AMAna Cláudia Medeiros-De-Souza

Ana Cláudia Medeiros-De-Souza

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ana Cláudia Medeiros-De-Souza has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Machine learning-based record linkage for brazilian health databases validated in Espírito Santo

    by Daniel Scaldaferri Lages, Thayna Karoline Sousa Silva, Patricia Bartholomay Oliveira, Dayan Carvalho Ramos Salles de Oliveira, Gustavo Cezar Wagner Leandro, David José Ferreira da Silva, Letícia de Oliveira Cardoso, Naíza Nayla Bandeira de Sá, Paula Carvalho de Freitas, Ana Claudia Medeiros-De-Souza

    A machine learning–based record linkage approach was developed within the TRAUMA project to support the integration of Brazilian Unified Health System (SUS) information systems. However, evidence comparing traditional linkage approaches with supervised machine learning models in large health datasets remains limited. This study evaluated the TRAUMA linkage method and compared it with CIDACS-RL, a widely used probabilistic linkage tool in Brazil. This methodological validation study used records from the Mortality Information System (SIM), Hospital Information System (SIH-SUS), Notifiable Diseases Information System (Sinan), and e-SUS Health Surveillance (e-SUS VS) from Espírito Santo, Brazil, between July 2018 and June 2025. Candidate pairs were generated through a multi-pass blocking strategy. The proposed method incorporated supervised machine learning to automate the classification of uncertain record pairs that would otherwise require manual review. A total of 106,363 labelled record pairs were used for model development and testing. Six machine learning algorithms were evaluated using sensitivity, specificity, precision, F1-score, and ROC-AUC. The best-performing algorithm was incorporated into the TRAUMA framework and compared with CIDACS-RL using a validated gold-standard dataset of 11,662 record pairs. LightGBM achieved the best performance. In the test dataset, the model obtained an ROC-AUC of 0.99996, sensitivity of 0.99731, precision of 0.99464, F1-score of 0.99597, and specificity of 0.99895. Performance remained stable in independent validation (ROC-AUC = 0.99988; F1-score = 0.99252). SHAP analysis identified date-of-birth variables and Jaro–Winkler and Levenshtein similarity measures as key predictors. Compared with CIDACS-RL, TRAUMA showed higher sensitivity, F1-score, and specificity estimates, with similar precision, and recovered more reference links. Both approaches demonstrated high performance for record linkage in administrative health databases. TRAUMA showed higher estimates of sensitivity, F1-score, and specificity while maintaining high precision and recovering more links contained in the reference dataset. These findings support both approaches as robust record linkage solutions, with the observed differences interpreted descriptively rather than as evidence of statistical superiority.

  • Open Access

    Effects of Injury Registry Data on Policymaking, Hospitalizations, and Mortality: Systematic Review

    by Ana Cláudia Medeiros-De-Souza, Luana Emanuelly Sinhori Lopes, Tayna Felicissimo Gomes de Souza Bandeira, Lucas Reis Correia, Naiza Nayla Bandeira de Sá, Bruno Zocca de Oliveira

    Background: The Brazilian project, launched in 2021, aims to establish a nationwide injury registry that systematically collects detailed information on incidents and individuals across the country, regardless of injury severity. The registry integrates information from prehospital and hospital care, various health systems lacking interoperability, and data from sectors such as firefighters and police. Its primary aim is to enhance health surveillance by providing timely, high-quality information that guides prevention strategies and informs policymaking. In addition, the project seeks to reduce morbidity and mortality associated with injuries. Objective: This study aimed to investigate the effects of injury registry data on policymaking, hospitalization rates or duration, and mortality. Methods: The systematic review followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, with a protocol registered in PROSPERO (International Prospective Register of Systematic Reviews, CRD42023481528). A total of 5 databases were searched in November 2023, with an update conducted in March 2024, incorporating reference lists from the studies included. Two reviewers independently screened records, extracted data, and assessed methodological quality using the Newcastle-Ottawa Scale, resolving disagreements with a third reviewer. Studies were eligible if they reported results related to the implementation and use of injury or trauma registry data for at least one outcome of interest, while those based on other sources were excluded. Synthesis of findings was presented in tables, and the observed results were reported as number or percentage differences. Results: Out of 9100 studies retrieved, 3951 were excluded due to duplication, leaving 5149 for selection, with 15 full texts reviewed. Only 5 studies met the inclusion criteria, highlighting a notable scarcity of research on the effects or results of registry data on injury outcomes. It is important to note that the studies included reflect correlations rather than causalities, and there are currently no publications on impact. The findings suggest that injury and trauma registries have the potential to inform policymaking, which can lead to enhanced health outcomes. One study noted a 3-day reduction in intensive care unit stay (from 16 to 13 days; P<.05) and a 4% reduction in expected hospital mortality (from 17.5% to 21.5%) for patients with an Injury Severity Score ≥16, while another showed a 42% annual decrease in traffic injury hospital admissions (from 45 to 16). Significant methodological heterogeneity and the small number of studies limited the feasibility of a meta-analysis. Conclusions: Establishing an injury registry in Brazil presents a significant opportunity to enhance health outcomes through informed policymaking. While it is crucial to set appropriate expectations regarding its effects on morbidity and mortality, particularly concerning the causality and transportability of the findings to the Brazilian context, its role in facilitating preventive measures and improving surveillance capabilities remains valuable.

  • Open Access

    Effects of Injury Registry Data on Policy Making, Hospitalizations, and Mortality: Protocol for a Systematic Review and Meta-Analysis

    by Ana Cláudia Medeiros-De-Souza, Luana Emanuelly Sinhori Lopes, Bruno Zocca de Oliveira, Edna Terezinha Rother, Lucas Reis Correia

    Background: Initiated in 2021, a Brazilian project aims to establish a national injury registry, compiling comprehensive data on events and individuals across the country, irrespective of injury severity. The registry integrates information from prehospital and hospital care, diverse health systems lacking interoperability, and sectors such as firefighters and the police. Its primary goal is to enhance health surveillance by providing timely, high-quality information, guiding prevention strategies, and informing policy making. The project still aims to reduce long-term morbidity and mortality associated with injuries. Objective: A knowledge gap remains regarding the effects of injury registries in relation to policies and injury outcomes. This protocol outlines a systematic review and meta-analysis to answer “What is the effect of implementation and use of injury registry data on policy making, hospitalization, and mortality?” Methods: The systematic review follows PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, focusing on studies reporting results related to the implementation and use of injury registries, including trauma registries. Outcomes of interest include policy making, hospitalization rates or duration, and mortality. Registries within well-defined administrative boundaries will be included. Data will be collected from PubMed, Embase, Scopus, Web of Science, Lilacs, and references. Records will be independently screened by 2 reviewers, with any disagreements resolved through arbitration by a third reviewer. Homogeneous studies, with 3 or more evaluating the same outcome, may undergo meta-analysis. Subgroup analyses by registry type, injury groups, and other selected variables of interest will be conducted. Sensitivity analysis, risk of bias assessment, publication bias evaluation, and quality appraisal will also be performed. Results: This systematic review will run from November 2023 to June 2024. No identical review was found. Search strategies were finalized, the bibliographic search started, duplicates were eliminated, and title and abstract screening began. Of 35 studies retrieved, 85 were excluded due to duplication, leaving 50 for selection. Conclusions: This study is timely, aligning with ongoing national efforts to implement an injury registry. By synthesizing available evidence, we will identify the potential of injury registries to guide the decisions of Brazilian policy makers. Trial Registration: PROSPERO CRD42023481528; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=481528 International Registered Report Identifier (IRRID): PRR1-10.2196/55029


  • Open Access

    Effects of Injury Registry Data on Policymaking, Hospitalizations, and Mortality: A Systematic Review (Preprint)

    by Ana Cláudia Medeiros-De-Souza, Luana Emanuelly Sinhori Lopes, Tayna Felicissimo Gomes de Souza Bandeira, Lucas Reis Correia, Naiza Nayla Bandeira de Sá, Bruno Zocca de Oliveira

    BACKGROUND Initiated in 2021, a Brazilian project has the objective of establishing a national injury registry that compiles comprehensive data on events and individuals nationwide, regardless of injury severity. The registry integrates information from pre-hospital and hospital care, various health systems lacking interoperability, and data from sectors such as firefighters and police. Its primary aim is to enhance health surveillance by providing timely, high-quality information that guides prevention strategies and informs policymaking. Additionally, the project seeks to reduce morbidity and mortality associated with injuries. OBJECTIVE This study investigates the effects of injury registry data on policymaking, hospitalization rates or duration, and mortality. METHODS The systematic review followed PRISMA guidelines, with a protocol registered in PROSPERO. Five databases were searched in November 2023, with an update conducted in March 2024, incorporating reference lists from the studies included. Two reviewers independently screened records, extracted data, and assessed methodological quality using the Newcastle-Ottawa Scale (NOS), resolving disagreements with a third reviewer. Studies were eligible if they reported results related to the implementation and use of injury or trauma registry data for at least one outcome of interest, while those based on other sources were excluded. Synthesis of results was presented in tables, and the observed effects were reported as number or percentage differences. RESULTS Out of 9,100 studies retrieved, 3,951 were excluded due to duplication, leaving 5,149 for selection, with 15 full texts reviewed. Only five studies met the inclusion criteria, highlighting a notable scarcity of research on the effects of registry data on injury outcomes. It's important to note that the studies included reflect correlations rather than causalities, and there are currently no publications on impact. The findings suggest that injury and trauma registries positively influence policymaking, which, in turn, enhances health outcomes. One study noted a 3-day reduction in intensive care unit stay and a 4.1% reduction in expected hospital mortality (from 22.8% to 18.7%) for patients with an Injury Severity Score (ISS) ≥ 16, while another showed a 42% annual decrease in traffic injury hospital admissions (from 45 to 16). Significant methodological heterogeneity and the small number of studies limited the feasibility of a meta-analysis. CONCLUSIONS Establishing an injury registry in Brazil presents a significant opportunity to enhance health outcomes through informed policymaking. While the direct effects on morbidity and mortality may not be immediately evident, the registry's role in facilitating preventive measures and improving surveillance capabilities is invaluable.

  • Open Access

    Effects of Injury Registry Data on Policy Making, Hospitalizations, and Mortality: Protocol for a Systematic Review and Meta-Analysis (Preprint)

    by Ana Cláudia Medeiros-De-Souza, Luana Emanuelly Sinhori Lopes, Bruno Zocca de Oliveira, Edna Terezinha Rother, Lucas Reis Correia

    BACKGROUND Initiated in 2021, a Brazilian project aims to establish a national injury registry, compiling comprehensive data on events and individuals across the country, irrespective of injury severity. The registry integrates information from prehospital and hospital care, diverse health systems lacking interoperability, and sectors such as firefighters and the police. Its primary goal is to enhance health surveillance by providing timely, high-quality information, guiding prevention strategies, and informing policy making. The project still aims to reduce long-term morbidity and mortality associated with injuries. OBJECTIVE A knowledge gap remains regarding the effects of injury registries in relation to policies and injury outcomes. This protocol outlines a systematic review and meta-analysis to answer “What is the effect of implementation and use of injury registry data on policy making, hospitalization, and mortality?” METHODS The systematic review follows PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, focusing on studies reporting results related to the implementation and use of injury registries, including trauma registries. Outcomes of interest include policy making, hospitalization rates or duration, and mortality. Registries within well-defined administrative boundaries will be included. Data will be collected from PubMed, Embase, Scopus, Web of Science, Lilacs, and references. Records will be independently screened by 2 reviewers, with any disagreements resolved through arbitration by a third reviewer. Homogeneous studies, with 3 or more evaluating the same outcome, may undergo meta-analysis. Subgroup analyses by registry type, injury groups, and other selected variables of interest will be conducted. Sensitivity analysis, risk of bias assessment, publication bias evaluation, and quality appraisal will also be performed. RESULTS This systematic review will run from November 2023 to June 2024. No identical review was found. Search strategies were finalized, the bibliographic search started, duplicates were eliminated, and title and abstract screening began. Of 35 studies retrieved, 85 were excluded due to duplication, leaving 50 for selection. CONCLUSIONS This study is timely, aligning with ongoing national efforts to implement an injury registry. By synthesizing available evidence, we will identify the potential of injury registries to guide the decisions of Brazilian policy makers. CLINICALTRIAL PROSPERO CRD42023481528; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=481528 INTERNATIONAL REGISTERED REPORT PRR1-10.2196/55029


  • Open Access

    Registros nacionais de anomalias congênitas no mundo: aspectos históricos e operacionais

    by Augusto César Cardoso-Dos-Santos, Ruanna Sandrelly de Miranda Alves, Ana Cláudia Medeiros-De-Souza, João Matheus Bremm, Julia Do Amaral Gomes, Ronaldo Fernandes Santos Alves, Valdelaine Etelvina Miranda de Araujo, Giovanny Vinícius Araújo de França

    Resumo Objetivo: Identificar registros de anomalias congênitas com cobertura nacional existentes no mundo, destacando suas principais características históricas e operacionais. Métodos: Revisão documental, mediante busca na base Medline/Pubmed e consulta a dados provenientes de relatórios, documentos oficiais e sítios eletrônicos. Foram incluídos trabalhos com relato de pelo menos um registro nacional. Resultados: Foram identificados 40 registros nacionais de anomalias congênitas em 39 países diferentes. Todos os registros incluídos no estudo localizavam-se em países de renda alta ou média superior, com concentração na Europa. A maior parte dos registros foi de base populacional, de notificação compulsória e com tempo limite para notificação de até 1 ano de idade. O registro brasileiro apresentou a maior cobertura anual. Conclusão: Os registros discutidos apresentaram características diversas, relacionadas à realidade de cada país. Os resultados apresentados fornecem subsídios para a temática da vigilância das anomalias congênitas, sobretudo em locais onde se deseja implementar tal atividade.


  • Open Access

    Lista de anomalias congênitas prioritárias para vigilância no âmbito do Sistema de Informações sobre Nascidos Vivos do Brasil

    by Augusto César Cardoso-Dos-Santos, Ana Cláudia Medeiros-De-Souza, João Matheus Bremm, Ronaldo Fernandes Santos Alves, Valdelaine Etelvina Miranda de Araújo, Júlio Cesar Loguercio Leite, Lavínia Schuler-Faccini, Maria Teresa Vieira Sanseverino, Simone de Menezes Karam, Têmis Maria Félix, et al.

    Resumo Objetivo Definir a lista de anomalias congênitas prioritárias para o aprimoramento do registro no Sistema de Informações sobre Nascidos Vivos (Sinasc). Métodos A partir da Décima Revisão da Classificação Estatística Internacional de Doenças e Problemas Relacionados à Saúde (CID-10), protocolos internacionais e reuniões com especialistas, a lista de anomalias prioritárias foi construída considerando-se dois critérios principais: ser diagnosticável ao nascimento; e possuir intervenção disponível em diferentes níveis. A lista foi submetida a apreciação da Sociedade Brasileira de Genética Médica e Genômica. Resultados Compuseram a lista oito grupos de anomalias congênitas distribuídos de acordo com o tipo de anomalia relacionada, bem como a parte do corpo afetada e sua correspondência ao código do capítulo XVII da CID-10. Conclusão A lista de anomalias congênitas prioritárias para notificação fornece subsídios para o aprimoramento do registro no Sinasc.


  • Open Access

    Anomalias congênitas na perspectiva da vigilância em saúde: compilação de uma lista com base na CID-10

    by João Matheus Bremm, Augusto César Cardoso-Dos-Santos, Vivyanne Santiago Magalhães, Ana Cláudia Medeiros-De-Souza, Ronaldo Fernandes Santos Alves, Valdelaine Etelvina Miranda de Araujo, Eduardo Marques Macario, Wanderson Kleber de Oliveira, Lavínia Schüler-Faccini, Maria Teresa Vieira Sanseverino, et al.

    Objetivo. Propor uma lista de anomalias congênitas com códigos correspondentes na Classificação Estatística Internacional de Doenças e Problemas Relacionados à Saúde – 10a Revisão (CID-10), visando aplicação no âmbito da vigilância em saúde. Métodos. Em dezembro de 2019, realizou-se busca nas seguintes fontes de dados: CID-10; CID-11; anomalias monitoradas por três modelos de vigilância; base de informações sobre doenças raras (Orphanet). Realizou-se extração das anomalias a partir dessas fontes, processamento para correspondência com base na CID-10 e compilação mediante revisão manual. Resultados. Foram identificados 898 códigos, dos quais 619 (68,3%) constavam no capítulo XVII da CID-10. Dos 279 códigos de outros capítulos, 19 foram exclusivos da busca na CID-11, 72 dos modelos de vigilância, 79 da Orphanet e 36 da busca de termos na CID-10. Conclusão. Os códigos que constam do capítulo XVII da CID-10 não captam a totalidade das anomalias congênitas, indicando a necessidade de adoção de uma lista ampliada.

  • Open Access

    Anomalias congênitas na perspectiva da vigilância em saúde: compilação de uma lista com base na CID-10

    by João Matheus Bremm, Augusto César Cardoso-Dos-Santos, Vivyanne Santiago Magalhães, Ana Cláudia Medeiros-De-Souza, Ronaldo Fernandes Santos Alves, Valdelaine Etelvina Miranda de Araujo, Eduardo Marques Macario, Wanderson Kleber de Oliveira, Lavínia Schüler-Faccini, Maria Teresa Vieira Sanseverino, et al.

    Resumo Objetivo: Propor uma lista de anomalias congênitas com códigos correspondentes na Classificação Estatística Internacional de Doenças e Problemas Relacionados à Saúde – 10ᵃ Revisão (CID-10), visando a aplicação no âmbito da vigilância em saúde. Métodos: Em dezembro de 2019, realizou-se busca nas seguintes fontes de dados: CID-10; CID-11; anomalias monitoradas por três modelos de vigilância; base de informações sobre doenças raras (Orphanet). Realizou-se extração das anomalias a partir dessas fontes, processamento para correspondência com base na CID-10 e compilação mediante revisão manual. Resultados: Foram identificados 898 códigos, dos quais 619 (68,9%) constavam no capítulo XVII da CID-10. Dos 279 códigos de outros capítulos, 19 foram exclusivos da busca na CID-11, 72 dos modelos de vigilância, 79 da Orphanet e 36 da busca de termos na CID-10. Conclusão: Os códigos que constam do capítulo XVII da CID-10 não captam a totalidade das anomalias congênitas, indicando a necessidade de adoção de uma lista ampliada.