Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.18/8767 |
Resumo: | Background and aims: The early diagnosis of familial hypercholesterolaemia is associated with a significant reduction in cardiovascular disease (CVD) risk. While the recent use of statistical and machine learning algorithms has shown promising results in comparison with traditional clinical criteria, when applied to screening of potential FH cases in large cohorts, most studies in this field are developed using a single cohort of patients, which may hamper the application of such algorithms to other populations. In the current study, a logistic regression (LR) based algorithm was developed combining observations from three different national FH cohorts, from Portugal, Brazil and Sweden. Independent samples from these cohorts were then used to test the model, as well as an external dataset from Italy. Methods: The area under the receiver operating characteristics (AUROC) and precision-recall (AUPRC) curves was used to assess the discriminatory ability among the different samples. Comparisons between the LR model and Dutch Lipid Clinic Network (DLCN) clinical criteria were performed by means of McNemar tests, and by the calculation of several operating characteristics. Results: AUROC and AUPRC values were generally higher for all testing sets when compared to the training set. Compared with DLCN criteria, a significantly higher number of correctly classified observations were identified for the Brazilian (p < 0.01), Swedish (p < 0.01), and Italian testing sets (p < 0.01). Higher accuracy (Acc), G mean and F1 score values were also observed for all testing sets. Conclusions: Compared to DLCN criteria, the LR model revealed improved ability to correctly classify observations, and was able to retain a similar number of FH cases, with less false positive retention. Generalization of the LR model was very good across all testing samples, suggesting it can be an effective screening tool if applied to different populations. |
id |
RCAP_6603a518f20941946ab47cdaf582856a |
---|---|
oai_identifier_str |
oai:repositorio.insa.pt:10400.18/8767 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adultsLogistic RegressionDutch Lipid Clinic Network CriteriaValidationFamilial HypercholesterolaemiaDoenças Cardio e Cérebro-vascularesBackground and aims: The early diagnosis of familial hypercholesterolaemia is associated with a significant reduction in cardiovascular disease (CVD) risk. While the recent use of statistical and machine learning algorithms has shown promising results in comparison with traditional clinical criteria, when applied to screening of potential FH cases in large cohorts, most studies in this field are developed using a single cohort of patients, which may hamper the application of such algorithms to other populations. In the current study, a logistic regression (LR) based algorithm was developed combining observations from three different national FH cohorts, from Portugal, Brazil and Sweden. Independent samples from these cohorts were then used to test the model, as well as an external dataset from Italy. Methods: The area under the receiver operating characteristics (AUROC) and precision-recall (AUPRC) curves was used to assess the discriminatory ability among the different samples. Comparisons between the LR model and Dutch Lipid Clinic Network (DLCN) clinical criteria were performed by means of McNemar tests, and by the calculation of several operating characteristics. Results: AUROC and AUPRC values were generally higher for all testing sets when compared to the training set. Compared with DLCN criteria, a significantly higher number of correctly classified observations were identified for the Brazilian (p < 0.01), Swedish (p < 0.01), and Italian testing sets (p < 0.01). Higher accuracy (Acc), G mean and F1 score values were also observed for all testing sets. Conclusions: Compared to DLCN criteria, the LR model revealed improved ability to correctly classify observations, and was able to retain a similar number of FH cases, with less false positive retention. Generalization of the LR model was very good across all testing samples, suggesting it can be an effective screening tool if applied to different populations.Highlights: Early diagnosis of familial hypercholesterolemia is associated with a significant reduction in cardiovascular disease risk; The development of a multi-cohort classification model can allow for better generalization of results; Compared to traditional clinical criteria, accuracy was higher with the developed classification model; Furthermore, sensitivity is not compromised with this model.The current work was supported by the programme Norte2020 (operação NORTE-08-5369-FSE-000018) and by Fundação para a Ciência e Tecnologia (FCT), under the projects UID/MAT/00006/2019 and PTDC/SAU-SER/29180/2017.ElsevierRepositório Científico do Instituto Nacional de SaúdeAlbuquerque, JoãoMedeiros, Ana MargaridaAlves, Ana CatarinaJannes, Cinthia ElimMancina, Rosellina M.Pavanello, ChiaraChora, Joana RitaMombelli, GiulianaCalabresi, LauraPereira, Alexandre da CostaKrieger, José EduardoRomeo, StefanoBourbon, MafaldaAntunes, Marília2023-11-15T12:05:00Z2023-102023-10-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.18/8767engAtherosclerosis. 2023 Oct:383:117314. doi: 10.1016/j.atherosclerosis.2023.117314. Epub 2023 Sep 28.0021-915010.1016/j.atherosclerosis.2023.117314info:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-18T01:30:50Zoai:repositorio.insa.pt:10400.18/8767Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:53:59.669008Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults |
title |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults |
spellingShingle |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults Albuquerque, João Logistic Regression Dutch Lipid Clinic Network Criteria Validation Familial Hypercholesterolaemia Doenças Cardio e Cérebro-vasculares |
title_short |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults |
title_full |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults |
title_fullStr |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults |
title_full_unstemmed |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults |
title_sort |
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults |
author |
Albuquerque, João |
author_facet |
Albuquerque, João Medeiros, Ana Margarida Alves, Ana Catarina Jannes, Cinthia Elim Mancina, Rosellina M. Pavanello, Chiara Chora, Joana Rita Mombelli, Giuliana Calabresi, Laura Pereira, Alexandre da Costa Krieger, José Eduardo Romeo, Stefano Bourbon, Mafalda Antunes, Marília |
author_role |
author |
author2 |
Medeiros, Ana Margarida Alves, Ana Catarina Jannes, Cinthia Elim Mancina, Rosellina M. Pavanello, Chiara Chora, Joana Rita Mombelli, Giuliana Calabresi, Laura Pereira, Alexandre da Costa Krieger, José Eduardo Romeo, Stefano Bourbon, Mafalda Antunes, Marília |
author2_role |
author author author author author author author author author author author author author |
dc.contributor.none.fl_str_mv |
Repositório Científico do Instituto Nacional de Saúde |
dc.contributor.author.fl_str_mv |
Albuquerque, João Medeiros, Ana Margarida Alves, Ana Catarina Jannes, Cinthia Elim Mancina, Rosellina M. Pavanello, Chiara Chora, Joana Rita Mombelli, Giuliana Calabresi, Laura Pereira, Alexandre da Costa Krieger, José Eduardo Romeo, Stefano Bourbon, Mafalda Antunes, Marília |
dc.subject.por.fl_str_mv |
Logistic Regression Dutch Lipid Clinic Network Criteria Validation Familial Hypercholesterolaemia Doenças Cardio e Cérebro-vasculares |
topic |
Logistic Regression Dutch Lipid Clinic Network Criteria Validation Familial Hypercholesterolaemia Doenças Cardio e Cérebro-vasculares |
description |
Background and aims: The early diagnosis of familial hypercholesterolaemia is associated with a significant reduction in cardiovascular disease (CVD) risk. While the recent use of statistical and machine learning algorithms has shown promising results in comparison with traditional clinical criteria, when applied to screening of potential FH cases in large cohorts, most studies in this field are developed using a single cohort of patients, which may hamper the application of such algorithms to other populations. In the current study, a logistic regression (LR) based algorithm was developed combining observations from three different national FH cohorts, from Portugal, Brazil and Sweden. Independent samples from these cohorts were then used to test the model, as well as an external dataset from Italy. Methods: The area under the receiver operating characteristics (AUROC) and precision-recall (AUPRC) curves was used to assess the discriminatory ability among the different samples. Comparisons between the LR model and Dutch Lipid Clinic Network (DLCN) clinical criteria were performed by means of McNemar tests, and by the calculation of several operating characteristics. Results: AUROC and AUPRC values were generally higher for all testing sets when compared to the training set. Compared with DLCN criteria, a significantly higher number of correctly classified observations were identified for the Brazilian (p < 0.01), Swedish (p < 0.01), and Italian testing sets (p < 0.01). Higher accuracy (Acc), G mean and F1 score values were also observed for all testing sets. Conclusions: Compared to DLCN criteria, the LR model revealed improved ability to correctly classify observations, and was able to retain a similar number of FH cases, with less false positive retention. Generalization of the LR model was very good across all testing samples, suggesting it can be an effective screening tool if applied to different populations. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-11-15T12:05:00Z 2023-10 2023-10-01T00:00:00Z |
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://hdl.handle.net/10400.18/8767 |
url |
http://hdl.handle.net/10400.18/8767 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Atherosclerosis. 2023 Oct:383:117314. doi: 10.1016/j.atherosclerosis.2023.117314. Epub 2023 Sep 28. 0021-9150 10.1016/j.atherosclerosis.2023.117314 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/embargoedAccess |
eu_rights_str_mv |
embargoedAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799135138079047680 |