Google Search Data Can Predict Cancer Incidence And Mortality

Searching about health and illness? These are among the most popular search topics. It seems that some of this search data may provide validated information on both the incidence and mortality from certain forms of cancer. In a recent study published in JAMA Dermatology , researchers asked a simple question:

The results were dramatic. By state, relative Google search volume statistically significantly correlated with cancer incidence rates in five of eight commonly diagnosed cancers in the United States (colon cancer: R = 0.61; P < .001; lung cancer: R = 0.73; P < .001; lymphoma: R = 0.51; P < .001; melanoma: R = 0.36; P = .01; and thyroid cancer: R = 0.30; P = .03). For four of those five cancers (colon cancer: R = 0.61; P < .001; lung cancer: R = 0.62; P < .001; lymphoma: R = 0.38; P = .006; and melanoma: R = 0.31; P = .03), relative Google search volume also correlated with mortality rates. The statistical correlation was highly significant.

It's an interesting and common dynamic. Just as we learn from searching the internet, the search provides information about us. From retail to navigation, the reciprocal benefit can now apply to health and cancer. But this general concept isn't new. In 2008, Google began an interesting analysis of flu-related search data in an attempt to predict real-time outbreaks. However, Google didn't match expectations and missed the peak of the 2013 flu season. An informative editorial in Nature provides a deeper perspective.

But the reality is that our digital footprint—from search to gaming—can provide a vast pool of information that can create a portrait of life, illness and wellness. The utilization of this data is important and vast. And while much of it is depersonalized and population-based, you have to ask your self if "Big Brother" is becoming "Big Doctor," too.