Detecting Devastating Diseases in Search Logs

Web search queries can offer a unique population-scale window onto streams of evidence that are useful for detecting the emergence of health conditions. We explore the promise of harnessing behavioral signals in search logs to provide advance warning about the presence of devastating diseases such as pancreatic cancer. Pancreatic cancer is often diagnosed too late to be treated effectively as the cancer has usually metastasized by the time of diagnosis. Symptoms of the early stages of the illness are often subtle and nonspecific. We identify searchers who issue credible, first-person diagnostic queries for pancreatic cancer and we learn models from prior search histories that predict which searchers will later input such queries. We show that we can infer the likelihood of seeing the rise of diagnostic queries months before they appear and characterize the tradeoff between predictivity and false positive rate. The findings highlight the potential of harnessing search logs for the early detection of pancreatic cancer and more generally for harnessing search systems to reduce health risks for individuals.