Record Linkage Strategies

Roos, Leslíe L.; Wajda, André

doi:10.1055/s-0038-1634828

Cited by 110 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…33±35 High percentages of successful linkages, although not as high as in our study, have been reported. 34 Thus, register-based follow-up studies of this kind are also possible in the absence of a national or regional identification number system, but they are likely to be more difficult and expensive.…”

Section: Discussionmentioning

confidence: 99%

Health registers as a feasible means of measuring health status in childhood – a 7‐year follow‐up of the 1987 Finnish birth cohort

Gissler

Hemminki

Louhiala

et al. 1998

Paediatric Perinatal Epid

View full text Add to dashboard Cite

Follow-up studies on health have usually been based on ad hoc cohort studies in which detailed information is collected specifically for research purposes on a certain group of people. The increasing collection of routine health data provides an alternative method of gathering follow-up data. In this study, the feasibility of using routinely collected health-register data and data linkages to follow up children's health was investigated. Five nationwide registers, 18 regional registers of intellectually disabled children and school administration data in one county were found to be of use for our follow-up and were combined with the 1987 Finnish Medical Birth Register (n = 60,254 births). In the follow-up, 62 children were untraced (0.1%), 327 were stillborn (0.5%), 440 died after birth (0.7%) and 287 emigrated (0.5%) before the age of 7 years. The cumulative incidences for all diseases (8.9% of all children living in Finland at the age of 7 years), for diabetes (3.0/1000), for epilepsy (6.8/1000) and for asthma (34.2/1000) correspond to the estimates of other studies, but our estimate for intellectual disabilities (18.0/1000, of whom 18% were reported to have an IQ of 70 or less) seems to be an underestimate. Our data collection did not provide reliable information on institutionalised children or children taken into care. Data collection conducted by using health registers is a feasible method, and it saves both time and financial resources compared with cohort studies. Potential problems with data linkage studies are variation in the content of data and in data quality of different registers and data protection issues.

show abstract

Section: Discussionmentioning

confidence: 99%

Health registers as a feasible means of measuring health status in childhood – a 7‐year follow‐up of the 1987 Finnish birth cohort

Gissler

Hemminki

Louhiala

et al. 1998

Paediatric Perinatal Epid

View full text Add to dashboard Cite

show abstract

“…Of these, only Roos and Wajda [20] compare deterministic and probabilistic methods and make suggestions on when their use is appropriate. The literature appears to contain no studies that compare how the methods compare quantitatively when applied to common data sets.…”

Section: Introductionmentioning

confidence: 98%

“…Newcombe [17] contains valuable information for practitioners. Larsen and Rubin [18], Winkler [19], and Roos and Wajda [20] compare di erent linkage strategies.…”

Section: Introductionmentioning

confidence: 99%

An empirical comparison of record linkage procedures

Gomatam

Carter

Ariet

et al. 2002

Statistics in Medicine

100

View full text Add to dashboard Cite

We consider the problem of record linkage in the situation where we have only non-unique identifiers, like names, sex, race etc., as common identifiers in databases to be linked. For such situations much work on probabilistic methods of record linkage can be found in the statistical literature. However, although many groups undoubtedly still use deterministic procedures, not much literature is available on deterministic strategies. Furthermore, there appears to exist almost no documentation on the comparison of results for the two strategies. In this work we compare a stepwise deterministic linkage strategy with a probabilistic strategy, as implemented in AUTOMATCH, for a situation in which the truth is known. The comparison was carried out on a linkage between medical records from the Regional Perinatal Intensive Care Centers database and educational records from the Florida Department of Education. Social security numbers, available in both databases, were used to decide the true status of each record pair after matching. Match rates and error rates for the two strategies are compared and a discussion of their similarities and differences, strengths and weaknesses is presented.

show abstract

“…The accuracy of record linkage using probabilistic data matching is high with the percentage of true matches estimated to be 97-99 percent depending on the number of matching variables used [9]. Validation of the registers involved in the linkages has been published [1].…”

Section: Quality Controlmentioning

confidence: 99%

Longitudinal, Whole-population Data Examining Pathways of Risk from Conception to Disease: The Western Australian Schizophrenia High-risk e-Cohort

Morgan

Valuri

Croft

et al. 2014

OHD

View full text Add to dashboard Cite

This database has been constructed to support a program of work designed to untangle genetic and environmental contributions to the risk for schizophrenia and other adverse outcomes in the offspring of mothers with schizophrenia and other severe mental illness. To do this, it utilises Western Australian whole-population health and social services databases. Records on the Western Australian psychiatric case register have been linked to Midwives’ Notification of Birth records and to Registrations of Births (for paternal links) as well as to other data sets. Maternal links identify women with psychosis who gave birth in Western Australia between 1980 and 2001. Comparison mothers are those with no record of psychiatric illness who gave birth in Western Australia over the same period. The study database comprises 246,873 mothers and 467,945 children: 889 mothers with schizophrenia (1,672 children); 1,644 mothers with bipolar disorder (3,358 children); 4,200 mothers with unipolar major depression (8,864 children); 775 mothers with other psychoses (1,592 children); and 239,365 comparison mothers (452,459 children). Full psychiatric histories for mothers, fathers and children have been extracted. At the time of the most recent update to the psychiatric data on children, 33,363 children had a history of psychiatric illness; 5,500 of these had had at least one contact with mental health services at which a diagnosis of a psychotic disorder had been recorded. Data have also been collected on obstetric complications and a range of infant and childhood morbidities including birth defects, intellectual disability, educational achievement, childhood abuse, criminal offending.The program aims are to: (i) determine the frequency and distribution of obstetric complications in women with schizophrenia compared to a non-psychiatric comparison group of mothers; (ii) explore the spectrum of outcomes for the children born to women with schizophrenia compared to comparison children, and to assess the specificity of these findings to maternal schizophrenia compared to maternal bipolar disorder, unipolar major depression and other psychotic illness; and (iii) examine the relationship between familial psychiatric status, obstetric complications and mental health outcomes for children.The data sit in an Ingres relational database. A full description of the database and its elements has been published [1]. Numbers in this article differ from previously published numbers as a result of new linkages and updates to the database.

show abstract

Record Linkage Strategies

Cited by 110 publications

References 16 publications

Health registers as a feasible means of measuring health status in childhood – a 7‐year follow‐up of the 1987 Finnish birth cohort

Health registers as a feasible means of measuring health status in childhood – a 7‐year follow‐up of the 1987 Finnish birth cohort

An empirical comparison of record linkage procedures

Longitudinal, Whole-population Data Examining Pathways of Risk from Conception to Disease: The Western Australian Schizophrenia High-risk e-Cohort

Contact Info

Product

Resources

About