SYSTEMS-LEVEL QUALITY IMPROVEMENT Using Google Trends to Predict Pediatric Respiratory Syncytial Virus Encounters at a Major Health Care System Matthew G. Crowson 1 & David Witsell 2 & Antoine Eskander 1 Received: 7 September 2019 /Accepted: 22 January 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract To assess whether Google search activity predicts lead-time for pediatric respiratory syncytial virus (RSV) encounters within a major health care system. Internet user search and health system encounter database analysis. Pediatric RSV encounter volumes across all clinics and hospitals in the Duke Health system were tabulated from 2005 to 2016. North Carolina Google user search activity for RSV were obtained over the same time period. Time series analysis was used to compare RSV encounters and search activity. Cross-correlation was used to determine the ‘lag’ time difference between Google user search interest for RSV and observed Pediatric RSV encounter volumes. Google search activity and Pediatric RSV encounter volumes demonstrated strong seasonality with predilection for winter months. Granger Causality testing revealed that North Carolina RSV Google search activity can predict pediatric RSV encounters at our health system (F = 5.72, p < 0.0001). Using cross-correlation, increases in Google search activity provided lead time of 0.21 weeks (1.47 days) prior to observed increases in Pediatric RSV encounter volumes at our health system. RSV is a common cause of upper airway obstruction in pediatric patients for which pediatric otolaryngologists are consulted. We demonstrate that Google search activity can predict RSV patient interactions with a major health system with a measurable lead-time. The ability to predict when illnesses in a population result in increased health care utilization would be an asset to health system providers, planners and administrators. Prediction of RSV would allow specific care pathways to be developed and resource needs to be anticipated before actual presentation. Keywords Google trends . Respiratory syncytial virus . RSV . Disease forecasting Introduction Recent epidemiological studies have concluded that nearly everyone worldwide will have been exposed to respiratory syncytial virus (RSV) by the age of two [1]. In developed countries, RSV infections tend to be self-limited with only limited morbidity and mortality [2]. Nearly all (99%) mortal- ity from RSV occurs in developing countries and in infants 6 months old or younger [3]. Nonetheless, the burden of annual RSV cases on the United States health care system is significant. Annual expenditures on care for pediatric RSV patients approached one billion dollars in the late 1990s, and in 2014 there were greater than 57,000 hospitalizations and over 1.2 million outpatient visits [4, 5]. The use of internet search engine data to track infectious disease activity became popular with novel analyses that tracked United States and global influenza epidemic activity in 2008–2009 [6]. In some cases, this methodology as proven advantageous to the traditional approaches used by the United States Centers for Disease Control and Prevention (CDC) as the traditional methods often lag by one or two weeks in reporting their results [6]. In the case of RSV, the CDC relies upon laboratories to voluntarily submit reports via the National Respiratory and Enteric Virus Surveillance System (NREVSS) [7]. The NREVSS system enumerates RSV tests submitted by participating laboratories and reports on the pro- portion of tests that are positive, submitting location, and when the test was collected. Since the first reported use of search engine data to track the 2008 influenza epidemic, a This article is part of the Topical Collection on Systems-Level Quality Improvement * Matthew G. Crowson matt.crowson@mail.utoronto.ca 1 Department of Otolaryngology-Head & Neck Surgery, Sunnybrook Health Sciences Centre, Toronto, Ontario M4N 3N5, Canada 2 Division of Otolaryngology-Head & Neck Surgery, Duke University Medical Center, Durham, NC, USA Journal of Medical Systems (2020) 44:57 https://doi.org/10.1007/s10916-020-1526-8