基于XGBoost方法的大肠杆菌-NC膜复合电极阻抗模型研究

doi:10.3969/j.issn.0258-8021.2021.03.07

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (7700 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The purpose of this work is to use machine learning method to analyze the concentration of large quantities of E. coli and evaluate the antibacterial effect of low threshold antibiotics. In this paper, XGBoost machine learning algorithm was used to construct a model of E. coli-NC membrane attachment on gold electrodes, which was used to detect the electrochemical impedance spectrum of E. coli at different concentrations. On this basis, the changes of impedance spectrum corresponding to the action of different concentrations of Amikacin Sulfate antibiotics on the standard concentration of E. coli were analyzed. The impedance curves were fitted with ZView to get seven electrochemical parameters according to the Randles equivalent circuit. The main four parameters of R_s, CPE-P, CPE-T and R₁, which were extracted by the principal component analysis (PCA) based on the principle of selecting the top 90% of the information quantity, were input to XGBoost prediction model. Prediction models of the two groups of experiments of E. coli liquid concentration and antibiotic concentration were established based on the predicted value of bacterial fluid concentration and antibiotic concentration. The predicted results of both groups were consistent with the experimental results, with the average root mean square error (RMSE) of the predicted E. coli concentration of 2.18×10^-3 lg CFU/mL and the maximum difference between the upper and lower limits of the predicted concentration of each group within 1.49×10⁷ CFU/mL. The average RMSE of antibiotics was 7.45×10^-3 μL/mL, and the regression accuracy was 0.01 μL/mL, which realized the rapid and accurate prediction of E. coli and antibiotic concentration. Therefore, the impedance model of E. coli-NC membrane based on XGBoost could be applied to quantitatively analyze the mass concentrations of E. coli and the evaluation of the effect of antibiotic antibacterial at critical low threshold, so as to quantitatively evaluate the long-term impedance change caused by the attachment of micro-proteins, bacteria and other biofilms on the electrode surface, showing great application value and significance in the rapid detection of electrochemistry in the field of food safety.

Key words： XGBoost method E. coli-NC membrane structure electrochemical impedance antibiotic detection

Received: 12 January 2021

PACS:

R318

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xu Ying
	Chen Yangzi
	Liu Zhe
	Sun Lesheng
	Jiang Yang
	Guo Miao

Cite this article:

Xu Ying,Chen Yangzi,Liu Zhe, et al. Research on Impedance Model of E. coli-NC Membrane Composite Electrode Based on XGBoost Algorithm[J]. Chinese Journal of Biomedical Engineering, 2021, 40(3): 310-320.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2021.03.07 OR http://cjbme.csbme.org/EN/Y2021/V40/I3/310

[1] Guo Junqi, Yang Lan, Bie Rongfang, et al. An XGBoost-based physical fitness evaluation model using advanced feature selection and Bayesian hyper-parameter optimization for wearable running monitoring [J]. Computer Networks, 2019, 151: 166-180.
[2] Zhang Hongbin, Qiu Diedie, Wu Renzhong, et al. Novel framework for image attribute annotation with gene selection XGBoost algorithm and relative attribute model [J]. Applied Soft Computing, 2019, 80: 57-79.
[3] Malvano F, Pilloton R, Albanese D, et al. Label-free impedimetric biosensors for the control of food safety - A review [J]. International Journal of Environmental Analytical Chemistry, 2020, 100(4): 468-491.
[4] 李杜娟. 快速检测致病性微生物的免疫生物传感器研究 [D]. 杭州: 浙江大学, 2010.
[5] 王泽华,曾冬冬,张欢, 等.电沉积纳米金修饰的16通道电流型PSA免疫传感器的制备 [J]. 中国生物医学工程学报, 2015, 34(1): 55-61.
[6] Chen Jing, Yu Qiwen, Fu Wei, et al. A Highly sensitive amperometric glutamate oxidase microbiosensor based on a reduced graphene oxide/prussian blue nanocube/gold nanoparticle composite film-modified Pt electrode [J]. Sensors, 2020, 20(10): 1-15.
[7] Sow PK, Sant S, Shukla A. EIS studies on electro-electrodi-alysis cell for concentration of hydriodic acid [J]. International Journal of Hydrogen Energy, 2010, 35(17): 8868-8875.
[8] Osorio WR. Freitas ES. Garcia A, et al. EIS and potentiodynamic polarization studies on immiscible monotectic Al-In alloys [J]. Electrochimica Acta, 2013,102(21): 436-445.
[9] 陈林,马青,王力等. 大鼠红细胞悬浮液阻抗谱 Cole-Cole数学模型分析 [J]. 航天医学与医学工程, 2010, 23:182-187.
[10] 王洪志,庞小峰,王爱华. 电阻抗法细菌药物敏感性快速检测装置的研制 [J]. 航天医学与医学工程, 2010, 23:455-458.
[11] 张新爱. 基于纳米材料新型电化学传感器的制备及其在生物样品分析中的应用研究 [D]. 上海:华东师范大学, 2011.
[12] Park J, Cho S. Development of interdigitated and chainshaped electrode array for electric cell-substrate impedance sensing [J]. Journal of Nanoscience & Nanotechnology, 2016, 16(11): 11911-11915.
[13] Park IH, Hong Y, Jun HS, et al. DAQ based impedance measurement system for low cost and portable electrical cellsubstrate impedance sensing [J]. Biochip Journal, 2018, 12: 18-24.
[14] 曾繁典. 抗生素及合成抗菌药物的滥用与危害[J]. 中国药物警戒, 2004, 1(1): 25-27.
[15] Furst AL, Hoepker AC, Francis MB. Quantifying hormone disruptors with an engineered bacterial biosensor [J]. ACS Central Science, 2017, 3(2): 110-116.
[16] Sheridan RP, Wang Min, Liaw A, et al. Extreme gradient boosting as a method for quantitative structure-activity relationships [J]. Journal of Chemical Information and Modeling, 2016, 56(12): 2353-2360.
[17] Chen Tianqi, Guestrin C. XGBoost: A scalable treeboosting system [C] // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16). New York: Association for Computing Machinery, 2016: 785-794.
[18] Ahamad MM, Aktar S, Rashed-Al-Mahfuz M, et al. A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients [J]. Expert Systems with Applications, 2020, 160: 1-10.
[19] Zhang Dongyang, Gong Yicheng. The comparison of LightGBM and XGBoost coupling factor analysis and prediagnosis of acute liver failure [J]. IEEE Access, 2020, 8: 220990-221003.
[20] Li Shenglong, Zhang Xiaojing. Research on orthopedic auxiliary classification and prediction model based on XGBoost algorithm [J]. Neural Computing and Applications, 2019, 32(7): 19711-19719.
[21] Chang Wenbing, Liu Yinglai, Xiao Yiyong, et al. Probability analysis of hypertension-related symptoms based on XGBoost and clustering algorithm [J]. Applied Sciences, 2019,9(6): 1-14.
[22] Giaever I, Keese CR. Monitoring fibroblast behavior in tissue culture with an applied electric field [J]. Proceedings of the National Academy of Sciences, 1984, 81(12): 3761-3764.
[23] Meng Tianjiao, Zhao Dan, Ye Huimin, et al. Construction of an ultrasensitive electrochemical sensing platform for microRNA-21 based on interface impedance spectroscopy [J]. Journal of Colloid and Interface Science, 2020, 578: 164-170.
[24] Ravi PV, Thangadurai DT, Nehru K, et al., Surface and morphology analyses, and voltammetry studies for electrochemical determination of cerium(Ⅲ) using a graphene nanobud-modified-carbon felt electrode in acidic buffer solution (pH 4.0 +/-0.05) [J]. Rsc Advances, 2020. 10(61): 37409-37418.
[25] 冯阳阳,李杜娟,叶尊忠等. 纳米颗粒在石英晶体微天平生物传感器中的应用与研究进展 [J]. 中国生物医学工程学报, 2011, 30(2): 299-307.
[26] 申建忠. 基于纳米复合材料新型电化学免疫传感器用于乳制品中大肠杆菌的检测研究 [D]. 镇江:江苏大学, 2016.
[27] 贾飞,闫文杰,戴瑞彤,等. 基于还原氧化石墨烯/碳纳米管-纳米金复合纳米材料的阻抗型电化学适配体传感器检测铜绿假单胞菌 [J/OL]. 食品科学, 29 Dec, 2020 [Epub ahead of print].
[28] 吴海云. 几种新型电化学生物传感器的构建与应用研究 [D]. 太原:山西农业大学, 2013.
[29] 苏敬. 一种用于快速检测氯霉素的基于硝酸纤维素膜的电化学免疫传感器 [D]. 郑州:郑州大学, 2012.
[30] Tseng PY, Chen Yiting, Wang Chuenheng, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning [J]. Critical Care, 2020, 24(1): 1-13.