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 4,2020

The World Health Organisation on Wednesday said that anti-malarial drug hydroxychloroquine (HCQ) will return to the solidarity trial for the potential treatment of coronavirus disease.

At a press conference in the WHO headquarters in Geneva, Director General Tedros Adhanom Ghebreyesus said: "On the basis of the available mortality data, the members of the committee recommended that there are no reasons to modify the trial protocol. The Executive Group received this recommendation and endorsed continuation of all arms of the solidarity trial, including hydroxychloroquine."

The world health body had temporarily suspended the usage of HCQ from the solidarity trial for coronavirus treatment on May 25 soon after a study published in one of the most reliable medical journals, which had suggested that the drug could cause more fatalities among COVID-19 patients.

However, the WHO chief said that the decision was taken as a precaution while the safety data was reviewed.

Ghebreyesus also said that the Data Safety and Monitoring Committee will continue to closely monitor the safety of all therapeutics being tested in the solidarity trial.

"So far, more than 3,500 patients have been recruited in 35 countries. WHO is committed to accelerating the development of effective therapeutics, vaccines and diagnostics as part of our commitment to serving the world with science, solutions and solidarity," he said.

Soon after HCQ was suspended from the trial, the Indian government had said that the antimalarial drug has been known for its benefits for a long time and its usage will be continued on the frontline workers, including police and healthcare professionals, as prophylaxis. The government had also said that studies were being conducted and the drug would be included in the clinical trial also for the treatment of coronavirus disease.

US President Donald Trump also had strongly advocated the use of HCQ and called it a "game-changer". He went to the extent of saying that he had taken the medicine.

Launched by WHO and partners, solidarity trial is an international clinical trial to find an effective treatment for COVID-19, including drugs to slow the progression of the disease or improve survival. The trial, which enrols patients from different countries, "will compare four treatment options against standard of care to assess their relative effectiveness against COVID-19", said WHO. 

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 19,2020

Researchers have found that patients with peripheral artery disease or stroke were less likely to receive recommended treatments to prevent heart attack than those with coronary artery disease. All three are types of atherosclerotic cardiovascular disease.

Depending on the location of the blockage, atherosclerosis increases the risk for three serious conditions: coronary artery disease, stroke and peripheral artery disease.

"Our study highlights the need for public health campaigns to direct equal attention to all three major forms of atherosclerotic cardiovascular disease," said senior study author Erin Michos from the Johns Hopkins University in the US.

"We need to generate awareness among both clinicians and patients that all of these diseases should be treated with aggressive secondary preventive medications, including aspirin and statins, regardless of whether people have heart disease or not," Michos added.

Since atherosclerosis can affect arteries in more than one part of the body, medical guidelines are to treat coronary artery disease, stroke and peripheral artery disease similarly with lifestyle changes and medication, including statins to lower cholesterol levels and aspirin to prevent blood clots.

Lifestyle changes include eating a healthy diet, being physically active, quitting smoking, controlling high cholesterol, controlling high blood pressure, treating high blood sugar and losing weight.

What was unclear was if people with stroke and peripheral artery disease received the same treatments prescribed for those with coronary artery disease.

This study compared more than 14,000 US adults enrolled in the 2006-2015 Medical Expenditure Panel Survey, a national survey of patient-reported health outcomes and conditions, and health care use and expenses.

Slightly more than half of the patients were men, the average age was 65, and all had either coronary artery disease, stroke or peripheral artery disease.

These individuals were the representative of nearly 16 million US adults living with one of the three forms of atherosclerotic cardiovascular disease.

Compared to participants with coronary artery disease, participants with peripheral artery disease were twice more likely to report no statin use and three times more likely to report no aspirin use.

Additionally, people with peripheral artery disease had the highest, annual, total out-of-pocket expenditures among the three atherosclerotic conditions.

The findings showed that participants with stroke were more than twice as likely to report no statin or aspirin use.

Moreover, those with stroke were more likely to report poor patient-provider communication, poor health care satisfaction and more emergency room visits.

"Our study highlights a missed opportunity for implementing life-saving preventive medications among these high-risk individuals," Michos said.

The study was presented in the virtual conference at the American Heart Association's Quality of Care & Outcomes Research Scientific Sessions 2020.

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
February 7,2020

Birmingham, Feb 7: According to a new study, social media users are more likely to eat healthy or junk food after getting influenced by their peer group.

The research published in the scientific journal 'Appetite' found that study participants ate an extra fifth of a portion of fruit and vegetables themselves for every portion they thought their social media peers ate. So, if they believed their friends got their 'five a day' of fruit and veg, they were likely to eat an extra portion themselves.

On the other hand, Facebook users were found to consume an extra portion of unhealthy snack foods and sugary drinks for every three portions they believed their online social circles did.
The findings suggested that people eat around a third more junk food if they think their friends also indulge in the same.

The Aston University researchers said the findings provide the first evidence to suggest our online social circles could be implicitly influencing our eating habits, with important implications for using 'nudge' techniques on social media to encourage healthy eating.

Researchers asked 369 university students to estimate the amount of fruit, vegetables, 'energy-dense snacks' and sugary drinks their Facebook peers consumed on a daily basis.

The information was cross-referenced with the participants' own actual eating habits and showed that those who felt their social circles 'approved' of eating junk food consumed significantly more themselves. Meanwhile, those who thought their friends ate a healthy diet ate more portions of fruit and veg. Their perceptions could have come from seeing friends' posts about the food and drink they consumed, or simply a general impression of their overall health.

There was no significant link between the participants' eating habits and their Body Mass Index (BMI), a standard measure of healthy weight, however. The researchers said the next stage of their work would track a participant group over time to see whether the influence of social media on eating habits had a longer-term impact on weight.

The most recent figures from the NHS's Health Survey for England showed that in 2018 only 28 percent of adults were eating the recommended five portions of fruit and vegetables per day. In Wales, this was 24 percent, in Scotland 22 percent and in Northern Ireland around 20 percent. Children and young people across the UK had even lower levels of fruit and veg consumption.

Aston University health psychology Ph.D. student Lily Hawkins, who led the study alongside supervisor Dr. Jason Thomas, said: "This study suggests we may be influenced by our social peers more than we realize when choosing certain foods. We seem to be subconsciously accounting for how others behave when making our own food choices. So if we believe our friends are eating plenty of fruit and veg we're more likely to eat fruit and veg ourselves. On the other hand, if we feel they're happy to consume lots of snacks and sugary drinks, it can give us a license to overeat foods that are bad for our health. The implication is that we can use social media as a tool to 'nudge' each other's eating behavior within friendship groups, and potentially use this knowledge as a tool for public health interventions."

"With children and young people spending a huge amount of time interacting with peers and influencers via social media, the important new findings from this study could help shape how we deliver interventions that help them adopt healthy eating habits from a young age and stick with them for life," said professor Claire Farrow.

A dietitian called Aisling Pigott further mentioned that "Research such as this demonstrates how we are influenced by online perceptions about how others eat. The promotion of positive health messages across social media, which are focused on promoting healthy choices and non-restrictive relationships with food and body, could nudge people into making positive decisions around the food they eat."

"We do have to be mindful of the importance of 'nudging' positive behaviors and not 'shaming' food choices on social media as a health intervention. We know that generating guilt around food is not particularly helpful when it comes to lifestyle change and maintenance," Aisling 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.