Abdelgadir Yasir H, Thongprayoon Charat, Craici Iasmina M, Cheungpasitporn Wisit, Miao Jing
Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA.
Healthcare (Basel). 2024 Dec 31;13(1):57. doi: 10.3390/healthcare13010057.
: It is often challenging for patients to understand treatment options, their mechanisms of action, and the potential side effects of each treatment option for glomerular disorders. This study explored the ability of ChatGPT to simplify these treatment options to enhance patient understanding. : GPT-4 was queried on sixty-seven glomerular disorders using two distinct queries for a general explanation and an explanation adjusted for an 8th grade level or lower. Accuracy was rated on a scale of 1 (incorrect) to 5 (correct and comprehensive). Readability was measured using the average of the Flesch-Kincaid Grade (FKG) and SMOG indices, along with the Flesch Reading Ease (FRE) score. The understandability score (%) was determined using the Patient Education Materials Assessment Tool for Printable Materials (PEMAT-P). : GPT-4's general explanations had an average readability level of 12.85 ± 0.93, corresponding to the upper end of high school. When tailored for patients at or below an 8th-grade level, the readability improved to a middle school level of 8.44 ± 0.72. The FRE and PEMAT-P scores also reflected improved readability and understandability, increasing from 25.73 ± 6.98 to 60.75 ± 4.56 and from 60.7% to 76.8% ( < 0.0001 for both), respectively. The accuracy of GPT-4's tailored explanations was significantly lower compared to the general explanations (3.99 ± 0.39 versus 4.56 ± 0.66, < 0.0001). : ChatGPT shows significant potential for enhancing the readability and understandability of glomerular disorder therapies for patients, but at a cost of reduced comprehensiveness. Further research is needed to refine the performance, evaluate the real-world impact, and ensure the ethical use of ChatGPT in healthcare settings.
对于患者来说，理解肾小球疾病的治疗方案、其作用机制以及每种治疗方案的潜在副作用往往具有挑战性。本研究探讨了ChatGPT简化这些治疗方案以提高患者理解能力的情况。针对67种肾小球疾病向GPT-4进行了查询，使用了两个不同的查询，一个是一般性解释，另一个是针对八年级及以下水平调整后的解释。准确性按1（错误）至5（正确且全面）的等级进行评分。可读性使用弗莱施-金凯德年级水平（FKG）和雾度指数的平均值以及弗莱施阅读简易度（FRE）得分来衡量。可理解性得分（%）使用针对印刷材料的患者教育材料评估工具（PEMAT-P）来确定。GPT-4的一般性解释的平均可读性水平为12.85±0.93，相当于高中高年级水平。当为八年级及以下水平的患者量身定制时，可读性提高到了初中水平的8.44±0.72。FRE和PEMAT-P得分也反映出可读性和可理解性有所提高，分别从25.73±6.98提高到60.75±4.56，从60.7%提高到76.8%（两者均<0.0001）。与一般性解释相比，GPT-4量身定制的解释的准确性显著降低（3.99±0.39对4.56±0.66，<0.0001）。ChatGPT在提高患者对肾小球疾病治疗的可读性和可理解性方面显示出巨大潜力，但代价是全面性降低。需要进一步研究来优化其性能、评估实际影响，并确保在医疗环境中道德地使用ChatGPT。
