Artificial intelligence to now help diagnose breast cancer

Agencies
August 10, 2019

Washington D.C., Aug 10: Researchers discovered an artificial intelligence system that could help pathologists read biopsies more accurately and to better detect and diagnose breast cancer. 

The new system, described in a study published in the journal 'JAMA Network Open,' helped interpret medical images used to diagnose breast cancer that can be difficult for the human eye to classify, and it does so nearly as accurate or better as experienced pathologists.

"It is critical to get a correct diagnosis from the beginning so that we can guide patients to the most effective treatments," said Dr. Joann Elmore, the study's senior author and a professor of medicine at the David Geffen School of Medicine at UCLA.

A 2015 study led by Elmore found that pathologists often disagree on the interpretation of breast biopsies, which are performed on millions of women each year.

That earlier research revealed that diagnostic errors occurred in about one out of every six women who had ductal carcinoma in situ (a noninvasive type of breast cancer), and that incorrect diagnoses were given in about half of the biopsy cases of breast atypia (abnormal cells that are associated with a higher risk for breast cancer).

"Medical images of breast biopsies contain a great deal of complex data and interpreting them can be very subjective. Distinguishing breast atypia from ductal carcinoma in situ is important clinically but very challenging for pathologists. Sometimes, doctors do not even agree with their previous diagnosis when they are shown the same case a year later," said Elmore, who is also a researcher at the UCLA Jonsson Comprehensive Cancer Center.

The scientists reasoned that artificial intelligence could provide more accurate readings consistently because by drawing from a large data set, the system can recognise patterns in the samples that are associated with cancer but are difficult for humans to see.

The team fed 240 breast biopsy images into a computer, training it to recognise patterns associated with several types of breast lesions, ranging from benign (noncancerous) and atypia to ductal carcinoma in situ, or DCIS, and invasive breast cancer. Separately, the correct diagnoses for each image were determined by a consensus among three expert pathologists.

To test the system, the researchers compared its readings to independent diagnoses made by 87 practising U.S. pathologists. While the artificial intelligence program came close to performing as well as human doctors in differentiating cancer from non-cancer cases, the AI program outperformed doctors when differentiating DCIS from atypia, considered the greatest challenge in breast cancer diagnosis.

The system correctly determined whether scans showed DCIS or atypia more often than the doctors; it had sensitivity between 0.88 and 0.89, while the pathologists' average sensitivity was 0.70. (A higher sensitivity score indicates a greater likelihood that diagnosis and classification are correct.)

"These results are very encouraging. There is low accuracy among practising pathologists in the U.S. when it comes to the diagnosis of atypia and ductal carcinoma in situ, and the computer-based automated approach shows great promise," Elmore 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
June 12,2020

Global poverty could rise to over one billion people due to the COVID-19 pandemic and more than half of the 395 million additional extreme poor would be located in South Asia, which would be the hardest-hit region in the world, according to a new report.

Researchers from King's College London and Australian National University published the new paper with the United Nations University World Institute for Development Economics Research (UNU-WIDER) said that poverty is likely to increase dramatically in middle-income developing countries and there could be a significant change in the distribution of global poverty.

The location of global poverty could shift back towards developing countries in South Asia and East Asia, the report said.

The paper, 'Precarity and the Pandemic: COVID-19 and Poverty Incidence, Intensity and Severity in Developing Countries,' finds that extreme poverty could rise to over one billion people globally as a result of the crisis.

The cost of the crisis in lost income could reach USD 500 million per day for the world's poorest people, and the intensity and severity of poverty are likely to be exacerbated dramatically.

The report said that based on the USD 1.90 a day poverty line and a 20 per cent contraction, more than half of the 395 million additional extreme poor would be located in South Asia, which would become the hardest hit region in the world mainly driven by the weight of populous India followed by sub-Saharan Africa which would comprise 30 per cent, or 119 million, of the additional poor.

The report added that as the value of the poverty line increases, a larger share of the additional poor will be concentrated in regions where the corresponding poverty line is more relevant given the average income level.

For instance, the regional distribution of the world's poor changes drastically when looking at the USD 5.50 a day poverty line the median poverty line among upper-middle-income countries.

At this level, almost 41 per cent of the additional half a billion poor under a 20 per cent contraction scenario would live in East Asia and the Pacific, chiefly China; a fourth would still reside in South Asia; and a combined 18 per cent would live in the Middle East and North Africa (MENA) and in Latin America and the Caribbean (LAC), whose individual shares are close to that recorded for sub-Saharan Africa.

India plays a significant role in driving the potential increases in global extreme poverty documented previously, comprising almost half the estimated additional poor regardless of the contraction scenario, the report said.

Nonetheless, there are other populous, low and lower-middle- income countries in South Asia, sub-Saharan Africa, and East Asia and the Pacific accounting for a sizeable share of the estimates: Nigeria, Ethiopia, Bangladesh, and Indonesia come next, in that order, concentrating a total of 18 19 per cent of the new poor, whereas the Democratic Republic of Congo, Tanzania, Pakistan, Kenya, Uganda, and the Philippines could jointly add 11 12 per cent.

Taken together, these figures imply that three quarters of the additional extreme poor globally could be living in just ten populous countries.

The report added that this high concentration of the additional extreme poor is staggering , although not necessarily unexpected given the size of each country's population.

On one hand, data shows that three of these ten countries (Ethiopia, India, and Nigeria) were among the top ten by number of extreme poor people in 1990 and remained within the ranks of that group until 2018.

Despite this crude fact, two of these countries have managed to achieve a sustained reduction in their incidence of poverty since the early 1990s, namely Ethiopia and India, reaching their lowest poverty headcount ratio ever recorded at about 22 and 13 per cent, respectively. Nonetheless, the potential contraction in per capita income/consumption imposed by the pandemic's economic effects could erase some of this progress.

The researchers are now calling for urgent global leadership from the G7, G20, and the multilateral system, and propose a three-point plan to address the impact of the COVID-19 on global poverty quickly.

Professor of International Development at King's College London and a Senior Non-Resident Research Fellow at UNU-WIDER Andy Sumner said the COVID-19 crisis could take extreme poverty back over one billion people because millions of people live just above poverty.

Millions of people live in a precarious position one shock away from poverty. And the current crisis could be that shock that pushes them into poverty.

Professor Kunal Sen, Director of UNU-WIDER said the new estimates about the level of poverty in the world and the cost of the COVID-19 pandemic to the world's poor are sobering.

We cannot stand by and see the hard work and effort of so many be eradicated. We will know what the real impact is in time, but the necessary action to ensure we achieve the Sustainable Development Goals by 2030 needs to be planned now, Sen 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
April 4,2020

Washington D.C., Apr 4: While consuming a high-diet salt can result in high blood pressure, a recent study has revealed a link between salt-rich diet and weaker immune system.

The study was conducted under the leadership of the University Hospital Bonn, and the results were published in the journal Science Translational Medicine.

The research was conducted on mice that were fed a high-salt diet. Later, they were found to suffer from much more severe bacterial infections.

Human volunteers who consumed an additional six grams of salt per day also showed pronounced immune deficiencies.

The World Health Organization (WHO) has recommended a maximum amount of five grams of salt a day.

It corresponds approximately to one level teaspoon. In reality, however, many Germans exceed this limit considerably. 

Figures from the Robert Koch Institute suggest that on average men consume ten, and women more than eight grams a day.

This means that we reach for the salt shaker much more than is good for us. After all, sodium chloride, which is its chemical name, raises blood pressure and thereby increases the risk of heart attack or stroke.

"We have now been able to prove for the first time that excessive salt intake also significantly weakens an important arm of the immune system," said Prof. Dr. Christian Kurts from the Institute of Experimental Immunology at the University of Bonn.

This finding is unexpected, as some studies point in the opposite direction. For example, infections with certain skin parasites in laboratory animals heal significantly faster if these consume a high-salt diet.

The study also sheds light on the fact that the skin serves as a salt reservoir.

"Our results show that this generalization is not accurate," emphasized Katarzyna Jobin, lead author of the study.

The body keeps the salt concentration in the blood and in the various organs largely constant. Otherwise important biological processes would be impaired. The only major exception is the skin which functions as a salt reservoir of the body. This is why the additional intake of sodium chloride works so well for some skin diseases.

However, other parts of the body are not exposed to the additional salt consumed with food. Instead, it is filtered out by the kidneys and excreted in the urine.

"We examined volunteers who consumed six grams of salt in addition to their daily intake," said Prof. Kurts. This is roughly the amount contained in two fast-food meals, i.e. two burgers and two portions of French fries.

After one week, from the results, it showed that the immune cells coped much worse with bacteria after the test subjects had started to eat a high-salt diet.

In human volunteers, excessive salt intake also resulted in increased glucocorticoid levels.

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
May 2,2020

Clinician-scientists have found that Irish patients admitted to hospital with severe coronavirus (COVID-19) infection are experiencing abnormal blood clotting that contributes to death in some patients.

The research team from the Royal College of Surgeons in Ireland found that abnormal blood clotting occurs in Irish patients with severe COVID-19 infection, causing micro-clots within the lungs.

According to the study, they also found that Irish patients with higher levels of blood clotting activity had a significantly worse prognosis and were more likely to require ICU admission.

"Our novel findings demonstrate that COVID-19 is associated with a unique type of blood clotting disorder that is primarily focussed within the lungs and which undoubtedly contributes to the high levels of mortality being seen in patients with COVID-19," said Professor James O'Donnell from St James's Hospital in Ireland.

In addition to pneumonia affecting the small air sacs within the lungs, the research team has also hundreds of small blood clots throughout the lungs.

This scenario is not seen with other types of lung infection and explains why blood oxygen levels fall dramatically in severe COVID-19 infection, the study, published in the British Journal of Haematology said.

"Understanding how these micro-clots are being formed within the lung is critical so that we can develop more effective treatments for our patients, particularly those in high-risk groups," O'Donnell said.

"Further studies will be required to investigate whether different blood-thinning treatments may have a role in selected high-risk patients in order to reduce the risk of clot formation," Professor O'Donnell added.

According to the study, emerging evidence also shows that the abnormal blood-clotting problem in COVID-19 results in a significantly increased risk of heart attacks and strokes.

As of Friday morning, the cases increased to 20,612 cases in Ireland, with 1,232 deaths so far, according to the Johns Hopkins University.

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.