Most of us don’t give much thought to the search history stored in our internet browsers. If we do give it any consideration, it’s simply to remind ourselves that we should clear it out so as to not leave a paper trail of sorts that can wreck relationships or get us fired. But now that we’ve entered the age of Big Data, when mountains of numbers, search queries, and seemingly meaningless data points can be used to generate pinpoint advertising placements and monstrous revenues, tech companies have found a new way to use our search history to actively keep us healthy.
In short, our search history can actually help scientists and analysts figure out if we’re on track for a cancer diagnosis in the near future.
Now, cancer and search engine history aren’t two things that we typically associate with one another, but scientists at Microsoft have found a link that could potentially save lives down the line. In a study published by Microsoft’s researchers in the Journal of Oncology Practice, the scientists dug through data from the company’s Bing search engine that helped screen for pancreatic cancer — one of the deadliest and hardest to treat types out there.
“We identified searchers in logs of online search activity who issued special queries that are suggestive of a recent diagnosis of pancreatic adenocarcinoma,” the study said. “We then went back many months before these landmark queries were made, to examine patterns of symptoms, which were expressed as searches about concerning symptoms.”
Search history: a gold mine of data
The team’s results?
“We found that signals about patterns of queries in search logs can predict the future appearance of queries that are highly suggestive of a diagnosis of pancreatic adenocarcinoma.” the study reads. “Signals in search logs show the possibilities of predicting a forthcoming diagnosis of pancreatic adenocarcinoma from combinations of subtle temporal signals revealed in the queries of searchers.”
Basically, the researchers used data compiled by Bing to look at the digital trail left by individuals who had recently been diagnosed with pancreatic cancer. They went back through their search histories to find clues that had been left prior to their diagnoses, to see if there were signs that could have tipped the individuals off that there were some serious health issues at play.
Using that data and the search histories available to them, the research team put together a model to try and figure out if they could accurately predict if someone had cancer. Using search history as a guide, the study says that they can actually make an accurate prediction between 5-15% of the time. And there were extremely low false-positives, meaning that potentially one out of every twenty (on the low end) cancer cases could be sniffed out early by looking at data patterns in search histories.
Avoiding serious health issues
While Microsoft’s study does show a promising new way that technology can help pinpoint cancer and other diseases before they gain too much traction, it’s really on you — the individual — to take the necessary steps to lead a healthy lifestyle. As medical research has progressed in recent decades, we have a very good idea of what factors increase or decrease our odds of developing different types of cancers, and what we can do to avoid it.
On a day to day basis, the best things you can do are to stay active by getting plenty of exercise and to follow a healthy diet. There are some warning signs to look out for, and foods that you should definitely avoid. For example, if you love beer and bacon, and happen to sport a beer belly, you might be headed down the path to stomach cancer. You can still partake in drinking and eating processed meats, but controlling your intake is important.
The more we learn about cancer, the easier it’s going to become to avoid a diagnosis. But it comes down to personal responsibility — as we all need to take charge of our own health. Big data can help sift through the numbers and find trends, but it can’t force you to eat right and take care of yourself.