McMinn David, Grant Tom, DeFord-Watts Laura, Porkess Veronica, Lens Margarita, Rapier Christopher, Joe Wilson Q, Becker Timothy A, Bender Walter
Sorcero, East Kilbride G75 8QD, United Kingdom.
UCB, Slough SL1 3WE, United Kingdom.
JAMIA Open. 2025 Apr 3;8(2):ooaf023. doi: 10.1093/jamiaopen/ooaf023. eCollection 2025 Apr.
To assess the capacity of a bespoke artificial intelligence (AI) process to help medical writers efficiently generate quality plain language summary abstracts (PLSAs).
Three independent studies were conducted. In Studies 1 and 3, original scientific abstracts (OSAs; = 48, = 2) and corresponding PLSAs written by medical writers versus bespoke AI were assessed using standard readability metrics. Study 2 compared time and effort of medical writers ( = 10) drafting PLSAs starting with an OSA ( = 6) versus the output of 1 bespoke AI ( = 6) and 1 non-bespoke AI ( = 6) process. These PLSAs ( = 72) were assessed by subject matter experts (SMEs; = 3) for accuracy and physicians ( = 7) for patient suitability. Lastly, in Study 3, medical writers ( = 22) and patients/patient advocates (= 5) compared quality of medical writer and bespoke AI-generated PLSAs.
In Study 1, bespoke AI PLSAs were easier to read than medical writer PLSAs across all readability metrics ( <.01). In Study 2, bespoke AI output saved medical writers >40% in time for PLSA creation and required less effort than unassisted writing. SME-assessed quality was higher for AI-assisted PLSAs, and physicians preferred bespoke AI-generated outputs for patient use. In Study 3, bespoke AI PLSAs were more readable and rated of higher quality than medical writer PLSAs.
The bespoke AI process may enhance access to health information by helping medical writers produce PLSAs of scientific content that are fit for purpose.
The bespoke AI process can more efficiently create better quality, more readable first draft PLSAs versus medical writer-generated PLSAs.
评估定制人工智能（AI）流程帮助医学撰写人员高效生成高质量的通俗易懂的摘要（PLSA）的能力。
进行了三项独立研究。在研究1和研究3中，使用标准可读性指标对原始科学摘要（OSA；n = 48，n = 2）以及医学撰写人员与定制AI撰写的相应PLSA进行了评估。研究2比较了医学撰写人员（n = 10）从OSA（n = 6）开始起草PLSA的时间和精力，与1个定制AI（n = 6）和1个非定制AI（n = 6）流程的输出。这些PLSA（n = 72）由主题专家（SME；n = 3）评估准确性，由医生（n = 7）评估对患者的适用性。最后，在研究3中，医学撰写人员（n = 22）和患者/患者倡导者（n = 5）比较了医学撰写人员和定制AI生成的PLSA的质量。
在研究1中，在所有可读性指标方面，定制AI的PLSA比医学撰写人员的PLSA更易读（P <.01）。在研究2中，定制AI的输出使医学撰写人员创建PLSA的时间节省了40%以上，并且比无辅助撰写所需的精力更少。AI辅助的PLSA经SME评估的质量更高，医生更倾向于定制AI生成的输出供患者使用。在研究3中，定制AI的PLSA比医学撰写人员的PLSA更具可读性且质量评级更高。
定制AI流程可能通过帮助医学撰写人员生成适合目标的科学内容的PLSA来增加获取健康信息的机会。
与医学撰写人员生成的PLSA相比，定制AI流程可以更高效地创建质量更高、可读性更强的初稿PLSA。
