When you don’t feel so well, what do you do? Millions upon millions of people turn to their favorite seach engines looking for information.
In fact, approximately 1% of Google searches are related to medical symptoms.
Google has been paying attention and this week, the search giant announced that it will start displaying lists of conditions related to symptoms described in searches.
For example, a search for “swollen joints” will return a list of conditions commonly associated with this symptom, such as arthritis.
For some searches, Google will “also give you an overview description along with information on self-treatment options and what might warrant a doctor’s visit.”
The company says that “by doing this, our goal is to help you to navigate and explore health conditions related to your symptoms, and quickly get to the point where you can do more in-depth research on the web or talk to a health professional.”
The information Google displays is based on health conditions that appear in search results and filtered against data the company collected from doctors for its Knowledge Graph.
Google says doctors from Harvard Medical School and Mayo Clinic provided feedback “for a representative sample of searches.”
A two-way street
Naturally, Google is quick to point out that despite its efforts to ensure accuracy, the information it displays is not a substitute for professional medical advice.
But if it can successfully help consumers separate the wheat from the chaff when they turn to the web with worry about a cough or a rash, Google has the potential to make an imprint on the way consumers use the internet to take care of their health.
Search’s biggest contribution to healthcare, however, might not be how it can help consumers but rather how it can help healthcare professionals better serve their patients.
Google rival Microsoft has been exploring whether data from its search engine, Bing, could one day help physicans diagnose illness earlier.
In a paper published in the Journal of Oncology Practice, Microsoft researchers described how they took anonymized Bing search logs to identify searches associated with individuals who had likely been recently diagnosed with pancreatic cancer.
They then looked at these individuals’ prior searches in hopes that they might identify queries that could have helped provide an earlier diagnosis.
The results were quite remarkable…
We find 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.
We show specifically that we can identify 5 to 15 percent of cases while preserving extremely low false positive rates of as low as 1 in 100,000.
Because this particular form of pancreatic cancer is fast-spreading and deadly, the ability to detect it even weeks earlier could mean the difference between life and death for a patient.
There are obviously numerous privacy and ethical considerations that would need to be addressed before this research could be applied in the real world, but the authors of the journal article do believe there is potential.
As Microsoft’s Mike Brunker explained:
They hope the positive results from the feasibility study will excite the broader medical community and generate discussion about how such a screening methodology might be used.
They suggest that it would likely involve analyzing anonymized data and having a method for people who opt in to receive some sort of notification about health risks, either directly or through their doctors, in the event algorithms detected a pattern of search queries that could signal a health concern.
While it could take some time for such a vision to be realized, the idea that one’s web search history could be capable of saving his or her life is an exciting one and might eventually lead to advances that enable doctors to better serve their patients.
For more on this topic, see: