基于近期(2024年)科学进展对可预见未来诊断放射科医生工作量的更新增长预期
该研究随机抽取2024年发表的416篇诊断影像学论文,由学术三级中心和非学术综合教学医院各一名放射科医生审阅,评估其对诊断放射科医生工作量的预期影响。在两种执业环境中,约56.5%的论文具有直接影响患者诊疗的潜力,其中约48.9%预计增加工作量;以人工智能为主要研究领域的论文显著更可能增加工作量(学术中心OR 14.3,95%CI 4.2-48.2;非学术中心OR 13.7,95%CI 4.1-46.5)。结论认为诊断放射科医生的工作量预计将增加,人工智能应用似乎总体上具有加重工作量的效应。
要点
- 2024年影像学文献中约56.5%可能直接影响患者诊疗,其中约48.9%预计增加放射科医生工作量。
- 以人工智能为主要研究领域的论文显著更可能增加工作量(OR 14.3,95%CI 4.2-48.2;OR 13.7,95%CI 4.1-46.5)。
- 学术三级中心与非学术综合教学医院两种执业环境的评估结果高度一致,均提示工作量增长。
核心结论
- 基于2024年科学文献,诊断放射科医生的工作量预计将增加,人工智能应用似乎总体上具有加重工作量的效应。
研究设计与样本
- 随机抽取2024年发表的416篇诊断影像学论文,由学术三级中心一名放射科医生和非学术综合教学医院另一名放射科医生审阅。
诊断标准与关键数值
- 学术三级中心环境:56.5%(235/416)论文可能直接影响患者诊疗,其中48.9%(115/235)增加工作量,48.1%(113/235)不改变工作量,0.4%(1/235)减少工作量,2.6%(6/235)影响不明确。
- 非学术综合教学医院环境:56.5%(231/416)论文可能直接影响患者诊疗,其中48.9%(113/231)增加工作量,48.1%(111/231)不改变工作量,0.4%(1/231)减少工作量,2.6%(6/231)影响不明确。
- 以人工智能为主要研究领域的论文较其他主要研究领域显著更可能增加工作量:学术三级中心OR 14.3(95%CI 4.2-48.2),P<0.001。
- 以人工智能为主要研究领域的论文较其他主要研究领域显著更可能增加工作量:非学术综合教学医院OR 13.7(95%CI 4.1-46.5),P<0.001。
临床应用与阅片要点
- 原文未据此给出推荐。
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 assess the expected impact of the 2024 medical imaging literature on the workload of diagnostic radiologists.
METHODS: A random sample of 416 articles on diagnostic imaging that was published in 2024 was reviewed by one radiologist working in an academic tertiary care center and another radiologist working in a non-academic general teaching hospital.
RESULTS: In the academic tertiary care hospital setting, 56.5 % (235/416) of articles had the potential to directly impact patient care, of which 48.9 % (115/235) would increase workload, 48.1 % (113/235) would not change workload, 0.4 % (1/235) would decrease workload, and 2.6 % (6/235) had an unclear effect on workload. Studies with Artificial Intelligence (AI) as primary research area were significantly (P < 0.001) more likely to increase workload compared to studies with another primary research area, with an Odds Ratio (OR) of 14.3 (95 % confidence interval [CI]: 4.2 to 48.2). In the non-academic general teaching hospital setting, 56.5 % (231/416) of articles had the potential to directly impact patient care, of which 48.9 % (113/231) would increase workload, 48.1 % (111/231) would not change workload, 0.4 % (1/231) would decrease workload, and 2.6 % (6/231) had an unclear effect on workload. Studies with AI as primary research area were significantly (P < 0.001) more likely to increase workload compared to studies with another primary research area, with an OR of 13.7 (95 % CI: 4.1 to 46.5).
CONCLUSION: The workload of diagnostic radiologists is expected to increase based on recent (2024) scientific literature, and AI applications generally seem to have an aggravating effect on workload.
引用
- Kwee TC, Kwee RM. Workload of diagnostic radiologists in the foreseeable future based on recent (2024) scientific advances: Updated growth expectations. Eur J Radiol. 2025. PMID: 40220736. doi:10.1016/j.ejrad.2025.112103
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。