Significance Language discordance has been shown to contribute to social disparities in healthcare. Contact tracing is essential to combating COVID-19, but language differences between contact tracers and patients have hindered its efficacy. We demonstrate a general method for leveraging machine learning and administrative data to maximize the impact of bilingual contact tracers and level language differences. We evaluate in a randomized controlled trial the impact of language matching on high-volume contact tracing in Santa Clara County, CA, and show that it reduces time spent and improves engagement with contact tracers. These results illustrate the advantages of utilizing bilingual personnel over third-party interpreters in improving social services. Contact tracing is a pillar of COVID-19 response, but language access and equity have posed major obstacles. COVID-19 has disproportionately affected minority communities with many non–English-speaking members. Language discordance can increase processing times and hamper the trust building necessary for effective contact tracing. We demonstrate how matching predicted patient language with contact tracer language can enhance contact tracing. First, we show how to use machine learning to combine information from sparse laboratory reports with richer census data to predict the language of an incoming case. Second, we embed this method in the highly demanding environment of actual contact tracing with high volumes of cases in Santa Clara County, CA. Third, we evaluate this language-matching intervention in a randomized controlled trial. We show that this low-touch intervention results in 1) significant time savings, shortening the time from opening of cases to completion of the initial interview by nearly 14 h and increasing same-day completion by 12%, and 2) improved engagement, reducing the refusal to interview by 4%. These findings have important implications for reducing social disparities in COVID-19; improving equity in healthcare access; and, more broadly, leveling language differences in public services.
【저자키워드】 COVID-19, machine learning, Contact tracing, health equity, language access, 【초록키워드】 Randomized controlled trial, Efficacy, Intervention, Laboratory, healthcare, Patient, Community, language, information, predict, equity, Contact, Volume, second, refusal, implication, effective, combating, ENhance, initial, IMPROVE, shown, predicted, affected, evaluate, contribute, reducing, reduce, Significance, 【제목키워드】 equity, Efficiency, IMPROVE,