1. Home
  2. ‘AI doctor’ could boost survival in sepsis patients

‘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

About text formats
  • 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
February 10,2020

Washington D.C, Feb 10: Children's vulnerability towards depression, anxiety, impulsive behaviour, and poor cognitive performance could be determined by considering the hours of sleep they manage to get.

Sleep states are active processes that support the reorganisation of brain circuitry. This makes sleep especially important for children, whose brains are developing and reorganising rapidly.

In a study by researchers from the University of Warwick -- recently published in the journal Molecular Psychiatry -- cases of 11,000 children aged between 9 and 11 years from the Adolescent Brain Cognitive Development dataset were analyzed to find out the relationship between sleep duration and brain structure.

The study was carried out by researchers Professor Jianfeng Feng, Professor Edmund Rolls, Dr. Wei Cheng and colleagues from the University of Warwick's Department of Computer Science and Fudan University.

Measures of depression, anxiety, impulsive behaviour and poor cognitive performance in the children were associated with shorter sleep duration. Moreover, the depressive problems were associated with short sleep duration one year later.

The reduced brain volume of areas such as orbitofrontal cortex, prefrontal, and temporal cortex, precuneus, and supramarginal gyrus was found to be associated with the shorter sleep duration.

Professor Jianfeng Feng, from the University of Warwick's Department of Computer Science, comments: "The recommended amount of sleep for children 6 to 12 years of age is 9-12 hours. However, sleep disturbances are common among children and adolescents around the world due to the increasing demand on their time from school, increased screen time use, and sports and social activities."

A previous study showed that about 60 per cent of adolescents in the United States receive less than eight hours of sleep on school nights.

Professor Jianfeng Feng further added: "Our findings showed that the total score for behavior problems in children with less than 7 hours sleep was 53 per cent higher on average and the cognitive total score was 7.8 per cent lower on average than for children with 9-11 hours of sleep. It highlights the importance of enough sleep in both cognition and mental health in children."

Professor Edmund Rolls from the University of Warwick's Department of Computer Science also commented: "These are important associations that have been identified between sleep duration in children, brain structure, and cognitive and mental health measures, but further research is needed to discover the underlying reasons for these relationships."

Comments

Add new comment

About text formats
  • 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
August 2,2020

Washington, Aug 2: Children under the age of five have between 10 to 100 times greater levels of genetic material of the coronavirus in their noses compared to older children and adults, a study in JAMA Pediatrics said Thursday.

Its authors wrote this meant that young children might be important drivers of Covid-19 transmission within communities -- a suggestion at odds with the current prevailing narrative.

The paper comes as the administration of US President Donald Trump is pushing hard for schools and daycare to reopen in order to kickstart the economy.

Between March 23 and April 27, researchers carried out nasal swab tests on 145 Chicago patients with mild to moderate illness within one week of symptom onset.

The patients were divided into three groups: 46 children younger than five-years-old, 51 children aged five to 17 years, and 48 adults aged 18 to 65 years.

The team, led by Dr Taylor Heald-Sargent of the Ann & Robert H. Lurie Children's Hospital, observed, "a 10-fold to 100-fold greater amount of SARS-CoV-2 in the upper respiratory tract of young children."

15 countries with the highest number of cases, deaths due to the Covid-19 pandemic

The authors added that a recent lab study had demonstrated that the more viral genetic material was present, the more infectious virus could be grown.

It has also previously been shown that children with high viral loads of the respiratory syncytial virus (RSV) are more likely to spread the disease.

"Thus, young children can potentially be important drivers of SARS-CoV-2 spread in the general population," the authors wrote.

"Behavioral habits of young children and close quarters in school and daycare settings raise concern for SARS-CoV-2 amplification in this population as public health restrictions are eased," they concluded.

The new findings are at odds with the current view among health authorities that young children -- who, it has been well established, are far less likely to fall seriously ill from the virus -- don't spread it much to others either.

However, there has been fairly little research on the topic so far.

One recent study in South Korea found children aged 10 to 19 transmitted Covid-19 within households as much as adults, but children under nine transmitted the virus at lower rates.

Comments

Add new comment

About text formats
  • 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
June 21,2020

Lower neighbourhood socioeconomic status and greater household crowding increase the risk of becoming infected with SARS-CoV-2, the virus that causes COVID-19, warn researchers.

"Our study shows that neighbourhood socioeconomic status and household crowding are strongly associated with risk of infection," said study lead author Alexander Melamed from Columbia University in the US.

"This may explain why Black and Hispanic people living in these neighbourhoods are disproportionately at risk for contracting the virus," Melamed added.

For the findings, published in the journal JAMA, the researchers examined the relationships between COVID-19 infection and neighbourhood characteristics in 396 women who gave birth during the peak of the Covid-19 outbreak in New York City. Since March 22, all women admitted to the hospitals for delivery have been tested for the virus, which gave the researchers the opportunity to detect all infections -- including infections with no symptoms -- in a defined population

The strongest predictor of COVID-19 infection among these women was residence in a neighbourhood where households with many people are common.The findings showed that women who lived in a neighbourhood with high household membership were three times more likely to be infected with the virus. Neighbourhood poverty also appeared to be a factor, the researchers said.Women were twice as likely to get COVID-19 if they lived in neighbourhoods with a high poverty rate, although that relationship was not statistically significant due to the small sample size.

The study revealed that there was no association between infection and population density.

"New York City has the highest population density of any city in the US, but our study found that the risks are related more to density in people's domestic environments rather than density in the city or within neighbourhoods," says co-author Cynthia Gyamfi-Bannerman."

The knowledge that SARS-CoV-2 infection rates are higher in disadvantaged neighbourhoods and among people who live in crowded households could help public health officials target preventive measures," the authors wrote.

Recently, another study published in the Journal of the American Planning Association, showed that dense areas were associated with lower COVID-19 death rates.

Comments

Add new comment

About text formats
  • 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.