This study presents a method for detecting influenza epidemics using search engine query data. Seasonal influenza is a major public health concern, causing millions of illnesses and deaths annually. A new influenza strain could lead to a pandemic. Early detection is crucial for reducing the impact of both seasonal and pandemic influenza. The authors propose using online search queries to monitor health-seeking behavior, as the frequency of certain queries is highly correlated with the percentage of physician visits for influenza-like illness (ILI). The study uses Google search queries to estimate weekly influenza activity in the US, with a reporting lag of about one day. Traditional surveillance systems rely on virological and clinical data, including ILI physician visits. However, these systems have a 1–2 week reporting lag. The authors developed a model that uses search queries to estimate the probability that a random physician visit is related to ILI. This model uses the log-odds of an ILI physician visit and the log-odds of an ILI-related search query. The model was validated against CDC data and showed a high correlation with ILI percentages. The final model used 45 search queries that were most correlated with CDC ILI data. These queries were found to be consistently related to ILI. The model was able to estimate ILI percentages 1–2 weeks ahead of CDC reports. The system can be used to track the spread of ILI in the US and may help public health officials respond better to seasonal epidemics. The study highlights the potential of using search engine query data for influenza surveillance. While the model is not a replacement for traditional surveillance systems, it can provide early detection of influenza outbreaks. The system is designed to be used in international settings as well. The authors conclude that harnessing the collective intelligence of millions of users can provide one of the most timely and broad-reaching influenza monitoring systems available.This study presents a method for detecting influenza epidemics using search engine query data. Seasonal influenza is a major public health concern, causing millions of illnesses and deaths annually. A new influenza strain could lead to a pandemic. Early detection is crucial for reducing the impact of both seasonal and pandemic influenza. The authors propose using online search queries to monitor health-seeking behavior, as the frequency of certain queries is highly correlated with the percentage of physician visits for influenza-like illness (ILI). The study uses Google search queries to estimate weekly influenza activity in the US, with a reporting lag of about one day. Traditional surveillance systems rely on virological and clinical data, including ILI physician visits. However, these systems have a 1–2 week reporting lag. The authors developed a model that uses search queries to estimate the probability that a random physician visit is related to ILI. This model uses the log-odds of an ILI physician visit and the log-odds of an ILI-related search query. The model was validated against CDC data and showed a high correlation with ILI percentages. The final model used 45 search queries that were most correlated with CDC ILI data. These queries were found to be consistently related to ILI. The model was able to estimate ILI percentages 1–2 weeks ahead of CDC reports. The system can be used to track the spread of ILI in the US and may help public health officials respond better to seasonal epidemics. The study highlights the potential of using search engine query data for influenza surveillance. While the model is not a replacement for traditional surveillance systems, it can provide early detection of influenza outbreaks. The system is designed to be used in international settings as well. The authors conclude that harnessing the collective intelligence of millions of users can provide one of the most timely and broad-reaching influenza monitoring systems available.