‘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 2,2020

London, Jul 2: The World Health Organisation says smoking is linked to a higher risk of severe illness and death from the coronavirus in hospitalised patients, although it was unable to specify exactly how much greater those risks might be.

In a scientific brief published this week, the U.N. health agency reviewed 34 published studies on the association between smoking and Covid-19, including the probability of infection, hospitalisation, severity of disease and death.

WHO noted that smokers represent up to 18% of hospitalised coronavirus patients and that there appeared to be a significant link between whether or not patients smoked and the severity of disease they suffered, the type of hospital interventions required and patients' risk of dying.

In April, French researchers released a small study suggesting smokers were at less risk of catching Covid-19 and planned to test nicotine patches on patients and health workers — but their findings were questioned by many scientists at the time who cited the lack of definitive data.

WHO says "the available evidence suggests that smoking is associated with increased severity of disease and death in hospitalized Covid-19 patients. It recommends that smokers quit.

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
May 13,2020

California, May 13: A fasting-mimicking diet could be more effective at treating some types of cancer when combined with vitamin C, suggests a new study conducted by the scientists from USC and the IFOM Cancer Institute in Milan.

In studies on mice, researchers found that the combination delayed tumour progression in multiple mouse models of colorectal cancer; in some mice, it caused disease regression. The results were published in the journal Nature Communications.

"For the first time, we have demonstrated how a completely non-toxic intervention can effectively treat an aggressive cancer," said Valter Longo, the study senior author and the director of the USC Longevity Institute at the USC Leonard Davis School of Gerontology and professor of biological sciences at the USC Dornsife College of Letters, Arts and Sciences.

"We have taken two treatments that are studied extensively as interventions to delay ageing-- a fasting-mimicking diet and vitamin C -- and combined them as a powerful treatment for cancer," added Longo.

The researchers said that while fasting remains a challenging option for cancer patients, a safer, more feasible option is a low-calorie, plant-based diet that causes cells to respond as if the body were fasting.

Their findings suggest that a low-toxicity treatment of fasting-mimicking diet plus vitamin C has the potential to replace more toxic treatments.

Results of prior research on the cancer-fighting potential of vitamin C have been mixed. Recent studies, though, are beginning to show some efficacy, especially in combination with chemotherapy.

In this new study, the research team wanted to find out whether a fasting-mimicking diet could enhance the high-dose vitamin C tumour-fighting action by creating an environment that would be unsustainable for cancer cells but still safe for normal cells.

"Our first in vitro experiment showed remarkable effects. When used alone, fasting-mimicking diet or vitamin C alone reduced cancer cell growth and caused a minor increase in cancer cell death. But when used together, they had a dramatic effect, killing almost all cancerous cells," said Longo.

Longo and his colleagues detected this strong effect only in cancer cells that had a mutation that is regarded as one of the most challenging targets in cancer research.

These mutations in the KRAS gene signal the body is resisting most cancer-fighting treatments, and they reduce a patient's survival rate. KRAS mutations occur in approximately a quarter of all human cancers and are estimated to occur in up to half of all colorectal cancers.

The study also provided clues about why previous studies of vitamin C as a potential anticancer therapy showed limited efficacy. By itself, a vitamin C treatment appears to trigger the KRAS-mutated cells to protect cancer cells by increasing levels of ferritin, a protein that binds iron.

But by reducing levels of ferritin, the scientists managed to increase vitamin C's toxicity for the cancer cells. Amid this finding, the scientists also discovered that colorectal cancer patients with high levels of the iron-binding protein have a lower chance of survival.

"In this study, we observed how fasting-mimicking diet cycles are able to increase the effect of pharmacological doses of vitamin C against KRAS-mutated cancers," said Maira Di Tano, a study co-author at the IFOM, FIRC Institute of Molecular Oncology in Milan, Italy.

"This occurs through the regulation of the levels of iron and of the molecular mechanisms involved in oxidative stress. The results particularly pointed to a gene that regulates iron levels: heme-oxygenase-1," added Tano.

The research team's prior studies showed that fasting and a fasting-mimicking diet slow cancer's progression and make chemotherapy more effective in tumour cells while protecting normal cells from chemotherapy-associated side effects. The combination enhances the immune system's anti-tumour response in breast cancer and melanoma mouse models.

The scientists believe cancer will eventually be treated with low-toxicity drugs in a manner similar to how antibiotics are used to treat infections that kill particular bacteria, but which can be substituted by other drugs if the first is not effective.

To move toward that goal, they say they needed to first test two hypotheses: that their non-toxic combination interventions would work in mice, and that it would look promising for human clinical trials.

In this new study, they said that they've demonstrated both. At least five clinical trials, including one at USC on breast cancer and prostate cancer patients, are now investigating the effects of the fasting-mimicking diets in combination with different cancer-fighting drugs.

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

The World Health Organisation has warned that the COVID-19 pandemic is entering a "new and dangerous" phase. Thursday saw the most cases in a single day reported to the WHO.

Tedros Adhanom Ghebreyesus said the day had seen 150,000 new cases with half of those coming from the Americas and large numbers also from the Middle East and South Asia, the BBC reported.

He said the virus was still spreading fast and the pandemic accelerating.

He acknowledged people might be fed up with self-isolating and countries were eager to open their economies but he said that now was a time for extreme vigilance.

Maria van Kerkhove, technical lead of the WHO's COVID-19 response, told a press conference the pandemic is "accelerating in many parts of the world".

"While we have seen countries have some success in suppressing transmission and bringing transition down to a low level, every country must remain ready," she said.

Mike Ryan, the head of the WHO's Health Emergencies Programme, said that some countries had managed to flatten the peak of infections without bringing them down to a very low level.

"You can see a situation in some countries where they could get a second peak now, because the disease has not been brought under control," he said.

"The disease will then go away and reduce to a low level, and they could then get a second wave again in the autumn or later in the year."

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.