School of Digital Media, Shenzhen Institute of Information Technology, Shenzhen, 518172, China.
Wenzhou Mingcheng Construction Investment Group Co., Ltd., China.
Comput Biol Chem. 2019 Feb;78:481-490. doi: 10.1016/j.compbiolchem.2018.11.017. Epub 2018 Nov 22.
Paraquat (PQ) poisoning seriously harms the health of humanity. An effective diagnostic method for paraquat poisoned patients is a crucial concern. Nevertheless, it's difficult to identify the patients with low intake of PQ or delayed treatment. Here, a new efficient diagnostic approach to integrate machine learning and gas chromatography-mass spectrometry (GC-MS), named GEE, is proposed to identify the PQ poisoned patients. First, GC-MS provides the original data that efficiently identified the paraquat-poisoned patients. According to the high dimensionality of the original data, in the second stage, the chaos enhanced grey wolf optimization (EGWO) is adopted to search the optimal feature sets to improve the accuracy of identification. Finally, the extreme learning machine (ELM) is used to identify the PQ poisoned patients. To efficiently evaluate the proposed method, four measures were used in our experiments and comparisons were made with six other methods. The PQ-poisoned patients and robust volunteers can be well identified by GEE and the values of AUC, accuracy, sensitivity and specificity were 95.14%, 93.89%, 94.44% and 95.83%, respectively. Our experimental results demonstrated that GEE had better performance and might serve as a novel candidate diagnosis of PQ-poisoned patients.
百草枯（PQ）中毒严重危害人类健康。寻找一种有效的诊断百草枯中毒患者的方法一直是研究的热点。然而，对于低剂量摄入或治疗延迟的患者，目前的诊断方法仍存在一定的局限性。本研究提出了一种基于机器学习和气相色谱-质谱联用（GC-MS）的新型诊断方法，命名为 GEE，用于识别百草枯中毒患者。首先，GC-MS 提供了原始数据，有效地识别了百草枯中毒患者。由于原始数据具有较高的维度，在第二阶段，采用混沌增强灰狼优化（EGWO）算法搜索最优特征集，以提高识别的准确性。最后，使用极限学习机（ELM）识别百草枯中毒患者。为了有效地评估所提出的方法，我们在实验中使用了四个度量标准，并与其他六种方法进行了比较。结果表明，GEE 能够很好地识别百草枯中毒患者和健康志愿者，AUC、准确率、敏感度和特异度的值分别为 95.14%、93.89%、94.44%和 95.83%。实验结果表明，GEE 具有较好的性能，可能成为一种新型的百草枯中毒患者诊断方法。
