Kepesidis Kosmas V, Jacob Philip, Schweinberger Wolfgang, Huber Marinus, Feiler Nico, Fleischmann Frank, Trubetskov Michael, Voronina Liudmila, Aschauer Jacqueline, Eissa Tarek, Gigou Lea, Karandušovsky Patrik, Pupeza Ioachim, Weigel Alexander, Azzeer Abdallah, Stief Christian G, Chaloupka Michael, Reinmuth Niels, Behr Jürgen, Kolben Thomas, Harbeck Nadia, Reiser Maximilian, Krausz Ferenc, Žigman Mihaela
Ludwig-Maximilians-Universität München (LMU), Chair of Experimental Physics - Laser Physics, 85748 Garching, Germany.
Max Planck Institute of Quantum Optics (MPQ), Laboratory for Attosecond Physics, 85748 Garching, Germany.
ACS Cent Sci. 2025 Apr 9;11(4):560-573. doi: 10.1021/acscentsci.4c02164. eCollection 2025 Apr 23.
Human biofluids serve as indicators of various physiological states, and recent advances in molecular profiling technologies hold great potential for enhancing clinical diagnostics. Leveraging recent developments in laser-based electric-field molecular fingerprinting, we assess its potential for diagnostics. In a proof-of-concept clinical study involving 2533 participants, we conducted randomized measurement campaigns to spectroscopically profile bulk venous blood plasma across lung, prostate, breast, and bladder cancer. Employing machine learning, we detected infrared signatures specific to therapy-naïve cancer states, distinguishing them from matched control individuals with a cross-validation ROC AUC of 0.88 for lung cancer and values ranging from 0.68 to 0.69 for the other three cancer entities. In an independent held-out test data set, designed to reflect different experimental conditions from those used during model training, we achieved a lung cancer detection ROC AUC of 0.81. Our study demonstrates that electric-field molecular fingerprinting is a robust technological framework broadly applicable to disease phenotyping under real-world conditions.
人体生物流体可作为各种生理状态的指标，分子谱分析技术的最新进展在增强临床诊断方面具有巨大潜力。利用基于激光的电场分子指纹识别技术的最新发展，我们评估了其在诊断方面的潜力。在一项涉及2533名参与者的概念验证临床研究中，我们开展了随机测量活动，以对肺癌、前列腺癌、乳腺癌和膀胱癌患者的静脉全血血浆进行光谱分析。通过机器学习，我们检测到了未经治疗的癌症状态所特有的红外特征，将其与匹配的对照个体区分开来，肺癌的交叉验证ROC AUC为0.88，其他三种癌症的该值在0.68至0.69之间。在一个独立的留出测试数据集中，该数据集旨在反映与模型训练期间不同的实验条件，我们实现了0.81的肺癌检测ROC AUC。我们的研究表明，电场分子指纹识别是一个强大的技术框架，广泛适用于现实世界条件下的疾病表型分析。
