Advertisement
Review Article| Volume 59, ISSUE 6, 103020, December 2020

Emerging use of machine learning and advanced technologies to assess red cell quality

  • Joseph A. Sebastian
    Correspondence
    Corresponding author at: 661 University Avenue, Toronto, ON, M5G 1X8, Canada.
    Affiliations
    Institute of Biomedical Engineering, University of Toronto, 164 College St., Toronto, Ontario, M5S 3G9, Canada

    Translational Biology and Engineering Program, Ted Rogers Center for Heart Research, 661 University Avenue, Toronto, ON, M5G 1X8, Canada
    Search for articles by this author
  • Michael C. Kolios
    Affiliations
    Department of Physics, Ryerson University, 350 Victoria St., Toronto, Ontario, M5B 2K3, Canada

    Institute of Biomedical Engineering, Science and Technology (iBEST), A Partnership Between Ryerson University and St. Michael’s Hospital, 209 Victoria St, Toronto, Ontario, M5B 1T8, Canada

    Keenan Research Centre for Biomedical Science, Li Ka Shing Knowledge Institute, St. Michael’s Hospital, 209 Victoria St., Toronto, Ontario, M5B 1T8, Canada
    Search for articles by this author
  • Jason P. Acker
    Affiliations
    Centre for Innovation, Canadian Blood Services, 8249-114 St., Edmonton, Alberta, T6G 2R8, Canada

    Department of Laboratory Medicine and Pathology, University of Alberta, 8249-114 St., Edmonton, Alberta, T6G 2R8, Canada
    Search for articles by this author
Published:November 21, 2020DOI:https://doi.org/10.1016/j.transci.2020.103020

      Abstract

      Improving blood product quality and patient outcomes is an accepted goal in transfusion medicine research. Thus, there is an urgent need to understand the potential adverse effects on red blood cells (RBCs) during pre-transfusion storage. Current assessment techniques of these degradation events, termed “storage lesions”, are subjective, labor-intensive, and complex. Here we describe emerging technologies that assess the biochemical, biophysical, and morphological characteristics of RBC storage lesions. Of these emerging techniques, machine learning (ML) has shown potential to overcome the limitations of conventional RBC assessment methods. Our previous work has shown that neural networks can extract chronological progressions of morphological changes in RBCs during storage without human input. We hypothesize that, with broader training and testing of multivariate data (e.g., varying donor factors and manufacturing methods), ML can further our understanding of clinical transfusion outcomes in multiple patient groups.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Transfusion and Apheresis Science
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Carson J.L.
        Red blood cell transfusion: a clinical practice guideline from the AABB*.
        Ann Intern Med. 2012; 157: 49https://doi.org/10.7326/0003-4819-157-1-201206190-00429
        • Mohandas N.
        • Chasis J.A.
        Red blood cell deformability, membrane material properties and shape: regulation by transmembrane, skeletal and cytosolic proteins and lipids.
        Semin Hematol. 1993; 30: 171-192
        • Hess J.R.
        Red cell changes during storage.
        Transfus Apher Sci. 2010; 43: 51-59https://doi.org/10.1016/j.transci.2010.05.009
        • Almizraq R.
        • Tchir J.D.R.
        • Holovati J.L.
        • Acker J.P.
        Storage of red blood cells affects membrane composition, microvesiculation, and in vitro quality.
        Transfusion. 2013; 53: 2258-2267https://doi.org/10.1111/trf.12080
        • Islamzada E.
        • Matthews K.
        • Guo Q.
        • Santoso A.T.
        • Duffy S.P.
        • Scott M.D.
        • et al.
        Deformability based sorting of stored red blood cells reveals donor-dependent aging curves.
        Lab Chip. 2020; 20: 226-235https://doi.org/10.1039/C9LC01058K
        • Matthews K.
        • Myrand-Lapierre M.-E.
        • Ang R.R.
        • Duffy S.P.
        • Scott M.D.
        • Ma H.
        Microfluidic deformability analysis of the red cell storage lesion.
        J Biomech. 2015; 48: 4065-4072https://doi.org/10.1016/j.jbiomech.2015.10.002
        • Xu Z.
        • Zheng Y.
        • Wang X.
        • Shehata N.
        • Wang C.
        • Sun Y.
        Stiffness increase of red blood cells during storage.
        Microsyst Nanoeng. 2018; 4: 17103https://doi.org/10.1038/micronano.2017.103
        • Cluitmans J.C.A.
        • Chokkalingam V.
        • Janssen A.M.
        • Brock R.
        • Huck W.T.S.
        • Bosman G.J.C.G.M.
        Alterations in red blood cell deformability during storage: a microfluidic approach.
        Biomed Res Int. 2014; 2014: 1-9https://doi.org/10.1155/2014/764268
        • Pinto R.N.
        • Hysi E.
        • Bagga K.
        • Sebastian J.A.
        • Douplik A.
        • Acker J.P.
        • et al.
        Feasibility of photoacoustic imaging for the non-invasive quality management of stored blood bags: photoacoustic analysis of stored blood.
        Vox Sang. 2019; 114: 701-710https://doi.org/10.1111/vox.12828
        • Pinto R.N.
        • Sebastian J.A.
        • Parsons M.J.
        • Chang T.C.
        • Turner T.R.
        • Acker J.P.
        • et al.
        Label‐free analysis of red blood cell storage lesions using imaging flow cytometry.
        Cytometry. 2019; 95: 976-984https://doi.org/10.1002/cyto.a.23846
        • Doan M.
        • Sebastian J.A.
        • Pinto R.N.
        • McQuin C.
        • Goodman A.
        • Wolkenhauer O.
        • et al.
        Label-free assessment of red blood cell storage lesions by deep learning.
        Bioinformatics. 2018; https://doi.org/10.1101/256180
        • Doan M.
        • Sebastian J.A.
        • Caicedo J.C.
        • Siegert S.
        • Roch A.
        • Turner T.R.
        • et al.
        Objective assessment of stored blood quality by deep learning.
        Proc Natl Acad Sci U S A. 2020; 202001227https://doi.org/10.1073/pnas.2001227117
        • Turner T.R.
        • Acker J.P.
        A Canadian perspective on the use and preparation of cryopreserved red cell concentrates.
        Transfus Apher Sci. 2020; 59102853https://doi.org/10.1016/j.transci.2020.102853
        • Yoshida T.
        • Blair A.
        • D’Alessandro A.
        • Nemkov T.
        • Dioguardi M.
        • Silliman C.C.
        • et al.
        Enhancing uniformity and overall quality of red cell concentrate with anaerobic storage.
        Blood Transfus. 2017; 15: 172-181https://doi.org/10.2450/2017.0325-16
        • Doan M.
        • Vorobjev I.
        • Rees P.
        • Filby A.
        • Wolkenhauer O.
        • Goldfeld A.E.
        • et al.
        Diagnostic potential of imaging flow cytometry.
        Trends Biotechnol. 2018; 36: 649-652https://doi.org/10.1016/j.tibtech.2017.12.008
        • Bok T.-H.
        • Hysi E.
        • Kolios M.C.
        In vitro photoacoustic spectroscopy of pulsatile blood flow: probing the interrelationship between red blood cell aggregation and oxygen saturation.
        J Biophotonics. 2018; 11e201700300https://doi.org/10.1002/jbio.201700300
        • Vardaki M.Z.
        • Atkins C.G.
        • Schulze H.G.
        • Devine D.V.
        • Serrano K.
        • Blades M.W.
        • et al.
        Raman spectroscopy of stored red blood cell concentrate within sealed transfusion blood bags.
        Analyst. 2018; 143: 6006-6013https://doi.org/10.1039/C8AN01509K
        • Gautam R.
        • Oh J.-Y.
        • Marques M.B.
        • Dluhy R.A.
        • Patel R.P.
        Characterization of storage-induced red blood cell hemolysis using Raman spectroscopy.
        Lab Med. 2018; 49: 298-310https://doi.org/10.1093/labmed/lmy018
        • D’Alessandro A.
        • Kriebardis A.G.
        • Rinalducci S.
        • Antonelou M.H.
        • Hansen K.C.
        • Papassideri I.S.
        • et al.
        An update on red blood cell storage lesions, as gleaned through biochemistry and omics technologies: an omics update on RBC storage.
        Transfusion. 2015; 55: 205-219https://doi.org/10.1111/trf.12804
        • Nishino T.
        • Yachie-Kinoshita A.
        • Hirayama A.
        • Soga T.
        • Suematsu M.
        • Tomita M.
        In silico modeling and metabolome analysis of long-stored erythrocytes to improve blood storage methods.
        J Biotechnol. 2009; 144: 212-223https://doi.org/10.1016/j.jbiotec.2009.08.010
        • Roback J.D.
        • Josephson C.D.
        • Waller E.K.
        • Newman J.L.
        • Karatela S.
        • Uppal K.
        • et al.
        Metabolomics of ADSOL (AS-1) red blood cell storage.
        Transfus Med Rev. 2014; 28: 41-55https://doi.org/10.1016/j.tmrv.2014.01.003
        • Maurya P.K.
        • Kumar P.
        • Chandra P.
        Biomarkers of oxidative stress in erythrocytes as a function of human age.
        WJM. 2015; 5: 216https://doi.org/10.5662/wjm.v5.i4.216
        • Bohonek M.
        • Kutac D.
        • Acker J.P.
        • Seghatchian J.
        Optimizing the supply of whole blood-derived bioproducts through the combined implementation of cryopreservation and pathogen reduction technologies and practices: an overview.
        Transfus Apher Sci. 2020; 59102754https://doi.org/10.1016/j.transci.2020.102754
        • D’Alessandro A.
        • Gevi F.
        • Zolla L.
        Red blood cell metabolism under prolonged anaerobic storage.
        Mol Biosyst. 2013; 9: 1196https://doi.org/10.1039/c3mb25575a
        • Gunčar G.
        • Kukar M.
        • Notar M.
        • Brvar M.
        • Černelč P.
        • Notar M.
        • et al.
        An application of machine learning to haematological diagnosis.
        Sci Rep. 2018; 8: 411https://doi.org/10.1038/s41598-017-18564-8
        • Doan M.
        • Case M.
        • Masic D.
        • Hennig H.
        • McQuin C.
        • Caicedo J.
        • et al.
        Label‐free leukemia monitoring by computer vision.
        Cytometry. 2020; 97: 407-414https://doi.org/10.1002/cyto.a.23987
        • Doan M.
        • Case M.
        • Mašić D.
        • Hennig H.
        • McQuin C.
        • Goodman A.
        • et al.
        Label-free analyses of minimal residual disease in ALL using deep learning and imaging flow cytometry.
        Blood. 2017; 130 (1437–1437)https://doi.org/10.1182/blood.V130.Suppl_1.1437.1437
        • Blasi T.
        • Hennig H.
        • Summers H.D.
        • Theis F.J.
        • Cerveira J.
        • Patterson J.O.
        • et al.
        Label-free cell cycle analysis for high-throughput imaging flow cytometry.
        Nat Commun. 2016; 7: 10256https://doi.org/10.1038/ncomms10256
        • Ching T.
        • Himmelstein D.S.
        • Beaulieu-Jones B.K.
        • Kalinin A.A.
        • Do B.T.
        • Way G.P.
        • et al.
        Opportunities and obstacles for deep learning in biology and medicine.
        J R Soc Interface. 2018; 1520170387https://doi.org/10.1098/rsif.2017.0387
        • Cao C.
        • Liu F.
        • Tan H.
        • Song D.
        • Shu W.
        • Li W.
        • et al.
        Deep learning and its applications in biomedicine.
        Genom Proteom Bioinform. 2018; 16: 17-32https://doi.org/10.1016/j.gpb.2017.07.003
        • Xu M.
        • Papageorgiou D.P.
        • Abidi S.Z.
        • Dao M.
        • Zhao H.
        • Karniadakis G.E.
        A deep convolutional neural network for classification of red blood cells in sickle cell anemia.
        PLoS Comput Biol. 2017; 13e1005746https://doi.org/10.1371/journal.pcbi.1005746
        • Alzubaidi L.
        • Fadhel M.A.
        • Al-Shamma O.
        • Zhang J.
        • Duan Y.
        Deep learning models for classification of red blood cells in microscopy images to aid in sickle cell anemia diagnosis.
        Electronics. 2020; 9: 427https://doi.org/10.3390/electronics9030427
        • Durant T.J.S.
        • Olson E.M.
        • Schulz W.L.
        • Torres R.
        Very deep convolutional neural networks for morphologic classification of erythrocytes.
        Clin Chem. 2017; 63: 1847-1855https://doi.org/10.1373/clinchem.2017.276345
        • Caicedo J.C.
        • McQuin C.
        • Goodman A.
        • Singh S.
        • Carpenter A.E.
        Weakly supervised learning of single-cell feature embeddings.
        in: 2018 IEEE/CVF conference on computer vision and pattern recognition, Salt Lake City, UT: IEEE2018: 9309-9318https://doi.org/10.1109/CVPR.2018.00970
        • Sebastian J.A.
        • Pinto R.N.
        • Turner T.
        • Parsons M.J.
        • Acker J.P.
        • Kolios M.C.
        Application of image flow cytometry on the characterization of red blood cell morphology: validation against the conventional technique and trends observed due to donor variability.
        Vox Sang. 2018; 113: 62https://doi.org/10.1111/vox.12658
        • Mykhailova O.
        • Olafson C.
        • Turner T.R.
        • DʼAlessandro A.
        • Acker J.P.
        Donor‐dependent aging of young and old red blood cell subpopulations: metabolic and functional heterogeneity.
        Transfusion. 2020; 60: 2633-2646https://doi.org/10.1111/trf.16017