基于呼气组学的肺癌分诊工具开发与多中心验证:一项 5,214 例参与者的前瞻性研究
Development and Multi-center Validation of a Breathomics-Based Triage Tool for Lung Cancer: A Prospective Study of 5,214 Participants.
作者
作者单位
- Departments of Respiratory and Critical Care Medicine and Thoracic Surgery, Chest Hospital, Tianjin University, Tianjin 300222, China.
- .Laser Medicine Laboratory, Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin 300192, China. Electronic address: sunmx@bme.cams.cn.
- WIM Spirare Technology Co., Ltd., Tianjin 300192, China.
- Departments of Respiratory and Critical Care Medicine and Thoracic Surgery, Chest Hospital, Tianjin University, Tianjin 300222, China. Electronic address: sdqmd@tju.edu.cn.
摘要
中文
计算机断层扫描(CT)固有的假阳性率亟需高效、无创的分诊工具,以将肺癌(LC)与良性病变区分开来,从而优化早期检测流程并减少不必要的有创操作。那么,基于机器学习(ML)、分子层面解析的呼气组学预测模型能否在真实世界症状性患者队列中,对影像学检出的肺部异常进行有效分诊?本大规模、前瞻性、多中心诊断准确性研究在两个院区共纳入 5,214 例伴影像学肺部异常的症状性患者。参与者被分为发现队列(n = 4,669)和地理独立外部验证队列(n = 545)。采用高通量质子转移反应飞行时间质谱(PTR-TOF-MS)分析呼出气中的挥发性有机化合物(VOCs)。整合特定 VOCs 特征与临床因素的 ML 模型经开发后锁定,并在外部队列中进行盲法验证。整合模型在独立内部测试集中受试者工作特征曲线下面积(AUC)为 0.891(95% 置信区间(CI):0.864–0.915)。在独立外部验证中,模型保持了稳健的诊断效能(AUC 0.850,95% CI:0.805–0.890)。在该验证队列中,采用预先设定的"排除"阈值,模型灵敏度达 93.1%(95% CI:90.5%–95.4%),总体特异度为 55.9%,阴性预测值(NPV)为 71.0%。值得注意的是,在目标应用人群——呼吸科亚组(n=155)中,灵敏度为 91.4%,特异度和 NPV 分别达 55.8% 和 89.0%。亚组分析证实该模型在不同临床场景中效能一致,尤其在早期病变检测中保持了稳健的准确性(AUC 0.849)。本研究是迄今最大规模的呼气检测质谱方法前瞻性验证。该验证后的预测模型有望成为一种稳健、无创的分诊工具。其整合至诊断路径中,尤其在呼吸科门诊场景中,显示出提升诊疗效率和减少不必要活检的潜力。
English
The inherent false-positive rate of computed tomography (CT) necessitates efficient, non-invasive triage tools to distinguish lung cancer (LC) from benign mimics, thereby streamlining early detection and mitigating unnecessary invasive procedures. Can a machine learning (ML)-derived-, molecularly-resolved breathomics prediction model effectively triage patients with radiologically detected pulmonary abnormalities in a real-world symptomatic cohort? In this large-scale, prospective, multicenter diagnostic accuracy study, we enrolled 5,214 symptomatic patients with radiological lung abnormalities at two campuses. Participants were allocated into a discovery cohort (n = 4,669) and a geographically independent external validation cohort (n = 545). Exhaled volatile organic compounds (VOCs) were analyzed using high-throughput proton-transfer-reaction time-of-flight mass spectrometry (PTR-TOF-MS). An ML model integrating a specific VOCs signature with clinical factors was developed, locked, and validated blind in the external cohort. The integrated model achieved an area under the receiver operating characteristic curve (AUC) of 0.891 (95% confidence interval (CI): 0.864-0.915) in the independent internal testing set. In the independent external validation, the model maintained robust performance (AUC 0.850, 95% CI: 0.805-0.890). In this validation cohort, applying the pre-specified 'rule-out' threshold, the model achieved a sensitivity of 93.1% (95% CI: 90.5%-95.4%), with an overall specificity of 55.9% and negative predictive value (NPV) of 71.0%. Importantly, in the intended-use pulmonary medicine subgroup (n=155), the sensitivity was 91.4%, with specificity and NPV reaching 55.8% and 89.0%, respectively. Subgroup analyses confirmed consistent efficacy across diverse clinical scenarios, notably maintaining robust accuracy in detecting early-stage disease (AUC 0.849). This study represents the largest prospective validation of a mass-spectrometry-based breath test to date. The validated prediction model holds potential to serve as a robust, non-invasive triage tool. Its integration into the diagnostic pathway shows promise for enhancing efficiency and reducing unnecessary biopsies, particularly in respiratory outpatient settings.
分类与指标
- 研究类型
- AI/ML
- 病种
- 肺癌
- JCR 分区
- Q1
- 影响因子
- 9.8
- 新锐分区
- 1区