University of California San Francisco and the Division of Research, Northern California Kaiser Permanente.
State University of New York Old Westbury and Arizona State University.
J Health Care Poor Underserved. 2021 May;32(2 Suppl):347-365. doi: 10.1353/hpu.2021.0067.
Limited health literacy (HL) partially mediates health disparities. Measurement constraints, including lack of validity assessment across racial/ethnic groups and administration challenges, have undermined the field and impeded scaling of HL interventions. We employed computational linguistics to develop an automated and novel HL measure, analyzing >300,000 messages sent by >9,000 diabetes patients via a patient portal to create a Literacy Profiles. We carried out stratified analyses among White/non-Hispanics, Black/non-Hispanics, Hispanics, and Asian/Pacific Islanders to determine if the Literacy Profile has comparable criterion and predictive validities. We discovered that criterion validity was consistently high across all groups (c-statistics 0.82-0.89). We observed consistent relationships across racial/ethnic groups between HL and outcomes, including communication, adherence, hypoglycemia, diabetes control, and ED utilization. While concerns have arisen regarding bias in AI, the automated Literacy Profile appears sufficiently valid across race/ethnicity, enabling HL measurement at a scale that could improve clinical care and population health among diverse populations.
健康素养（HL）有限部分导致了健康差距。测量限制，包括缺乏跨种族/民族群体的有效性评估以及管理挑战，已经削弱了该领域，并阻碍了 HL 干预措施的扩展。我们运用计算语言学开发了一种自动化的新型 HL 衡量标准，通过分析 9000 多名糖尿病患者通过患者门户发送的超过 300,000 条消息，创建了一个 Literacy Profiles。我们在白人和非西班牙裔、黑人和非西班牙裔、西班牙裔以及亚裔/太平洋岛民中进行了分层分析，以确定 Literacy Profile 是否具有可比的标准和预测有效性。我们发现，所有组的标准有效性都非常高（c 统计量为 0.82-0.89）。我们观察到 HL 与包括沟通、依从性、低血糖、糖尿病控制和 ED 使用在内的结果之间存在一致的关系，跨越了种族/民族群体。虽然人们对人工智能中的偏见提出了担忧，但自动化的 Literacy Profile 在跨种族/民族方面似乎具有足够的有效性，使 HL 测量能够达到改善不同人群临床护理和人口健康的规模。
