A Rapid Electrochemical Detection Method of Low-Concentration Dopamine Based on Machine Learning
Liu Zhe1, Sun Lesheng1, Yu Jun1, Lu Ning1, Xu Ying1*, Guo Miao2
1(Institute of Instrument Science and Engineering, School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China) 2(School of Information Engineering, Hangzhou Dianzi University, Hangzhou 311305, China)
Abstract：Portable potentiostat is facing the problem that the accuracy is low and vulnerable under the test conditions. This paper proposed an electrochemical detection data analysis method by combining nanomaterial modified electrodes and machine learning. Under the presence of multiple experimental interference factors, this method was able to achieve the accurate detection of dopamine (DA). The AuNPs/GCE electrode was prepared by electrodepositing gold nanoparticles on the surface of glassy carbon electrode (GCE) by chronoamperometry, and the electrocatalytic activity for the redox of dopamine of AuNPs/GCE was verified by cyclic voltammetry (CV). Under the different solution pH values and scanning speeds, the AuNPs/GCE electrode was applied to perform repetitive accurate cyclic voltammetric detection of dopamine solutions of different concentrations. After the extraction of important characteristics including the peak height, peak potential, baseline slope, peak area and initial redox potential of the detection data, the extreme gradient boosting tree model (XGBoost) and the random forest model (RF) were applied to construct a two-stage concentration prediction analysis. The results showed that the MAE, RMSE and MAPE% of XGBoost-RF concentration prediction model were reduced to 53.9%, 39.7% and 2.7% respectively compared with the traditional SVR model. The training time of RF prediction model was reduced by 23%, the prediction accuracy was improved by 7%, and the fitting degree (R-squared) between predicted value and experimental value was 0.943. In conclusion, this method effectively reduced the influence of different experimental factors in the detection process. It Also improved the detection accuracy and reduced the complexity of the experiment. Therefore, it is of great significance to realize the on-site and rapid electrochemical detection of microscale element.
刘哲, 孙乐圣, 于骏, 陆柠, 徐莹, 郭淼. 基于机器学习的低浓度多巴胺快速电化学检测方法研究[J]. 中国生物医学工程学报, 2022, 41(4): 452-461.
Liu Zhe, Sun Lesheng, Yu Jun, Lu Ning, Xu Ying, Guo Miao. A Rapid Electrochemical Detection Method of Low-Concentration Dopamine Based on Machine Learning. Chinese Journal of Biomedical Engineering, 2022, 41(4): 452-461.
[1] Patella B, Sortino A, Aiello G, et al. Reduced graphene oxide decorated with metals nanoparticles electrode as electrochemical sensor for dopamine[C]//International Conference on Flexible and Printable Sensors and Systems(FLEPS). Glasgow: IEEE, 2019: 1-3. [2] Suganya K, Kayalvizhi E, Yuvaraj R, et al. Effect of Withania Somnifera on the antioxidant and neurotransmitter status in sleep deprivation induced Wistar rats[J]. Bioinformation, 2020, 16(8): 631-637. [3] Gashevskaya A, Dorozhko E, Korotkova E, et al. Voltammetric method for determination of glutathione on a gold-carbon-containing electrode[J]. Inorganic Materials, 2020, 56(14): 1362-1368. [4] Anbumannan V, Kumar RTR, Suresh K. Enhanced electrochemical detection of dopamine by graphene oxide/tungsten trioxide nanocomposite[J]. Materials Science in Semiconductor Processing, 2021, 127: 105696. [5] Li Rui, Liang Huanru, Zhu Mingfang, et al. Electrochemical dual signal sensing platform for the simultaneous determination of dopamine, uric acid and glucose based on copper and cerium bimetallic carbon nanocomposites[J]. Bioelectrochemistry, 2021, 139(5): 107745. [6] Zhao Yulaing, Zhang Hongyu, Li Yang, et al. AI powered electrochemical multi-component detection of insulin and glucose in serum[J]. Biosensors & Bioelectronics, 2021, 186: 113291. [7] Liu Wenjie, Shi Qiaofang, Zheng Gang, et al. Electrocatalytic oxidation toward dopamine and acetaminophen based on AuNPs@TCnA/GN modified glassy carbon electrode[J]. Analytica Chimica Acta, 2019, 1075: 81-90. [8] Mahalakshmi S, Sridevi V. In situ electrodeposited gold nanoparticles on polyaniline-modified electrode surface for the detection of dopamine in presence of ascorbic acid and uric acid[J]. Electrocatalysis, 2021, 12(4): 415-435. [9] Guan Huanan, Liu Bo, Gong Dezhaung, et al. Direct electrochemical enhanced detection of dopamine based on peroxidase-like activity of Fe3O4@Au composite nanoparticles[J]. Microchemical Journal, 2021, 164(7): 105943. [10] Ghanbari K, Nejabati F. Ternary nanocomposite based reduced graphene oxide/chitosan/Cr2O3 for simultaneous determination of dopamine, uric acid, xanthine, and hypoxanthine in fish meat[J]. Analytical Methods, 2020, 12(12): 1650-1661. [11] Shashikumara JK, Swamy BEK. Electrochemical investigation of dopamine in presence of uric acid and ascorbic acid at poly (reactive blue) modified carbon paste electrode: a voltammetric study[J]. Sensors International, 2020, 1: 100008. [12] Cheng Fei, Yang Chuanhua, Zhou Can, etal.Simultaneous determination of metal ions in zinc sulfate solution using UV-Vis spectrometry and SPSE-XGBoost method[J]. Sensors, 2020, 20(17): 4936. [13] Tahtaisleyen S, Gorduk O, Sahin Y. Electrochemical determination of tartrazine using a graphene/poly(l-phenylalanine) modified pencil graphite electrode[J]. Analytical Letters, 2020, 53(11): 1-21. [14] 朱旭,吴淑芳,李春兰,等. 聚L-精氨酸/纳米金修饰电极测定多巴胺[J]. 理化检验(化学分册), 2015, 51(8): 1057-1062. [15] Xu Ying, Dai Yan, Li Chao, et al. PC software-based portable cyclic voltammetry system with PB-MCNT-GNPs-modified electrodes for E. coli detection[J]. Review of Scientific Instruments, 2020, 91(1): 1-5. [16] 代燕. 基于电化学参数分析的便携式恒电位仪系统设计及应用[D]. 杭州:杭州电子科技大学, 2020. [17] 张跃华. 基于低维碳及其纳米复合材料电化学传感器的构建与应用[D]. 南京:南京理工大学, 2017. [18] 唐圳雄,唐东林,丁超,侯军. 基于XGBoost特征重要度的储罐缺陷ANN面积量化模型[J]. 电子测量与仪器学报, 2020, 34(8): 109-115. [19] Mounesh, Reddy K. Novel garnished cobalt(II) phthalocyanine with MWCNTs on modified GCE: sensitive and reliable electrochemical investigation of paracetamol and dopamine[J]. New Journal of Chemistry, 2020, 44(39): 16831-16844. [20] Schaumloffel L, Dambros J, Fernandes P, et al. Direct and simultaneous determination of four phenolic antioxidants in biodiesel using differential pulse voltammetry assisted by artificial neural networks and variable selection by decision trees[J]. Fuel, 2019, 236: 803-810. [21] 秦喜文,吕思奇,李巧玲. 利用整体经验模态分解和随机森林的脑电信号分类研究[J]. 中国生物医学工程学报, 2018, 37(6):665-672. [22] Wei Zhenbo, Yang Yanan, Zhu Luyi, et al. Application of novel nanocomposite-modified electrodes for identifying rice wines of different brands[J]. RSC Advances, 2018, 8(24):13333-13343.
