Colorectal Cancer Detection in Sweat Samples Using Data Processing Techniques and the Cyranose 320 Electronic Nose
Juan Alejandro Carrillo Jaimes et al.
Abstract
Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide, underscoring the urgent need for non-invasive and cost-effective screening strategies. This study evaluates the feasibility of using the Cyranose 320 electronic nose to discriminate between CRC patients and healthy controls through volatile organic compound (VOC) analysis of sweat samples. A total of 65 sweat samples (31 CRC, 34 controls) were analyzed. The data processing pipeline included Relative Difference (RD) feature extraction, Quantile Transformer scaling, Orthogonal Signal Correction (OSC), and Principal Component Analysis (PCA), followed by supervised machine learning classification. PCA revealed strong class separability, with the first three principal components explaining 95.72% of the total variance (PC1: 91.28%). Supervised classification using nested cross-validation demonstrated robust performance across seven algorithms. Random Forest achieved the best results, with 95.4% accuracy, 93.5% sensitivity, 97.1% specificity, and an AUC of 0.967. Decision Tree showed comparable performance, while all evaluated models exceeded an AUC of 0.90. Confusion matrix analysis confirmed high true positive rates and minimal false positives, particularly for tree-based ensemble methods. These findings demonstrate that sweat-derived VOC profiling using the Cyranose 320, combined with advanced data preprocessing and multivariate analysis, provides strong discriminative capability for CRC detection. The results support the potential of sweat-based electronic nose systems as a non-invasive, scalable, and patient-friendly screening approach, warranting validation in larger independent cohorts.
摘要
结直肠癌(CRC)仍然是全球癌症相关死亡的主要原因,这凸显了对非侵入性和具有成本效益的筛查策略的迫切需求。本研究评估了使用Cyranose 320电子鼻通过分析汗液样本中的挥发性有机化合物(VOC)来区分CRC患者和健康对照者的可行性。共分析了65份汗液样本(31份CRC,34份对照)。数据处理流程包括相对差异(RD)特征提取、分位数变换器缩放、正交信号校正(OSC)和主成分分析(PCA),随后进行监督机器学习分类。PCA显示出很强的类别可分性,前三个主成分解释了总方差的95.72%(PC1:91.28%)。使用嵌套交叉验证的监督分类在七种算法中表现出稳健的性能。随机森林取得了最佳结果,准确率为95.4%,敏感性为93.5%,特异性为97.1%,AUC为0.967。决策树表现出相当的性能,而所有评估模型的AUC均超过0.90。混淆矩阵分析证实了高真阳性率和极少的假阳性,尤其是对于基于树的集成方法。这些发现表明,使用Cyranose 320对汗液来源的VOC进行分析,结合先进的数据预处理和多变量分析,为CRC检测提供了强大的判别能力。结果支持基于汗液的电子鼻系统作为一种非侵入性、可扩展且对患者友好的筛查方法的潜力,值得在更大的独立队列中进行验证。
Keywords: Electronic nose, Cyranose 320, Colorectal Cancer, Sweat analysis, Volatile organic compounds, Machine Learning
关键词: 电子鼻,Cyranose 320,结直肠癌,汗液分析,挥发性有机化合物,机器学习
II.MATERIALS AND METHODS 材料与方法
A.Study Design研究设计
This quantitative study evaluated the diagnostic potential of the Cyranose 320 electronic nose for colorectal cancer detection. Biological samples were collected from colorectal cancer patients and healthy controls at Hospital Erasmo Meoz in Cúcuta, Norte de Santander, Colombia. After collection, samples were transported to Mexico for analysis with the Cyranose 320 device. The study followed a controlled observational design, ensuring consistency in sample handling and analytical procedures.
这项定量研究评估了Cyranose 320电子鼻用于结直肠癌检测的诊断潜力。生物样本采集自哥伦比亚北桑坦德省库库塔的Erasmo Meoz医院的结直肠癌患者和健康对照者。采集后,样本被运往墨西哥,使用Cyranose 320设备进行分析。该研究遵循对照观察设计,确保样本处理和分析程序的一致性。
The study comprised 65 sweat samples (34 controlsand 31 cancer samples). All samples were properly labeled and stored in accordance with standard biosafety protocols prior toanalysis. Sample anonymization was performed to protect patient confidentiality, and all procedures were conducted in accordance with ethical and institutional guidelines.
该研究包括65份汗液样本(34份对照和31份癌症样本)。所有样本在分析前均按照标准生物安全方案进行了正确标记和储存。进行了样本匿名化以保护患者机密性,所有程序均按照伦理和机构指南进行。
B.Instrumentation:
Cyranose 320 Electronic NoseThe Cyranose 320 (Sensigent, Baldwin Park, CA, USA) is a portable electronic nose featuring a proprietary 32-channel polymer composite sensor array for volatile organic compound (VOC) detection. The device operates on the principle of chemiresistive transduction, in which each sensor comprisesa unique conductive polymer mixed with carbon black particles. When VOCs interact with the sensor array, the polymeric films absorb varying amounts of vapor and swell, thereby altering electrical resistance, which is captured as digital patterns that representunique “olfactory fingerprints” for different substances.
B. 仪器:Cyranose 320电子鼻
Cyranose 320(Sensigent, Baldwin Park, CA, USA)是一种便携式电子鼻,具有专有的32通道聚合物复合传感器阵列,用于挥发性有机化合物(VOC)检测。该设备基于化学电阻转导原理工作,其中每个传感器由独特的导电聚合物与炭黑颗粒混合组成。当VOC与传感器阵列相互作用时,聚合物薄膜吸收不同量的蒸汽并膨胀,从而改变电阻,这些电阻被捕获为代表不同物质独特“嗅觉指纹”的数字模式。
As illustrated in Figure 1, the compact, handheld design of the Cyranose 320 enables its use in clinical and laboratory settings, facilitating rapid,on-site analysis.
如图1所示,Cyranose 320的紧凑手持设计使其能够在临床和实验室环境中使用,便于快速现场分析。
The sensor array responds collectively to complex VOC mixtures, allowing pattern-based discrimination rather than single-compound identification. This makes the device particularly suitable for biomedical applications, in which disease-related metabolic changes are reflected as variations in global VOC profiles rather than by isolated biomarkers
传感器阵列对复杂的VOC混合物做出集体响应,允许基于模式的区分而非单化合物识别。这使得该设备特别适用于生物医学应用,在这些应用中,疾病相关的代谢变化反映为整体VOC谱的变化,而不是孤立的生物标志物。

