基于报告的胰腺囊性病变自动追踪：对指南生长分类的影响
该回顾性研究开发并评估了一种结合大语言模型与规则算法的混合工具，用于在系列影像报告中追踪胰腺囊性病变，并应用于单中心队列分析囊肿生长。算法与放射科医生标注的一致性达96%（κ=0.81）。应用不同指南和比较方法时，囊肿生长分类比例存在差异，基线囊肿大小是满足京都生长率标准的最强预测因子。
要点
- 混合LLM与规则算法可可靠自动追踪系列报告中的胰腺囊性病变。
- ACR绝对生长标准与京都生长率标准在不同比较方法下分类比例不同。
- 基线囊肿大小是满足京都生长率标准的最强预测因子。
核心结论
- 混合LLM与规则算法能够可靠地自动纵向追踪系列放射学报告中的胰腺囊性病变。
- 大规模应用时，囊肿生长分类因指南框架和间隔比较方法而异，基线囊肿大小是满足京都生长率阈值的最强预测因子。
研究设计与样本
- 回顾性研究，纳入2005年至2024年间由腹部放射科医生解读的所有腹部影像报告。
- 使用经验证的大语言模型识别描述胰腺囊性病变的报告，混合算法结合LLM提取的囊肿特征与规则逻辑匹配主导囊肿。
- 两位盲法放射科医生独立标注部分报告中的囊肿匹配，第三位放射科医生仲裁分歧。
- 总体队列包括8,176例患者（61.8%女性；平均年龄67.6±11.7岁），8,389个囊肿，28,489份报告，平均随访40.6±28.5个月。
- 采用ACR标准评估绝对大小生长，采用京都标准评估囊肿生长率作为担忧特征，分析满足京都生长率标准的预测因子使用多变量Cox回归。
诊断标准与关键数值
- 算法与裁决参考标准的一致性为96%，Cohen's κ为0.81（95% CI: 0.66-0.91）。
- 年生长率为0.35 mm/年。
- ACR绝对生长标准与京都囊肿生长率标准使用首末次检查比较时，分类囊肿比例分别为16.3%与7.4%（p < 0.001）。
- 使用连续检查比较时，京都囊肿生长率标准与ACR绝对生长标准分类比例分别为21.4%与14%（p < 0.001）。
- 较大基线囊肿大小预测满足京都囊肿生长率标准（HR 1.9-4.0；最高HR 4.0，95% CI 3.08-5.21；p < 0.001）。
临床应用与阅片要点
- 该自动化追踪工具可用于系列报告中胰腺囊性病变的纵向监测，提高报告一致性。
- 报告时应明确所采用的指南框架（ACR或京都）及比较方法（首末次或连续），因其影响生长分类比例。
- 基线囊肿较大者需更密切关注生长率，因其更可能满足京都生长率标准。
局限性
- 单中心回顾性研究设计。
- 算法验证仅基于部分报告的子集标注。
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 develop and evaluate a hybrid large language model (LLM)- and rule-based algorithm for tracking pancreatic cystic lesions (PCLs) across serial radiology reports and apply it to a single-center cohort to characterize cyst growth using first-to-last and consecutive comparisons.
METHODS: This retrospective study included all abdominal imaging reports interpreted by abdominal radiologists between 2005 and 2024. A validated LLM identified reports describing PCLs. A hybrid algorithm combining LLM-extracted cyst features (size, location) with rule-based logic matched dominant cysts across serial reports. Two blinded radiologists independently annotated cyst matches in a subset of reports. Agreement between algorithm and radiologists was assessed using percent agreement and Cohen's κ. Discrepancies were adjudicated by a third radiologist for error analysis. Absolute size-based growth was assessed according to American College of Radiology (ACR) criteria, whereas cyst growth rate as a worrisome feature was assessed per Kyoto criterion, using both first-to-last and consecutive studies. Predictors of meeting the Kyoto cyst growth rate criterion were analyzed using multivariable Cox regression.
RESULTS: In 58 patients with 418 longitudinal reports, agreement with the adjudicated reference standard was 96%. Cohen's κ was 0.81 (95% CI: 0.66-0.91). The overall cohort included 8,176 patients (61.8% female; mean age 67.6 ± 11.7 years) with 8,389 cysts across 28,489 reports over 40.6 ± 28.5 months (annual growth rate = 0.35 mm/year). ACR absolute growth criteria classified a higher proportion of cysts than the Kyoto cyst growth rate criterion using first-to-last examinations (16.3% vs. 7.4%, p < 0.001), whereas Kyoto cyst growth rate criterion identified a higher proportion using consecutive examinations (21.4% vs. 14%, p < 0.001). Larger baseline cyst size predicted meeting the Kyoto cyst growth rate criterion (HR 1.9-4.0; highest HR 4.0, 95% CI 3.08-5.21; p < 0.001).
CONCLUSION: A hybrid LLM-rule-based algorithm enables reliable automated longitudinal tracking of PCLs across serial radiology reports. When applied at scale, cyst growth classification varied according to the guideline framework and interval comparison method used, and baseline cyst size was the strongest predictor of meeting Kyoto growth rate threshold.
引用
- Huang C, Liu B, Kang SK, et al. Automated report-based tracking of pancreatic cysts: implications for guideline-defined growth classification. Abdom Radiol (NY). 2026. PMID: 41998419. doi:10.1007/s00261-026-05497-y
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。