Results from simulated data sets: probabilistic record linkage outperforms deterministic record linkage

Tromp, M.; Ravelli, Anita C.J.; Bonsel, Gouke J.; Hasman, Arie; Reitsma, Johannes B.

doi:10.1016/j.jclinepi.2010.05.008

Cited by 107 publications

(78 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Além disso, estas estratégias menos restritas aumentam o número de registros falsos relacionados com maior tempo de execução 17,30,31, Quanto aos resultados do escore, para todas as topografias, o valor maior ou igual ao escore dezoito foi o mais acurado, dado que acima deste ponto de corte encontram-se a maioria dos pares verdadeiros, otimizando a revisão manual. Este achado corrobora com o estudo de Tromp et al 8 no qual foi observado que, a partir do escore 18, estavam localizados 94% dos pares verdadeiros 8 . Destaca-se que, no artigo citado, os autores, além do uso do "nome" e "data de nascimento" para o linkage, utilizaram o "CEP" e o "hospital" para o cálculo do escore, o que não foi viável, pois as variáveis referentes ao logradouro apresentaram muitos valores ignorados.…”

Section: Resultsunclassified

“…Todavia, nesta técnica, o poder de discriminação das variáveis utilizadas no processo de relacionamento é influenciado pelo número de valores válidos e suas uniformidade. Em relacionamentos de bases de dados que utilizam poucos campos e os mesmos apresentam baixo poder discriminatório, os erros de homônimos tendem a aumentar o número de falsos-positivos [5][6][7][8][9] . Nos últimos anos, foram desenvolvidas pesquisas para avaliar a acurácia do linkage probabilístico, na qual esta técnica faz uso de um escore que verifica o quão verossimilhante os registros pareados pertencem à mesma pessoa; isto é, dentre os registros, quais formam pares verdadeiros.…”

Section: Introductionunclassified

See 1 more Smart Citation

Determinação de um ponto de corte para a identificação de pares verdadeiros pelo método probabilístico de linkage de base de dados

et al. 2014

View full text Add to dashboard Cite

Cad. Saúde Colet., 2014, Rio de Janeiro, 22 (4): 428-36Resumo O objetivo deste estudo foi propor pontos de corte nos escores calculados no processo de linkage probabilístico, para as diversas topografias de câncer. Neste estudo foi utilizada a base de dados do RCBP-SP, composta por 343.306 casos incidentes de câncer do município de São Paulo, registrados no período de 1997 a 2005, com idades que variaram de menos um a 106 anos, de ambos os sexos. Para o linkage probabilístico, realizado no programa Reclink III, foram utilizadas a base de dados do PRO-AIM e APAC-SIA/SUS. Foram calculados os valores da área sob a curva, sensibilidade e especificidade para determinar o ponto de corte do escore de maior precisão na identificação dos pares verdadeiros. Na análise das topografias, verificou-se que o ponto de corte no escore 18 apresentou boa acurácia, com valores de sensibilidade que variaram de 73,7 a 96,7% e de especificidade de 98,5 a 99,4%. Conclui-se que, acima do escore 18 encontravam-se quase a totalidade dos pares verdadeiros, enquanto que abaixo deste, menos de 1% dos registros vinculados eram verdadeiros.Palavras-chave: sistemas de informação; registro médico coordenado; neoplasias. AbstractThe aim of this study was to propose cut-off points for scores calculated in the probabilistic record linkage process for several cancer topographies. In this study we used the PBCR-SP database composed of 343,306 incident cancer cases from the municipality of São Paulo, registered from 1997 through 2005, aged from less than one to 106 years, of both sexes. PRO-AIM and APAC-SIA/SUS databases were used to probabilistic record linkage using Reclink III software. Area under the curve, sensitivity and specificity values were calculated to determine the cut-off point with the highest accuracy in identifying true matches. In the topography analyses, it was found that the cut-off at score 18 showed good accuracy, with sensitivity ranging from 73.7 to 96.7% and specificity ranging from 98.5 to 99.4%. We concluded that above score 18 nearly all true pairs were found. Whereas, below this cut-off, less than 1% of linked records were true matches.

show abstract

Section: Resultsunclassified

Section: Introductionunclassified

Determinação de um ponto de corte para a identificação de pares verdadeiros pelo método probabilístico de linkage de base de dados

et al. 2014

View full text Add to dashboard Cite

show abstract

“…The variables may present errors and flaws in information, lack of a univocal indicator or few variables to relate the records in databases with many cases [17][18][19] . In this study, the results were analyzed by the identification of true pairs, according to completeness and quality of the databases.…”

Section: Discussionmentioning

confidence: 99%

Melhora na qualidade e completitude da base de dados do Registro de Câncer de Base Populacional do município de São Paulo: uso das técnicas de linkage

Peres

Latorre

Tanaka

et al. 2016

Rev. bras. epidemiol.

View full text Add to dashboard Cite

ABSTRACT:The availability of large computerized databases on health turned the record linkage technique into an alternative for different study designs. This technique provides the creation of more complete databases, at low operational costs. Objective: The aim of this study was to improve the quality of information and data completeness through probabilistic and deterministic record linkage between Population-based Cancer Registry of São Paulo (PBCR-SP) for incident cancer cases, death database and drugs/medical procedures database. Methods: We used the database of the PBCRP-SP composed of 343,306 incident cancer cases in the municipality of São Paulo in the period between 1997 and 2005 with ages raging from under 1 to 106 years old, from both sexes. Three databases were used for linkage, namely Improvement Program for Mortality Information in São Paulo city (PRO-AIM), Authorization of Procedures of High Complexity/Cost of Outpatient Information System from the Unified Health System (APAC-SIA/SUS), and Foundation State System of Data Analysis (Foundation SEADE). Crude incidence (CIR) and mortality rates (CMR) were calculated and overall survival analysis was performed using the Kaplan-Meier method. Results: After record linkage, it was possible to observe gain of 4.3% for the CIR and 25.8% for CMR. The overall survival analysis showed that before record linkage there was an underestimation of the probability of being alive for all variables (p < 0.001). Conclusion: The linkage techniques contributed with the improvement of the quality of RCBP-SP information both on completeness of data, as in defining the vital status of the patient. In addition, the results found in this study reflect the ability of databases when worked jointly, providing subsidies for various types of studies and information for planning policies and strategic actions.

show abstract

“…Physician-diagnosed cause of death and hospital admission diagnosis was retrieved via probabilistic medical record linkage with the National Death Registry and the National Registry of Hospital Discharge Diagnoses [31]. We included fatal and non-fatal cardiovascular events that occurred between the CT examination and January 2008.…”

Section: Outcome Measuresmentioning

confidence: 99%

Pulmonary function and CT biomarkers as risk factors for cardiovascular events in male lung cancer screening participants: the NELSON study

et al. 2014

View full text Add to dashboard Cite

Objective The objective of this study was to investigate the association of spirometry and pulmonary CT biomarkers with cardiovascular events. Methods In this lung cancer screening trial 3,080 male participants without a prior cardiovascular event were analysed. Fatal and non-fatal cardiovascular events were included. Spirometry included forced expiratory volume measured in units of one-second percent predicted (FEV 1 %predicted) and FEV 1 divided by forced vital capacity (FVC; FEV 1 /FVC). CT examinations were quantified for coronary artery calcium volume, pulmonary emphysema (perc15) and bronchial wall thickness (pi10). Data were analysed via a Cox proportional hazard analysis, net reclassification improvement (NRI) and C-indices.Results 184 participants experienced a cardiovascular event during a median follow-up of 2.9 years. Age, pack-years and smoking status adjusted hazard ratios were 0.992 (95 % confidence interval (CI) 0.985-0.999) for FEV 1 %predicted, 1.000 (95%CI 0.986-1.015) for FEV 1 /FVC, 1.014 (95%CI 1.005-1.023) for perc15 per 10 HU, and 1.269 (95%CI 1.024-1.573) for pi10 per 1 mm. The incremental C-index (<0.015) and NRI (<2.8 %) were minimal. Coronary artery calcium volume had a hazard ratio of 1.046 (95%CI 1.034-1.058) per 100 mm 3 , an increase in C-index of 0.076 and an NRI of 16.9 % (P<0.0001). Conclusions Pulmonary CT biomarkers and spirometry measurements were significantly associated with cardiovascular events, but did not contain clinically relevant independent prognostic information for cardiovascular events. Key Points • Pulmonary CT biomarkers and spirometry are associated with cardiovascular events • These pulmonary measurements do not contain clinically relevant independent prognostic information • Only coronary calcium score improved cardiovascular risk prediction above age and smoking

show abstract

Results from simulated data sets: probabilistic record linkage outperforms deterministic record linkage

Cited by 107 publications

References 31 publications

Determinação de um ponto de corte para a identificação de pares verdadeiros pelo método probabilístico de linkage de base de dados

Determinação de um ponto de corte para a identificação de pares verdadeiros pelo método probabilístico de linkage de base de dados

Melhora na qualidade e completitude da base de dados do Registro de Câncer de Base Populacional do município de São Paulo: uso das técnicas de linkage

Pulmonary function and CT biomarkers as risk factors for cardiovascular events in male lung cancer screening participants: the NELSON study

Contact Info

Product

Resources

About