Department of Forensic Pharmacology and Toxicology, Zurich Institute of Forensic Medicine, University of Zurich, Zurich, Switzerland.
Department of Forensic Imaging/Virtopsy, Zurich Institute of Forensic Medicine, University of Zurich, Zurich, Switzerland.
Clin Chem Lab Med. 2021 Mar 22;59(8):1392-1399. doi: 10.1515/cclm-2021-0010. Print 2021 Jul 27.
Urine sample manipulation including substitution, dilution, and chemical adulteration is a continuing challenge for workplace drug testing, abstinence control, and doping control laboratories. The simultaneous detection of sample manipulation and prohibited drugs within one single analytical measurement would be highly advantageous. Machine learning algorithms are able to learn from existing datasets and predict outcomes of new data, which are unknown to the model.
Authentic human urine samples were treated with pyridinium chlorochromate, potassium nitrite, hydrogen peroxide, iodine, sodium hypochlorite, and water as control. In total, 702 samples, measured with liquid chromatography coupled to quadrupole time-of-flight mass spectrometry, were used. After retention time alignment within Progenesis QI, an artificial neural network was trained with 500 samples, each featuring 33,448 values. The feature importance was analyzed with the local interpretable model-agnostic explanations approach.
Following 10-fold cross-validation, the mean sensitivity, specificity, positive predictive value, and negative predictive value was 88.9, 92.0, 91.9, and 89.2%, respectively. A diverse test set (n=202) containing treated and untreated urine samples could be correctly classified with an accuracy of 95.4%. In addition, 14 important features and four potential biomarkers were extracted.
With interpretable retention time aligned liquid chromatography high-resolution mass spectrometry data, a reliable machine learning model could be established that rapidly uncovers chemical urine manipulation. The incorporation of our model into routine clinical or forensic analysis allows simultaneous LC-MS analysis and sample integrity testing in one run, thus revolutionizing this field of drug testing.
尿液样本的操作，包括替代、稀释和化学掺假，是工作场所药物测试、禁欲控制和兴奋剂控制实验室面临的持续挑战。在单一分析测量中同时检测样本操作和禁用药物将非常有利。机器学习算法能够从现有数据集中学习，并预测模型未知的新数据的结果。
使用吡啶氯铬酸盐、亚硝酸钾、过氧化氢、碘、次氯酸钠和水对 702 份经液相色谱-四极杆飞行时间质谱法测定的真实人体尿液样本进行处理。在 Progenesis QI 中进行保留时间对齐后，使用 500 个样本训练人工神经网络，每个样本有 33448 个值。使用局部可解释模型不可知解释方法分析特征重要性。
经过 10 倍交叉验证，平均灵敏度、特异性、阳性预测值和阴性预测值分别为 88.9%、92.0%、91.9%和 89.2%。一个包含处理和未处理尿液样本的多样化测试集（n=202）可以以 95.4%的准确率进行正确分类。此外，还提取了 14 个重要特征和 4 个潜在生物标志物。
使用可解释的保留时间对齐液相色谱高分辨率质谱数据，可以建立一个可靠的机器学习模型，快速发现化学尿液操作。将我们的模型纳入常规临床或法医分析中，可以在一次运行中同时进行 LC-MS 分析和样本完整性测试，从而彻底改变药物测试领域。
