Miskiewicz Michael J, Perez Matthew, Capotosto Salvatore, Ling Kenny, Hance Frederick, Komatsu David, Wang Edward D
Department of Orthopedic Surgery, Stony Brook University, Stony Brook, USA.
Cureus. 2024 Nov 1;16(11):e72833. doi: 10.7759/cureus.72833. eCollection 2024 Nov.
Health literacy plays a vital role in determining one's health status, as studies have shown that poor health literacy is associated with negative health results. The Centers for Disease Control and Prevention (CDC) and the National Institutes of Health (NIH) advise that patient educational materials (PEMs) should be written at an eighth-grade reading level or lower, matching the average reading level of adult Americans. This study evaluated the ability of generative artificial intelligence (AI) to rewrite PEMs about rotator cuff injuries (RCIs) to align with the eighth-grade reading level recommendation of the CDC and NIH.
Online PEMs about RCI from the 25 highest ranked orthopedic hospitals from the 2022 U.S. News and World Report Best Hospitals Specialty Ranking were collected. Chat Generative Pretrained Transformer Plus, version 4.0 (OpenAI, San Francisco, CA) was then instructed to rewrite the PEMs to adhere to CDC and NIH-recommended guidelines. Readability scores were calculated for the original and rewritten PEMs, and paired t-tests were used to determine statistical significance.
Analysis of the original and rewritten PEMs about RCI demonstrated significant reductions in reading-grade level and word count of 4.33 ± 1.50 (p < 0.001) and 442.68 ± 351.45 (p < 0.001), respectively.
Our study determined that generative AI is capable of rewriting PEMs about RCI at a reading comprehension level that conforms to the CDC and NIH guidelines. Hospital administrators and orthopedic surgeons should consider the findings of this study, and the potential utility of AI when crafting PEMs of their own.
健康素养在决定一个人的健康状况方面起着至关重要的作用,因为研究表明,健康素养低下与不良健康结果相关。疾病控制与预防中心(CDC)和美国国立卫生研究院(NIH)建议,患者教育材料(PEMs)应以八年级及以下的阅读水平编写,以匹配成年美国人的平均阅读水平。本研究评估了生成式人工智能(AI)重写关于肩袖损伤(RCIs)的患者教育材料,使其符合疾病控制与预防中心和美国国立卫生研究院八年级阅读水平建议的能力。
收集了来自2022年《美国新闻与世界报道》最佳医院专科排名中排名前25的骨科医院的关于肩袖损伤的在线患者教育材料。然后指示Chat Generative Pretrained Transformer Plus 4.0版本(OpenAI,加利福尼亚州旧金山)重写这些患者教育材料,以符合疾病控制与预防中心和美国国立卫生研究院推荐的指南。计算原始和重写的患者教育材料的可读性分数,并使用配对t检验确定统计学意义。
对关于肩袖损伤的原始和重写的患者教育材料的分析表明,阅读年级水平和单词数分别显著降低了4.33±1.50(p<0.001)和442.68±351.45(p<0.001)。
我们的研究确定,生成式人工智能能够以符合疾病控制与预防中心和美国国立卫生研究院指南的阅读理解水平重写关于肩袖损伤的患者教育材料。医院管理人员和骨科医生在编写自己的患者教育材料时应考虑本研究的结果以及人工智能的潜在用途。