Lin Shuang, Yan Runlan, Zhu Junqi, Li Bei, Zhong Yinyan, Han Shuang, Wang Huiting, Wu Jianmin, Chen Zhao, Jiang Yuyue, Pan Aiwu, Huang Xuqing, Chen Xiaoming, Zhu Pingya, Cao Sheng, Liang Wenhua, Ye Peng, Gao Yue
Department of Thoracic Surgery, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, 310006, China.
Department of Geriatrics, Zhejiang Key Laboratory of Traditional Chinese Medicine for the Prevention and Treatment of Senile Chronic Diseases, Affiliated Hangzhou First People's Hospital, School of Medicine, Westlake University, Hangzhou, 310006, China.
Adv Sci (Weinh). 2025 Jun;12(22):e2416719. doi: 10.1002/advs.202416719. Epub 2025 May 14.
Most lung cancer (LC) patients are diagnosed at advanced stages due to the lack of effective screening tools. This multicenter study analyzes 1043 saliva samples (334 LC cases and 709 non-LC cases) using a novel high-throughput platform for metabolic fingerprint acquisition. Machine learning identifies 35 metabolic features distinguishing LC from non-LC subjects, enabling the development of a classification model named SalivaMLD. In the validation set and test set, SalivaMLD demonstrates strong diagnostic performance, achieving an area under the curve of 0.849-0.850, a sensitivity of 81.69-83.33%, and a specificity of 74.23-74.39%, outperforming conventional tumor biomarkers. Notably, SalivaMLD exhibits superior accuracy in distinguishing early stage LC patients. Hence, this rapid and noninvasive screening method may be widely applied in clinical practice for LC detection.
由于缺乏有效的筛查工具，大多数肺癌（LC）患者在晚期才被诊断出来。这项多中心研究使用一种新型的高通量平台来获取代谢指纹，对1043份唾液样本（334例LC病例和709例非LC病例）进行了分析。机器学习识别出35种代谢特征，可将LC患者与非LC患者区分开来，从而开发出一种名为SalivaMLD的分类模型。在验证集和测试集中，SalivaMLD表现出强大的诊断性能，曲线下面积达到0.849 - 0.850，灵敏度为81.69% - 83.33%，特异性为74.23% - 74.39%，优于传统肿瘤生物标志物。值得注意的是，SalivaMLD在区分早期LC患者方面表现出卓越的准确性。因此，这种快速且无创的筛查方法可能会在临床实践中广泛应用于LC检测。
