脑CT诊断门诊癌症患者颅内疾病:评估增强前平扫的诊断价值
本研究回顾了得克萨斯大学MD安德森癌症中心门诊癌症分期患者的脑CT报告,评估平扫CT相对于增强CT的附加诊断价值,并基于GPT-3模型筛选及成本效果分析。结果显示仅0.96%(95%CI 0.63-1.40)的报告有平扫独有的有意义发现(均为出血),增量成本效果比为1855至4122美元。作者认为对无症状癌症患者分期,单独增强脑CT已足够。
要点
- 门诊癌症患者脑CT中,平扫独有且具临床意义的发现仅占0.96%(95%CI 0.63-1.40),且均为出血。
- 平扫发现一例增强遗漏的有意义病灶的增量成本效果比为1855至4122美元。
- 对无症状癌症患者分期,单独增强脑CT已足够,平扫附加诊断价值有限。
核心结论
- 在门诊癌症患者脑CT筛查颅内疾病中,平扫CT相比单独增强CT提供的附加诊断价值有限;考虑到相关经济成本、工作量和患者辐射暴露,单独增强脑CT足以用于无症状癌症患者的分期。
研究设计与样本
- 回顾性研究,由一名神经放射学专科医师审阅737份门诊脑CT报告(2014年10月至2016年3月,同时行增强和平扫),另用微调后的GPT-3模型从1980份额外报告(2017年1月至2022年4月)中筛选高可能独有有意义平扫发现的报告,由2名神经放射学医师手工复核,必要时由第三名裁决;基于Medicare报销计算增量成本效果比。
诊断标准与关键数值
- 平扫CT独有且有临床意义的发现占全部报告的0.96%(95%CI 0.63-1.40);初始数据集737份报告中7份有平扫独有有意义发现,均为出血;第二数据集1980份报告中GPT-3筛选出145份供复核,其中19份有平扫独有有意义发现。
临床应用与阅片要点
- 作者认为,对无症状癌症患者进行分期时,单独增强脑CT已足够;考虑平扫相关的经济成本、工作量和患者辐射暴露,平扫CT附加诊断价值有限。
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
BACKGROUND AND PURPOSE: Brain imaging with MRI or CT is standard in screening for intracranial disease among ambulatory patients with cancer. Though MRI offers greater sensitivity, CT is frequently employed because of its accessibility, affordability, and faster acquisition time. However, the necessity of routinely performing a noncontrast CT with the contrast-enhanced study is unknown. This study evaluates the clinical and economic utility of the noncontrast portion of the brain CT examination.
MATERIALS AND METHODS: A board-certified neuroradiologist reviewed 737 brain CT reports from outpatients at The University of Texas MD Anderson Cancer Center who underwent contrast and noncontrast CT for cancer staging (October 2014 to March 2016) to assess if clinically meaningful findings were identified only on noncontrast CT. A Generative Pretrained Transformers-3 (GPT-3) model was then fine-tuned to extract reports with a high likelihood of unique and meaningful noncontrast findings from 1980 additional brain CT reports (January 2017 to April 2022). These reports were manually reviewed by 2 neuroradiologists, with adjudication by a third reviewer if needed. The incremental cost-effectiveness ratio of noncontrast CT inclusion was then calculated based on Medicare reimbursement and the 95% CI of the proportion of all reports in which noncontrast CT was necessary for identifying meaningful findings.
RESULTS: Seven of 737 reports in the initial data set revealed meaningful findings unique to the noncontrast CT, all of which were hemorrhage. The GPT-3 model identified 145 additional reports with a high unique noncontrast CT finding likelihood for manual review from the second data set of 1980 reports. Nineteen of these reports were found to have unique and meaningful noncontrast CT findings. In total, 0.96% (95% CI: 0.63-1.40) of reports had meaningful findings identified only on noncontrast CT. The incremental cost-effectiveness ratio for the identification of a single meaningful finding on noncontrast CT missed on the contrast-enhanced study was $1855 to $4122.
CONCLUSIONS: In brain CT for ambulatory screening for intracranial disease in patients with cancer, noncontrast CT offers limited additional diagnostic value compared with contrast-enhanced CT alone. Considering the associated financial cost, workload, and patient radiation exposure associated with performing a noncontrast CT, contrast-enhanced brain CT alone is sufficient for cancer staging in patients with asymptomatic cancer.
引用
- Wang E, Darbandi A, Tu L, et al. Brain CT for Diagnosis of Intracranial Disease in Ambulatory Patients with Cancer: Assessment of the Diagnostic Value of Scanning without Contrast prior to with Contrast. AJNR Am J Neuroradiol. 2026. PMID: 40925682. doi:10.3174/ajnr.A8995
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。