文献速递介入技术与安全

利用大语言模型提升介入放射学以患者为中心诊疗中操作信息的可读性(PRO-READ IR)

Enhanced PROcedural Information READability for Patient-Centered Care in Interventional Radiology With Large Language Models (PRO-READ IR).
PubMed 文献 · J Am Coll Radiol · 2024-08-30

本研究评估GPT-4为10项常见介入放射学操作生成患者教育材料的能力,由4名临床医师和9名非临床评估者评价,并用可读性指标与radiologyinfo.org比较。GPT-4生成材料的Flesch-Kincaid平均年级为7.8±0.87,优于radiologyinfo.org的9.6±0.83(P=0.007),Gunning Fog指数更低、Flesch阅读轻松度更高,提示可读性更好。

要点

  • GPT-4生成的介入操作患者教育材料在临床适宜性上获医师认可,10项中9项被评为完全适宜。
  • GPT-4材料可读性达7至8年级水平,优于radiologyinfo.org的9至10年级水平。
  • 非临床评估者对多数操作说明评价为优秀或良好,但胸腔穿刺、输液港置入和CT引导活检有14%评为一般。

核心结论

  • GPT-4生成的介入放射学操作说明通过提供易于理解的解释,有助于改善健康素养和以患者为中心的诊疗。

研究设计与样本

  • 研究纳入10项介入放射学操作,为GPT-4准备提示词以通俗语言生成患者教育说明,由4名临床医师和9名非临床评估者通过问卷调查评价临床适宜性、可理解性和清晰度,并使用经验证的可读性指标进行年级水平评估,同时与radiologyinfo.org的患者说明进行配对t检验比较。

诊断标准与关键数值

  • GPT-4生成的全部操作说明Flesch-Kincaid平均年级为7.8±0.87,radiologyinfo.org为9.6±0.83,P=0.007。
  • GPT-4生成说明的Gunning Fog平均指数为10.4±1.2,radiologyinfo.org为12.7±0.93,P=0.006。
  • GPT-4生成说明的Flesch阅读轻松度平均分为69.4±4.8,radiologyinfo.org为51.3±3.9,P=0.0001。

临床应用与阅片要点

  • 4名临床医师评价显示,9项GPT-4生成说明完全适宜,动脉栓塞说明 somewhat appropriate。
  • 9名非临床评估者中,57%将腹腔穿刺、透析导管置入、血栓切除术、超声引导活检和肾造瘘管说明评为优秀,43%评为良好。
  • 动脉栓塞和胆道引流说明获28.6%优秀、71.4%良好;胸腔穿刺、输液港置入和CT引导活检说明获43%优秀、43%良好、14%一般。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: To evaluate the extent to which Generative Pre-trained Transformer 4 (GPT-4) can educate patients by generating easily understandable information about the most common interventional radiology (IR) procedures.

MATERIALS AND METHODS: We reviewed 10 IR procedures and prepared prompts for GPT-4 to provide patient educational instructions about each procedure in layman's terms. The instructions were then evaluated by four clinical physicians and nine nonclinical assessors to determine their clinical appropriateness, understandability, and clarity using a survey. A grade-level readability assessment was performed using validated metrics to evaluate accessibility to a wide patient population. The same procedures were also evaluated from the patient instructions available at radiologyinfo.org and compared with GPT-generated instructions utilizing a paired t test.

RESULTS: Evaluation by four clinical physicians shows that nine GPT-generated instructions were fully appropriate, whereas arterial embolization instructions was somewhat appropriate. Evaluation by nine nonclinical assessors shows that paracentesis, dialysis catheter placement, thrombectomy, ultrasound-guided biopsy, and nephrostomy-tube instructions were rated excellent by 57% and good by 43%. The arterial embolization and biliary-drain instructions were rated excellent by 28.6% and good by 71.4%. In contrast, thoracentesis, port placement, and CT-guided biopsy instructions received 43% excellent, 43% good, and 14% fair. The readability assessment across all procedural instructions showed a better Flesch-Kincaid mean grade of GPT-4 instructions compared with radiologyinfo.org (7.8 ± 0.87 versus 9.6 ± 0.83; P = .007) indicating excellent readability at 7th- to 8th-grade level compared with 9th to 10th grade. Additionally there was a lower Gunning Fog mean index (10.4 ± 1.2 versus 12.7 ± 0.93; P = .006), and higher Flesch Reading Ease mean score (69.4 ± 4.8 versus 51.3±3.9; P = .0001) indicating better readability.

CONCLUSION: IR procedural instructions generated by GPT-4 can aid in improving health literacy and patient-centered care in IR by generating easily understandable explanations.

来源:J Am Coll Radiol,查看原文。版权归原作者所有。

引用

  1. Elhakim T, Brea AR, Fidelis W, et al. Enhanced PROcedural Information READability for Patient-Centered Care in Interventional Radiology With Large Language Models (PRO-READ IR). J Am Coll Radiol. 2024. PMID: 39216782. doi:10.1016/j.jacr.2024.08.010

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。