Dou Jingrui, Dawuti Wubulitalifu, Zheng Xiangxiang, Zhang Rui, Zhou Jing, Lin Renyong, Lü Guodong
State Key Laboratory of Pathogenesis, Prevention, and Treatment of Central Asian High Incidence Diseases, Clinical Medical Research Institute, The First Affiliated Hospital of Xinjiang Medical University, No. 137 Liyushan South Road, Urumqi 830054, China; School of Public Health, Xinjiang Medical University, Urumqi 830054, China.
School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China.
Photodiagnosis Photodyn Ther. 2022 Dec;40:103102. doi: 10.1016/j.pdpdt.2022.103102. Epub 2022 Aug 31.
In this paper, we investigated the possibility of using urine fluorescence spectroscopy and machine learning method to identify hepatocellular carcinoma (HCC) and liver cirrhosis from healthy people. Urine fluorescence spectra of HCC (n = 62), liver cirrhosis (n = 65) and normal people (n = 60) were recorded at 405 nm excitation using a Fluorescent scan multimode reader. The normalized fluorescence spectra revealed endogenous metabolites differences associated with the disease, mainly the abnormal metabolism of porphyrin derivatives and bilirubin in the urine of patients with HCC and liver cirrhosis compared to normal people. The Support vector machine (SVM) algorithm was used to differentiate the urine fluorescence spectra of the HCC, liver cirrhosis and normal groups, and its overall diagnostic accuracy was 83.42%, the sensitivity for HCC and liver cirrhosis were 93.55% and 73.85%, and the specificity for HCC and liver cirrhosis were 88.00% and 89.34%, respectively. This exploratory work shown that the combination of urine fluorescence spectroscopy and SVM algorithm has great potential for the noninvasive screening of HCC and liver cirrhosis.
在本文中，我们研究了利用尿液荧光光谱法和机器学习方法从健康人群中识别肝细胞癌（HCC）和肝硬化的可能性。使用荧光扫描多模式读数器在405nm激发波长下记录了HCC患者（n = 62）、肝硬化患者（n = 65）和正常人（n = 60）的尿液荧光光谱。归一化后的荧光光谱揭示了与疾病相关的内源性代谢物差异，主要是与正常人相比，HCC和肝硬化患者尿液中卟啉衍生物和胆红素的代谢异常。使用支持向量机（SVM）算法对HCC组、肝硬化组和正常组的尿液荧光光谱进行区分，其总体诊断准确率为83.42%，对HCC和肝硬化的敏感度分别为93.55%和73.85%，对HCC和肝硬化的特异度分别为88.00%和89.34%。这项探索性工作表明，尿液荧光光谱法和SVM算法相结合在HCC和肝硬化的无创筛查方面具有巨大潜力。
