Slashdot Mirror
Microsoft Analyzes Web Searches, Finds Clues For Early Cancer Detection (computerworld.com)
An anonymous reader quotes a report from Computerworld: Analyzing online activities can provide clues as to a person's chances of having cancer, Microsoft researchers showed in a paper published this week. Specifically, the researchers demonstrated that by analyzing web query logs they were able to identify internet users who had pancreatic cancer even before they'd been diagnosed. The study suggest that "low-cost, high-coverage surveillance systems" can be created to passively observe search behavior and to provide early warning for pancreatic cancer, and with extension of the methodology, for other challenging cancers," the researchers concluded. "Surveillance systems could also provide for automated capture and summarization of data and landmarks over time so as to provide patients with talking points in their discussion with medical professionals." The researchers used proprietary logs of 9.2 million web queries on Microsoft's own Bing search engine but focused exclusively on English-speaking people in the U.S. from October 2013 to May 2015. First, the team identified searchers in logs of online search activity who made "special queries" that are suggestive of a recent diagnosis of pancreatic cancer. Those queries included phrases such as "Why did I get cancer in pancreas," and "I was told I have pancreatic cancer, what to expect." The team then went back "many months" before the initial queries were made to examine patterns of symptoms as they were expressed by web searches about pancreatic cancer symptoms. "We showed specifically that we can identify 5% to 15% of cases, while preserving extremely low false-positive rates," the researchers said in their paper. The false positives ranged from one in 10,000 to one in 100,000.
Researchers have very low false-positive rate when analyzing past data.
They just scan the user agent of the browser connecting, and if it contains "Linux" it means there is a cancer infection in the eyes of Microsoft.
THAT'S what they'd use it for.
To protect us from Cancer.
They looked for people searching for "how to cope with stage 4 cancer" and sure enough, those people had it in most cases. How DO they do it?
And your search engine mining your search history to figure out which diseases you might have is not creepy at all! No sir.
And surely there is nothing else that could be done with this technique.
I'd suggest this one instead.
STOP watching/tracking what I'm doing with my computer -- it's creepy as fuck!
(Switched to Mac years ago, not going back to windows and it's "telemetry". Not so sure of Apple either, but at least they claim to not track users and collect data on them -- their business model (currently) is selling shiny toys -- not selling data. And they have been pushing back on surveillance in the courts and their encryption is good. Filevault should be on by default.)
Ian Ameline
And it isn't anonymous if they can link it to the same user. What ethics board approved this?
Most of the users with pancreatic cancer had recently been tricked into upgrading to Windows 10... why is Microsoft covering up this disturbing fact?
cancer
or
dissident ideology
which one do you think is likely to be acted on to promote stability for the economy from which microsoft profits?
Seriously us people who aren't herd animals need to get it together. There is clearly a massive conspiracy against us all. Are you going to wait around to see what the top of the hierarchy does with all of this information they have on us once the economy becomes majorly automated?
I never thought anyone would be able to make cancer diagnoses creepy and unnerving.. kudos Microsoft
Where would you like me to go today?
Either way I'm going there.
They can identify you are likely to have pancreatic cancer when you enter searches for "Do I have pancreatic cancer?" and "Pancreatic cancer symptoms." It's not like they're diagnosing cancer in seemingly healthy people. They're just going to be telling people what they've already figured out. At the very least, these people would already know about their symptoms.
Unless you have symptoms that are just in common with pancreatic cancer symptoms, in which case they are just symptoms of something else. The study has a biased sample, since they where studying the history of "known cancer" patients (or someone who lies to search engines... for example, I just now searched "I think I have pancreatic cancer"... Shit! - oh, wait, I just searched for "medical student syndrome", too! Whew! That's what I have.)
This issue is a bit more complicated than you think.
Clippy: It looks like you may have cancer! Would you like me to schedule an appointment with an oncologist?
A post a day keeps productivity at bay.
nest thermostats could have sensors in them to detect 'aromas' of drug use and manufacturing....
cameras in phones and computers to capture faces and recognize stacks of money or credit cards
microphones in same, to record based on trigger keywords...
sewer systems could have sensors in them to detect illicit chemicals and drugs (this already happens, btw)...
papers being recycled could be scanned and archived for later analysis....
where do you draw the line at "good" mass surveillance and "bad".. you don't.. it's ALL BAD.
meanwhile you pay them to spy on you.
they sold you out.
The reason pancreatic cancer is so deadly is because it is seldom detected in its early stages and spreads rapidly. Symptoms may not appear until the cancer is already spread through the body, where it becomes too late to do anything surgically to remove it. So there's a good chance that the people who are going online and searching about their symptoms already have the cancer in an advanced stage. Not sure what the predictive value is in that. Maybe the method would be useful for other diseases, though.
Spying on everything you do is really in your best interest.
Sign below this pentagram...
Just what I need, a pop up window that says "CONGRATULATIONS YOU'RE THE 1 MILLIONTH VISITOR WITH PANCREATIC CANCER!"
And drug use, and sexual interests, and political affiliations...
Sounds just as another try to justify snooping. Big companies often make false research requests. I see no reason for this to be something else.
This is where a good doctor comes in. If you are vomiting and have abdominal pains and DO NOT go to the Doctor then you should have no expectations of survival once this fast-moving Cancer is revealed. A good Doc will run tests when presented with these symptoms and hopefully catch it early. A good Doc with EXP will know what's up when presented with your symptoms.
Do yourself a favor, stop searching on WebMD, Google and Bing. Visit your Doctor instead.
"I was told I have pancreatic cancer today." "OMG! The doctor told you?" "No, NSA sent me a letter."
Perhaps this is the sort of thing that they intend to do with data collected via Win10/Visual Studio 2015 compiled object's telemetry.
You have none.
And how many of their research subjects had been diagnosed with hypochondria? Searching for symptoms and eventual disease isn't unlikely pattern, whereas someone actually suffering from it would be more likely to only ask a doctor. Didn't bother to read the article, of course, but hopefully they did also check whether they did search indicating diagnosis also before, and possibly for other diseases.
I also have to join those questioning the "false positive" rate there. People are perhaps even more liable to search for other people's conditions than their own, and while showing them a banner like "Your searches indicate X" would work just as well, in the context of the study that should count as a false positive. One question on this is exactly how they're counting or reporting false positives. Approximately 5 in 100.000 will get pancreating cancer *in their lifetime*, which comes to neighborhood 1 to 1.000.000 million per year. If their algorithm actually tagges 1 in 10.000 users as having pancreatic cancer then it is next to useless. If 1 in 10.000 tagged didn't turn out to have pancreatic cancer, then it's unbelievable.
And indeed, assuming they were searching for identifiable symptoms, wouldn't they have discovered their cancer earlier? Is this a case of too slow medical system, or just a case of people who already know they have pancreatic cancer sometimes making searches looking like recent diagnosis... the example of "Why did I get pancreatic cancer?" in the summary for example is pretty telling, as that would seem quite likely search for a late-stage patient.
I wonder if my search history would have shown I was likely to have it. My symptoms were so vague that I waited about 6 weeks before going to the doctor - general discomfort in the abdominal area (2 different spots that were separated), a little more gas and diarrhea than normal, possibly slight weight loss, maybe a bit more tired than normal. The doctor ordered tests that showed gall stones and positive for H. Pylori (main cause of ulcers). She put me on antibiotics for the H. Pylori but my impression was she didn't think that was it. It wasn't till I started throwing up, went to the E.R., turned yellow while IN E.R., that they ordered the CAT scan that revealed the tumor. It also showed a lesion in my liver and the E.R. doctors told me it had already spread (the liver lesion turned out to be benign).
I may be one of the 'lucky' ones. Mine was operable and I got in a trial for an immuno-therapy drug. I'm now almost 3 months post-op (the Wipple procedure is NOT for wimps), there was no cancer in the margins or in the lymph nodes near it, and my tumor marker level is now at 20. I just started my 2nd round of chemo and may actually survive the cancer.
What a crock of doublespeak claptrap.
Some symptoms that doctors may dismiss as other illnesses, this search capability may catch.
I check my symptoms online, and the next day I get a note from a (for profit) medical service: Come in for a checkup.
I research my leaky faucet, and the next day I get a visit from a friendly neighbourhood plumber.
I research privacy, and the next day a government official calls to say how my privacy is assured, they want to take care of me.
I can sit back and know that everyone is concerned about my welfare....
What I took away from this is that people who use Bing get cancer.
One in ten thousand is a lot of erroneous diagnoses when you're doing web search scraping.