Data management and data analysis techniques in pharmacoepidemiological studies using a pre-planned multi-database approach: a systematic literature review

Pooling of primary care electronic health record (EHR) data on Huntington's disease (HD) and cancer: establishing comparability of two large UK databases

OBJECTIVES

To explore whether UK primary care databases arising from two different software systems can be feasibly combined, by comparing rates of Huntington's disease (HD, which is rare) and 14 common cancers in the two databases, as well as characteristics of people with these conditions.

DESIGN

Descriptive study.

SETTING

Primary care electronic health records from Clinical Practice Research Datalink (CPRD) GOLD and CPRD Aurum databases, with linked hospital admission and death registration data.

PARTICIPANTS

4986 patients with HD and 1 294 819 with an incident cancer between 1990 and 2019.

PRIMARY AND SECONDARY OUTCOME MEASURES

Incidence and prevalence of HD by calendar period, age group and region, and annual age-standardised incidence of 14 common cancers in each database, and in a subset of 'overlapping' practices which contributed to both databases. Characteristics of patients with HD or incident cancer: medical history, recent prescribing, healthcare contacts and database follow-up.

RESULTS

Incidence and prevalence of HD were slightly higher in CPRD GOLD than CPRD Aurum, but with similar trends over time. Cancer incidence in the two databases differed between 1990 and 2000, but converged and was very similar thereafter. Participants in each database were most similar in terms of medical history (median standardised difference, MSD 0.03 (IQR 0.01-0.03)), recent prescribing (MSD 0.06 (0.03-0.10)) and demographics and general health variables (MSD 0.05 (0.01-0.09)). Larger differences were seen for healthcare contacts (MSD 0.27 (0.10-0.41)), and database follow-up (MSD 0.39 (0.19-0.56)).

CONCLUSIONS

Differences in cancer incidence trends between 1990 and 2000 may relate to use of a practice-level data quality filter (the 'up-to-standard' date) in CPRD GOLD only. As well as the impact of data curation methods, differences in underlying data models can make it more challenging to define exactly equivalent clinical concepts in each database. Researchers should be aware of these potential sources of variability when planning combined database studies and interpreting results.

The Value of Federated Data Networks in Oncology: What Research Questions Do They Answer? Outcomes From a Systematic Literature Review

OBJECTIVES

Real-world evidence (RWE) plays an important role in addressing key research questions of interest to healthcare decision makers. Federated data networks (FDNs) apply novel technology to enable the conduct of RWE studies with multiple partners, without the need to share the individual partner's data set. A systematic review of the published literature was performed to determine which types of research questions can best be addressed through FDNs, specifically in the field of oncology.

METHODS

Systematic searches of MEDLINE and Embase were undertaken to identify the types of research questions that had been addressed in studies using FDNs. Additional information was retrieved about study characteristics, statistical methods, and the FDN itself.

RESULTS

In total, 40 publications were included where research questions on the following had been addressed (multiple categories possible): disease natural history (58%), safety surveillance (18%), treatment pathways (15%), comparative effectiveness (10%), and cost/resource use studies (3%)-13% of studies had to be left uncategorized. A total of 50% of the studies were run with data partners in networks of ≤5. The size of the networks ranged from 227 patients to >5 million patients. Statistical methods used included distributed learning and distributed regression methods.

CONCLUSIONS

Further work is needed to raise awareness of the important role that FDNs can play in leveraging readily available RWE to address key research questions of interest in cancer and the benefits to the research community in engaging in federated data initiatives with a long-term perspective.

Use of the French national health insurance information system for research in the field of mental health: Systematic review and perspectives

PURPOSE

This systematic review registered in PROSPERO (CRD42021225296) aimed to describe the use of the French national health insurance information system, which covers the entire French population (67 million inhabitants), for research in the field of mental health.

METHODS

Three electronic databases and a journal hand-search identified 15 265 articles from January 1, 2003 (year of creation of the database) to October 31, 2020. Studies of any design were eligible for inclusion provided that they (i) made use of at least one component of the French health insurance database and (ii) focused on a topic in near and far connection with the field of mental health in France. Database used, design and methods, study period, population, key findings, and type of use for medical research were described.

RESULTS

A total of 152 studies were included in the review analysis. There was an increase in the number of published articles over time throughout the studied period. Studies focusing on adults (n = 139) largely outnumbered those focusing on children and adolescents (n = 11). Pharmacoepidemiological studies were by far the most frequent (n = 123), followed by methodological studies (n = 23), epidemiological studies (n = 17), and health economics studies (n = 3). The most studied psychotropic drugs were antidepressants (n = 27), anxiolytics (n = 27), and opioids (n = 25) while fewer studies focused on methylphenidate (n = 6) and on mood stabilizers (n = 5). Few studies specifically focused on psychiatric disorders, mainly depression (n = 4), suicide (n = 4), and psychotic disorders (n = 3).

CONCLUSION

This systematic review highlighted a relatively poor exploitation of the Système national des données de santé database in the field of psychiatric research with regard to the great possibilities it offers, with a clear lag in certain fields such as epidemiological or health economics studies and in specific populations, in particular children and adolescents.

A systematic review of how missing data are handled and reported in multi-database pharmacoepidemiologic studies

Purpose

Pharmacoepidemiologic multi‐database studies (MDBS) provide opportunities to better evaluate the safety and effectiveness of medicines. However, the issue of missing data is often exacerbated in MDBS, potentially resulting in bias and precision loss. We sought to measure how missing data are being recorded and addressed in pharmacoepidemiologic MDBS.

Methods

We conducted a systematic literature search in PubMed for pharmacoepidemiologic MDBS published between 1st January 2018 and 31st December 2019. Included studies were those that used ≥2 distinct databases to assess the same safety/effectiveness outcome associated with a drug exposure. Outcome variables extracted from the studies included strategies to execute a MDBS, reporting of missing data (type, bias evaluation) and the methods used to account for missing data.

Results

Two thousand seven hundred and twenty‐six articles were identified, and 62 studies were included: using data from either North America (56%), Europe (31%), multiple regions (11%) or East‐Asia (2%). Thirty‐five (56%) articles reported missing data: 11 of these studies reported that this could have introduced bias and 19 studies reported a method to address missing data. Thirteen (68%) carried out a complete case analysis, 2 (11%) applied multiple imputation, 2 (11%) used both methods, 1 (5%) used mean imputation and 1 (5%) substituted information from a similar variable.

Conclusions

Just over half of the recent pharmacoepidemiologic MDBS reported missing data and two‐thirds of these studies reported how they accounted for it. We should increase our vigilance for database completeness in MDBS by reporting and addressing the missing data that could introduce bias.

Approaches for combining primary care electronic health record data from multiple sources: a systematic review of observational studies

OBJECTIVE

To identify observational studies which used data from more than one primary care electronic health record (EHR) database, and summarise key characteristics including: objective and rationale for using multiple data sources; methods used to manage, analyse and (where applicable) combine data; and approaches used to assess and report heterogeneity between data sources.

DESIGN

A systematic review of published studies.

DATA SOURCES

Pubmed and Embase databases were searched using list of named primary care EHR databases; supplementary hand searches of reference list of studies were retained after initial screening.

STUDY SELECTION

Observational studies published between January 2000 and May 2018 were selected, which included at least two different primary care EHR databases.

RESULTS

6054 studies were identified from database and hand searches, and 109 were included in the final review, the majority published between 2014 and 2018. Included studies used 38 different primary care EHR data sources. Forty-seven studies (44%) were descriptive or methodological. Of 62 analytical studies, 22 (36%) presented separate results from each database, with no attempt to combine them; 29 (48%) combined individual patient data in a one-stage meta-analysis and 21 (34%) combined estimates from each database using two-stage meta-analysis. Discussion and exploration of heterogeneity was inconsistent across studies.

CONCLUSIONS

Comparing patterns and trends in different populations, or in different primary care EHR databases from the same populations, is important and a common objective for multi-database studies. When combining results from several databases using meta-analysis, provision of separate results from each database is helpful for interpretation. We found that these were often missing, particularly for studies using one-stage approaches, which also often lacked details of any statistical adjustment for heterogeneity and/or clustering. For two-stage meta-analysis, a clear rationale should be provided for choice of fixed effect and/or random effects or other models.

Lessons from meta-analyses of randomized clinical trials for analysis of distributed networks of observational databases

Networks of constellations of longitudinal observational databases, often electronic medical records or transactional insurance claims or both, are increasingly being used for studying the effects of medicinal products in real-world use. Such databases are frequently configured as distributed networks. That is, patient-level data are kept behind firewalls and not communicated outside of the data vendor other than in aggregate form. Instead, data are standardized across the network, and queries of the network are executed locally by data partners, and summary results provided to a central research partner(s) for amalgamation, aggregation, and summarization. Such networks can be huge covering years of data on upwards of 100 million patients. Examples of such networks include the FDA Sentinel Network, ASPEN, CNODES, and EU-ADR. As this is a new emerging field, we note in this paper the conceptual similarities and differences between the analysis of distributed networks and the now well-established field of meta-analysis of randomized clinical trials (RCTs). We recommend, wherever appropriate, to apply learnings from meta-analysis to help guide the development of distributed network analyses of longitudinal observational databases.

Cancer risk among insulin users: comparing analogues with human insulin in the CARING five-country cohort study

AIMS/HYPOTHESIS

The aim of this work was to investigate the relationship between use of certain insulins and risk for cancer, when addressing the limitations and biases involved in previous studies.

METHODS

National Health Registries from Denmark (1996-2010), Finland (1996-2011), Norway (2005-2010) and Sweden (2007-2012) and the UK Clinical Practice Research Datalink database (1987-2013) were used to conduct a cohort study on new insulin users (N = 327,112). By using a common data model and semi-aggregate approach, we pooled individual-level records from five cohorts and applied Poisson regression models. For each of ten cancer sites studied, we estimated the rate ratios (RRs) by duration (≤0.5, 0.5-1, 1-2, 2-3, 3-4, 4-5, 5-6 and >6 years) of cumulative exposure to insulin glargine or insulin detemir relative to that of human insulin.

RESULTS

A total of 21,390 cancer cases occurred during a mean follow-up of 4.6 years. No trend with cumulative treatment time for insulin glargine relative to human insulin was observed in risk for any of the ten studied cancer types. Of the 136 associations tested in the main analysis, only a few increased and decreased risks were found: among women, a higher risk was observed for colorectal (RR 1.54, 95% CI 1.06, 2.25) and endometrial cancer (RR 1.78, 95% CI 1.07, 2.94) for ≤0.5 years of treatment and for malignant melanoma for 2-3 years (RR 1.92, 95% CI 1.02, 3.61) and 4-5 years (RR 3.55, 95% CI 1.68, 7.47]); among men, a lower risk was observed for pancreatic cancer for 2-3 years (RR 0.34, 95% CI 0.17, 0.66) and for liver cancer for 3-4 years (RR 0.36, 95% CI 0.14, 0.94) and >6 years (RR 0.22, 95% CI 0.05, 0.92). Comparisons of insulin detemir with human insulin also showed no consistent differences.

CONCLUSIONS/INTERPRETATION

The present multi-country study found no evidence of consistent differences in risk for ten cancers for insulin glargine or insulin detemir use compared with human insulin, at follow-up exceeding 5 years.

Lessons learned on the design and the conduct of Post-Authorization Safety Studies: review of 3 years of PRAC oversight

AIMS

To describe and characterize the first cohort of Post-Authorization Safety Study (PASS) protocols reviewed under the recent European pharmacovigilance legislation.

METHODS

A systematic approach was used to compile all publicly available information on PASS protocols and assessments submitted from July 2012 to July 2015 from Pharmacovigilance Risk Assessment Committee (PRAC) minutes, European Medicines Agency (EMA) and European Network of Pharmacovigilance and Pharmacoepidemiology (ENCePP) webpages.

RESULTS

During the study period, 189 different PASS protocols were submitted to the PRAC, half of which were entered in the ENCePP electronic register of post-authorization studies (EU-PAS) by July 2015. Those protocols were assessed during 353 PRAC reviews. The EMA published only 31% of the PRAC feedback, of which the main concerns were study design (37%) and feasibility (30%). Among the 189 PASS, slightly more involved primary data capture (58%). PASS assessing drug utilization mainly leveraged secondary data sources (58%). The majority of the PASS did not include a comparator (65%) and 35% of PASS also evaluated clinical effectiveness endpoints.

CONCLUSIONS

To the best of our knowledge this is the first comprehensive review of three years of PASS protocols submitted under the new pharmacovigilance legislation. Our results show that both EMA and PASS sponsors could respectively increase the availability of protocol assessments and documents in the EU-PAS. Protocol content review and the high number of PRAC comments related to methodological issues and feasibility concerns should raise awareness among PASS stakeholders to design more thoughtful studies according to pharmacoepidemiological principles and existing guidelines.

Overview of drug data within French health insurance databases and implications for pharmacoepidemiological studies

In this study, we aimed to provide an updated overview of drug data contained in the French health insurance database (SNIIRAM) and its associated national representative sample (EGB). This study identified most common problems concerning drug data: (i) change in level of coverage of drugs of interest (drug no more eligible for reimbursement or no more prescription-only), (ii) break in patients' eligibility (in connection with change of healthcare plan or patients' identifier), and (iii) technical and regulatory issues. We provide a brief checklist to enable a structured identification of these issues. The impact of gap in drug data availability on study validity will depend on the research question, drug, setting, and population of interest. The French health insurance database and associated sample are valuable resources for pharmacoepidemiological research. There is a need to pursue further methodological and validation studies to promote accurate and transparent use of French health insurance databases for pharmacoepidemiology.

Individual-based versus aggregate meta-analysis in multi-database studies of pregnancy outcomes: the Nordic example of selective serotonin reuptake inhibitors and venlafaxine in pregnancy

PURPOSE

Compare analyses of a pooled data set on the individual level with aggregate meta-analysis in a multi-database study.

METHODS

We reanalysed data on 2.3 million births in a Nordic register based cohort study. We compared estimated odds ratios (OR) for the effect of selective serotonin reuptake inhibitors (SSRI) and venlafaxine use in pregnancy on any cardiovascular birth defect and the rare outcome right ventricular outflow tract obstructions (RVOTO). Common covariates included maternal age, calendar year, birth order, maternal diabetes, and co-medication. Additional covariates were added in analyses with country-optimized adjustment.

RESULTS

Country adjusted OR (95%CI) for any cardiovascular birth defect in the individual-based pooled analysis was 1.27 (1.17-1.39), 1.17 (1.07-1.27) adjusted for common covariates and 1.15 (1.05-1.26) adjusted for all covariates. In fixed effects meta-analyses pooled OR was 1.29 (1.19-1.41) based on crude country specific ORs, 1.19 (1.09-1.29) adjusted for common covariates, and 1.16 (1.06-1.27) for country-optimized adjustment. In a random effects model the adjusted OR was 1.07 (0.87-1.32). For RVOTO, OR was 1.48 (1.15-1.89) adjusted for all covariates in the pooled data set, and 1.53 (1.19-1.96) after country-optimized adjustment. Country-specific adjusted analyses at the substance level were not possible for RVOTO.

CONCLUSION

Results of fixed effects meta-analysis and individual-based analyses of a pooled dataset were similar in this study on the association of SSRI/venlafaxine and cardiovascular birth defects. Country-optimized adjustment attenuated the estimates more than adjustment for common covariates only. When data are sparse pooled data on the individual level are needed for adjusted analyses. Copyright © 2016 John Wiley & Sons, Ltd.

Observational Studies of Drug Safety in Multi-Database Studies: Methodological Challenges and Opportunities

INTRODUCTION/OBJECTIVE

The Canadian Network for Observational Drug Effect Studies (CNODES), a network of researchers and databases, is a collaborating center of the Drug Safety and Effectiveness Network. CNODES' main mandate is to conduct observational studies of drug safety based on queries developed and submitted by Health Canada and other federal, provincial, and territorial stakeholders. Through a case study we explore several methodological opportunities and challenges that arise in distributed pharmacoepidemiology networks.

CASE STUDY

We use as a case study a study of proton pump inhibitors and hospitalization for community-acquired pneumonia. Challenges arise in the design and conduct of studies at individual sites, and then with processes and methods for combining data. On the other hand, distributed networks provide opportunities, such as the ability to detect and understand heterogeneity, in sample sizes that would typically be impossible for a single study.

CONCLUSIONS

Networks such as CNODES provide the opportunity to detect and quantify important safety signals from administrative data, and provide many challenges for methods research in pharmacoepidemiology using distributed data. As networks increase in size and scope of research questions, the need for methodological developments should continue to grow.

Designing and incorporating a real world data approach to international drug development and use: what the UK offers

Assessments of the safety, efficacy and appropriate use of new medicines lie at the heart of treatment development and subsequent adoption in clinical practice. Highly controlled randomised clinical trials routinely inform decisions on the approval, coverage and use of a medicine. Researchers and decision makers have become increasingly aware that these experimental data alone are insufficient to address those decisions fully. Real world data recorded from routine healthcare delivery by healthcare professionals and patients help provide a more complete picture of care. The UK, with its connectivity and rich longitudinal patient records, accumulated research and informatics experience and National Health Service, provides an exemplar of how real world data address a wide range of challenges across drug development.

Data management and data analysis techniques in pharmacoepidemiological studies using a pre-planned multi-database approach: a systematic literature review

PURPOSE

To identify pharmacoepidemiological multi-database studies and to describe data management and data analysis techniques used for combining data.

METHODS

Systematic literature searches were conducted in PubMed and Embase complemented by a manual literature search. We included pharmacoepidemiological multi-database studies published from 2007 onwards that combined data for a pre-planned common analysis or quantitative synthesis. Information was retrieved about study characteristics, methods used for individual-level analyses and meta-analyses, data management and motivations for performing the study.

RESULTS

We found 3083 articles by the systematic searches and an additional 176 by the manual search. After full-text screening of 75 articles, 22 were selected for final inclusion. The number of databases used per study ranged from 2 to 17 (median = 4.0). Most studies used a cohort design (82%) instead of a case-control design (18%). Logistic regression was most often used for individual-level analyses (41%), followed by Cox regression (23%) and Poisson regression (14%). As meta-analysis method, a majority of the studies combined individual patient data (73%). Six studies performed an aggregate meta-analysis (27%), while a semi-aggregate approach was applied in three studies (14%). Information on central programming or heterogeneity assessment was missing in approximately half of the publications. Most studies were motivated by improving power (86%).

CONCLUSIONS

Pharmacoepidemiological multi-database studies are a well-powered strategy to address safety issues and have increased in popularity. To be able to correctly interpret the results of these studies, it is important to systematically report on database management and analysis techniques, including central programming and heterogeneity testing.