Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.vetpar.2016.12.016 http://hdl.handle.net/11449/173972 |
Resumo: | Quantification of Leishmania infantum load via real-time quantitative polymerase chain reaction (qPCR) in lymph node aspirates is an accurate tool for diagnostics, surveillance and therapeutics follow-up in dogs with leishmaniasis. However, qPCR requires infrastructure and technical training that is not always available commercially or in public services. Here, we used a machine learning technique, namely Radial Basis Artificial Neural Network, to assess whether parasite load could be learned from clinical data (serological test, biochemical markers and physical signs). By comparing 18 different combinations of input clinical data, we found that parasite load can be accurately predicted using a relatively small reference set of 35 naturally infected dogs and 20 controls. In the best case scenario (use of all clinical data), predictions presented no bias or inflation and an accuracy (i.e., correlation between true and predicted values) of 0.869, corresponding to an average error of ±38.2 parasites per unit of volume. We conclude that reasonable estimates of L. infantum load from lymph node aspirates can be obtained from clinical records when qPCR services are not available. |
id |
UNSP_3162aab66bcaa10433c8c90020a6154b |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/173972 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networksCanis lupus familiarisLeishmania spp.Machine learningqPCRQuantification of Leishmania infantum load via real-time quantitative polymerase chain reaction (qPCR) in lymph node aspirates is an accurate tool for diagnostics, surveillance and therapeutics follow-up in dogs with leishmaniasis. However, qPCR requires infrastructure and technical training that is not always available commercially or in public services. Here, we used a machine learning technique, namely Radial Basis Artificial Neural Network, to assess whether parasite load could be learned from clinical data (serological test, biochemical markers and physical signs). By comparing 18 different combinations of input clinical data, we found that parasite load can be accurately predicted using a relatively small reference set of 35 naturally infected dogs and 20 controls. In the best case scenario (use of all clinical data), predictions presented no bias or inflation and an accuracy (i.e., correlation between true and predicted values) of 0.869, corresponding to an average error of ±38.2 parasites per unit of volume. We conclude that reasonable estimates of L. infantum load from lymph node aspirates can be obtained from clinical records when qPCR services are not available.São Paulo State University (Unesp). School of Veterinary Medicine Araçatuba. Department of Clinics Surgery and Animal ReproductionSão Paulo State University (Unesp) School of Agricultural and Veterinarian Sciences Jaboticabal Department of Preventative Veterinary Medicine and Animal ReproductionUSP − Universidade de São Paulo Departamento de Patologia Veterinária Faculdade de Medicina Veterinária e ZootecniaSão Paulo State University (Unesp) School of Veterinary Medicine Araçatuba Department of Support Production and Animal HealthSão Paulo State University (Unesp). School of Veterinary Medicine Araçatuba. Department of Clinics Surgery and Animal ReproductionSão Paulo State University (Unesp) School of Agricultural and Veterinarian Sciences Jaboticabal Department of Preventative Veterinary Medicine and Animal ReproductionSão Paulo State University (Unesp) School of Veterinary Medicine Araçatuba Department of Support Production and Animal HealthUniversidade Estadual Paulista (Unesp)Universidade de São Paulo (USP)Torrecilha, Rafaela Beatriz Pintor [UNESP]Utsunomiya, Yuri Tani [UNESP]Batista, Luís Fábio da SilvaBosco, Anelise Maria [UNESP]Nunes, Cáris Maroni [UNESP]Ciarlini, Paulo César [UNESP]Laurenti, Márcia Dalastra2018-12-11T17:08:34Z2018-12-11T17:08:34Z2017-01-30info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article13-18application/pdfhttp://dx.doi.org/10.1016/j.vetpar.2016.12.016Veterinary Parasitology, v. 234, p. 13-18.1873-25500304-4017http://hdl.handle.net/11449/17397210.1016/j.vetpar.2016.12.0162-s2.0-850070296312-s2.0-85007029631.pdf36139400182995000000-0003-1480-5208Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengVeterinary Parasitology1,275info:eu-repo/semantics/openAccess2024-09-04T19:15:10Zoai:repositorio.unesp.br:11449/173972Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462024-09-04T19:15:10Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks |
title |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks |
spellingShingle |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks Torrecilha, Rafaela Beatriz Pintor [UNESP] Canis lupus familiaris Leishmania spp. Machine learning qPCR |
title_short |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks |
title_full |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks |
title_fullStr |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks |
title_full_unstemmed |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks |
title_sort |
Prediction of lymph node parasite load from clinical data in dogs with leishmaniasis: An application of radial basis artificial neural networks |
author |
Torrecilha, Rafaela Beatriz Pintor [UNESP] |
author_facet |
Torrecilha, Rafaela Beatriz Pintor [UNESP] Utsunomiya, Yuri Tani [UNESP] Batista, Luís Fábio da Silva Bosco, Anelise Maria [UNESP] Nunes, Cáris Maroni [UNESP] Ciarlini, Paulo César [UNESP] Laurenti, Márcia Dalastra |
author_role |
author |
author2 |
Utsunomiya, Yuri Tani [UNESP] Batista, Luís Fábio da Silva Bosco, Anelise Maria [UNESP] Nunes, Cáris Maroni [UNESP] Ciarlini, Paulo César [UNESP] Laurenti, Márcia Dalastra |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade de São Paulo (USP) |
dc.contributor.author.fl_str_mv |
Torrecilha, Rafaela Beatriz Pintor [UNESP] Utsunomiya, Yuri Tani [UNESP] Batista, Luís Fábio da Silva Bosco, Anelise Maria [UNESP] Nunes, Cáris Maroni [UNESP] Ciarlini, Paulo César [UNESP] Laurenti, Márcia Dalastra |
dc.subject.por.fl_str_mv |
Canis lupus familiaris Leishmania spp. Machine learning qPCR |
topic |
Canis lupus familiaris Leishmania spp. Machine learning qPCR |
description |
Quantification of Leishmania infantum load via real-time quantitative polymerase chain reaction (qPCR) in lymph node aspirates is an accurate tool for diagnostics, surveillance and therapeutics follow-up in dogs with leishmaniasis. However, qPCR requires infrastructure and technical training that is not always available commercially or in public services. Here, we used a machine learning technique, namely Radial Basis Artificial Neural Network, to assess whether parasite load could be learned from clinical data (serological test, biochemical markers and physical signs). By comparing 18 different combinations of input clinical data, we found that parasite load can be accurately predicted using a relatively small reference set of 35 naturally infected dogs and 20 controls. In the best case scenario (use of all clinical data), predictions presented no bias or inflation and an accuracy (i.e., correlation between true and predicted values) of 0.869, corresponding to an average error of ±38.2 parasites per unit of volume. We conclude that reasonable estimates of L. infantum load from lymph node aspirates can be obtained from clinical records when qPCR services are not available. |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-01-30 2018-12-11T17:08:34Z 2018-12-11T17:08:34Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.vetpar.2016.12.016 Veterinary Parasitology, v. 234, p. 13-18. 1873-2550 0304-4017 http://hdl.handle.net/11449/173972 10.1016/j.vetpar.2016.12.016 2-s2.0-85007029631 2-s2.0-85007029631.pdf 3613940018299500 0000-0003-1480-5208 |
url |
http://dx.doi.org/10.1016/j.vetpar.2016.12.016 http://hdl.handle.net/11449/173972 |
identifier_str_mv |
Veterinary Parasitology, v. 234, p. 13-18. 1873-2550 0304-4017 10.1016/j.vetpar.2016.12.016 2-s2.0-85007029631 2-s2.0-85007029631.pdf 3613940018299500 0000-0003-1480-5208 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Veterinary Parasitology 1,275 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
13-18 application/pdf |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
repositoriounesp@unesp.br |
_version_ |
1810021365439266816 |