A computer program can identify breast cancer from routine scans with greater accuracy than human experts, researchers said in what they hoped could prove a breakthrough in the fight against the global killer.
Breast cancer is one of the most common cancers in women, with more than two million new diagnoses last year alone.
Regular screening is vital in detecting the earliest signs of the disease in patients who show no obvious symptoms.
In Britain, women over 50 are advised to get a mammogram every three years, the results of which are analyzed by two independent experts.
But interpreting the scans leaves room for error, and a small percentage of all mammograms either return a false positive — misdiagnosing a healthy patient as having cancer — or false negative — missing the disease as it spreads.
Now researchers at Google Health have trained an artificial intelligence model to detect cancer in breast scans from thousands of women in Britain and the United States.
The images had already been reviewed by doctors in real life but unlike in a clinical setting, the machine had no patient history to inform its diagnoses.
The team found that their AI model could predict breast cancer from the scans with a similar accuracy level to expert radiographers.
Further, the AI showed a reduction in the proportion of cases where cancer was incorrectly identified — 5.7 percent in the US and 1.2 percent in Britain, respectively.
It also reduced the percentage of missed diagnoses by 9.4 percent among US patients and by 2.7 percent in Britain.
“The earlier you identify a breast cancer the better it is for the patient,” Dominic King, UK lead at Google Health, told AFP.
“We think about this technology in a way that supports and enables an expert, or a patient ultimately, to get the best outcome from whatever diagnostics they’ve had.”
– Computer ‘second opinion’ –
In Britain all mammograms are reviewed by two radiologists, a necessary but labour-intensive process.
The team at Google Health also conducted experiments comparing the computer’s decision with that of the first human scan reader.
If the two diagnoses agreed, the case was marked as resolved. Only with discordant outcomes was the machine then asked to compare with the second reader’s decision.
The study by King and his team, published in Nature, showed that using AI to verify the first human expert reviewer’s diagnosis could save up to 88 percent of the workload for the second clinician.
“Find me a country where you can find a nurse or doctor that isn’t busy,” said King.
“There’s the opportunity for this technology to support the existing excellent service of the (human) reviewers.”
Ken Young, a doctor who manages mammogram collection for Cancer Research UK, contributed to the study.
He said it was unique for its use of real-life diagnosis scenarios from nearly 30,000 scans.
“We have a sample that is representative of all the women that might come through breast screening,” he said.
“It includes easy cases, difficult cases and everything in between.”
The team said further research was needed but they hoped that the technology could one day act as a “second opinion” for cancer diagnoses.
Trump administration quietly guts COVID-19 paid leave provision that already excluded 75 percent of workers
The Trump administration has quietly issued new guidance that will exempt many small businesses from having to provide some workers with paid leave during the coronavirus pandemic.
The Department of Labor issued a temporary rule Wednesday that effectively exempted businesses with fewer than 50 workers from being required to provide 12 weeks of paid leave for workers whose children are suddenly at home from school or child care under the coronavirus stimulus package signed by President Donald Trump.
This article first appeared in Salon.
Trump is deploying national guardsman to provide pandemic support without any health benefits: report
The National Guard are an essential part of the fight against the coronavirus pandemic, and thousands of them have potentially been exposed to infected civilians, making it a particularly dangerous and important time to serve.
But according to The Daily Beast, the guard has been deployed in a way that prevents them from being eligible for the military's health care system.
"The approximately 20,000 guardsmen who have been called up to help states around the country deal with the spread of the coronavirus are federalized on what’s called Title 32 status, which puts them in command of their various state governors but with the federal government paying costs," wrote senior national security correspondent Spencer Ackerman. "But according to the National Guard’s advocates and the U.S. governors’ association, the guardsmen are activated on orders that last 30 days. That puts them one single day shy of the requirement allowing the military health insurance system known as TRICARE — think of it as Medicare For All In Uniform — to cover them."
Vaccine researchers grew ‘alarmed’ as Trump’s CDC wasted weeks of their time with a flawed coronavirus test: report
According to a report from the Washington Post, in the early days as health officials became concerned about the possibility of the COVID-19 pandemic blossoming out of China, researchers sat and wasted days they could have used to start developing a vaccine because they were assured by the Centers for Disease Control (CDC) that a testing kit was on its way.
As it turned out, that test was flawed.
Relying on emails and interviews, the Post is reporting, "On a Jan. 15 conference call, a leading scientist at the federal Centers for Disease Control and Prevention assured local and state public health officials from across the nation that there would soon be a test to detect a mysterious virus spreading from China. Stephen Lindstrom told them the threat was remote and they may not need the test his team was developing 'unless the scope gets much larger than we anticipate,' according to an email summarizing the call."