Journal Home > Volume 16 , Issue 10
Nano Research 2023, 16(10): 12084-12091 https://doi.org/10.1007/s12274-022-5311-5
Research Article | Issue | Published: 19 January 2023

Artificial intelligence-assisted colorimetry for urine glucose detection towards enhanced sensitivity, accuracy, resolution, and anti-illuminating capability

Show Author's Information Fan Feng1,§,  Zeping Ou2,§,  Fangdou Zhang1,§,  Jinxing Chen3,  Jiankun Huang1,  Jingxiang Wang4,  Haiqiang Zuo2( ),  Jingbin Zeng1( )
State Key Laboratory for Heavy Oil Processing, College of Chemistry and Chemical Engineering, China University of Petroleum (East China), Qingdao 266580, China
College of New Energy, China University of Petroleum (East China), Qingdao 266580, China
Institute of Functional Nano & Soft Materials (FUNSOM), Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices, Soochow University, Suzhou 215123, China
Qingdao Fifth People’s Hospital, Qingdao 266580, China

§ Fan Feng, Zeping Ou, and Fangdou Zhang contributed equally to this work.

Keywords:
artificial intelligence, colorimetry, urine glucose, plasmonic nanosensor, smartphone platform
Topics:
Nano detection
Cite this article:
Feng F, Ou Z, Zhang F, et al. Artificial intelligence-assisted colorimetry for urine glucose detection towards enhanced sensitivity, accuracy, resolution, and anti-illuminating capability. Nano Research, 2023, 16(10): 12084-12091. https://doi.org/10.1007/s12274-022-5311-5
Download citation
EndNote(RIS)
BibTeX

10458

Views

86

Downloads

Citations

10

Crossref

6

WoS

11

Scopus

0

CSCD

Abstract Full text Electronic supplementary material About this article

Colorimetry often suffers from deficiency in quantitative determination, susceptibility to ambient illuminance, and low sensitivity and visual resolution to tiny color changes. To offset these deficiencies, we incorporate deep machine learning into colorimetry by introducing a convolutional neural network (CNN) with powerful parallel processing, self-organization, and self-learning capabilities. As a proof of concept, a plasmonic nanosensor is proposed for the colorimetric detection of glucose by coupling Benedict’s reagent with gold nanoparticles (AuNPs), which relies on the assemble of AuNPs into dendritic nanochains by Cu2O. The distinct difference of refractive index between Cu2O and Au and the localized surface plasmon resonance coupling effect among AuNPs leads to a broad spectral shift as well as abundant color changes, thereby providing sufficient data for self-learning enabled by machine learning. The CNN is then used to fully diversify the learning and training of the images from standard samples under different ambient conditions and to obtain a classifier that can not only recognize tiny color changes that are imperceptible to human eyes, but also exhibit high accuracy and excellent anti-environmental interference capability. This classifier is then compiled as an application (APP) and implanted into a smartphone with Android environment. 306 clinical urine samples were detected using the proposed method and the results showed a satisfactory correlation (87.6%) with that of a standard blood glucose test method. More importantly, this method can be generalized to other applications in colorimetry, and more broadly, in other scientific domains that involve image analysis and quantification.


menu
Abstract
Full text
Outline
Electronic supplementary material
About this article

Artificial intelligence-assisted colorimetry for urine glucose detection towards enhanced sensitivity, accuracy, resolution, and anti-illuminating capability

Show Author's information Fan Feng1,§, Zeping Ou2,§, Fangdou Zhang1,§, Jinxing Chen3, Jiankun Huang1, Jingxiang Wang4, Haiqiang Zuo2( ), Jingbin Zeng1( )
State Key Laboratory for Heavy Oil Processing, College of Chemistry and Chemical Engineering, China University of Petroleum (East China), Qingdao 266580, China
College of New Energy, China University of Petroleum (East China), Qingdao 266580, China
Institute of Functional Nano & Soft Materials (FUNSOM), Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices, Soochow University, Suzhou 215123, China
Qingdao Fifth People’s Hospital, Qingdao 266580, China

§ Fan Feng, Zeping Ou, and Fangdou Zhang contributed equally to this work.

Abstract

Colorimetry often suffers from deficiency in quantitative determination, susceptibility to ambient illuminance, and low sensitivity and visual resolution to tiny color changes. To offset these deficiencies, we incorporate deep machine learning into colorimetry by introducing a convolutional neural network (CNN) with powerful parallel processing, self-organization, and self-learning capabilities. As a proof of concept, a plasmonic nanosensor is proposed for the colorimetric detection of glucose by coupling Benedict’s reagent with gold nanoparticles (AuNPs), which relies on the assemble of AuNPs into dendritic nanochains by Cu2O. The distinct difference of refractive index between Cu2O and Au and the localized surface plasmon resonance coupling effect among AuNPs leads to a broad spectral shift as well as abundant color changes, thereby providing sufficient data for self-learning enabled by machine learning. The CNN is then used to fully diversify the learning and training of the images from standard samples under different ambient conditions and to obtain a classifier that can not only recognize tiny color changes that are imperceptible to human eyes, but also exhibit high accuracy and excellent anti-environmental interference capability. This classifier is then compiled as an application (APP) and implanted into a smartphone with Android environment. 306 clinical urine samples were detected using the proposed method and the results showed a satisfactory correlation (87.6%) with that of a standard blood glucose test method. More importantly, this method can be generalized to other applications in colorimetry, and more broadly, in other scientific domains that involve image analysis and quantification.

Keywords: artificial intelligence, colorimetry, urine glucose, plasmonic nanosensor, smartphone platform

References(38)

[1]

Unser, S.; Campbell, I.; Jana, D.; Sagle, L. Direct glucose sensing in the physiological range through plasmonic nanoparticle formation. Analyst 2015, 140, 590–599.
DOI Google Scholar
[2]

Chen, S.; Hai, X.; Chen, X. W.; Wang, J. H. In situ growth of silver nanoparticles on graphene quantum dots for ultrasensitive colorimetric detection of H2O2 and glucose. Anal. Chem. 2014, 86, 6689–6694.
DOI Google Scholar
[3]

Huang, Z. M.; Yang, J.; Zhang, L.; Geng, X.; Ge, J.; Hu, Y. L.; Li, Z. H. A novel one-step colorimetric assay for highly sensitive detection of glucose in serum based on MnO2 nanosheets. Anal. Methods 2017, 9, 4275–4281.
DOI Google Scholar
[4]

Li, C. H.; Hu, J. M.; Liu, T.; Liu, S. Y. Stimuli-triggered off/on switchable complexation between a novel type of charge-generation polymer (CGP) and gold nanoparticles for the sensitive colorimetric detection of hydrogen peroxide and glucose. Macromolecules 2011, 44, 429–431.
DOI Google Scholar
[5]

Radhakumary, C.; Sreenivasan, K. Naked eye detection of glucose in urine using glucose oxidase immobilized gold nanoparticles. Anal. Chem. 2011, 83, 2829–2833.
DOI Google Scholar
[6]

Shen, W.; Deng, H. M.; Gao, Z. Q. Gold nanoparticle-enabled real-time ligation chain reaction for ultrasensitive detection of DNA. J. Am. Chem. Soc. 2012, 134, 14678–14681.
DOI Google Scholar
[7]

Qiang, H.; Wei, X. C.; Liu, Q. Y.; Chen, Z. B. Iodide-responsive Cu-Au nanoparticle-based colorimetric sensor array for protein discrimination. ACS Sustain. Chem. Eng. 2018, 6, 15720–15726.
DOI Google Scholar
[8]

Teng, Y.; Shi, J.; Pong, P. W. T. Sensitive and specific colorimetric detection of cancer cells based on folate-conjugated gold-iron-oxide composite nanoparticles. ACS Appl. Nano Mater. 2019, 2, 7421–7431.
DOI Google Scholar
[9]

Li, J. W.; Wang, Y.; Zhang, Q. H.; Huo, D. Q.; Hou, C. J.; Zhou, J.; Luo, H. B.; Yang, M. New application of old methods: Development of colorimetric sensor array based on Tollen’s reagent for the discrimination of aldehydes based on Tollen’s reagent. Anal. Chim. Acta 2020, 1096, 138–147.
DOI Google Scholar
[10]

Lin, F. H.; Doong, R. A. Bifunctional Au-Fe3O4 heterostructures for magnetically recyclable catalysis of nitrophenol reduction. J. Phys. Chem. C 2011, 115, 6591–6598.
DOI Google Scholar
[11]

Dong, C.; Wang, Z. Q.; Zhang, Y. J.; Ma, X. H.; Iqbal, M. Z.; Miao, L. J.; Zhou, Z. W.; Shen, Z. Y.; Wu, A. G. High-performance colorimetric detection of thiosulfate by using silver nanoparticles for smartphone-based analysis. ACS Sens. 2017, 2, 1152–1159.
DOI Google Scholar
[12]

Zeng, J. B.; Zhang, Y.; Zeng, T.; Aleisa, R.; Qiu, Z. W.; Chen, Y. Z.; Huang, J. K.; Wang, D. W.; Yan, Z. F.; Yin, Y. D. Anisotropic plasmonic nanostructures for colorimetric sensing. Nano Today 2020, 32, 100855.
DOI Google Scholar
[13]

Wang, H. Q.; Yang, L.; Chu, S. Y.; Liu, B. H.; Zhang, Q. K.; Zou, L. M.; Yu, S. M.; Jiang, C. L. Semiquantitative visual detection of lead ions with a smartphone via a colorimetric paper-based analytical device. Anal. Chem. 2019, 91, 9292–9299.
DOI Google Scholar
[14]

Wang, X. H.; Chang, T. W.; Lin, G. H.; Gartia, M. R.; Liu, G. L. Self-referenced smartphone-based nanoplasmonic imaging platform for colorimetric biochemical sensing. Anal. Chem. 2017, 89, 611–615.
DOI Google Scholar
[15]

Xu, M.; Huang, W.; Lu, D. K.; Huang, C. Y.; Deng, J. J.; Zhou, T. S. Alizarin Red-Tb3+ complex as a ratiometric colorimetric and fluorescent dual probe for the smartphone-based detection of an anthrax biomarker. Anal. Methods 2019, 11, 4267–4273.
DOI Google Scholar
[16]

Liu, F.; Chen, R.; Song, W. L.; Li, L. W.; Lei, C. Y.; Nie, Z. Modular combination of proteolysis-responsive transcription and spherical nucleic acids for smartphone-based colorimetric detection of protease biomarkers. Anal. Chem. 2021, 93, 3517–3525.
DOI Google Scholar
[17]

Nelis, J. L. D.; Zhao, Y. F.; Bura, L.; Rafferty, K.; Elliott, C. T.; Campbell, K. A randomized combined channel approach for the quantification of color- and intensity-based assays with smartphones. Anal. Chem. 2020, 92, 7852–7860.
DOI Google Scholar
[18]

Gardner, W.; Hook, A. L.; Alexander, M. R.; Ballabio, D.; Cutts, S. M.; Muir, B. W.; Pigram, P. J. ToF-SIMS and machine learning for single-pixel molecular discrimination of an acrylate polymer microarray. Anal. Chem. 2020, 92, 6587–6597.
DOI Google Scholar
[19]

Yang, X.; Sun, M. T.; Wang, T.; Wong, M. W.; Huang, D. J. A smartphone-based portable analytical system for on-site quantification of hypochlorite and its scavenging capacity of antioxidants. Sens. Actuators B: Chem. 2019, 283, 524–531.
DOI Google Scholar
[20]

Bao, X.; Jiang, S.; Wang, Y.; Yu, M.; Han, J. A remote computing based point-of-care colorimetric detection system with a smartphone under complex ambient light conditions. Analyst 2018, 143, 1387–1395.
DOI Google Scholar
[21]

Kılıç, V.; Alankus, G.; Horzum, N.; Mutlu, A. Y.; Bayram, A.; Solmaz, M. E. Single-image-referenced colorimetric water quality detection using a smartphone. ACS Omega 2018, 3, 5531–5536.
DOI Google Scholar
[22]

Kim, H.; Awofeso, O.; Choi, S.; Jung, Y.; Bae, E. Colorimetric analysis of saliva-alcohol test strips by smartphone-based instruments using machine-learning algorithms. Appl. Opt. 2017, 56, 84–92.
DOI Google Scholar
[23]

Sajed, S.; Kolahdouz, M.; Sadeghi, M. A.; Razavi, S. F. High-performance estimation of lead ion concentration using smartphone-based colorimetric analysis and a machine learning approach. ACS Omega 2020, 5, 27675–27684.
DOI Google Scholar
[24]

Mutlu, A. Y.; Kılıç, V.; Özdemir, G. K.; Bayram, A.; Horzum, N.; Solmaz, M. E. Smartphone-based colorimetric detection via machine learning. Analyst 2017, 142, 2434–2441.
DOI Google Scholar
[25]

Solmaz, M. E.; Mutlu, A. Y.; Alankus, G.; Kılıç, V.; Bayram, A.; Horzum, N. Quantifying colorimetric tests using a smartphone app based on machine learning classifiers. Sens. Actuators B: Chem. 2018, 255, 1967–1973.
DOI Google Scholar
[26]

He, H.; Yan, S.; Lyu, D. Y.; Xu, M. X.; Ye, R. Q.; Zheng, P.; Lu, X. Y.; Wang, L.; Ren, B. Deep learning for biospectroscopy and biospectral imaging: State-of-the-art and perspectives. Anal. Chem. 2021, 93, 3653–3665.
DOI Google Scholar
[27]
Krizhevsky, A.; Sutskever, I.; Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, 2012, pp 1097–1105.
[28]

Li, Z. L.; Chang, X. L.; Wang, Y.; Wei, C. T.; Wang, J.; Ai, K. L.; Zhang, Y.; Lu, L. H. Point-and-shoot strategy for identification of alcoholic beverages. Anal. Chem. 2018, 90, 9838–9844.
DOI Google Scholar
[29]
Ren, S. Q.; He, K. M.; Girshick, R.; Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, 2015, pp 91–99.
[30]
Tania, M. H.; Lwin, K. T.; Shabut, A. M.; Abu-Hassan, K. J.; Kaiser, M. S.; Hossain, M. A. Assay type detection using advanced machine learning algorithms. In Proceedings of the 2019 13th International Conference on Software, Knowledge, Information Management and Applications, Island of Ulkulhas, Maldives, 2019, pp 1–8.
DOI
[31]

Badrinarayanan, V.; Kendall, A.; Cipolla, R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 2481–2495.
DOI Google Scholar
[32]

Hubel, D. H.; Wiesel, T. N. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol. 1962, 160, 106–154.
DOI Google Scholar
[33]

Liu, D. Y.; Ding, S. Y.; Lin, H. X.; Liu, B. J.; Ye, Z. Z.; Fan, F. R.; Ren, B.; Tian, Z. Q. Distinctive enhanced and tunable plasmon resonant absorption from controllable Au@Cu2O nanoparticles: Experimental and theoretical modeling. J. Phys. Chem. C 2012, 116, 4477–4483.
DOI Google Scholar
[34]

Sekhar, H.; Rao, D. N. Preparation, characterization and nonlinear absorption studies of cuprous oxide nanoclusters, micro-cubes and micro-particles. J. Nanopart. Res. 2012, 14, 976.
DOI Google Scholar
[35]

Zheng, G. W.; Wang, J. S.; Li, H. Y.; Li, Y. L.; Hu, P. WO3/Cu2O heterojunction for the efficient photoelectrochemical property without external bias. Appl. Catal. B: Environ. 2020, 265, 118561.
DOI Google Scholar
[36]

Morales, J.; Sánchez, L.; Martín, F.; Ramos-Barrado, J. R.; Sánchez, M. Use of low-temperature nanostructured CuO thin films deposited by spray-pyrolysis in lithium cells. Thin Solid Films 2005, 474, 133–140.
DOI Google Scholar
[37]

Behjati, S.; Sheibani, S.; Herritsch, J.; Gottfried, J. M. Photodegradation of dyes in batch and continuous reactors by Cu2O-CuO nano-photocatalyst on Cu foils prepared by chemical-thermal oxidation. Mater. Res. Bull. 2020, 130, 110920.
DOI Google Scholar
[38]
Ravindran, S. How artificial intelligence is helping to prevent blindness. Nature, in press, https://doi.org/10.1038/d41586-019-01111-y.
DOI
Video
12274_2022_5311_MOESM2_ESM.mp4
File
12274_2022_5311_MOESM1_ESM.pdf (858.4 KB)
Publication history
Copyright
Acknowledgements

Publication history

Received: 03 July 2022
Revised: 08 November 2022
Accepted: 09 November 2022
Published: 19 January 2023
Issue date: October 2023

Copyright

© Tsinghua University Press 2022

Acknowledgements

Acknowledgements

This work was financially supported by the National Natural Science Foundation of China (No. 21876206), the Shandong Key Fundamental Research Project (No. ZR202010280003), the Fundamental Research Funds for the Central Universities (No. 18CX02037A), and the Youth Innovation and Technology project of Universities in Shandong Province (No. 2020KJC007).

Return