Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal

Detalhes bibliográficos
Autor(a) principal: Portela, Diana 
Data de Publicação: 2023
Outros Autores: Amaral, Rita, Rodrigues, Pedro P. , Freitas, Alberto , Costa, Elísio , Fonseca, João A. , Sousa-Pinto, Bernardo 
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.22/22714
Resumo: Quantifying and dealing with lack of consistency in administrative databases (namely, under-coding) requires tracking patients longitudinally without compromising anonymity, which is often a challenging task. This study aimed to (i) assess and compare different hierarchical clustering methods on the identification of individual patients in an administrative database that does not easily allow tracking of episodes from the same patient; (ii) quantify the frequency of potential under-coding; and (iii) identify factors associated with such phenomena. We analysed the Portuguese National Hospital Morbidity Dataset, an administrative database registering all hospitalisations occurring in Mainland Portugal between 2011–2015. We applied different approaches of hierarchical clustering methods (either isolated or combined with partitional clustering methods), to identify potential individual patients based on demographic variables and comorbidities. Diagnoses codes were grouped into the Charlson an Elixhauser comorbidity defined groups. The algorithm displaying the best performance was used to quantify potential under-coding. A generalised mixed model (GML) of binomial regression was applied to assess factors associated with such potential under-coding. We observed that the hierarchical cluster analysis (HCA) + k-means clustering method with comorbidities grouped according to the Charlson defined groups was the algorithm displaying the best performance (with a Rand Index of 0.99997). We identified potential under-coding in all Charlson comorbidity groups, ranging from 3.5% (overall diabetes) to 27.7% (asthma). Overall, being male, having medical admission, dying during hospitalisation or being admitted at more specific and complex hospitals were associated with increased odds of potential under-coding. We assessed several approaches to identify individual patients in an administrative database and, subsequently, by applying HCA + k-means algorithm, we tracked coding inconsistency and potentially improved data quality. We reported consistent potential under-coding in all defined groups of comorbidities and potential factors associated with such lack of completeness. Our proposed methodological framework could both enhance data quality and act as a reference for other studies relying on databases with similar problems.
id RCAP_5fd7ff69045452b114ef72f369d00baa
oai_identifier_str oai:recipp.ipp.pt:10400.22/22714
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in PortugalData qualityPublic health informaticsMedical records: evaluationHealth information managementQuantifying and dealing with lack of consistency in administrative databases (namely, under-coding) requires tracking patients longitudinally without compromising anonymity, which is often a challenging task. This study aimed to (i) assess and compare different hierarchical clustering methods on the identification of individual patients in an administrative database that does not easily allow tracking of episodes from the same patient; (ii) quantify the frequency of potential under-coding; and (iii) identify factors associated with such phenomena. We analysed the Portuguese National Hospital Morbidity Dataset, an administrative database registering all hospitalisations occurring in Mainland Portugal between 2011–2015. We applied different approaches of hierarchical clustering methods (either isolated or combined with partitional clustering methods), to identify potential individual patients based on demographic variables and comorbidities. Diagnoses codes were grouped into the Charlson an Elixhauser comorbidity defined groups. The algorithm displaying the best performance was used to quantify potential under-coding. A generalised mixed model (GML) of binomial regression was applied to assess factors associated with such potential under-coding. We observed that the hierarchical cluster analysis (HCA) + k-means clustering method with comorbidities grouped according to the Charlson defined groups was the algorithm displaying the best performance (with a Rand Index of 0.99997). We identified potential under-coding in all Charlson comorbidity groups, ranging from 3.5% (overall diabetes) to 27.7% (asthma). Overall, being male, having medical admission, dying during hospitalisation or being admitted at more specific and complex hospitals were associated with increased odds of potential under-coding. We assessed several approaches to identify individual patients in an administrative database and, subsequently, by applying HCA + k-means algorithm, we tracked coding inconsistency and potentially improved data quality. We reported consistent potential under-coding in all defined groups of comorbidities and potential factors associated with such lack of completeness. Our proposed methodological framework could both enhance data quality and act as a reference for other studies relying on databases with similar problems.SAGE JournalsRepositório Científico do Instituto Politécnico do PortoPortela, Diana Amaral, RitaRodrigues, Pedro P. Freitas, Alberto Costa, Elísio Fonseca, João A. Sousa-Pinto, Bernardo 2023-04-12T15:18:14Z2023-02-172023-02-17T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.22/22714engPortela D, Amaral R, Rodrigues PP, et al. Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal. Health Information Management Journal. 2023;0(0). doi:10.1177/183335832211446631833-358310.1177/183335832211446631833-3575info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-04-19T01:47:00Zoai:recipp.ipp.pt:10400.22/22714Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:49:41.549033Repositório 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 Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
title Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
spellingShingle Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
Portela, Diana 
Data quality
Public health informatics
Medical records: evaluation
Health information management
title_short Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
title_full Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
title_fullStr Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
title_full_unstemmed Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
title_sort Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal
author Portela, Diana 
author_facet Portela, Diana 
Amaral, Rita
Rodrigues, Pedro P. 
Freitas, Alberto 
Costa, Elísio 
Fonseca, João A. 
Sousa-Pinto, Bernardo 
author_role author
author2 Amaral, Rita
Rodrigues, Pedro P. 
Freitas, Alberto 
Costa, Elísio 
Fonseca, João A. 
Sousa-Pinto, Bernardo 
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Repositório Científico do Instituto Politécnico do Porto
dc.contributor.author.fl_str_mv Portela, Diana 
Amaral, Rita
Rodrigues, Pedro P. 
Freitas, Alberto 
Costa, Elísio 
Fonseca, João A. 
Sousa-Pinto, Bernardo 
dc.subject.por.fl_str_mv Data quality
Public health informatics
Medical records: evaluation
Health information management
topic Data quality
Public health informatics
Medical records: evaluation
Health information management
description Quantifying and dealing with lack of consistency in administrative databases (namely, under-coding) requires tracking patients longitudinally without compromising anonymity, which is often a challenging task. This study aimed to (i) assess and compare different hierarchical clustering methods on the identification of individual patients in an administrative database that does not easily allow tracking of episodes from the same patient; (ii) quantify the frequency of potential under-coding; and (iii) identify factors associated with such phenomena. We analysed the Portuguese National Hospital Morbidity Dataset, an administrative database registering all hospitalisations occurring in Mainland Portugal between 2011–2015. We applied different approaches of hierarchical clustering methods (either isolated or combined with partitional clustering methods), to identify potential individual patients based on demographic variables and comorbidities. Diagnoses codes were grouped into the Charlson an Elixhauser comorbidity defined groups. The algorithm displaying the best performance was used to quantify potential under-coding. A generalised mixed model (GML) of binomial regression was applied to assess factors associated with such potential under-coding. We observed that the hierarchical cluster analysis (HCA) + k-means clustering method with comorbidities grouped according to the Charlson defined groups was the algorithm displaying the best performance (with a Rand Index of 0.99997). We identified potential under-coding in all Charlson comorbidity groups, ranging from 3.5% (overall diabetes) to 27.7% (asthma). Overall, being male, having medical admission, dying during hospitalisation or being admitted at more specific and complex hospitals were associated with increased odds of potential under-coding. We assessed several approaches to identify individual patients in an administrative database and, subsequently, by applying HCA + k-means algorithm, we tracked coding inconsistency and potentially improved data quality. We reported consistent potential under-coding in all defined groups of comorbidities and potential factors associated with such lack of completeness. Our proposed methodological framework could both enhance data quality and act as a reference for other studies relying on databases with similar problems.
publishDate 2023
dc.date.none.fl_str_mv 2023-04-12T15:18:14Z
2023-02-17
2023-02-17T00:00:00Z
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/10400.22/22714
url http://hdl.handle.net/10400.22/22714
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Portela D, Amaral R, Rodrigues PP, et al. Unsupervised algorithms to identify potential under-coding of secondary diagnoses in hospitalisations databases in Portugal. Health Information Management Journal. 2023;0(0). doi:10.1177/18333583221144663
1833-3583
10.1177/18333583221144663
1833-3575
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv SAGE Journals
publisher.none.fl_str_mv SAGE Journals
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_ 1799131577320472576