Automated cough detection has significant applications for the surveillance of diseases and supports medical decisions, as cough sounds can be a useful biomarker. However, the implementation and evaluation of robust cough detection models can be challenging due to the lack of real-world data. To evaluate the feasibility of using cough as a biomarker for disease surveillance, we have deployed our system in outpatient clinics in Iowa City area from January 1st to March 31st, 2017. This period includes the preponderance of the 2017 flu season. We are releasing a subset of 3-second file that include coughs (2,883) and non-cough sounds (3,191).