Journal of the American College of Radiology最新文献

英文中文

Office-Based Diagnostic Imaging Interpreted by Nonphysician Practitioners: Characteristics, Recent Trends, and State Variation 由非执业医师解读的诊室诊断成像：特征、最新趋势和各州差异。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.10.008

Eric W. Christensen PhD , Clinton T. Case BS , Robert W. Morris MD , Casey E. Pelzl MPH , Elizabeth Y. Rula PhD , Richard Duszak Jr. MD

Purpose

Diagnostic imaging interpretations by nonphysician practitioners (NPPs) are increasing. With hospital-based imaging overwhelmingly interpreted by radiologists, we studied office-based interpretations by NPPs by their physician employer specialty.

Methods

Linking Medicare claims and provider datasets, we identified imaging interpretation claims submitted by nurse practitioners and physician assistants (together NPPs) in office settings, mapping NPPs to physician employer specialties, and assessed NPP characteristics and practice patterns.

Results

Between 2013 and 2022, the share of office-based imaging interpretations by NPPs increased 9.0% annually (from 2.52% to 5.47%) overall and by the following modalities: radiography (8.9%; 4.30%-9.23%), ultrasound (9.4%; 0.52%-1.18%), CT (9.4%; 0.13%-0.28%), MR (9.9%, 0.19%-0.44%), and nuclear medicine (7.2%; 0.07%-0.12%). Just 5.55% of NPPs rendered interpretations. NPPs employed by primary care physicians (PCPs) and orthopedists interpreted the largest shares of NPP imaging (39.5% and 34.1%, respectively). By modality, the largest shares by employer specialties were PCPs and orthopedists for radiography (39.7%, 37.4%), PCPs and practices without physicians for ultrasound (44.7%, 12.7%), PCPs and otolaryngologists for CT (58.2%, 17.1%), orthopedists and PCPs for MR (60.3%, 24.0%), and PCPs and cardiologists for nuclear medicine (40.4%, 25.9%). Younger NPPs (<35 years) interpreted imaging more frequently than older counterparts (≥65) (odds ratio 1.42 [95% confidence interval: 1.37-1.48]) and male NPPs interpreted imaging more frequently than female NPPs (odds ratio 1.61 [95% confidence interval: 1.58-1.63]). Overall interpretation shares ranged from 13.16% in Alaska to 0.29% in Washington, DC.

Conclusion

In Medicare, the share of office-based imaging interpretations performed by NPPs is increasing, varying considerably by state. Interpretations are performed by relatively few NPPs, particularly those younger, male, and employed by PCPs and orthopedists.

目的：非医师执业者（NPPs）对诊断成像的解释越来越多。由于医院的影像诊断绝大多数由放射科医生负责，我们按医生雇主的专业对非医师从业人员在办公室进行的影像诊断进行了研究：我们将医疗保险报销单和医疗服务提供者数据集联系起来，确定了执业护士和医生助理（合称 NPPs）在诊室环境中提交的影像解读报销单，将 NPPs 与医生雇主专业进行了映射，并评估了 NPP 的特征和执业模式：从 2013 年到 2022 年，NPP 在诊室成像诊断中所占的比例每年增长 9.0%（从 2.52% 增长到 5.47%），总体而言，NPP 在以下医学模式中所占的比例每年增长 9.0%：放射（8.9%；4.30%-9.23%）、超声（9.4%；0.52%-1.18%）、CT（9.4%；0.13%-0.28%）、磁共振（9.9%，0.19%-0.44%）和核医学（7.2%；0.07%-0.12%）。仅有 5.55% 的 NPP 提供解释。初级保健医生 (PCP) 和矫形外科医生聘用的 NPP 在 NPP 成像中提供解释的比例最大（分别为 39.5% 和 34.1%）。按方式划分，雇主专科所占比例最大的是初级保健医生和骨科医生负责放射摄影（39.7%，37.4%），初级保健医生和无医生诊所负责超声波（44.7%，12.7%），初级保健医生和耳鼻喉科医生负责 CT（58.2%，17.1%），骨科医生和初级保健医生负责 MR（60.3%，24.0%），初级保健医生和心脏病医生负责核医学（40.4%，25.9%）。较年轻的国家医疗计划人员（结论：在医疗保险中，诊室医疗所占比例较低：在医疗保险中，由非专业医师进行诊室成像解释的比例正在增加，各州之间差异很大。进行判读的 NPP 相对较少，尤其是那些年轻、男性、受雇于初级保健医生和骨科医生的 NPP。

{"title":"Office-Based Diagnostic Imaging Interpreted by Nonphysician Practitioners: Characteristics, Recent Trends, and State Variation","authors":"Eric W. Christensen PhD , Clinton T. Case BS , Robert W. Morris MD , Casey E. Pelzl MPH , Elizabeth Y. Rula PhD , Richard Duszak Jr. MD","doi":"10.1016/j.jacr.2024.10.008","DOIUrl":"10.1016/j.jacr.2024.10.008","url":null,"abstract":"<div><h3>Purpose</h3><div>Diagnostic imaging interpretations by nonphysician practitioners (NPPs) are increasing. With hospital-based imaging overwhelmingly interpreted by radiologists, we studied office-based interpretations by NPPs by their physician employer specialty.</div></div><div><h3>Methods</h3><div>Linking Medicare claims and provider datasets, we identified imaging interpretation claims submitted by nurse practitioners and physician assistants (together NPPs) in office settings, mapping NPPs to physician employer specialties, and assessed NPP characteristics and practice patterns.</div></div><div><h3>Results</h3><div>Between 2013 and 2022, the share of office-based imaging interpretations by NPPs increased 9.0% annually (from 2.52% to 5.47%) overall and by the following modalities: radiography (8.9%; 4.30%-9.23%), ultrasound (9.4%; 0.52%-1.18%), CT (9.4%; 0.13%-0.28%), MR (9.9%, 0.19%-0.44%), and nuclear medicine (7.2%; 0.07%-0.12%). Just 5.55% of NPPs rendered interpretations. NPPs employed by primary care physicians (PCPs) and orthopedists interpreted the largest shares of NPP imaging (39.5% and 34.1%, respectively). By modality, the largest shares by employer specialties were PCPs and orthopedists for radiography (39.7%, 37.4%), PCPs and practices without physicians for ultrasound (44.7%, 12.7%), PCPs and otolaryngologists for CT (58.2%, 17.1%), orthopedists and PCPs for MR (60.3%, 24.0%), and PCPs and cardiologists for nuclear medicine (40.4%, 25.9%). Younger NPPs (<35 years) interpreted imaging more frequently than older counterparts (≥65) (odds ratio 1.42 [95% confidence interval: 1.37-1.48]) and male NPPs interpreted imaging more frequently than female NPPs (odds ratio 1.61 [95% confidence interval: 1.58-1.63]). Overall interpretation shares ranged from 13.16% in Alaska to 0.29% in Washington, DC.</div></div><div><h3>Conclusion</h3><div>In Medicare, the share of office-based imaging interpretations performed by NPPs is increasing, varying considerably by state. Interpretations are performed by relatively few NPPs, particularly those younger, male, and employed by PCPs and orthopedists.</div></div>","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 1","pages":"Pages 56-65"},"PeriodicalIF":4.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142683744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Patient-Friendly Summary of the ACR Appropriateness Criteria®: Imaging After Mastectomy and Breast Reconstruction ACR 适宜性标准®患者友好摘要：乳房切除术和乳房重建术后的成像。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.09.011

Sania Choudhary , Nina S. Vincoff MD

引用次数: 0

Utilization of CT for Extremity Cellulitis: A Retrospective Single-Center Analysis 四肢蜂窝组织炎的计算机断层扫描应用：单中心回顾性分析。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.10.011

Cynthia E. Burke BS , Owen R. Maley MD , Benjamin Mancini BS , SaraPettey Sandifer BS , Sahil Sardesai BS , Tonya S. King PhD , Donald J. Flemming MD

Purpose

Routine imaging of soft tissue infection is not recommended and represents a potential area of CT overuse. The utility of CT in patients with superficial soft tissue infection of the extremities is unknown. The purpose of this study is to evaluate the utilization and clinical impact of CT ordered in the setting of extremity cellulitis.

Methods

We retrospectively analyzed patients with extremity cellulitis examined with CT between 2012 and 2021 at a single center. We collected patient history, diagnostic imaging characteristics, and subsequent surgery decision. We hypothesized that yield of CT for deep infection was significantly lower than 10% and that yield was decreasing over time. These hypotheses were evaluated with Rao-Scott χ² tests and repeated measures logistic regression.

Results

There were 496 eligible encounters among 463 patients. Yield of positive CT among lower extremity patients was 5.5% (95% confidence interval 3.33-7.75), significantly less than our hypothesis of 10% (P = .003). In 71.8% of encounters, patients underwent diagnostic imaging studies in addition to CT. Utilization rose from 0.08% per hospital visit in 2012 to 2013 to 0.14% in 2020 to 2021, with differences in yield between time periods not reaching statistical significance (P = .059). Among 496 encounters, 62 received surgery (12.1%), with 21 of these cases preceded by a positive CT for deep infection.

Conclusions

Our 10-year single-center analysis of CT use for extremity cellulitis demonstrated a low yield of positive CT findings for deep infection and limited impact of CT on surgical management. A high incidence of patients undergoing multiple radiologic examinations suggests uncertainty in selecting appropriate imaging modalities in this clinical scenario.

Summary

This single-center retrospective analysis found that CT examination of patients with clinically diagnosed cellulitis of the extremities has significantly low yield for deep infection in the lower extremities.

目的：不建议对软组织感染进行常规成像，这是计算机断层扫描（CT）过度使用的潜在领域。CT 在四肢浅表软组织感染患者中的作用尚不清楚。本研究的目的是评估肢端蜂窝织炎患者使用 CT 的情况及其临床影响：我们对 2012-2021 年间在一个中心接受 CT 检查的四肢蜂窝织炎患者进行了回顾性分析。我们收集了患者病史、影像诊断特征和后续手术决定。我们假设CT对深部感染的诊断率明显低于10%，而且随着时间的推移诊断率在下降。我们通过 Rao-Scott Chi-Square 检验和重复测量逻辑回归对这些假设进行了评估：结果：463 名患者中有 496 例符合条件。下肢患者的 CT 阳性率为 5.5%（95%CI 3.33-7.75），明显低于我们假设的 10%（P=0.003）。在 71.8% 的就诊中，患者除 CT 外还接受了影像诊断检查。每次医院就诊的使用率从2012-2013年的0.08%上升到2020-2021年的0.14%，不同时期的使用率差异未达到统计学意义（P=0.059）。在 496 例就诊中，62 例接受了手术（12.1%），其中 21 例在手术前进行了深部感染 CT 阳性检测：我们对肢体蜂窝织炎使用 CT 的 10 年单中心分析显示，CT 发现深部感染阳性的比例较低，CT 对手术治疗的影响有限。接受多次放射检查的患者比例较高，这表明在这种临床情况下选择合适的成像模式存在不确定性。

{"title":"Utilization of CT for Extremity Cellulitis: A Retrospective Single-Center Analysis","authors":"Cynthia E. Burke BS , Owen R. Maley MD , Benjamin Mancini BS , SaraPettey Sandifer BS , Sahil Sardesai BS , Tonya S. King PhD , Donald J. Flemming MD","doi":"10.1016/j.jacr.2024.10.011","DOIUrl":"10.1016/j.jacr.2024.10.011","url":null,"abstract":"<div><h3>Purpose</h3><div>Routine imaging of soft tissue infection is not recommended and represents a potential area of CT overuse. The utility of CT in patients with superficial soft tissue infection of the extremities is unknown. The purpose of this study is to evaluate the utilization and clinical impact of CT ordered in the setting of extremity cellulitis.</div></div><div><h3>Methods</h3><div>We retrospectively analyzed patients with extremity cellulitis examined with CT between 2012 and 2021 at a single center. We collected patient history, diagnostic imaging characteristics, and subsequent surgery decision. We hypothesized that yield of CT for deep infection was significantly lower than 10% and that yield was decreasing over time. These hypotheses were evaluated with Rao-Scott χ<sup>2</sup> tests and repeated measures logistic regression.</div></div><div><h3>Results</h3><div>There were 496 eligible encounters among 463 patients. Yield of positive CT among lower extremity patients was 5.5% (95% confidence interval 3.33-7.75), significantly less than our hypothesis of 10% (<em>P</em> = .003). In 71.8% of encounters, patients underwent diagnostic imaging studies in addition to CT. Utilization rose from 0.08% per hospital visit in 2012 to 2013 to 0.14% in 2020 to 2021, with differences in yield between time periods not reaching statistical significance (<em>P</em> = .059). Among 496 encounters, 62 received surgery (12.1%), with 21 of these cases preceded by a positive CT for deep infection.</div></div><div><h3>Conclusions</h3><div>Our 10-year single-center analysis of CT use for extremity cellulitis demonstrated a low yield of positive CT findings for deep infection and limited impact of CT on surgical management. A high incidence of patients undergoing multiple radiologic examinations suggests uncertainty in selecting appropriate imaging modalities in this clinical scenario.</div></div><div><h3>Summary</h3><div>This single-center retrospective analysis found that CT examination of patients with clinically diagnosed cellulitis of the extremities has significantly low yield for deep infection in the lower extremities.</div></div>","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 1","pages":"Pages 76-83"},"PeriodicalIF":4.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142570534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Shaping the Future of Radiology Through Medical Student Education 通过医学生教育塑造放射学的未来。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.12.001

Anastacia Wahl MS , Francis Deng MD

引用次数: 0

Large Language Model Use in Radiology Residency Applications: Unwelcomed but Inevitable 在放射科住院医师申请中使用大型语言模型：不受欢迎但不可避免。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.08.027

Emile B. Gordon MD , Charles M. Maxfield MD , Robert French MD, MBA , Laura J. Fish MD , Jacob Romm MD , Emily Barre MPH, BSE , Erica Kinne MD , Ryan Peterson MD , Lars J. Grimm MD, MHS

Objective

This study explores radiology program directors’ perspectives on the impact of large language model (LLM) use among residency applicants to craft personal statements.

Methods

Eight program directors from the Radiology Residency Education Research Alliance participated in a mixed-methods study, which included a survey regarding impressions of artificial intelligence (AI)-generated personal statements and focus group discussions (July 2023). Each director reviewed four personal statement variations for five applicants, anonymized to author type: the original and three Chat Generative Pre-trained Transformer-4.0 (GPT) versions generated with varying prompts, aggregated for analysis. A 5-point Likert scale surveyed the writing quality, including voice, clarity, engagement, organization, and perceived origin of each statement. An experienced qualitative researcher facilitated focus group discussions. Data analysis was performed using a rapid analytic approach with a coding template capturing key areas related to residency applications.

Results

GPT-generated statement ratings were more often average or worse in quality (56%, 268 of 475) than ratings of human-authored statements (29%, 45 of 160). Although reviewers were not confident in their ability to distinguish the origin of personal statements, they did so reliably and consistently, identifying the human-authored personal statements at 95% (38 of 40) as probably or definitely original. Focus group discussions highlighted the inevitable use of AI in crafting personal statements and concerns about its impact on the authenticity and the value of the personal statement in residency selections. Program directors were divided on the appropriate use and regulation of AI.

Discussion

Radiology residency program directors rated LLM-generated personal statements as lower in quality and expressed concern about the loss of the applicant’s voice but acknowledged the inevitability of increased AI use in the generation of application statements.

目的本研究探讨放射学项目主任对住院医师申请者使用大语言模型（LLM）撰写个人陈述的影响的看法：来自放射学住院医师教育研究联盟（RRERA）的八位项目主任参与了一项混合方法研究，其中包括一项关于人工智能生成的个人陈述印象的调查和焦点小组讨论（2023 年 7 月）。每位主任审查了五位申请人的四份个人陈述变体，并对作者类型进行了盲审：原始版本和根据不同提示生成的三个 ChatGPT-4.0 版本，汇总后进行分析。采用 5 分李克特量表对写作质量进行调查，包括语音、清晰度、参与度、条理性以及每份陈述的感知来源。一位经验丰富的定性研究人员主持了焦点小组讨论。数据分析采用快速分析方法进行，编码模板捕捉了与住院实习申请相关的关键领域：结果：GPT生成的声明（GPT）的评分质量一般或更差（56%，268/475），高于人类撰写的声明（Hu）的评分（29% [45/160]）。尽管审稿人对自己辨别个人陈述来源的能力并不自信，但他们的辨别能力是可靠和一致的，95%（38/40）的人撰个人陈述可能或肯定是原创的。焦点小组讨论强调了在撰写个人陈述时不可避免地使用人工智能的问题，以及人工智能对个人陈述的真实性和在住院医生遴选中的价值所产生的影响。项目主任们对人工智能的适当使用和监管存在分歧：放射科住院医师培训项目主任认为由 LLM 生成的个人陈述质量较低，并对失去申请人的声音表示担忧，但也承认在生成申请陈述时越来越多地使用人工智能是不可避免的。

{"title":"Large Language Model Use in Radiology Residency Applications: Unwelcomed but Inevitable","authors":"Emile B. Gordon MD , Charles M. Maxfield MD , Robert French MD, MBA , Laura J. Fish MD , Jacob Romm MD , Emily Barre MPH, BSE , Erica Kinne MD , Ryan Peterson MD , Lars J. Grimm MD, MHS","doi":"10.1016/j.jacr.2024.08.027","DOIUrl":"10.1016/j.jacr.2024.08.027","url":null,"abstract":"<div><h3>Objective</h3><div>This study explores radiology program directors’ perspectives on the impact of large language model (LLM) use among residency applicants to craft personal statements.</div></div><div><h3>Methods</h3><div>Eight program directors from the Radiology Residency Education Research Alliance participated in a mixed-methods study, which included a survey regarding impressions of artificial intelligence (AI)-generated personal statements and focus group discussions (July 2023). Each director reviewed four personal statement variations for five applicants, anonymized to author type: the original and three Chat Generative Pre-trained Transformer-4.0 (GPT) versions generated with varying prompts, aggregated for analysis. A 5-point Likert scale surveyed the writing quality, including voice, clarity, engagement, organization, and perceived origin of each statement. An experienced qualitative researcher facilitated focus group discussions. Data analysis was performed using a rapid analytic approach with a coding template capturing key areas related to residency applications.</div></div><div><h3>Results</h3><div>GPT-generated statement ratings were more often average or worse in quality (56%, 268 of 475) than ratings of human-authored statements (29%, 45 of 160). Although reviewers were not confident in their ability to distinguish the origin of personal statements, they did so reliably and consistently, identifying the human-authored personal statements at 95% (38 of 40) as probably or definitely original. Focus group discussions highlighted the inevitable use of AI in crafting personal statements and concerns about its impact on the authenticity and the value of the personal statement in residency selections. Program directors were divided on the appropriate use and regulation of AI.</div></div><div><h3>Discussion</h3><div>Radiology residency program directors rated LLM-generated personal statements as lower in quality and expressed concern about the loss of the applicant’s voice but acknowledged the inevitability of increased AI use in the generation of application statements.</div></div>","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 1","pages":"Pages 33-40"},"PeriodicalIF":4.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142302711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Seven Challenges in Radiology Practice: From Declining Reimbursement to Inadequate Labor Force: Summary of the 2023 ACR Intersociety Meeting 放射学实践中的七大挑战：从报销减少到劳动力不足：ACR 2023 年学会间会议摘要。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.08.030

Bettina Siewert MD , Michael A. Bruno MD , J. Daniel Bourland PhD , Priscilla J. Slanetz MD, MPH , Paul Guillerman MD , Erin S. Schwartz MD , Harriet J. Paltiel MD , Ronald Hublall MD , Olga R. Brook MD , Mary H. Scanlon MD , Frank J. Lexa MD, MBA

This summary of the proceedings of the 2023 ACR Intersociety Meeting discusses the seven most important challenges facing radiology today: declining reimbursement, corporatization and consolidation, inadequate labor force, imaging appropriateness, burnout, turf wars with nonphysicians, and workflow efficiency. Participants in the Intersociety Summer Conference-2023 focused their effort on identifying potential solutions given how critical these topics are to the sustainability of the profession.

本白皮书讨论了放射科目前面临的七项最重要的挑战：报销额度下降、公司化和合并、劳动力不足、成像适宜性、职业倦怠、与非医师的地盘争夺战以及工作流程效率。鉴于这些问题对放射学行业的可持续发展至关重要，Intersociety 2023 年夏季会议的与会者们集中精力找出了潜在的解决方案。

引用次数: 0

Editors' Note 编辑注

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.10.012

引用次数: 0

Enhancing Insights for Implementing a Virtual Research Collaboration Program 增强实施虚拟研究合作计划的洞察力

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2023.09.018

Amir Hassankhani MD, Melika Amoukhteh MD, Ali Gholamrezanezhad MD

引用次数: 0

Patient-Friendly Summary of the ACR Appropriateness Criteria®: Chronic Hand and Wrist Pain: 2024 Update ACR适宜性标准®患者友好摘要：慢性手部和腕部疼痛：2024 年更新版》。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.09.010

Jeshwanth Mohan , Shari T. Jawetz MD

引用次数: 0

Enhanced PROcedural Information READability for Patient-Centered Care in Interventional Radiology With Large Language Models (PRO-READ IR) PRO-READ IR：利用大语言模型增强介入放射学中以患者为中心的程序信息可读性。

IF 4 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Journal of the American College of Radiology

Pub Date : 2025-01-01 DOI: 10.1016/j.jacr.2024.08.010

Tarig Elhakim MD , Allison R. Brea , Wilton Fidelis , Sriram S. Paravastu MD , Mira Malavia BA , Mustafa Omer MBBS , Ana Mort , Shakthi Kumaran Ramasamy MBBS , Satvik Tripathi , Michael Dezube MEng , Sara Smolinski-Zhao MD , Dania Daye MD, PhD

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.

目的：评估 GPT-4 在多大程度上可以通过生成有关最常见的介入放射学（IR）手术的易懂信息来教育患者：我们回顾了 10 种介入放射学手术，并为 GPT-4 准备了提示，以通俗易懂的语言为患者提供有关每种手术的教育指导。然后由 4 名临床医生和 9 名非临床评估人员对这些说明进行评估，通过调查确定其临床适宜性、可理解性和清晰度。使用经过验证的指标对可读性进行了分级评估，以评估广大患者的易读性。此外，还对放射学信息网站（radioologyinfo.org）上的患者指南中的相同程序进行了评估，并通过配对 t 检验将其与 GPT 生成的指南进行了比较：结果：由 4 名临床医师进行的评估显示，9 份 GPT 生成的说明完全正确，而动脉栓塞说明则有些不妥。9 名非临床评估人员的评估结果显示，57% 的人认为腹腔穿刺术、透析导管置入术、血栓切除术、超声引导活组织检查和肾造瘘管术的指导非常好，43% 的人认为很好。动脉栓塞术和胆道引流术的指导被 28.6% 的人评为 "优"，71.4% 的人评为 "良"。相比之下，胸腔穿刺术、穿刺孔置入术和 CT 引导下活检术说明的优秀率为 43%，良好率为 43%，一般率为 14%。对所有手术指南的可读性评估显示，GPT-4指南的Flesch-Kincaid平均等级比radioologyinfo.org高（7.8±0.87 vs 9.6±0.83,p=0.007），表明7-8年级的可读性比9-10年级的优秀。此外，Gunning-Fog平均指数（10.4±1.2 vs. 12.7±0.93,p=0.006）更低，Flesch阅读轻松度平均分（69.4±4.8 vs. 51.3±3.9,p=0.0001）更高，表明可读性更好：结论：由GPT-4生成的IR程序说明通过生成易于理解的解释，有助于提高IR的健康素养和以患者为中心的护理。

{"title":"Enhanced PROcedural Information READability for Patient-Centered Care in Interventional Radiology With Large Language Models (PRO-READ IR)","authors":"Tarig Elhakim MD , Allison R. Brea , Wilton Fidelis , Sriram S. Paravastu MD , Mira Malavia BA , Mustafa Omer MBBS , Ana Mort , Shakthi Kumaran Ramasamy MBBS , Satvik Tripathi , Michael Dezube MEng , Sara Smolinski-Zhao MD , Dania Daye MD, PhD","doi":"10.1016/j.jacr.2024.08.010","DOIUrl":"10.1016/j.jacr.2024.08.010","url":null,"abstract":"<div><h3>Purpose</h3><div>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.</div></div><div><h3>Materials and methods</h3><div>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 <span><span>radiologyinfo.org</span><svg><path></path></svg></span> and compared with GPT-generated instructions utilizing a paired <em>t</em> test.</div></div><div><h3>Results</h3><div>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 <span><span>radiologyinfo.org</span><svg><path></path></svg></span> (7.8 ± 0.87 versus 9.6 ± 0.83; <em>P</em> = .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; <em>P</em> = .006), and higher Flesch Reading Ease mean score (69.4 ± 4.8 versus 51.3±3.9; <em>P</em> = .0001) indicating better readability.</div></div><div><h3>Conclusion</h3><div>IR procedural instructions generated by GPT-4 can aid in improving health literacy and patient-centered care in IR by generating easily understandable explanations.</div></div>","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 1","pages":"Pages 84-97"},"PeriodicalIF":4.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142115724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Journal of the American College of Radiology

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀