Deep learning of HIV field-based rapid tests

Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa...

Full description

Saved in:
Bibliographic Details
Published inNature medicine Vol. 27; no. 7; pp. 1165 - 1170
Main Authors Turbé, Valérian, Herbst, Carina, Mngomezulu, Thobeka, Meshkinfamfard, Sepehr, Dlamini, Nondumiso, Mhlongo, Thembani, Smit, Theresa, Cherepanova, Valeriia, Shimada, Koki, Budd, Jobie, Arsenov, Nestor, Gray, Steven, Pillay, Deenan, Herbst, Kobus, Shahmanesh, Maryam, McKendry, Rachel A.
Format Journal Article
LanguageEnglish
Published New York Nature Publishing Group US 01.07.2021
Nature Publishing Group
Subjects
692/699/255/1901
706/134
AIDS Serodiagnosis - methods
Algorithms
Applications programs
Biomedical and Life Sciences
Biomedicine
Cancer Research
Deep Learning
Diagnosis
Disease control
Field study
HIV
HIV infection
HIV Infections - diagnosis
Human immunodeficiency virus
Humans
Image acquisition
Image classification
Income
Infectious Diseases
Learning algorithms
Letter
Low income groups
Machine learning
Medical imaging
Medical personnel
Medical tests
Metabolic Diseases
Mobile computing
Molecular Medicine
Neurosciences
Quality assurance
Rural Health Services - organization & administration
Sensitivity and Specificity
South Africa
Technology application
Time and Motion Studies
South Africa
United Kingdom
Online AccessGet full text

Cover

Abstract Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans—experienced nurses and newly trained community health worker staff—and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning–enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics 1 , an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections. In a pilot field study conducted in rural South Africa, deep learning algorithms can accurately classify rapid HIV tests as positive or negative, highlighting the potential of deep learning–enabled diagnostics for use in low- and middle-income countries.
AbstractList Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans--experienced nurses and newly trained community health worker staff--and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning-enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics.sup.1, an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections. In a pilot field study conducted in rural South Africa, deep learning algorithms can accurately classify rapid HIV tests as positive or negative, highlighting the potential of deep learning-enabled diagnostics for use in low- and middle-income countries.
Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans--experienced nurses and newly trained community health worker staff--and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning-enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics.sup.1, an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections.
Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here, we use deep learning to classify images of rapid HIV tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral-flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%), compared to traditional visual interpretation by humans -experienced nurses and newly trained community health worker staff - and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning-enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics 1 , for Real-time connectivity, Ease of specimen collection, Affordable, Sensitive, Specific, User-friendly, Rapid, Equipment-free, and Deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support, and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency, and improve patient outcomes and outbreak management of emerging infections.
Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans-experienced nurses and newly trained community health worker staff-and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning-enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics , an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections.
Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans-experienced nurses and newly trained community health worker staff-and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning-enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics1, an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections.
Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans—experienced nurses and newly trained community health worker staff—and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning–enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics 1 , an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections. In a pilot field study conducted in rural South Africa, deep learning algorithms can accurately classify rapid HIV tests as positive or negative, highlighting the potential of deep learning–enabled diagnostics for use in low- and middle-income countries.
Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans—experienced nurses and newly trained community health worker staff—and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning–enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics1, an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections.In a pilot field study conducted in rural South Africa, deep learning algorithms can accurately classify rapid HIV tests as positive or negative, highlighting the potential of deep learning–enabled diagnostics for use in low- and middle-income countries.
Audience Academic
Author McKendry, Rachel A.
Cherepanova, Valeriia
Shahmanesh, Maryam
Mhlongo, Thembani
Turbé, Valérian
Gray, Steven
Mngomezulu, Thobeka
Meshkinfamfard, Sepehr
Shimada, Koki
Arsenov, Nestor
Pillay, Deenan
Herbst, Kobus
Dlamini, Nondumiso
Budd, Jobie
Smit, Theresa
Herbst, Carina
AuthorAffiliation 2 Africa Health Research Institute, K-RITH Tower Building, Nelson R. Mandela Medical School, 719 Umbilo Rd, Umbilo, Durban, 4001, South Africa
3 Department of Computer Science, University College London, Gower St, Bloomsbury, London WC1E 6EA, UK
5 UCL Centre for Advanced Spatial Analysis, Gower Street, London, WC1E 6BT, UK
1 London Centre for Nanotechnology, University College London, 17-19 Gordon Street, London WC1H 0AH, UK
4 Division of Medicine, Rayne Building, University College London, 5 University Street, London, WC1E 6JF, UK
8 Institute for Global Health, University College London, Mortimer Market Centre, off Capper Street, London WC1E 6JB, UK
6 Division of Infection and Immunity, UCL Cruciform Building, University College London, Gower Street, London, WC1E 6BT, UK
7 DSI-MRC South African Population Research Infrastructure Network, 491 Peter Mokaba Ridge Road, Durban, South Africa
AuthorAffiliation_xml – name: 3 Department of Computer Science, University College London, Gower St, Bloomsbury, London WC1E 6EA, UK
– name: 5 UCL Centre for Advanced Spatial Analysis, Gower Street, London, WC1E 6BT, UK
– name: 4 Division of Medicine, Rayne Building, University College London, 5 University Street, London, WC1E 6JF, UK
– name: 1 London Centre for Nanotechnology, University College London, 17-19 Gordon Street, London WC1H 0AH, UK
– name: 6 Division of Infection and Immunity, UCL Cruciform Building, University College London, Gower Street, London, WC1E 6BT, UK
– name: 7 DSI-MRC South African Population Research Infrastructure Network, 491 Peter Mokaba Ridge Road, Durban, South Africa
– name: 2 Africa Health Research Institute, K-RITH Tower Building, Nelson R. Mandela Medical School, 719 Umbilo Rd, Umbilo, Durban, 4001, South Africa
– name: 8 Institute for Global Health, University College London, Mortimer Market Centre, off Capper Street, London WC1E 6JB, UK
Author_xml – sequence: 1
  givenname: Valérian
  orcidid: 0000-0002-4979-197X
  surname: Turbé
  fullname: Turbé, Valérian
  email: v.turbe@ucl.ac.uk
  organization: London Centre for Nanotechnology, University College London
– sequence: 2
  givenname: Carina
  surname: Herbst
  fullname: Herbst, Carina
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School
– sequence: 3
  givenname: Thobeka
  surname: Mngomezulu
  fullname: Mngomezulu, Thobeka
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School
– sequence: 4
  givenname: Sepehr
  surname: Meshkinfamfard
  fullname: Meshkinfamfard, Sepehr
  organization: London Centre for Nanotechnology, University College London
– sequence: 5
  givenname: Nondumiso
  surname: Dlamini
  fullname: Dlamini, Nondumiso
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School
– sequence: 6
  givenname: Thembani
  surname: Mhlongo
  fullname: Mhlongo, Thembani
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School
– sequence: 7
  givenname: Theresa
  surname: Smit
  fullname: Smit, Theresa
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School
– sequence: 8
  givenname: Valeriia
  surname: Cherepanova
  fullname: Cherepanova, Valeriia
  organization: Department of Computer Science, University College London
– sequence: 9
  givenname: Koki
  surname: Shimada
  fullname: Shimada, Koki
  organization: Department of Computer Science, University College London
– sequence: 10
  givenname: Jobie
  orcidid: 0000-0003-3337-6859
  surname: Budd
  fullname: Budd, Jobie
  organization: London Centre for Nanotechnology, University College London, Division of Medicine, University College London
– sequence: 11
  givenname: Nestor
  surname: Arsenov
  fullname: Arsenov, Nestor
  organization: London Centre for Nanotechnology, University College London
– sequence: 12
  givenname: Steven
  orcidid: 0000-0001-7673-9993
  surname: Gray
  fullname: Gray, Steven
  organization: UCL Centre for Advanced Spatial Analysis
– sequence: 13
  givenname: Deenan
  orcidid: 0000-0003-2431-244X
  surname: Pillay
  fullname: Pillay, Deenan
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School, Division of Infection and Immunity, University College London
– sequence: 14
  givenname: Kobus
  orcidid: 0000-0002-5436-9386
  surname: Herbst
  fullname: Herbst, Kobus
  email: Kobus.Herbst@ahri.org
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School, DSI-MRC South African Population Research Infrastructure Network
– sequence: 15
  givenname: Maryam
  orcidid: 0000-0001-7129-8535
  surname: Shahmanesh
  fullname: Shahmanesh, Maryam
  email: m.shahmanesh@ucl.ac.uk
  organization: Africa Health Research Institute, Nelson R. Mandela Medical School, Institute for Global Health, University College London
– sequence: 16
  givenname: Rachel A.
  orcidid: 0000-0003-2018-6829
  surname: McKendry
  fullname: McKendry, Rachel A.
  email: r.a.mckendry@ucl.ac.uk
  organization: London Centre for Nanotechnology, University College London, Division of Medicine, University College London
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34140702$$D View this record in MEDLINE/PubMed
BookMark eNqNkttq3DAQhk1JaQ7tC_SiGAqlhTqVZFmHm0JID1kIBHoIvROyPfIqeKWNZZf27TvbTZO4LKUIIaH55p8R8x9meyEGyLKnlBxTUqo3idNK04Iw3LRUvNAPsgNacVFQSb7t4Z1IVShdif3sMKUrQkhJKv0o2y855UQSdpC9fgewznuwQ_Chy6PLzxaXufPQt0VtE7T5YNe-zUdIY3qcPXS2T_Dk5jzKvn54_-X0rDi_-Lg4PTkvGsn5WIBTZc0d01Q7Jsq2tUI6ydoaa2oGmpWlsLKWkkAlVMUaJaSsrdaKY1DU5VH2dqu7nuoVtA2EcbC9WQ9-ZYefJlpv5pHgl6aL340UlIqKo8DLG4EhXk_Yuln51EDf2wBxSoYhw3Frhejzv9CrOA0Bv4dURRUhVMg7qrM9GB9cxLrNRtScCKEEY0xppIodVAcBsEmcnfP4POOPd_C4Wlj5ZmfCq1kCMiP8GDs7pWQWnz_9P3txOWdf3GOXYPtxmWI_jT6GNAfZFmyGmNIA7nYolJiNKc3WlAZNaX6b0mySnt0f523KHxciUG6BhKHQwXA3g3_I_gJ1yOeq
CitedBy_id crossref_primary_10_1016_j_bios_2024_116325
crossref_primary_10_1038_s41467_023_36017_x
crossref_primary_10_1371_journal_pgph_0001443
crossref_primary_10_2196_37850
crossref_primary_10_1155_2024_5002521
crossref_primary_10_1038_s44222_022_00007_3
crossref_primary_10_1126_science_adh1114
crossref_primary_10_1093_infdis_jiac293
crossref_primary_10_1038_s43856_023_00312_x
crossref_primary_10_1039_D3SD00304C
crossref_primary_10_1039_D2LC00662F
crossref_primary_10_1016_j_xcrm_2022_100784
crossref_primary_10_1038_s41591_021_01624_y
crossref_primary_10_1038_s43856_022_00146_z
crossref_primary_10_3389_fpubh_2024_1334881
crossref_primary_10_1038_s41378_023_00562_8
crossref_primary_10_1038_s41467_023_38104_5
crossref_primary_10_1002_anie_202112031
crossref_primary_10_1016_j_ijid_2024_107011
crossref_primary_10_2196_38533
crossref_primary_10_3390_bios13020298
crossref_primary_10_1371_journal_pgph_0001077
crossref_primary_10_3390_s23146401
crossref_primary_10_1039_D2SD00197G
crossref_primary_10_1016_j_jcvp_2022_100064
crossref_primary_10_1515_labmed_2023_0037
crossref_primary_10_1021_acsami_1c17589
crossref_primary_10_3343_alm_2023_43_5_401
crossref_primary_10_3389_fmicb_2023_1232295
crossref_primary_10_3389_fpubh_2023_1201725
crossref_primary_10_1007_s43681_021_00106_8
crossref_primary_10_1039_D2LC00609J
crossref_primary_10_36930_40340408
crossref_primary_10_1038_s41467_022_35696_2
crossref_primary_10_3390_ai4020024
crossref_primary_10_1002_ange_202112031
crossref_primary_10_37737_ace_22009
Cites_doi 10.1186/1756-0500-5-154
10.1038/nature21056
10.1371/journal.pone.0004351
10.1109/CVPR.2018.00474
10.7448/IAS.20.7.21755
10.1038/s41591-018-0107-6
10.1016/S2352-3018(18)30044-4
10.1038/s41564-018-0295-3
10.1128/CVI.05069-11
10.1158/1078-0432.CCR-18-2495
10.1136/sextrans-2017-053511
10.1186/s12889-018-6120-3
10.1021/nn500614k
10.1007/978-981-15-3383-9_15
10.1093/inthealth/ihv062
10.1038/nature16038
10.1186/s12889-017-4370-0
10.2196/11203
10.1016/j.jcv.2011.09.014
10.1016/j.jviromet.2013.04.003
10.1186/s12889-016-3648-y
10.1136/bmj.39210.582801.BE
10.1371/journal.pone.0066905
10.1038/s41563-019-0339-y
10.1038/s41563-019-0360-1
10.1093/ije/dyaa264
10.1007/s10461-014-0818-8
10.1258/ijsa.2012.011422
10.1007/s12559-016-9404-x
10.1109/ICCV.2019.00140
10.1128/JCM.01761-07
10.1126/scitranslmed.aaa0056
10.3390/s151129569
10.1309/AJCPYWX49IZSQKFS
10.1039/c2lc40235a
10.1126/science.aar6404
ContentType Journal Article
Copyright The Author(s), under exclusive licence to Springer Nature America, Inc. 2021
2021. The Author(s), under exclusive licence to Springer Nature America, Inc.
COPYRIGHT 2021 Nature Publishing Group
Copyright Nature Publishing Group Jul 2021
Copyright_xml – notice: The Author(s), under exclusive licence to Springer Nature America, Inc. 2021
– notice: 2021. The Author(s), under exclusive licence to Springer Nature America, Inc.
– notice: COPYRIGHT 2021 Nature Publishing Group
– notice: Copyright Nature Publishing Group Jul 2021
DBID CGR
CUY
CVF
ECM
EIF
NPM
AAYXX
CITATION
IOV
ISR
3V.
7QG
7QL
7QP
7QR
7T5
7TK
7TM
7TO
7U7
7U9
7X7
7XB
88A
88E
88I
8AO
8FD
8FE
8FH
8FI
8FJ
8FK
8G5
ABUWG
AFKRA
AZQEC
BBNVY
BENPR
BHPHI
C1K
CCPQU
DWQXO
FR3
FYUFA
GHDGH
GNUQQ
GUQSH
H94
HCIFZ
K9.
LK8
M0S
M1P
M2O
M2P
M7N
M7P
MBDVC
P64
PQEST
PQQKQ
PQUKI
PRINS
Q9U
RC3
7X8
5PM
DOI 10.1038/s41591-021-01384-9
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
CrossRef
Gale In Context: Opposing Viewpoints
Gale In Context: Science
ProQuest Central (Corporate)
Animal Behavior Abstracts
Bacteriology Abstracts (Microbiology B)
Calcium & Calcified Tissue Abstracts
Chemoreception Abstracts
Immunology Abstracts
Neurosciences Abstracts
Nucleic Acids Abstracts
Oncogenes and Growth Factors Abstracts
Toxicology Abstracts
Virology and AIDS Abstracts
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Biology Database (Alumni Edition)
Medical Database (Alumni Edition)
Science Database (Alumni Edition)
ProQuest Pharma Collection
Technology Research Database
ProQuest SciTech Collection
ProQuest Natural Science Collection
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
Research Library (Alumni Edition)
ProQuest Central (Alumni)
ProQuest Central
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
Natural Science Collection
Environmental Sciences and Pollution Management
ProQuest One Community College
ProQuest Central Korea
Engineering Research Database
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
Research Library Prep
AIDS and Cancer Research Abstracts
SciTech Premium Collection
ProQuest Health & Medical Complete (Alumni)
Biological Sciences
Health & Medical Collection (Alumni Edition)
Medical Database
Research Library
Science Database
Algology Mycology and Protozoology Abstracts (Microbiology C)
Biological Science Database
Research Library (Corporate)
Biotechnology and BioEngineering Abstracts
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest Central Basic
Genetics Abstracts
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
CrossRef
Research Library Prep
ProQuest Central Student
Oncogenes and Growth Factors Abstracts
ProQuest Central Essentials
Nucleic Acids Abstracts
SciTech Premium Collection
ProQuest Central China
Environmental Sciences and Pollution Management
Health Research Premium Collection
Natural Science Collection
Biological Science Collection
Chemoreception Abstracts
ProQuest Medical Library (Alumni)
Virology and AIDS Abstracts
ProQuest Science Journals (Alumni Edition)
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
Biological Science Database
Neurosciences Abstracts
ProQuest Hospital Collection (Alumni)
Biotechnology and BioEngineering Abstracts
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
Engineering Research Database
ProQuest One Academic
Calcium & Calcified Tissue Abstracts
Technology Research Database
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
Research Library (Alumni Edition)
ProQuest Natural Science Collection
ProQuest Pharma Collection
ProQuest Biology Journals (Alumni Edition)
ProQuest Central
Genetics Abstracts
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Bacteriology Abstracts (Microbiology B)
Algology Mycology and Protozoology Abstracts (Microbiology C)
AIDS and Cancer Research Abstracts
ProQuest Research Library
ProQuest Central Basic
Toxicology Abstracts
ProQuest Science Journals
ProQuest SciTech Collection
ProQuest Medical Library
Animal Behavior Abstracts
Immunology Abstracts
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList





MEDLINE

MEDLINE - Academic

Research Library Prep
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Biology
EISSN 1546-170X
EndPage 1170
ExternalDocumentID A668622289
10_1038_s41591_021_01384_9
34140702
Genre Journal Article
GeographicLocations South Africa
United Kingdom
GeographicLocations_xml – name: South Africa
– name: United Kingdom
GrantInformation_xml – fundername: RCUK | Engineering and Physical Sciences Research Council (EPSRC)
  sequence: 0
  grantid: EP/K031953/1; EP/R00529X/1; EP/K031953/1; EP/R00529X/1; EP/R00529X/1; EP/K031953/1; EP/R00529X/1; EP/K031953/1; EP/R00529X/1
  funderid: https://doi.org/10.13039/501100000266
– fundername: Wellcome Trust (Wellcome)
  sequence: 0
  grantid: 082384/Z/07/Z; 082384/Z/07/Z; 082384/Z/07/Z
  funderid: https://doi.org/10.13039/100004440
– fundername: RCUK | Medical Research Council (MRC)
  sequence: 0
  grantid: MR/P024378/1; MR/P024378/1; MR/P024378/1; MR/P024378/1; MR/P024378/1
  funderid: https://doi.org/10.13039/501100000265
– fundername: Medical Research Council
  grantid: MR/P024378/1
– fundername: Wellcome Trust
  grantid: 082384
– fundername: Wellcome Trust
GroupedDBID ---
.-4
.55
.GJ
0R~
123
1CY
29M
2FS
36B
39C
3O-
3V.
4.4
53G
5BI
5M7
5RE
5S5
70F
7X7
85S
88A
88E
88I
8AO
8FE
8FH
8FI
8FJ
8G5
8R4
8R5
AAEEF
AARCD
AAYOK
AAYZH
AAZLF
ABAWZ
ABCQX
ABDBF
ABDPE
ABEFU
ABJNI
ABLJU
ABOCM
ABUWG
ACBWK
ACGFO
ACGFS
ACGOD
ACIWK
ACMJI
ACPRK
ADBBV
ADFRT
AENEX
AFBBN
AFKRA
AFRAH
AFSHS
AGAYW
AGCDD
AGEZK
AGHTU
AHBCP
AHMBA
AHOSX
AHSBF
AIBTJ
ALFFA
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AMTXH
ARMCB
ASPBG
AVWKF
AXYYD
AZFZN
AZQEC
B0M
BBNVY
BENPR
BHPHI
BKKNO
BPHCQ
BVXVI
CCPQU
CS3
DB5
DU5
DWQXO
EAD
EAP
EBC
EBD
EBS
EE.
EJD
EMB
EMK
EMOBN
EPL
ESX
EXGXG
F5P
FEDTE
FQGFK
FSGXE
FYUFA
GNUQQ
GUQSH
GX1
HCIFZ
HMCUK
HVGLF
HZ~
IAO
IEA
IH2
IHR
IHW
INH
INR
IOF
IOV
ISR
ITC
J5H
L7B
LGEZI
LK8
LOTEE
M0L
M1P
M2O
M2P
M7P
MK0
N9A
NADUK
NNMJJ
NXXTH
O9-
ODYON
P2P
PQQKQ
PROAC
PSQYO
Q2X
RIG
RNS
RNT
RNTTT
RVV
SHXYY
SIXXV
SJN
SNYQT
SV3
TAE
TAOOD
TBHMF
TDRGL
TSG
TUS
UKHRP
UQL
X7M
XJT
YHZ
ZGI
~8M
CGR
CUY
CVF
ECM
EIF
NPM
AAYXX
CITATION
AAEXX
ABEEJ
ABVXF
ADZGE
AADEA
7QG
7QL
7QP
7QR
7T5
7TK
7TM
7TO
7U7
7U9
7XB
8FD
8FK
C1K
FR3
H94
K9.
M7N
MBDVC
P64
PQEST
PQUKI
PRINS
Q9U
RC3
7X8
5PM
ID FETCH-LOGICAL-c744t-ef83b4f2919f263dda67f72db40792e92336a7b770e56852c8677ba9984e926b3
IEDL.DBID 7X7
ISSN 1078-8956
IngestDate Tue Sep 17 21:18:02 EDT 2024
Fri Dec 06 00:25:24 EST 2024
Tue Dec 17 13:44:31 EST 2024
Tue Nov 19 20:48:25 EST 2024
Thu Nov 14 20:56:07 EST 2024
Tue Nov 12 23:28:28 EST 2024
Thu Aug 01 20:12:36 EDT 2024
Thu Aug 01 20:08:06 EDT 2024
Tue Aug 20 22:13:37 EDT 2024
Fri Dec 06 04:42:52 EST 2024
Sat Nov 02 12:20:34 EDT 2024
Fri Dec 13 01:25:21 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
License 2021. The Author(s), under exclusive licence to Springer Nature America, Inc.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c744t-ef83b4f2919f263dda67f72db40792e92336a7b770e56852c8677ba9984e926b3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-5436-9386
0000-0003-2018-6829
0000-0002-4979-197X
0000-0003-2431-244X
0000-0001-7129-8535
0000-0001-7673-9993
0000-0003-3337-6859
OpenAccessLink https://www.nature.com/articles/s41591-021-01384-9.pdf
PMID 34140702
PQID 2551800167
PQPubID 33975
PageCount 6
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_7611654
proquest_miscellaneous_2543454398
proquest_journals_2551800167
gale_infotracmisc_A668622289
gale_infotracgeneralonefile_A668622289
gale_infotracacademiconefile_A668622289
gale_incontextgauss_ISR_A668622289
gale_incontextgauss_IOV_A668622289
gale_healthsolutions_A668622289
crossref_primary_10_1038_s41591_021_01384_9
pubmed_primary_34140702
springer_journals_10_1038_s41591_021_01384_9
PublicationCentury 2000
PublicationDate 2021-07-01
PublicationDateYYYYMMDD 2021-07-01
PublicationDate_xml – month: 07
  year: 2021
  text: 2021-07-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
– name: United States
PublicationTitle Nature medicine
PublicationTitleAbbrev Nat Med
PublicationTitleAlternate Nat Med
PublicationYear 2021
Publisher Nature Publishing Group US
Nature Publishing Group
Publisher_xml – sequence: 0
  name: Nature Publishing Group US
– sequence: 0
  name: Nature Publishing Group
– name: Nature Publishing Group
References CC Johnson (1384_CR16) 2017; 20
1384_CR40
J De Fauw (1384_CR22) 2018; 24
T Crucitti (1384_CR14) 2011; 18
KJ Land (1384_CR1) 2019; 4
S Baveewo (1384_CR13) 2012; 5
1384_CR3
1384_CR2
EG Martin (1384_CR8) 2011; 52
FJ Louis (1384_CR11) 2013; 140
T Laksanasopin (1384_CR33) 2015; 7
N Zeng (1384_CR27) 2016; 8
TC Witzel (1384_CR31) 2017; 17
AP Nsabimana (1384_CR32) 2018; 4
D Gareta (1384_CR41) 2021; 50
1384_CR25
L-T Allan-Blitz (1384_CR35) 2018; 94
RM Galiwango (1384_CR10) 2013; 192
1384_CR26
PJ García (1384_CR18) 2013; 8
M Doan (1384_CR20) 2019; 18
Y Xu (1384_CR23) 2019; 25
M Neuman (1384_CR29) 2018; 18
B Tegbaru (1384_CR15) 2007; 45
KM Learmonth (1384_CR17) 2008; 46
C Figueroa (1384_CR5) 2018; 5
A Carrio (1384_CR28) 2015; 15
DB Klarkowski (1384_CR6) 2009; 4
CRH Aicken (1384_CR30) 2016; 16
RH Gray (1384_CR7) 2007; 335
R Sacks (1384_CR19) 2012; 23
O Mudanyali (1384_CR34) 2012; 12
A Esteva (1384_CR21) 2017; 542
F Cham (1384_CR9) 2012; 1
AC Ghani (1384_CR4) 2015; 528
RB Peck (1384_CR12) 2014; 18
1384_CR36
1384_CR37
1384_CR38
D Silver (1384_CR24) 2018; 362
1384_CR39
References_xml – volume: 5
  year: 2012
  ident: 1384_CR13
  publication-title: BMC Res. Notes
  doi: 10.1186/1756-0500-5-154
  contributor:
    fullname: S Baveewo
– volume: 542
  start-page: 115
  year: 2017
  ident: 1384_CR21
  publication-title: Nature
  doi: 10.1038/nature21056
  contributor:
    fullname: A Esteva
– volume: 4
  start-page: e4351
  year: 2009
  ident: 1384_CR6
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0004351
  contributor:
    fullname: DB Klarkowski
– ident: 1384_CR38
  doi: 10.1109/CVPR.2018.00474
– volume: 20
  year: 2017
  ident: 1384_CR16
  publication-title: J. Int. AIDS Soc.
  doi: 10.7448/IAS.20.7.21755
  contributor:
    fullname: CC Johnson
– volume: 24
  start-page: 1342
  year: 2018
  ident: 1384_CR22
  publication-title: Nat. Med.
  doi: 10.1038/s41591-018-0107-6
  contributor:
    fullname: J De Fauw
– volume: 5
  start-page: e277
  year: 2018
  ident: 1384_CR5
  publication-title: Lancet HIV
  doi: 10.1016/S2352-3018(18)30044-4
  contributor:
    fullname: C Figueroa
– volume: 4
  start-page: 46
  year: 2019
  ident: 1384_CR1
  publication-title: Nat. Microbiol.
  doi: 10.1038/s41564-018-0295-3
  contributor:
    fullname: KJ Land
– volume: 18
  start-page: 1480–1485
  year: 2011
  ident: 1384_CR14
  publication-title: Clin. Vaccine Immunol.
  doi: 10.1128/CVI.05069-11
  contributor:
    fullname: T Crucitti
– volume: 25
  start-page: 3266
  year: 2019
  ident: 1384_CR23
  publication-title: Clin. Cancer Res.
  doi: 10.1158/1078-0432.CCR-18-2495
  contributor:
    fullname: Y Xu
– volume: 94
  start-page: 589
  year: 2018
  ident: 1384_CR35
  publication-title: Sex. Transm. Infect.
  doi: 10.1136/sextrans-2017-053511
  contributor:
    fullname: L-T Allan-Blitz
– volume: 18
  year: 2018
  ident: 1384_CR29
  publication-title: BMC Public Health
  doi: 10.1186/s12889-018-6120-3
  contributor:
    fullname: M Neuman
– ident: 1384_CR36
  doi: 10.1021/nn500614k
– ident: 1384_CR39
  doi: 10.1007/978-981-15-3383-9_15
– ident: 1384_CR3
  doi: 10.1093/inthealth/ihv062
– ident: 1384_CR37
– volume: 528
  start-page: S50
  year: 2015
  ident: 1384_CR4
  publication-title: Nature
  doi: 10.1038/nature16038
  contributor:
    fullname: AC Ghani
– volume: 17
  year: 2017
  ident: 1384_CR31
  publication-title: BMC Public Health
  doi: 10.1186/s12889-017-4370-0
  contributor:
    fullname: TC Witzel
– volume: 4
  start-page: e11203
  year: 2018
  ident: 1384_CR32
  publication-title: JMIR Public Health Surveill.
  doi: 10.2196/11203
  contributor:
    fullname: AP Nsabimana
– volume: 52
  start-page: S11
  year: 2011
  ident: 1384_CR8
  publication-title: J. Clin. Virol.
  doi: 10.1016/j.jcv.2011.09.014
  contributor:
    fullname: EG Martin
– volume: 192
  start-page: 25
  year: 2013
  ident: 1384_CR10
  publication-title: J. Virol. Methods
  doi: 10.1016/j.jviromet.2013.04.003
  contributor:
    fullname: RM Galiwango
– ident: 1384_CR26
– volume: 16
  year: 2016
  ident: 1384_CR30
  publication-title: BMC Public Health
  doi: 10.1186/s12889-016-3648-y
  contributor:
    fullname: CRH Aicken
– volume: 335
  start-page: 188
  year: 2007
  ident: 1384_CR7
  publication-title: Brit. Med. J.
  doi: 10.1136/bmj.39210.582801.BE
  contributor:
    fullname: RH Gray
– volume: 8
  start-page: e66905
  year: 2013
  ident: 1384_CR18
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0066905
  contributor:
    fullname: PJ García
– volume: 18
  start-page: 414
  year: 2019
  ident: 1384_CR20
  publication-title: Nat. Mater.
  doi: 10.1038/s41563-019-0339-y
  contributor:
    fullname: M Doan
– ident: 1384_CR25
  doi: 10.1038/s41563-019-0360-1
– volume: 50
  start-page: 33
  year: 2021
  ident: 1384_CR41
  publication-title: Int. J. Epidemiol.
  doi: 10.1093/ije/dyaa264
  contributor:
    fullname: D Gareta
– ident: 1384_CR2
– volume: 18
  start-page: 422
  year: 2014
  ident: 1384_CR12
  publication-title: AIDS Behav.
  doi: 10.1007/s10461-014-0818-8
  contributor:
    fullname: RB Peck
– volume: 1
  start-page: 39
  year: 2012
  ident: 1384_CR9
  publication-title: Afr. J. Lab. Med.
  contributor:
    fullname: F Cham
– volume: 23
  start-page: 644
  year: 2012
  ident: 1384_CR19
  publication-title: Int. J. STD AIDS
  doi: 10.1258/ijsa.2012.011422
  contributor:
    fullname: R Sacks
– volume: 8
  start-page: 684
  year: 2016
  ident: 1384_CR27
  publication-title: Cogn. Comput.
  doi: 10.1007/s12559-016-9404-x
  contributor:
    fullname: N Zeng
– ident: 1384_CR40
  doi: 10.1109/ICCV.2019.00140
– volume: 45
  start-page: 293
  year: 2007
  ident: 1384_CR15
  publication-title: Ethiop. Med. J.
  contributor:
    fullname: B Tegbaru
– volume: 46
  start-page: 1692
  year: 2008
  ident: 1384_CR17
  publication-title: J. Clin. Microbiol.
  doi: 10.1128/JCM.01761-07
  contributor:
    fullname: KM Learmonth
– volume: 7
  start-page: 273re1
  year: 2015
  ident: 1384_CR33
  publication-title: Sci. Transl. Med.
  doi: 10.1126/scitranslmed.aaa0056
  contributor:
    fullname: T Laksanasopin
– volume: 15
  start-page: 29569
  year: 2015
  ident: 1384_CR28
  publication-title: Sensors (Basel)
  doi: 10.3390/s151129569
  contributor:
    fullname: A Carrio
– volume: 140
  start-page: 867
  year: 2013
  ident: 1384_CR11
  publication-title: Am. J. Clin. Pathol.
  doi: 10.1309/AJCPYWX49IZSQKFS
  contributor:
    fullname: FJ Louis
– volume: 12
  start-page: 2678–2686
  year: 2012
  ident: 1384_CR34
  publication-title: Lab Chip
  doi: 10.1039/c2lc40235a
  contributor:
    fullname: O Mudanyali
– volume: 362
  start-page: 1140
  year: 2018
  ident: 1384_CR24
  publication-title: Science
  doi: 10.1126/science.aar6404
  contributor:
    fullname: D Silver
SSID ssj0003059
Score 2.6105907
Snippet Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been...
SourceID pubmedcentral
proquest
gale
crossref
pubmed
springer
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 1165
SubjectTerms 692/699/255/1901
706/134
AIDS Serodiagnosis - methods
Algorithms
Applications programs
Biomedical and Life Sciences
Biomedicine
Cancer Research
Deep Learning
Diagnosis
Disease control
Field study
HIV
HIV infection
HIV Infections - diagnosis
Human immunodeficiency virus
Humans
Image acquisition
Image classification
Income
Infectious Diseases
Learning algorithms
Letter
Low income groups
Machine learning
Medical imaging
Medical personnel
Medical tests
Metabolic Diseases
Mobile computing
Molecular Medicine
Neurosciences
Quality assurance
Rural Health Services - organization & administration
Sensitivity and Specificity
South Africa
Technology application
Time and Motion Studies
Title Deep learning of HIV field-based rapid tests
URI https://link.springer.com/article/10.1038/s41591-021-01384-9
https://www.ncbi.nlm.nih.gov/pubmed/34140702
https://www.proquest.com/docview/2551800167
https://search.proquest.com/docview/2543454398
https://pubmed.ncbi.nlm.nih.gov/PMC7611654
Volume 27
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Nb9QwEB1BKxAXBOUrUEpACA7UauI4dnxCu9DVFqkLKrTam5U4ztJLsjS7B_49Y8ebkhUgDlEOfpGS8YxnJh6_AXgdsVjHhicEMy9KWGYkKSSTJNJCM6nRATregtMZn56zT_N07n-4tb6scrMmuoW6bLT9R35ELXWYK5p_v_xBbNcou7vqW2jchN2YoitHfRbzPuGyuiy7msOMZJgI-EMzUZIdtei4bM0Ptcl0kjEiB45pe3n-zT9t105ubaA6vzS5B3d9QBmOOg24DzdMvQe3uhaTP_fg9qnfPH8Ahx-NWYa-TcQibKpwenIRuhI2Yp1ZGV7ly8syxOBz1T6E88nxtw9T4pslEC0YWxFTZUnBKipjWVGelGXORSVoWWDGJqnBOC7huSiEiEzKs5RqS2RX5JhtMRzkRfIIduqmNk8g5Ak-F-Uiz1PJqrTCpCcVJc51LFMdV2kA7zaSUsuOE0O5vewkU51cFcpVObkqGcALK0zVnevsDUqNuD2cQjHhC-CVQ1g6itrWuyzydduqk88X_wH6ejYAvfWgqsHZ0bk_Y4DfZWmuBsg3A-SiI_n-E3B_AETr08PhjY4ob_2tutbVAF72w_ZJW9FWm2ZtMSxheMksgMedSvXCxMgCZy2iAYiBsvUAywk-HKkvvztucMEtnxIL4HCjltev9fc5evrvr3gGd6izFFulvA87q6u1eY6x2Ko4cAZ3ALujyXg8w_v4ePbl7BcZ6S0H
link.rule.ids 230,314,780,784,885,12056,21388,27924,27925,31719,31720,33744,33745,43310,43805,73745,74302
linkProvider ProQuest
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB7BVjwuCMqjgUIDQnCgVhPbseMTKtBqF7oLKm3Vm5WHs-0lWZrdA_-esePdkhUgDjn5s5SMZzwz8fgbgNcRj4vYCEYw86KEp0aRXHFFokIWXBXoAB1vwXgihqf883ly7n-4tb6scrknuo26bAr7j3yPWuowVzT_fvaD2K5R9nTVt9C4CRuWOT0ZwMaHg8m349VejNqsuqrDlKSYCvhrMxFL91p0Xbbqh9p0mqWcqJ5rWt-gf_NQ69WTa0eozjMd3od7PqQM9zsdeAA3TL0Jt7omkz834fbYH58_hN1PxsxC3yhiGjZVOBydha6IjVh3VoZX2eyyDDH8nLeP4PTw4OTjkPh2CaSQnM-JqVKW84qqWFVUsLLMhKwkLXPM2RQ1GMkxkclcysgkIk1oYans8gzzLY6DImePYVA3tdmCUDCcF2UyyxLFq6TCtCeRJa52rJIirpIA3i0lpWcdK4Z2p9ks1Z1cNcpVO7lqFcCOFabubnauTErvC3s9hWLKF8Arh7CEFLWteJlmi7bVo69n_wH6ftwDvfWgqsHVKTJ_ywC_yxJd9ZBveshpR_P9J-B2D4j2V_SHlzqivf23-lpbA3i5GrYzbU1bbZqFxXDG8VFpAE86lVoJE2MLXLWIBiB7yrYCWFbw_kh9eeHYwaWwjEo8gN2lWl6_1t_X6Om_v2IH7gxPxkf6aDT58gzuUmc1tmZ5Gwbzq4V5jpHZPH_hze8XqPsuRw
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3Nb9MwFH-CTkxcEIyvwGABITgwq4ntxPEJDbaqBVamwabdrHzYZZe0LO2B_55nx81IBYhDT36Rkvf96p9_BngV8biMdcoITl6U8ExLUkguSVSKkssSC6DjLTiepuMz_vEiufD4p8bDKtc50SXqal7a_8iH1FKHOdD80HhYxMnh6N3iB7E3SNmdVn-dxk3YwqoY0QFsvT-anpx2eRk9W7YIxIxkOBb4IzQRy4YNljGLAKJ2tGYZJ7JXpjaT9W_VahNJubGd6qrU6C7c8e1leND6wz24oesduNVeOPlzB7aP_Vb6fdg_1HoR-ksjZuHchOPJeegAbcSWtiq8yheXVYit6LJ5AGejo28fxsRfnUBKwfmSaJOxghsqY2loyqoqT4URtCpwfpNUY1fH0lwUQkQ6SbOElpbWrshx9uK4mBbsIQzqea0fQ5gyfC7KRZ4nkpvE4AiUiAotH8ukjE0SwNu1ptSiZchQbmebZarVq0K9KqdXJQPYs8pU7SnPLrzUQWqPqlAc_wJ46SQsOUVtzTzLV02jJl_O_0Po62lP6I0XMnO0Tpn7Ewf4XZb0qif5uic5aym__yS42xPEWCz7y2sfUT4XNOracwN40S3bJy2-rdbzlZXhjONPZgE8al2qUyb2GWi1iAYges7WCViG8P5KffndMYWL1LIr8QD21255_Vp_t9GTf3_FHmxj5KnPk-mnp3CbuqCx8OVdGCyvVvoZNmnL4rmPvl9J8zJ0
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+learning+of+HIV+field-based+rapid+tests&rft.jtitle=Nature+medicine&rft.date=2021-07-01&rft.pub=Nature+Publishing+Group&rft.issn=1078-8956&rft.eissn=1546-170X&rft.volume=27&rft.issue=7&rft.spage=1165&rft.epage=1170&rft_id=info:doi/10.1038%2Fs41591-021-01384-9&rft.externalDBID=HAS_PDF_LINK
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1078-8956&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1078-8956&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1078-8956&client=summon