‘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 21,2020

New Delhi, Jul 21: The Centre has written to all states and union territories warning against the use of N-95 masks with valved respirators by people, saying these do not prevent the virus from spreading out and are "detrimental" to the measures adopted for its containment.

The Director General of Health Services (DGHS) in the Ministry of Health, in a letter to the Principal Secretaries of health and medical education of states, said it has been observed that there is "inappropriate use" of N-95 masks, particularly those with valved respirators, by the public other than designated health workers.

The DGHS referred to the advisory on the use of homemade protective cover for face and mouth available on the website of the Ministry of Health.

"It is to bring to your knowledge that the use of valved respirator N-95 masks is detrimental to the measures adopted for preventing the spread of coronavirus as it does not prevent the virus from escaping out of the mask. In view of the above, I request you to instruct all concerned to follow the use of face/mouth cover and prevent inappropriate use of N-95 masks," DGHS Rajiv Garg said in the letter.

The government had in April issued an advisory on the use of homemade protective cover for face and mouth, asking people to wear it, particularly when they step out of their residences.

The advisory stressed such face covers must be washed and cleaned each day, as instructed, and stated that any used cotton cloth can be used to make this face cover.

The colour of the fabric does not matter but one must ensure that the fabric is washed well in boiling water for five minutes and dried well before making the face cover. Adding salt to this water is recommended, it said.

It also listed the procedures of making such homemade masks, asking to ensure it fits the face well and there are no gaps on the sides.

It urges people to wash hands thoroughly before wearing the face cover, switching to another fresh one as the face cover becomes damp or humid, and never reusing it after single use without cleaning it.

"Never share the face cover with anyone. Every member in a family should have separate face cover," the advisory stated.

India's COVID-19 case tally crossed the 11-lakh mark on Monday, while the total number of recovered patients increased to over seven lakh, according to Union health ministry data.

The death toll due to the disease rose to 27,497 with 681 fatalities reported in one day.

The ministry data updated at 8 am on Monday showed that a record single-day jump of 40,425 COVID-19 cases had taken the total number of cases to 11,18,043.

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
June 20,2020

At a time when the country is yet to recover from the shock of losing 20 Indian soldiers in a violent clash with the Chinese People's Liberation Army (PLA) troops in Ladakh's Galwan Valley, another shocker has come to light with news coming of a malware hitting the Indian Railways network and snooping its data for foreign countries, including train movements, sources in the intelligence agencies said on Friday.

Meanwhile, Railways Board Chairman V K Yadav said that the national transporter keeps on receiving malware security threats and the engineers in the railways keep on taking all precautions and keeps on updating the firewalls to prevent data theft.

The news comes a day after the Dedicated Freight Corridor Corporation Limited (DFCCIL) decided to terminate the 417-km signalling project worth Rs 471 crore with Chinese firm Beijing National Railway Research and Design Institute of Signal and Communication Group Company Limited (BNRRDISC) due to non-performance.

According to intelligence agency sources, the system of the Railways has been hit by the APT 36 Malware campaign. The source said that the intel agencies have also alerted the Railway Board to instantly disconnect the system with the Internet and change the password immediately.

The source said the APT 36 Malware is connected to Pakistan, which is a close ally of China. The source further said that following the red flag from the intel agencies, the system of a senior Principal Executive Director of the Railways, working in its vigilance department, has been taken for cleaning the malware threat.

As per the source, through the APT 36 Malware campaign, data stored in the Indian Railways systems were being stolen and stored in foreign locations, including the movement of the trains.

He further claimed that the APT 36 Malware also tried to take defence movement data. 

The source said the APT 36 Malware effect was reported from at least four systems of the Indian Railways.

Responding to queries, the Railways Board Chairman said: "Whether it is our systems or the IRCTC, we continuously update it with firewalls, and it is an ongoing process as we get the updates." 

Yadav said that our system is updated time to time. "We get malware threat on a regular basis. And we look at it continuously," he said. 

When pressed further about the malware threat in four railways systems, he said: "It has not come to our notice that some information has been leaked. Our systems are secure and our engineers keep on working on it."

According to intel sources, besides Railways, there was also malware threat in the defence, central police organisations, education and healthcare sectors, the source said.

In view of the threat, the intel agencies have asked the departments concerned to change the passwords of emails and online services from secure computers, format the hard-disk of the affected computers after taking back-up and re-install the operating systems and other softwares.

Sources in the Railways had said on Thursday that DFFCIL, which is looking after the work of the Dedicated Freight Corridor Project, has decided to terminate the tender with BNRRDISC.

A source in the Railway Ministry said that it has informed the Railway Board and the World Bank to take the final decision in the matter.

The source said the project was awarded to the Chinese firm in 2016 for signalling and telecommunication work on the 417-km Kanpur-Deen Dayal Upadhyaya section of the Eastern Dedicated Freight Corridor (EDFC). 

The source disclosed that the contract was awarded to the Beijing National Railway Research and Design Institute in June 2016. The source further said that even after four years, the progress in the project was only 20%. The issues that led to the termination of the project are reluctance by the company to furnish technical documents, as per the contract agreement, such as logic design of electronic interlocking.

The source further said that other issues like non-availability of their engineers and authorised personnel on site were a serious constraint. Even physical work could not progress as they have no tie-up with local agencies. 

The 3,373-km DFC, a flagship project of the Railways, aims to augment rail transport capacity to meet the growing requirement of movement of goods by segregating freight from passenger traffic.

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 25,2020

The COVID-19 pandemic and the subsequent lockdown saw many people turning chefs overnight, but those who could not turned to online delivery of food. And not just any food, as per a new report, Indians "craved the most for Biryani" during the lockdown.

The "StatEATistics report: The Quarantine Edition" from food delivery platform Swiggy found that Indians ordered biryani over "5.5 lakh times" from their favourite restaurants.

The new normal might have opened a pandora's box of behavioral changes, but some old habits die hard like the love for Biryani, which took the top spot for overall orders. It was followed by butter naan and masala dosa at 3,35,185 and 3,31,423, respectively.

Biryani has topped the list of most ordered dishes for the fourth year in a row, the food delivery platform noted.

Indians didn't forget to indulge their sweet tooth in the uncertain months of lockdown. Their favourite comfort food during the lockdown period was the moist and decadent Choco Lava cake, ordered around 1,29,000 times.

"The humble Gulab Jamun (84,558) and chic Butterscotch Mousse cake (27,317) followed suit," said the report derived from Swiggy's order analysis in the past few months across cities that it is present in.

Also, as birthday parties moved to video calls, and virtual cake cutting sessions, according to the food delivery platform, it delivered nearly "1,20,000 cakes" to complete these celebrations.

According to the report, on average, "65,000 meal orders" were placed by 8 pm each day to make sure food arrived in time for dinner.

"It was the busiest hour for Swiggy delivery partners and restaurants. On average, they (customers) chose to tip Rs.23.65, with one particularly generous customer tipping Rs. 2500!," it added.

For those who only relied on home-made food during the quarantine, Swiggy delivered a whooping 323 million kgs of onions and 56 million kgs of bananas through its grocery section and hence ensured that its consumers were all stocked up.

That said, it also took care of the 'quick-fix meal' tribe -- consumers who resort to the evergreen college hacks of living on instant noodles.

"Around 3,50,000 packets of this ideal easy to cook meal were ordered during the lockdown," it said.

In all, Swiggy delivered 40 million orders across food, groceries, medicines and other household items during India's lockdowns. It also delivered over 73,000 bottles of sanitizers and hand wash along with 47,000 face masks as the definition of essentials' changed during these uncertain times.

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.