Modeling workflow to design machine translation applications for public health practice

Anne M Turner; Megumu K Brownstein; Kate Cole; Hilary Karasz; Katrin Kirchhoff

doi:10.1016/j.jbi.2014.10.005

Modeling workflow to design machine translation applications for public health practice

J Biomed Inform. 2015 Feb:53:136-46. doi: 10.1016/j.jbi.2014.10.005. Epub 2014 Oct 17.

Authors

Anne M Turner¹, Megumu K Brownstein², Kate Cole³, Hilary Karasz⁴, Katrin Kirchhoff⁵

Affiliations

¹ University of Washington Northwest Center for Public Health Practice, 1107 NE 45th Street, Suite 400, Box 354809, Seattle, WA 98105, USA; Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, USA; Department of Health Services, University of Washington, Seattle, WA, USA. Electronic address: amturner@uw.edu.
² University of Washington Northwest Center for Public Health Practice, 1107 NE 45th Street, Suite 400, Box 354809, Seattle, WA 98105, USA.
³ Department of Health Services, University of Washington, Seattle, WA, USA.
⁴ Public Health - Seattle & King County, Seattle, WA, USA.
⁵ Department of Electrical Engineering, University of Washington, Seattle, WA, USA.

Abstract

Objective: Provide a detailed understanding of the information workflow processes related to translating health promotion materials for limited English proficiency individuals in order to inform the design of context-driven machine translation (MT) tools for public health (PH).

Materials and methods: We applied a cognitive work analysis framework to investigate the translation information workflow processes of two large health departments in Washington State. Researchers conducted interviews, performed a task analysis, and validated results with PH professionals to model translation workflow and identify functional requirements for a translation system for PH.

Results: The study resulted in a detailed description of work related to translation of PH materials, an information workflow diagram, and a description of attitudes towards MT technology. We identified a number of themes that hold design implications for incorporating MT in PH translation practice. A PH translation tool prototype was designed based on these findings.

Discussion: This study underscores the importance of understanding the work context and information workflow for which systems will be designed. Based on themes and translation information workflow processes, we identified key design guidelines for incorporating MT into PH translation work. Primary amongst these is that MT should be followed by human review for translations to be of high quality and for the technology to be adopted into practice.

Conclusion: The time and costs of creating multilingual health promotion materials are barriers to translation. PH personnel were interested in MT's potential to improve access to low-cost translated PH materials, but expressed concerns about ensuring quality. We outline design considerations and a potential machine translation tool to best fit MT systems into PH practice.

Keywords: Human centered design; Natural language processing; Public health informatics; Public health practice; Workflow.

Publication types

Research Support, N.I.H., Extramural

MeSH terms

Access to Information
Algorithms
Communication
Electronic Data Processing
Focus Groups
Health Education / methods*
Health Promotion
Health Services Accessibility
Humans
Language
Machine Learning
Public Health Administration
Public Health Informatics
Public Health Practice*
Quality Assurance, Health Care
Translating*
Washington
Workflow*

Abstract

Publication types

MeSH terms

Grants and funding