Validation testing of a language translation device for suitability in assisting Australian radiation therapists to communicate with Mandarin-speaking patients

INTRODUCTION: Clear, timely communication between practitioners and patients is key in ensuring equitable access to health services and optimal care. Australia’s linguistically diverse population adds complexity to healthcare provision. This paper describes a validation study to assess clinical suitability of a language translation device, intended for use with Mandarin speaking patients undergoing radiotherapy (RT). MATERIALS AND METHODS: After a comprehensive device selection process, common phrases used in RT practice were curated within one clinical center and translated by interpreters. Phrases were categorized by conversation type and readability (according to Flesch-Kincaid and FORCAST scores). Validation of device performance was undertaken by purposely selected radiation therapists (RTTs) who tested and evaluated the device using a survey with 5-point Likert scale responses. Statistical analysis was undertaken on Excel using Pearson’s chi-square, z-test, interrater reliability/agreement and linear regression analyses. RESULTS: Six RTTs and two interpreters volunteered to participate in this study. 188 common phrases were spoken verbatim into the device and scored on a 5-point Likert scale, yielding an overall output accuracy of 66%. A z-test confirmed significance against prior comparative research and Linear regression analysis observed improved output between consecutive participants. 62.7% of interpreter scores were identical; a further 29.1% constituted a single point scoring variation. Poorer outcomes were observed with colloquial English and lower readability. CONCLUSIONS: This study found the device produced suitable translation accuracy and identified language styles that should be avoided with use. Further research could consider clinical application, expanded languages and/or health disciplines, and development of a national RTT phrase list.