Real-Time Biosurveillance Program (RTBP) introduces modern surveillance technology to health departments in Sri Lanka and Tamil Nadu, India. Triage data from each patient visit (basic demographics, signs, symptoms, preliminary diagnoses) is recorded on paper at health facilities. Case records are transmitted daily to a central database using the RTBP mobile phone application. It is done by medical professionals in India, but in Sri Lanka, due to staffing constraints, the same duty is performed by lower cost personnel with limited domain knowledge. That results in noticeable differences in data entry error rates between the two locations. Most of such issues are due to systematic and subjectivemisinterpretations of the handwritten doctor notes by the data entry personnel. If not identified and remedied quickly, these errors can adversely affect accuracy and timeliness of health events detection. There is a need to support system managers in their efforts to maintain high reliability of data used for public health surveillance.
Objective
We present a method for automated detection of systematic data entry errors in real time biosurveillance.