Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence. / Jensen, Emil Alstrup; Serhatlioglu, Murat; Uyanik, Cihan; Hansen, Anne Todsen; Puthusserypady, Sadasivan; Dziegiel, Morten Hanefeld; Kristensen, Anders.

In: Advanced Materials Technologies, Vol. 9, No. 2, 2301462, 2024.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Jensen, EA, Serhatlioglu, M, Uyanik, C, Hansen, AT, Puthusserypady, S, Dziegiel, MH & Kristensen, A 2024, 'Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence', Advanced Materials Technologies, vol. 9, no. 2, 2301462. https://doi.org/10.1002/admt.202301462

APA

Jensen, E. A., Serhatlioglu, M., Uyanik, C., Hansen, A. T., Puthusserypady, S., Dziegiel, M. H., & Kristensen, A. (2024). Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence. Advanced Materials Technologies, 9(2), [2301462]. https://doi.org/10.1002/admt.202301462

Vancouver

Jensen EA, Serhatlioglu M, Uyanik C, Hansen AT, Puthusserypady S, Dziegiel MH et al. Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence. Advanced Materials Technologies. 2024;9(2). 2301462. https://doi.org/10.1002/admt.202301462

Author

Jensen, Emil Alstrup ; Serhatlioglu, Murat ; Uyanik, Cihan ; Hansen, Anne Todsen ; Puthusserypady, Sadasivan ; Dziegiel, Morten Hanefeld ; Kristensen, Anders. / Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence. In: Advanced Materials Technologies. 2024 ; Vol. 9, No. 2.

Bibtex

@article{030afbc5542f47a98122024e9d7a4fe1,

title = "Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence",

abstract = "Label-free blood typing by Raman spectroscopy (RS) is demonstrated by training an artificial intelligence (AI) model on 271 blood typed donor whole blood samples. A fused silica micro-capillary flow cell enables fast generation of a large dataset of Raman spectra of individual donors. A combination of resampling methods, machine learning and deep learning is used to classify the ABO blood group, 27 erythrocyte antigens, 4 platelet antigens, regular anti-B titers of blood group A donors, regular anti-A,-B titers of blood group O donors, and ABH-secretor status, from a single Raman spectrum. The average area under the curve value of the ABO classification is 0.91 ± 0.03 and 0.72 ± 0.09, respectively, for the remaining traits. The classification performance of all parameters is discussed in the context of dataset balance and antigen concentration. Post-hoc scalability analysis of the models shows the potential of RS and AI for future applications in transfusion medicine and blood banking.",

keywords = "blood typing, machine/deep learning, micro-capillary fluidics, precision transfusion medicines, Raman spectroscopy",

author = "Jensen, {Emil Alstrup} and Murat Serhatlioglu and Cihan Uyanik and Hansen, {Anne Todsen} and Sadasivan Puthusserypady and Dziegiel, {Morten Hanefeld} and Anders Kristensen",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors. Advanced Materials Technologies published by Wiley-VCH GmbH.",

year = "2024",

doi = "10.1002/admt.202301462",

language = "English",

volume = "9",

journal = "Advanced Materials Technologies",

issn = "2365-709X",

publisher = "Wiley-Blackwell",

number = "2",

}

RIS

TY - JOUR

T1 - Label-Free Blood Typing by Raman Spectroscopy and Artificial Intelligence

AU - Jensen, Emil Alstrup

AU - Serhatlioglu, Murat

AU - Uyanik, Cihan

AU - Hansen, Anne Todsen

AU - Puthusserypady, Sadasivan

AU - Dziegiel, Morten Hanefeld

AU - Kristensen, Anders

PY - 2024

Y1 - 2024

N2 - Label-free blood typing by Raman spectroscopy (RS) is demonstrated by training an artificial intelligence (AI) model on 271 blood typed donor whole blood samples. A fused silica micro-capillary flow cell enables fast generation of a large dataset of Raman spectra of individual donors. A combination of resampling methods, machine learning and deep learning is used to classify the ABO blood group, 27 erythrocyte antigens, 4 platelet antigens, regular anti-B titers of blood group A donors, regular anti-A,-B titers of blood group O donors, and ABH-secretor status, from a single Raman spectrum. The average area under the curve value of the ABO classification is 0.91 ± 0.03 and 0.72 ± 0.09, respectively, for the remaining traits. The classification performance of all parameters is discussed in the context of dataset balance and antigen concentration. Post-hoc scalability analysis of the models shows the potential of RS and AI for future applications in transfusion medicine and blood banking.

AB - Label-free blood typing by Raman spectroscopy (RS) is demonstrated by training an artificial intelligence (AI) model on 271 blood typed donor whole blood samples. A fused silica micro-capillary flow cell enables fast generation of a large dataset of Raman spectra of individual donors. A combination of resampling methods, machine learning and deep learning is used to classify the ABO blood group, 27 erythrocyte antigens, 4 platelet antigens, regular anti-B titers of blood group A donors, regular anti-A,-B titers of blood group O donors, and ABH-secretor status, from a single Raman spectrum. The average area under the curve value of the ABO classification is 0.91 ± 0.03 and 0.72 ± 0.09, respectively, for the remaining traits. The classification performance of all parameters is discussed in the context of dataset balance and antigen concentration. Post-hoc scalability analysis of the models shows the potential of RS and AI for future applications in transfusion medicine and blood banking.

KW - blood typing

KW - machine/deep learning

KW - micro-capillary fluidics

KW - precision transfusion medicines

KW - Raman spectroscopy

U2 - 10.1002/admt.202301462

DO - 10.1002/admt.202301462

M3 - Journal article

AN - SCOPUS:85178488219

VL - 9

JO - Advanced Materials Technologies

JF - Advanced Materials Technologies

SN - 2365-709X

IS - 2

M1 - 2301462

ER -

ID: 381056044

Department of Clinical Medicine