Volatile organic compounds (VOCs) are an increasingly meaningful method for the early detection of various types of cancers, including lung cancer, through non-invasive methods. Traditional cancer detection techniques such as biopsies, imaging, and blood tests, though effective, often involve invasive procedures or are costly, time consuming, and painful. Recent advancements in technology have led to the exploration of VOC detection as a promising non-invasive and comfortable alternative. VOCs are organic chemicals that have a high vapor pressure at room temperature, making them readily detectable in breath, urine, and skin. The present study leverages artificial intelligence (AI) and machine learning algorithms to enhance classification accuracy and efficiency in detecting lung cancer through VOC analysis collected from exhaled breath air. Unlike other studies that primarily focus on identifying specific compounds, this study takes an agnostic approach, maximizing detection efficiency over the identification of specific compounds focusing on the overall compositional profiles and their differences across groups of patients. The results reported hereby uphold the potential of AI-driven techniques in revolutionizing early cancer detection methodologies towards their implementation in a clinical setting.
挥发性有机化合物（VOCs）作为一种通过非侵入性方法早期检测肺癌等多种癌症的手段，其临床意义日益凸显。传统的癌症检测技术如组织活检、影像学检查和血液检测虽然有效，但通常具有侵入性，且存在成本高、耗时长、伴随疼痛等局限。随着技术进步，VOCs检测因其无创、便捷的特性成为备受关注的新型检测途径。VOCs是在常温下具有高蒸气压的有机化合物，可经由呼出气体、尿液和皮肤表面进行检测。本研究采用人工智能与机器学习算法，通过对呼出气体中VOCs的分析，提升了肺癌检测的分类准确率与效率。与既往研究主要聚焦于特定化合物鉴定不同，本研究采用未知化合物分析策略，不过度关注具体化合物识别，而是通过最大化检测效率，重点分析不同患者群体的整体成分谱差异。研究结果证实了人工智能技术在革新早期癌症检测方法、推动临床转化应用方面的巨大潜力。
肿瘤(癌症)患者之家