Ann Lab Med.  2023 Sep;43(5):401-407. 10.3343/alm.2023.43.5.401.

Artificial Intelligence in Point-of-Care Testing

• Khan AI
• Khan M
• Khan R

• KMID: 2551987
• DOI: http://doi.org/10.3343/alm.2023.43.5.401

Abstract

With the projected increase in the global population, current healthcare delivery models will face severe challenges. Rural and remote areas, whether in developed or developing countries, are characterized by the same challenges: the unavailability of hospitals, lack of trained and skilled staff performing tests, and poor compliance with quality assurance protocols. Point-of-care testing using artificial intelligence (AI) is poised to be able to address these challenges. In this review, we highlight some key areas of application of AI in point-of-care testing, including lateral flow immunoassays, bright-field microscopy, and hematology, demonstrating this rapidly expanding field of laboratory medicine.

Keyword

Artificial intelligence; Point-of-care testing; Lateral flow immunoassay; Immunoassay; Hematology; Bright-field microscopy; Microscopy; Convolutional neural network; Malaria; Hemoglobin; Anemia

Figure

• 

  Fig. 1 Schematic of the electrophoretic process for POC testing of anemia and Hb variants. (A) A whole blood specimen (red) is mixed with a standard calibrator (blue) and electrophoresed on the cellulose acetate paper. (B) Within 2.5 minutes, the Hb is separated from the standard. A ML ANN is used to determine the Hb concentration and anemia status. (C) Within 8 minutes, the Hb is separated into the different variants, and major variants are determined (Adapted from An, et al. [27].). Abbreviations: POC, point-of-care; ML machine learning; ANN, artificial neural network.

Reference

1. United Nations. Global issues. https://www.un.org/en/globalissues/population. Updated on Aug 2022.

2. Weka. Machine learning vs. neural networks (differences explained). https://www.weka.io/learn/machine-learning-gpu/machine-learning-vs-neural-networks. Updated on Sept 2021.

3. IBM. What are neural networks? https://www.ibm.com/topics/neural-networks. Updated on Dec 2022.

4. Western Governors University. Neural networks and deep learning explained. https://www.wgu.edu/blog/neural-networks-deep-learning-explained2003.html#openSubscriberModal. Updated on Mar 2020.

5. Kosack CS, Page AL, Klatser PR. 2017; A guide to aid the selection of diagnostic tests. Bull World Health Organ. 95:639–45. DOI: 10.2471/BLT.16.187468. PMID: 28867844. PMCID: PMC5578377.

6. Xu Y, Liu Y, Wu Y, Xia X, Liao Y, Li Q. 2014; Fluorescent probe-based lateral flow assay for multiplex nucleic acid detection. Anal Chem. 86:5611–4. DOI: 10.1021/ac5010458. PMID: 24892496.

7. Liu CY, Ma W, Gao ZY, Huang JY, Hou Y, Xu CL, et al. 2014; Upconversion luminescence nanoparticles-based lateral flow immunochromatographic assay for cephalexin detection. J Mater Chem C. 2:9637–42. DOI: 10.1039/C4TC02034K.

8. Yan W, Wang K, Xu H, Huo X, Jin Q, Cui D. 2019; Machine learning approach to enhance the performance of MNP-labeled lateral flow immunoassay. Nanomicro Lett. 11:7. DOI: 10.1007/s40820-019-0239-3. PMID: 34137967. PMCID: PMC7770769.

9. Wang CY, Hou F, Ma YC. 2015; Simultaneous quantitative detection of multiple tumor markers with a rapid and sensitive multicolor quantum dots based immunochromatographic test strip. Biosens Bioelectron. 68:156–62. DOI: 10.1016/j.bios.2014.12.051. PMID: 25562743.

10. Zhao Y, Yang M, Fu Q, Ouyang H, Wen W, Song Y, et al. 2018; A nanozyme- and ambient light-based smartphone platform for simultaneous detection of dual biomarkers from exposure to organophosphorus pesticides. Anal Chem. 90:7391–8. DOI: 10.1021/acs.analchem.8b00837. PMID: 29792679.

11. Turbé V, Herbst C, Mngomezulu T, Meshkinfamfard S, Dlamini N, Mhlongo T, et al. 2021; Deep learning of HIV field-based rapid tests. Nat Med. 27:1165–70. DOI: 10.1038/s41591-021-01384-9. PMID: 34140702. PMCID: PMC7611654.

12. Perkins DJ, Were T, Davenport GC, Kempaiah P, Hittner JB, Ong'echa JM. 2011; Severe malarial anemia: innate immunity and pathogenesis. Int J Biol Sci. 7:1427–42. DOI: 10.7150/ijbs.7.1427. PMID: 22110393. PMCID: PMC3221949.

13. WHO. World Malaria Report, 2020. https://www.who.int/publications/i/item/9789240015791. Updated on Nov 2020.

14. Belachew EB. 2018; Immune response and evasion mechanisms of Plasmodium falciparum parasites. J Immunol Res. 2018:6529681. DOI: 10.1155/2018/6529681. PMID: 29765991. PMCID: PMC5889876.

15. Wilson ML. 2013; Laboratory diagnosis of malaria: conventional and rapid diagnostic methods. Arch Pathol Lab Med. 137:805–11. DOI: 10.5858/arpa.2011-0602-RA. PMID: 23721276.

16. Ratnawati , Hatta M, Smits HL. 2008; Point-of-care testing for malaria outbreak management. Trans R Soc Trop Med Hyg. 102:699–704. DOI: 10.1016/j.trstmh.2008.04.018. PMID: 18513771.

17. LeCun Y, Bengio Y, Hinton G. 2015; Deep learning. Nature. 521:436–44. DOI: 10.1038/nature14539. PMID: 26017442.

18. Das D, Vongpromek R, Assawariyathipat T, Srinamon K, Kennon K, Stepniewska K, et al. 2022; Field evaluation of the diagnostic performance of EasyScan GO: a digital malaria microscopy device based on machine-learning. Malar J. 21:122. DOI: 10.1186/s12936-022-04146-1. PMID: 35413904. PMCID: PMC9004086.

19. WHO guideline on control and elimination of human schistosomiasis [Internet]. World Health Organization;Geneva: 2022. https://www.ncbi.nlm.nih.gov/books/NBK578389/.Updated on March, 2023.

20. Oyibo P, Jujjavarapu S, Meulah B, Agbana T, Braakman I, van Diepen A, et al. 2022; Schistoscope: an automated microscope with artificial intelligence for detection of Schistosoma haematobium eggs in resource-limited settings. Micromachines (Basel). 13:643. DOI: 10.3390/mi13050643. PMID: 35630110. PMCID: PMC9146062.

21. WHO. Diagnostic target product profiles for monitoring, evaluation and surveillance of schistosomiasis control programmes. Geneva, Switzerland: World Health Organization.

22. Bransky A, Larsson A, Aardal E, Ben-Yosef Y, Christenson RH. 2021; A novel approach to hematology testing at the point of care. J Appl Lab Med. 6:532–42. DOI: 10.1093/jalm/jfaa186. PMID: 33274357. PMCID: PMC7798949.

23. Ben-Yosef Y, Marom B, Hirshberg G, D'Souza C, Larsson A, Bransky A. 2016; The HemoScreen, a novel haematology analyser for the point of care. J Clin Pathol. 69:720–5. DOI: 10.1136/jclinpath-2015-203484. PMID: 26786235.

24. Fåhræus R, Lindqvist T. 1931; The viscosity of the blood in narrow capillary tubes. Am J Physiol. 96:562–8. DOI: 10.1152/ajplegacy.1931.96.3.562.

25. Leshansky AM, Bransky A, Korin N, Dinnar U. 2007; Tunable nonlinear viscoelastic "focusing" in a microfluidic device. Phys Rev Lett. 98:234501. DOI: 10.1103/PhysRevLett.98.234501. PMID: 17677908.

26. Bachar N, Benbassat D, Brailovsky D, Eshel Y, Glück D, Levner D, et al. 2021; An artificial intelligence-assisted diagnostic platform for rapid near-patient hematology. Am J Hematol. 96:1264–74. DOI: 10.1002/ajh.26295. PMID: 34264525. PMCID: PMC9290600.

27. An R, Man Y, Iram S, Kucukal E, Hasan MN, Huang Y, et al. 2021; Point-of-care microchip electrophoresis for integrated anemia and hemoglobin variant testing. Lab Chip. 21:3863–75. DOI: 10.1039/D1LC00371B. PMID: 34585199. PMCID: PMC9714341.

28. Soares Magalhães RJ, Clements AC. 2011; Spatial heterogeneity of haemoglobin concentration in preschool-age children in sub-Saharan Africa. Bull World Health Organ. 89:459–68. DOI: 10.2471/BLT.10.083568. PMID: 21673862. PMCID: PMC3099553.