Lowering the burden of medical translation by enabling international healthcare professionals as human editors of machine translations

PROJECT SUMMARY Language access solutions in healthcare have focused almost exclusively on the provision of verbal medical interpretation, despite federal and state laws that mandate translation of written information for patients with limited English proficiency (LEP). In recent years, machine translation (MT) has made significant strides, but when it comes to mission-critical technical materials such as healthcare information, the accuracy rate of machine-only translations plummets. Thus, experts recommend MT as a starting point for translating health-related material then supplementing with human quality assurance editing. However, coordinating machine translation with bilingual human editors who have technical medical knowledge is a challenge, especially for less commonly supported languages. Translation vendors currently pass on the associated costs of human assistance to healthcare institutions. The Canopy Translate project will address these deficits by implementing a novel, human-assisted machine translation (HAMT) process. The envisioned workflow management platform will leverage MT engines to expedite the initial rendering of source documents into a target language, then invite bilingual healthcare professionals around the world to apply human editing to the machine-generated translation. The bilingual contributors, who will gain complimentary access to our Medical English eLearning courses as an incentive for their participation, will complete the editing task through gamified learning exercises. For example, a nurse in the Philippines has native fluency in Tagalog and advanced general English but desires to improve his medical English. He can edit a machine-generated Tagalog translation one sentence at a time in the form of a gamified activity. Other contributors will edit the same text for additional quality assurance to form the final, polished version in Tagalog. The system will then organize the final translated content into a reusable document library. In Phase I, we will test the feasibility of this hybrid HAMT approach for medical content. Upon meeting feasibility benchmarks, we will advance to Phase II, during which we will create a minimum viable product, encompassing several novel natural language processing (NLP) algorithms, and evaluate the translation output according to a set of quality benchmarks. If successful, this project will significantly improve the availability, speed, and cost-effectiveness of producing multilingual health content, with potential to reduce health disparities in LEP populations.