The new A.I. system could soon make its way onto your smartphone.

Your phone might someday save your skin.

Stanford researchers say they've created a new artificial intelligence system that can identify skin cancer as well as trained doctors can. According to a study they published in science journal Nature, the program was able to distinguish between cancerous moles and harmless ones with more than 90 percent accuracy.

The researchers trained the system by feeding it nearly 130,000 images of moles and lesions, with some of them being cancerous. The system scanned the images pixel by pixel, identifying characteristics that helped it make each diagnosis. Using machine learning, the A.I. grew more accurate as it studied more samples.

It then went head to head with 21 trained dermatologists. The result: The A.I. software achieved "performance on par with all tested experts." The system correctly identified 96 percent of the malignant samples, and 90 percent of the (generally harmless) benign ones. For the doctors in the study, those numbers were 95 percent and 76 percent, respectively.

This could have huge implications: The study points out that 5.4 million new cases of skin cancer are diagnosed each year in the U.S. alone. If installed in smartphones, the authors say, this technology could provide a simple, low cost form of early detection.

Identifying melanoma early on is critical. The five-year survival rate when the cancer is caught in its earliest stages is 99 percent. That number drops to 14 percent when detected in its late stages. Having the equivalent of a dermatologist--as far as diagnosing goes--in your pocket could help patients keep a closer watch on their own skin and seek medical treatment sooner.

That's not to say dermatologists will be replaced--they'd still be the ones to perform any procedures necessary. And in a blog post on Stanford's website, the authors suggest doctors might use the tool for in-office diagnoses.

Before the system can achieve its potential, though, it will have to be able to detect cancer from images captured by smartphones. While phone cameras are rapidly improving, the A.I. is currently trained to work only with high quality medical images.

Still, the technology is moving in that direction. Being able to detect early could have an impact on the 10,000 people who die from skin cancer each year in the U.S. alone.

The Stanford researchers developed the framework for the A.I. system using an image classification algorithm that had previously been built by Google.

Source: This article was published inc.com By Kevin J. Ryan

Categorized in Online Research

In the 12 years that I've covered wireless industry for CNET, the debate over whether cell phone use is hazardous to our health has long simmered in the background. It comes to a boil each time a new study analyzing a possible link is released, briefly grabbing the attention of the phone-wielding public.

The latest flash came May 26 when the US National Toxicology Program published a multiyear study that found a potential link between phone use and cancer. Male rats that were exposed to the same wireless signals our cell phones emit today were more likely to develop certain types of brain and heart tumors than the control rats. The more exposure a rat received, the study reported, the more likely is was to develop a cancer of some form. No difference was observed between female rats; findings from mice subjects have yet to be disclosed (the full report from the study will be released next year).

The study's observations, especially when relayed quickly in our sound bite news culture, have alarmed some people. I understand why. In my years covering this issue, passions on the debate run deep. Some readers and experts are convinced we're on the verge of a major public health crisis, while others dismiss the debate as tinfoil-hat pseudoscience. Most of the public, however, doesn't appear to care. Ever since scientists first started asking questions, cell phone use has only skyrocketed with 92 percent of Americans now owning mobile phones.

That trend isn't going to change anytime soon. Nor should it. Despite what this study has demonstrated, and how some headlines have interpreted it, there's still no definitive answer to whether cell phones are dangerous. And as I'll discuss in a minute, we may never get one at all. This one study is not a reason to stop using your phone, and in today's modern world it would be near impossible to do so. Still, it is OK for you to pay attention to this debate and be aware of its developments. If you're just getting caught up, here's what you need to know.

Take no study in a vacuum

Remember that this is just one study in a crowded field that has been running for decades. Previous studies also have found links between phone use and cancer, while others have found no correlation (there are far too many to list here).

As with many other things that scientists study in our universe, there's no consensus as of yet. Studies will differ, they will dispute each other and they will ask new questions we haven't asked before. Don't rely on one study to draw conclusions in your head, that's not how science works.

We may never get an answer

Science takes time -- a lot of it. Consider how long humans smoked before the evidence that it's harmful began to influence public policy. Cell phones, however, are still a new technology. "We need more data to be certain of anything," Dr. Jana Witt, Cancer Research UK's health information officer told me in a phone interview. "It's difficult to get definitive answer or proof."

Dr. Witt told me her organization would look for a comprehensive review of all available evidence showing a link. "We'd look at epidemiological (the science of how disease spreads) studies of humans that show a correlation, even if they may not be able to show a causation directly," she said. "They'd be combined with lab studies showing that [cell phone radiation] changes genetic material and studies of animals."

In other words, don't pine for a magical day when we we can say without any doubt that cell phones cause cancer. Likewise, don't wait for science to "prove" that phone use is not harmful.

Consider every study carefully

When any study is published, it will (rightfully) be analyzed and picked apart to find weaknesses or errors with the research. That's an important step that aids in further study. I won't do that here, leaving it to others to point out the red flags instead.


Those include how the rats were exposed to emissions (nine hours per day and over their entire bodies is different how humans would use a cell phone), the type of rats used and their ages, whether the study was properly reviewed, small sample sizes and the fact that the study reported a "low incidence" of cancer in the test rats.

In an emailed statement, Dr. Witt wrote that it's also unclear how the findings of a study on rats would translate to people. "There's been a lot of research into any potential cancer risk of using mobile phones and overall there's good evidence that the risk of brain tumours isn't higher in people who have used a mobile phone for up to 10 years," she wrote. "Ongoing research to check for effects over a longer time, or in children, is important."

It's also wise to consider who funds a study when evaluating its findings. For example, would you inherently trust a study from the National Beef Association recommending that you eat steak once a week? No, of course not.

About a phone's SAR

For a long time CNET kept comprehensive cell phone radiation charts, which showed the maximum SAR (aka Specific Absorption Rate or how much radio frequency a phone emits) for every phone we reviewed.

As background, the Federal Communications Commission mandates that every phone sold in the US must have a SAR of no higher than 1.6 watts/kilogram (w/kg). Before it can go on sale, the FCC tests a phone to find its SAR in facility in Maryland (though some health advocates charge that the FCC test is outdated). Canada also has a 1.6 w/kg limit, while the European Union and Australia mandate a 2.0 w/kg limit.

Two years ago, though, we discontinued the charts because a SAR by itself isn't a reliable measure of whether a phone is safe. A handset may have a SAR of 0.9 w/kg, but that's not necessarily safer than a phone with 1.2 w/kg. A handset's SAR can vary widely during a call as you alternate between transmission bands and as you increase your distance from a tower. And it may never reach the highest recorded SAR found in the FCC test at all.

What the industry says

Not surprisingly, the wireless industry, led by the Cellular Telecommunications Industry Association in the US, is quick to insist that phone use is safe. It cites studies that back up this position and is critical of studies that say differently. The CTIA also has pushed back vigorously against local governments that have tried to mandate health warnings to cell phone use.

In 2013 after a lawsuit from the CTIA, for instance, the San Francisco Board of Supervisors voted to kill a law that would have forced phone retailers to list a handset's SAR at the point of sale. Though similar legislation has mostly stalled in other cities this year, the nearby city of Berkeley was able to implement a law mandating health notices after a federal judge dismissed a CTIA suit.

Again, think about what happened with smoking. Even if the scientific community were to reach a consensus that wireless signals are likely to cause cancer, drafting safety legislation and changing public behavior will be a long battle the industry will be intimately involved in.

What the skeptics say

Those doubting a link between phone use and cancer raise a number of great questions. For instance, if cell phones really are dangerous, then why are brain cancer rates falling? Others contend that phones emit far less radiation than could ever be considered harmful and the kind of radiation (non-ionizing) they emit can't adversely affect human cells.

What's more, radiation -- at least in low doses -- is everywhere, even before the advent of wireless technology. We'll never get away from it completely: We're addicted to Wi-Fi, and we use baby monitors, walkie-talkies and cordless phones. Not all of it is harmful.

Why study continues

It continues because it's a good question to ask. "There a lot of studies that are still happening and we're still gathering data for," Dr. Witt told me. "The evidence will become clearer in the future."

And it isn't just about brain cancer. Cell phone use is affecting our bodies in other ways. They keep us awake at night, give us sore necks and texting thumbs and make us more distracted. Texting and driving is incredibly dangerous and some studies have suggested that phones could give children headaches or decrease male fertility. Maybe we'll have to wait until kids raised with cell phone are well into adulthood to know more.

Don't dismiss health advocates out of hand

I used to get a lot of email labeling people concerned about cell phones use as fear-mongering nuts. That's an unfair generalization to make. Instead, consider that many are intelligent, sincere and well-intentioned people. Some have lost loved ones to brain cancer and worry that cell phone is a possible cause. They're not just peddling nonsense, they're looking for answers and they want to save others from the same fate. Let's meet them halfway.

On a more personal note, I'll never forget one of the first things a good friend asked me after he was diagnosed with brain cancer in 2009 (he passed away four years later). "Do you think it could be my phone?" he asked. I replied with what I knew about the debate at the time, but realized it would be of little comfort. But he just wanted to know, "Why me?"

What you can do

If you are concerned, here's what you can do. Most of these precautions are recommended by and the National Cancer Institute and the Centers for Disease Control and Prevention in the US, the UK's National Health Service and the Australian Radiation Protection and Nuclear Safety Agency. And even if you think these simple steps are silly, consider that following them isn't going to harm you.

  • Text instead of placing a voice call and use a headset to keep the phone away from your head when possible.
  • If you're pregnant, avoid carrying a phone next to your stomach or in your bra.
  • Men: Don't carry the phone in a pants pocket next to your groin.
  • Limit phone use for children, who have smaller and thinner skulls.
  • Don't sleep with an active phone under the pillow. Put it on your bedside table instead. And if you need to keep your phone on for middle-of-the-night emergency calls, at least silence text alerts so you can get a restful night's sleep.
  • Be careful with accessories promising protection. Pong's line of phones cases promise to refocus RF energy away from your head while not reducing signal strength. Again, though, there's no guarantee that such a case makes your phone safer. Don't bother with the shiny, gold-lined radiation "shields" you can find online. They're useless.

Source: This article was published cnet.com By Kent German

Categorized in Others

Microsoft scientists have demonstrated that by analyzing large samples of search engine queries they may in some cases be able to identify internet users who are suffering from pancreatic cancer, even before they have received a diagnosis of the disease.

The scientists said they hoped their work could lead to early detection of cancer. Their study was published on Tuesday in The Journal of Oncology Practice by Dr. Eric Horvitz and Dr. Ryen White, the Microsoft researchers, and John Paparrizos, a Columbia University graduate student.

“We asked ourselves, ‘If we heard the whispers of people online, would it provide strong evidence or a clue that something’s going on?’” Dr. Horvitz said.

The researchers focused on searches conducted on Bing, Microsoft’s search engine, that indicated someone had been diagnosed with pancreatic cancer. From there, they worked backward, looking for earlier queries that could have shown that the Bing user was experiencing symptoms before the diagnosis. Those early searches, they believe, can be warning flags.

While five-year survival rates for pancreatic cancer are extremely low, early detection of the disease can prolong life in a very small percentage of cases. The study suggests that early screening can increase the five-year survival rate of pancreatic patients to 5 to 7 percent, from just 3 percent.

The researchers reported that they could identify from 5 to 15 percent of pancreatic cases with false positive rates of as low as one in 100,000. The researchers noted that false positives could lead to raised medical costs or create significant anxiety for people who later found out they were not sick.

The data used by the researchers was anonymized, meaning it did not carry identifying markers like a user name, so the individuals conducting the searches could not be contacted.

A logical next step would be to figure out what to do with that search information. One possibility would be some sort of health service where users could allow their searches to be collected, allowing scientists to monitor for questions that indicate warning flag symptoms.

“The question, ‘What might we do? Might there be a Cortana for health some day?’” said Dr. Horvitz, in a reference to the company’s speech-oriented online personal assistant software service.

Although the researchers declined to offer specific details, Dr. White is now the chief technology officer of health intelligence in a recently created Health & Wellness division at Microsoft.


They acknowledged that health-related data generated from web search histories was still new territory for the medical profession.

“I think the mainstream medical literature has been resistant to these kinds of studies and this kind of data,” Dr. Horvitz said. “We’re hoping that this stimulates quite a bit of interesting conversation.”

The new research is based on the ability of the Microsoft team to accurately distinguish between web searches that are casual or based on anxiety and those that are genuine searches for specific medical symptoms by people who are experiencing them, he noted.

Both a computer scientist and a medical doctor by training, Dr. Horvitz said he had been exploring this area in part because of a phone conversation with a close friend who had described symptoms. Based on their conversation, Dr. Horvitz advised him to contact his doctor. He received a diagnosis of pancreatic cancer and died several months later.

The availability of vast sets of behavior data based on individual web queries using the search engines offered by companies like Google and Microsoft has for a number of years been seen as a potential indicator of health-related information.

In 2009, Google published a research paper that explored the potential of early detection of flu epidemics based on statistical analysis of web search logs, though the results of that effort ultimately fell short of what had been hoped.

More recently, Microsoft researchers have had significant success in finding early evidence of adverse drug reactions from patterns observed in web logs. In 2013, they detected unreported side effects of prescription drugs before they were found by the Food and Drug Administration’s warning system.

The researchers are exploring evidence related to a range of devastating diseases. They also said that unlike the drug interaction data, which would be of direct value to the F.D.A. as an early alert, it was possible that symptom alert data might be made available as part of a broader online health service that a company like Microsoft might offer.

Source : nytimes.com

Categorized in Search Engine

airs logo

Association of Internet Research Specialists is the world's leading community for the Internet Research Specialist and provide a Unified Platform that delivers, Education, Training and Certification for Online Research.

Get Exclusive Research Tips in Your Inbox

Receive Great tips via email, enter your email to Subscribe.

Follow Us on Social Media