.

The study also found that mortality was lowest in patients where the human doctor’s doses of fluids and vasopressor matched the AI system’s suggestion. However, when the doctor’s decision differed from the AI system, a patient had a reduced chance of survival. The team found when the doctor’s decision varied from the AI Clinician’s suggestion, it was on average to administer too much fluid and too little vasopressor but importantly it varied between individual patients.

“The AI Clinician was able to ‘learn’ from far more patients than any doctor could see in a lifetime,” said Anthony Gordon, a professor at Imperial College London. “It has learnt from 100,000 patients and ‘remembered’ them all equally whereas doctors are always susceptible to recall bias, where they particularly remember recent cases or unusual cases,” Gordon said.

Comments

Add new comment

  • Coastaldigest.com reserves the right to delete or block any comments.
  • Coastaldigset.com is not responsible for its readers’ comments.
  • Comments that are abusive, incendiary or irrelevant are strictly prohibited.
  • Please use a genuine email ID and provide your name to avoid reject.
Agencies
July 24,2020

Colorado, Jul 24: A new study has found that physical stress in one's job may be associated with faster brain ageing and poorer memory.

Aga Burzynska, an assistant professor in the Department of Human Development and Family Studies, and her research team connected occupational survey responses with brain-imaging data from 99 cognitively normal older adults, age 60 to 79. They found that those who reported high levels of physical stress in their most recent job had smaller volumes in the hippocampus and performed poorer on memory tasks. The hippocampus is the part of the brain that is critical for memory and is affected in both normal ageing and in dementia.

Their findings were published this summer in Frontiers in Human Neuroscience under the research topic 'Work and Brain Health Across the Lifespan.'

"We know that stress can accelerate physical ageing and is the risk factor for many chronic illnesses," Burzynska said. "But this is the first evidence that occupational stress can accelerate brain and cognitive ageing."

She added that it is important to understand how occupational exposures affect the ageing of our brains.

"An average American worker spends more than eight hours at work per weekday, and most people remain in the workforce for over 40 years," Burzynska said. "By pure volume, occupational exposures outweigh the time we spend on leisure social, cognitive and physical activities, which protect our ageing minds and brains."

Physical demands at work

Burzynska explained that the association between "physical stress" and brain/memory were driven by physical demands at work. These included excessive reaching, or lifting boxes onto shelves, not necessarily aerobic activity. This is important because earlier work by Burzynska and her colleagues showed that leisure aerobic exercise is beneficial for brain health and cognition, from children to very old adults. Therefore, the researchers controlled for the effects of leisure physical activity and exercise.

As expected, leisure physical activity was associated with greater hippocampal volume, but the negative association with physical demands at work persisted.

"This finding suggests that physical demands at work may have parallel yet opposing associations with brain health," Burzynska explained. "Most interventions for postponing cognitive decline focus on leisure, not on your job. It's kind of unknown territory, but maybe future research can help us make some tweaks to our work environment for long-term cognitive health."

She added that the results could have important implications for society.

"Caring for people with cognitive impairment is so costly, on economic, emotional and societal levels," Burzynska said. "If we can support brain health earlier, in middle-aged workers, it could have an enormous impact."

The researchers considered and corrected for several other factors that could be related to work environment, memory and hippocampus, such as age, gender, brain size, educational level, job title, years in the occupation and general psychological stress.

One piece of the puzzle

"The research on this topic is so fragmented," Burzynska said. "One previous study linked mid-life managerial experience with greater hippocampus volume in older age. Another showed that taxi drivers had larger hippocampi than a city's bus drivers, presumably due to the need to navigate. In our study, job complexity and psychological stress at work were not related to hippocampal volume and cognition. Clearly, our study is just one piece of the puzzle, and further research is needed."

The magnetic resonance imaging (MRI) data used for the study was collected at the University of Illinois Urbana-Champaign between 2011 and 2014.

CSU researchers now can collect MRI data with the new 3T scanner at the University's Translational Medicine Institute.

With this new capability, Burzynska, along with Michael Thomas and Lorann Stallones of CSU's Department of Psychology, is launching a new project, "Impact of Occupational Exposures and Hazards on Brain and Cognitive Health Among Aging Agricultural Workers," which will involve collecting MRI brain scans and identifying risk and protective factors that could help the agricultural community age successfully. The project recently obtained funding as an Emerging Issues Short-Term Project from the High Plains Intermountain Center for Agricultural Health and Safety.

The Department of Human Development and Family Studies is part of CSU's College of Health and Human Sciences.

Comments

Add new comment

  • Coastaldigest.com reserves the right to delete or block any comments.
  • Coastaldigset.com is not responsible for its readers’ comments.
  • Comments that are abusive, incendiary or irrelevant are strictly prohibited.
  • Please use a genuine email ID and provide your name to avoid reject.
Agencies
July 3,2020

Apart from the many benefits of doing exercise, new research has now found that exercise can slow down or prevent the development of macular degeneration and may benefit other common causes of vision loss, such as glaucoma and diabetic retinopathy.

The new study from the University of Virginia School of Medicine found that exercise reduced the harmful overgrowth of blood vessels in the eyes of lab mice by up to 45 per cent. This tangle of blood vessels is a key contributor to macular degeneration and several other eye diseases.

The study represents the first experimental evidence showing that exercise can reduce the severity of macular degeneration, a leading cause of vision loss, the scientists report. Ten million Americans are estimated to have the condition.

"There has long been a question about whether maintaining a healthy lifestyle can delay or prevent the development of macular degeneration. The way that question has historically been answered has been by taking surveys of people, asking them what they are eating and how much exercise they are performing," said researcher Bradley Gelfand, PhD, of UVA's Center for Advanced Vision Science.

"That is basically the most sophisticated study that has been done. The problem with that is that people are notoriously bad self-reporters ... and that can lead to conclusions that may or not be true. This [study] offers hard evidence from the lab for the very first time," Gelfand added.

Enticingly, the research found that the bar for receiving the benefits from exercise was relatively low - more exercise didn't mean more benefit.

"Mice are kind of like people in that they will do a spectrum of exercise. As long as they had a wheel and ran on it, there was a benefit. The benefit that they obtained is saturated at low levels of exercise," Gelfand said.

An initial test comparing mice that voluntarily exercised versus those that did not found that exercise reduced the blood vessel overgrowth by 45%. A second test, to confirm the findings, found a reduction of 32 per cent.

The scientists aren't certain exactly how exercise is preventing the blood vessel overgrowth. There could be a variety of factors at play, they say, including increased blood flow to the eyes.

Gelfand, of UVA's Department of Ophthalmology and Department of Biomedical Engineering, noted that the onset of vision loss is often associated with a decrease in exercise.

"It is fairly well known that as people's eyes and vision deteriorate, their tendency to engage in physical activity also goes down. It can be a challenging thing to study with older people. ... How much of that is one causing the other?" he said.
The researchers already have submitted grant proposals in hopes of obtaining funding to pursue their findings further.

"The next step is to look at how and why this happens, and to see if we can develop a pill or method that will give you the benefits of exercise without having to exercise," Gelfand said.

He explained, "We're talking about a fairly elderly population [of people with macular degeneration], many of whom may not be capable of conducting the type of exercise regimen that may be required to see some kind of benefit." (He urged people to consult their doctors before beginning any aggressive exercise program.)
Gelfand, a self-described couch potato, disclosed a secret motivation for the research: "One reason I wanted to do this study was sort of selfish. I was hoping to find some reason not to exercise," he joked. "It turned out exercise really is good for you."

Comments

Add new comment

  • Coastaldigest.com reserves the right to delete or block any comments.
  • Coastaldigset.com is not responsible for its readers’ comments.
  • Comments that are abusive, incendiary or irrelevant are strictly prohibited.
  • Please use a genuine email ID and provide your name to avoid reject.
Agencies
March 16,2020

New Delhi, Mar 16: A recent survey across 140 districts of the country shows that about 54 per cent of Indians are finding travelling to be unsafe as the deadly coronavirus (COVID-19) pandemic sweeps globally.

The big worry that people have is community transmission, something that researchers from around the world have approximated at 10 per cent of total infections and more common in places like Wuhan in China, South Korea, Iran and Italy.

The months of March to June have historically been high travel season for most Indians, largely due to the summer vacations in schools. "But it seems that Indians do not want to take a chance with this rather scary virus and are either cancelling or postponing their travel plans," concluded the survey by LocalCircles.

The survey gathered more than 22,000 responses from participants in tier one, two and three cities. It said 48 per cent Indians plan to cancel their international business travel for the next four months.

Besides, nearly 38 per cent of respondents said they had to pay cancellation fee to the website, travel agent, airline or railways.

"These are testing times for the entire travel and tourism industry -- airlines, hotels, travel agents as well as small tour and taxi operators. The best solution at this point is to adjust cost structures, stay flexible and work with a collective approach to minimise the period of impact to both citizens and business," said LocalCircles.

Comments

Add new comment

  • Coastaldigest.com reserves the right to delete or block any comments.
  • Coastaldigset.com is not responsible for its readers’ comments.
  • Comments that are abusive, incendiary or irrelevant are strictly prohibited.
  • Please use a genuine email ID and provide your name to avoid reject.