218963 Using Optical Character Recognition (OCR) to collect, manage and analyze data and guide decision making in Los Angeles County during H1N1

Monday, November 8, 2010

Sinan Khan, MPH, MA , Department of Public Health, Los Angeles County, Los Angeles, CA
Dee Ann Bagwell, MA, MPH , Department of Public Health, Los Angeles County, Los Angeles, CA
Alonzo L. Plough, PhD, MPH , Department of Public Health, Los Angeles County, Los Angeles, CA
Alvin Nelson, MD , Department of Public Health, Los Angeles County, Los Angeles, CA
During H1N1, Los Angeles County Department of Public Health (LACDPH) deployed an Optical Character Recognition System (OCR) that would provide decision makers with time critical information based on client data collected at 109 Points of Dispensing (PODs) between October 23rd, 2009 and December 9th, 2009. This data enabled decision makers to confirm the effectiveness of their outreach strategy and ensure that the CDC established priority groups were being reached.

OCR forms (translated into ten different languages) collected demographic information as well as vaccine and site information. All forms were scanned, away from PODs, using the OCR System that converted hand written text into digitized characters and imported data into a central data repository along with a digital copy of the original form. LACDPH built data-dictionaries/look-up fields in order to reduce scanning errors and significantly reduce the amount of time requiring data cleaning. The system generated data-reports for presentation to decision makers based on demographics and vaccination information.

Since LACDPH vaccinated 195,246 individuals, the OCR System made it possible to collect, analyze and accurately report time sensitive data to decision makers and guide planning and outreach efforts and enabled LACDPH to track vaccine and collect data at an individual level. The OCR Systems ability to scan data from multiple locations to a central repository reduced the burden on a single location to mass scan forms. The system enabled LACDPH to report client data to the CDC CRA system in a timely manner given the size of the client base. The system enabled LACDPH to find client forms incase of adverse events. In addition, the system enabled LACDPH to gather information such as distance traveled, using GIS, by individuals to get to PODs, effectiveness of POD sites and vaccination rates among various minority ethnic groups to improve outreach during future events.

Learning Areas:
Administration, management, leadership
Biostatistics, economics
Communication and informatics
Other professions or practice related to public health
Provision of health care to the public
Public health administration or related administration

Learning Objectives:
1. Evaluate the feasibility of using Optical Character Recognition (OCR) Technology to collect, manage and analyze data during a a large scale emergency. 2. Demonstrate the need for rapid data collection and assessment in order to guide decision making during a large scale emergency. 3. Describe lessons learned for future deployment of OCR during a Public Health Event

Keywords: Disasters, Data Collection

Presenting author's disclosure statement:

Qualified on the content I am responsible for because: As the project manager for development and implementation of Optical Character Recognition Software during emergency response for the Los Angeles County Department of Public Health
Any relevant financial relationships? No

I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.

Back to: 3366.0: The Role of HIIT in Emergency Preparedness