Dataset Information

Secure Record Linkage of Large Health Data Sets: Evaluation of a Hybrid Cloud Model.

ABSTRACT: BACKGROUND:The linking of administrative data across agencies provides the capability to investigate many health and social issues with the potential to deliver significant public benefit. Despite its advantages, the use of cloud computing resources for linkage purposes is scarce, with the storage of identifiable information on cloud infrastructure assessed as high risk by data custodians. OBJECTIVE:This study aims to present a model for record linkage that utilizes cloud computing capabilities while assuring custodians that identifiable data sets remain secure and local. METHODS:A new hybrid cloud model was developed, including privacy-preserving record linkage techniques and container-based batch processing. An evaluation of this model was conducted with a prototype implementation using large synthetic data sets representative of administrative health data. RESULTS:The cloud model kept identifiers on premises and uses privacy-preserved identifiers to run all linkage computations on cloud infrastructure. Our prototype used a managed container cluster in Amazon Web Services to distribute the computation using existing linkage software. Although the cost of computation was relatively low, the use of existing software resulted in an overhead of processing of 35.7% (149/417 min execution time). CONCLUSIONS:The result of our experimental evaluation shows the operational feasibility of such a model and the exciting opportunities for advancing the analysis of linkage outputs.

SUBMITTER: Brown AP

PROVIDER: S-EPMC7542414 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Secure Record Linkage of Large Health Data Sets: Evaluation of a Hybrid Cloud Model.

Brown Adrian Paul AP Randall Sean M SM

JMIR medical informatics 20200923 9

<h4>Background</h4>The linking of administrative data across agencies provides the capability to investigate many health and social issues with the potential to deliver significant public benefit. Despite its advantages, the use of cloud computing resources for linkage purposes is scarce, with the storage of identifiable information on cloud infrastructure assessed as high risk by data custodians.<h4>Objective</h4>This study aims to present a model for record linkage that utilizes cloud computin ...[more]

PMID: 32965236

Similar Datasets

Project description:IntroductionThe robustness of record linkage evaluation measures is of high importance since linkage techniques are assessed based on these. However, minimal research has been conducted to evaluate the suitability of existing evaluation measures in the context of linking groups of records. Linkage quality is generally evaluated based on traditional measures such as precision and recall. As we show, these traditional evaluation measures are not suitable for evaluating groups of linked records because they evaluate the quality of individual record pairs rather than the quality of records grouped into clusters.ObjectivesWe set out to highlight the shortcomings of traditional evaluation measures and then propose a novel method to evaluate clustering quality in the context of group-based record linkage.MethodsThe proposed linkage evaluation method assesses how well individual records have been allocated into predicted groups/clusters with respect to ground-truth data. We first identify the best representative predicted cluster for each ground-truth cluster and, based on the resulting mapping, each record in a ground-truth cluster is assigned to one of seven categories. These categories reflect how well the linkage technique assigned records into groups.ResultsWe empirically evaluated our proposed method using real-world data and showed that it better reflects the quality of clusters generated by three group-based record linkage techniques. We also showed that traditional measures such as precision and recall can produce ambiguous results whereas our method does not.ConclusionsThe proposed evaluation method provides unambiguous results regarding the assessed group-based record linkage approaches. The method comprises of seven categories which reflect how each record was predicted, providing more detailed information about the quality of the linkage result. This will help to make better-informed decisions about which linkage technique is best suited for a given linkage application.

Project description:BackgroundThe evaluation of demonstration sites set up to provide improved access to psychological therapies (IAPT) comprised the study of all people identified as having common mental health problems (CMHP), those referred to the IAPT service, and a sample of attenders studied in-depth. Information technology makes it feasible to link practice, hospital and IAPT clinic data to evaluate the representativeness of these samples. However, researchers do not have permission to browse and link these data without the patients' consent.ObjectiveTo demonstrate the use of a mixed deterministic-probabilistic method of secure and private record linkage (SAPREL)--to describe selection bias in subjects chosen for in-depth evaluation.MethodWe extracted, pseudonymised and used fuzzy logic to link multiple health records without the researcher knowing the patient's identity. The method can be characterised as a three party protocol mainly using deterministic algorithms with dynamic linking strategies; though incorporating some elements of probabilistic linkage. Within the data providers' safe haven we extracted: Demographic data, hospital utilisation and IAPT clinic data; converted post code to index of multiple deprivation (IMD); and identified people with CMHP. We contrasted the age, gender, ethnicity and IMD for the in-depth evaluation sample with people referred to IAPT, use hospital services, and the population as a whole.ResultsThe in IAPT-in-depth group had a mean age of 43.1 years; CI: 41.0-45.2 (n=166); the IAPT-referred 40.2 years; CI: 39.4-40.9 (n=1118); and those with CMHP 43.6 years SEM 0.15. (n=12210). Whilst around 67% of those with a CMHP were women, compared to 70% of those referred to IAPT, and 75% of those subject to in-depth evaluation (Chi square p<0.001). The mean IMD score for the in-depth evaluation group was 36.6; CI: 34.2-38.9; (n=166); of those referred to IAPT 38.7; CI: 37.9-39.6; (n=1117); and of people with CMHP 37.6; CI 37.3-37.9; (n=12143).ConclusionsThe sample studied in-depth were older, more likely female, and less deprived than people with CMHP, and fewer had recorded ethnic minority status. Anonymous linkage using SAPREL provides insight into the representativeness of a study population and possible adjustment for selection bias.

Project description:PurposeRecruitment and follow-up in epidemiological studies are time-consuming and expensive. Combining online data collection with a register of individuals who agree to be contacted about research opportunities provides an efficient, cost-effective platform for population-based research. HealthWise Wales (HWW) aims to facilitate research by recruiting a cohort of individuals who have consented to be informed about research projects, advertising studies to participants, supporting data collection on specific topics and providing access to linked healthcare data for secondary analyses. In this paper, we describe the design of the project, ongoing data collection, methods of data linkage to routine healthcare records, baseline characteristics of participants, the strengths and limitations of the register, and the ways in which the project can support researchers.ParticipantsAdults (aged 16 years and above) living or receiving their healthcare in Wales are eligible for inclusion. Participants consent to be contacted for follow-up data collection and for their details to be used to access their routinely collected National Health Service records for research purposes. Data are collected using a web-based application, with new questionnaires added every 6?months. Data collection on sociodemographic and lifestyle factors is repeated at intervals of 2-3 years. Recruitment is ongoing, with 21?779 participants alive and currently registered.Findings to date99% of participants have complete information on age and sex, and 64% have completed questionnaires on sociodemographic and lifestyle factors. These data can be linked with national health databases within the Secure Anonymised Information Linkage (SAIL) databank, with 93% of participants matching a record in SAIL. HWW has facilitated the recruitment of 43?826 participants to 15 different studies.Future plansThe medium-term goal for the project is to enrol at least 50?000 adults. Recruitment strategies are being devised to achieve a study sample that closely models the population of Wales. Potential biosampling methods are also currently being explored.

Project description:BackgroundMulti-dimensional scaling (MDS) is aimed to represent high dimensional data in a low dimensional space with preservation of the similarities between data points. This reduction in dimensionality is crucial for analyzing and revealing the genuine structure hidden in the data. For noisy data, dimension reduction can effectively reduce the effect of noise on the embedded structure. For large data set, dimension reduction can effectively reduce information retrieval complexity. Thus, MDS techniques are used in many applications of data mining and gene network research. However, although there have been a number of studies that applied MDS techniques to genomics research, the number of analyzed data points was restricted by the high computational complexity of MDS. In general, a non-metric MDS method is faster than a metric MDS, but it does not preserve the true relationships. The computational complexity of most metric MDS methods is over O(N2), so that it is difficult to process a data set of a large number of genes N, such as in the case of whole genome microarray data.ResultsWe developed a new rapid metric MDS method with a low computational complexity, making metric MDS applicable for large data sets. Computer simulation showed that the new method of split-and-combine MDS (SC-MDS) is fast, accurate and efficient. Our empirical studies using microarray data on the yeast cell cycle showed that the performance of K-means in the reduced dimensional space is similar to or slightly better than that of K-means in the original space, but about three times faster to obtain the clustering results. Our clustering results using SC-MDS are more stable than those in the original space. Hence, the proposed SC-MDS is useful for analyzing whole genome data.ConclusionOur new method reduces the computational complexity from O(N3) to O(N) when the dimension of the feature space is far less than the number of genes N, and it successfully reconstructs the low dimensional representation as does the classical MDS. Its performance depends on the grouping method and the minimal number of the intersection points between groups. Feasible methods for grouping methods are suggested; each group must contain both neighboring and far apart data points. Our method can represent high dimensional large data set in a low dimensional space not only efficiently but also effectively.

Dataset Information

Secure Record Linkage of Large Health Data Sets: Evaluation of a Hybrid Cloud Model.

Publications

Secure Record Linkage of Large Health Data Sets: Evaluation of a Hybrid Cloud Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets