‘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.
News Network
February 26,2020

New York, Feb 26:  A new wearable sensor that works in conjunction with artificial intelligence (AI) technology could help doctors remotely detect critical changes in heart failure patients days before a health crisis occurs, says a study.

The researchers said the system could eventually help avert up to one in three heart failure readmissions in the weeks following initial discharge from the hospital and help patients sustain a better quality of life.

"This study shows that we can accurately predict the likelihood of hospitalisation for heart failure deterioration well before doctors and patients know that something is wrong," says the study's lead author Josef Stehlik from University of Utah in the US.

"Being able to readily detect changes in the heart sufficiently early will allow physicians to initiate prompt interventions that could prevent rehospitalisation and stave off worsening heart failure," Stehlik added.

According to the researchers, even if patients survive, they have poor functional capacity, poor exercise tolerance and low quality of life after hospitalisations.

"This patch, this new diagnostic tool, could potentially help us prevent hospitalizations and decline in patient status," Stehlik said.

For the findings, published in the journal Circulation: Heart Failure, the researchers followed 100 heart failure patients, average age 68, who were diagnosed and treated at four veterans administration (VA) hospitals in Utah, Texas, California, and Florida.

After discharge, participants wore an adhesive sensor patch on their chests 24 hours a day for up to three months.

The sensor monitored continuous electrocardiogram (ECG) and motion of each subject.

This information was transmitted from the sensor via Bluetooth to a smartphone and then passed on to an analytics platform, developed by PhysIQ, on a secure server, which derived heart rate, heart rhythm, respiratory rate, walking, sleep, body posture and other normal activities.

Using artificial intelligence, the analytics established a normal baseline for each patient. When the data deviated from normal, the platform generated an indication that the patient's heart failure was getting worse.

Overall, the system accurately predicted the impending need for hospitalization more than 80 per cent of the time.

On average, this prediction occurred 10.4 days before a readmission took place (median 6.5 days), the study 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
January 16,2020

Thiruvananthapuram, Jan 16: Kerala Tourism on Wednesday shared a recipe of a popular meat dish in the Central Travancore region of Kerala, Beef Ularthiyathu, which is a special delicacy in the region.

Taking to its Twitter handle, the Kerala Tourism wrote, "Tender chunks of beef, slow-roasted with aromatic spices, coconut pieces, and curry leaves. A recipe for the most classic dish, Beef Ularthiyathu, the stuff of legends, from the land of spices, Kerala."

The State Tourism also shared the recipe of the delicacy with Twitteratis.

The tweet which has garnered 3.5 thousand likes so far had received a mixed response

While some said "beef is not Kerala's culture", others termed the recipe 'a match made in heaven".

Dr Vireandta Jilowa wrote, "Surprised to see it, that beef is being consumed despite BJP government in the Centre."

"We are not slaves of BJP at the Centre....people eat whatever they like in this state, including beef, pork, mutton and fish," another user Tatheesh Vijayakumar wrote.

In 2017, The Minister for Environment, Forest and Climate Change Harsh Vardhan had ordered that the ministry has notified the Prevention of Cruelty to Animals (Regulation of Livestock Markets) Rules, 2017 to ensure that the sale of cattle is not meant for slaughter purposes.

Regulating animal trade is a state business, but animal welfare is a central subject.

In lieu of this, there was widespread opposition of the order, with many states openly denying accepting the notification.

Porotta and Kappa biriyani with beef are counted as delicacies by Keralites. 

Also Read: The Art of Prepping Meat

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.
News Network
January 31,2020

Jan 31: Cervical cancer could be eliminated worldwide as a public health issue within the next 100 years, according to two studies which may lead to better strategies for screening and vaccination against the malignant disease.

According to the studies, published in the journal The Lancet, more than 74 million cervical cancer cases, and 60 million deaths could be averted, and the disease eliminated in the 78 countries which have the highest disease burden.

The researchers, including those from Laval University in Canada, said cervical cancer is the second most frequent cancer among women in low-income and lower-middle-income countries (LMICs) with 2,90,000 (51 per cent) of the 5,70,000 new cases worldwide reported in women living in LMICs.

In the current studies, the scientists used the WHO draft strategy of cervical cancer elimination which defines plans for vaccination against the disease's causative agent, the human papillomavirus (HPV).

These plans, they explained, call for 90 per cent of girls to be vaccinated against HPV by 2030, and for 70 per cent of women to be screened for cervical cancer once or twice in their lifetime.

About 90 per cent of women with precancerous lesions, or cervical cancer are also advised to receive appropriate treatment, according to the WHO draft strategy, the scientists said.

In the second study, the research team analysed the impact of three elements of the WHO strategy on deaths from cervical cancer -- modelling the impact of scaling up cancer treatment, as well as vaccination and screening

"Our findings emphasise the importance of acting immediately to combat cervical cancer on all three fronts," said Karen Canfell from the University of Sydney in Australia, who co-led both the studies.

"In just 10 years, it's possible to reduce deaths from the disease by a third and, over the next century, more than 60 million women's lives could be saved. This would represent an enormous gain in terms of both quality of life, and lives saved," Canfell said.

By adding the two screening tests, and with the treatment of precancerous cervical lesions, cases of the cancer may drop by 97 per cent, and 72 million cervical cancer cases could be averted over the next century, the researchers said.

Scaling-up of appropriate cancer treatment could avert 62 million cervical cancer deaths, the study noted.

"For the first time, we've estimated how many cases of cervical cancer could be averted if WHO's strategy is rolled out and when elimination might occur," said Marc Brisson, study co-author from Laval University.

"Our results suggest that to eliminate cervical cancer it will be necessary to achieve both high vaccination coverage, and a high uptake of screening and treatment, especially in countries with the highest burden of the disease," Brisson added.

Based on the results of the studies, WHO's cervical cancer elimination strategy has been updated which will be presented for adoption at the World Health Assembly in May 2020, the scientists noted.

"If the strategy is adopted and applied by member states, cervical cancer could be eliminated in high income countries by 2040, and across the globe within the next century, which would be a phenomenal victory for women's health," Brisson said.

"However, this can only be achieved with considerable international financial and political commitment, in order to scale-up prevention and treatment," he added.

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.