Looking for a diseases diagnosis based on a simple internet search may not be a bad idea after all! In the case of pancreatic cancer, it maybe useful to get an early diagnosis as well.
Scientists from Microsoft may have figured out a way to identify internet users suffering from pancreatic cancer before they even receive their diagnosis. The identification is based on analysing large samples of data collected form search engine queries in some cases.
The study published in The Journal of Oncology Practice involved 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 methodology used in the study was to work backward on searches conducted on Bing, Microsoft’s search engine indicating someone diagnosed with pancreatic cancer. From there, they looked for earlier queries from these Bing users which showed they were experiencing symptoms before the diagnosis. This could help in early diagnosis and possibly be the warning signs of pancreatic cancer.
Pancreatic cancer is difficult to diagnose and most patients get a diagnosis only at later stages of cancer. The five-year survival rate is very low but catching it earlier would possibly help to prolong life in some cases. The results of the study suggest that early screening could increase the five year survival rate from 3% to 5 – 7%.
What is more interesting is that the researchers could identify 5 to 15% of the pancreatic cases based only on search queries with a false positive rate as low as one in 100,000. The low false positive rate for diagnosis is especially important to prevent high medical costs and anxiety among people.
The key point is that 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, Dr. Horvitz noted.
Currently the study is based on only a selective anonymous population of people using Bing as the search engine. To make it applicable to and accessible, the next step would be to figure out a kind of interface that would allow the users to voluntarily feed in data to allow scientists to look for red 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.
However, this would take more effort and approval from medical practitioners.
“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.
As for now, the study is extremely interesting and also can be expanded to various other diseases and likewise. Hopefully, in the near future a diagnosis would merely be a mouse-click away.
Source: New York Times