Search

Abstract Synthetic data generation is being increasingly used as a privacy preserving approach for sharing health data. In addition to protecting privacy, it is important to ensure that generated data has high utility. A common way to assess utility is the ability of synthetic data to replicate results from the real data. Replicability has been defined using two criteria: (a) replicate the results of the analyses on real data, and (b) ensure valid population inferences from the synthetic data. A simulation study using three heterogeneous real-world datasets evaluated the replicability of logistic regression workloads. Eight replicability metrics were evaluated: decision agreement, estimate agreement, standardized difference, confidence interval overlap, bias, confidence interval coverage, statistical power, and precision (empirical SE). The analysis of synthetic data used a multiple imputation approach whereby up to 20 datasets were generated and the fitted logistic regression models were combined using combining rules for fully synthetic datasets. The effects of synthetic data amplification were evaluated, and two types of generative models were used: sequential synthesis using boosted decision trees and a generative adversarial network (GAN). Privacy risk was evaluated using a membership disclosure metric. For sequential synthesis, adjusted model parameters after combining at least ten synthetic datasets gave high decision and estimate agreement, low standardized difference, as well as high confidence interval overlap, low bias, the confidence interval had nominal coverage, and power close to the nominal level. Amplification had only a marginal benefit. Confidence interval coverage from a single synthetic dataset without applying combining rules were erroneous, and statistical power, as expected, was artificially inflated when amplification was used. Sequential synthesis performed considerably better than the GAN across multiple datasets. Membership disclosure risk was low for all datasets and models. For replicable results, the statistical analysis of fully synthetic data should be based on at least ten generated datasets of the same size as the original whose analyses results are combined. Analysis results from synthetic data without applying combining rules can be misleading. Replicability results are dependent on the type of generative model used, with our study suggesting that sequential synthesis has good replicability characteristics for common health research workloads.

An estimated 2.5–3 million individuals (0.4%) in Europe are affected by inflammatory bowel disease (IBD). Whilst incidence rates for IBD are stabilising across Europe, the prevalence is rising and subsequently resulting in a significant cost to the healthcare system of an estimated 4.6–5.6 billion euros per year. Hospitalisation and surgical resection rates are generally on a downward trend, which is contrary to the rising cost of novel medication. This signifies a large part of healthcare cost and burden. Despite publicly funded healthcare systems in most European countries, there is still wide variation in how patients receive and/or pay for biologic medication. This review will provide an overview and discuss the different healthcare systems within Western Europe and the barriers that affect overall management of a changing IBD landscape, including differences to hospitalisation and surgical rates, access to medication and clinical trial participation and recruitment. This review will also discuss the importance of standardising IBD management to attain high-quality care for all patients with IBD.

This review aimed to illustrate the types, limitations, and possible alternatives of peer review (PR) based on a literature review together with the opinions of a social media audience via Twitter. This study was conducted via the #OpenSourceResearch collaborative platform and combined a comprehensive literature search on the current PR system with the opinions of a social media audience of surgeons who are actively engaged in the current PR system. Six independent researchers conducted a literature search of electronic databases in addition to Google Scholar. Electronic polls were organized via Twitter to assess surgeons’ opinions on the current PR system and potential alternative approaches. PR can be classified into single-blind, double-blind, triple-blind, and open PR. Newer PR systems include interactive platforms, prepublication and postpublication commenting or review, transparent review, and collaborative review. The main limitations of the current PR system are its allegedly time-consuming nature and inconsistent, biased, and non-transparent results. Suggestions to improve the PR process include employing an interactive, double-blind PR system, using artificial intelligence to recruit reviewers, providing incentives for reviewers, and using PR templates. The above results offer several concepts for possible alternative approaches and modifications to this critically important process.

Introduction: With many anonymization algorithms developed for structured medical health data (SMHD) in the last decade, our systematic review provides a comprehensive bird’s eye view of algorithms for SMHD anonymization.Methods: This systematic review was conducted according to the recommendations in the Cochrane Handbook for Reviews of Interventions and reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Eligible articles from the PubMed, ACM digital library, Medline, IEEE, Embase, Web of Science Collection, Scopus, ProQuest Dissertation, and Theses Global databases were identified through systematic searches. The following parameters were extracted from the eligible studies: author, year of publication, sample size, and relevant algorithms and/or software applied to anonymize SMHD, along with the summary of outcomes.Results: Among 1,804 initial hits, the present study considered 63 records including research articles, reviews, and books. Seventy five evaluated the anonymization of demographic data, 18 assessed diagnosis codes, and 3 assessed genomic data. One of the most common approaches was k-anonymity, which was utilized mainly for demographic data, often in combination with another algorithm; e.g., l-diversity. No approaches have yet been developed for protection against membership disclosure attacks on diagnosis codes.Conclusion: This study reviewed and categorized different anonymization approaches for MHD according to the anonymized data types (demographics, diagnosis codes, and genomic data). Further research is needed to develop more efficient algorithms for the anonymization of diagnosis codes and genomic data. The risk of reidentification can be minimized with adequate application of the addressed anonymization approaches.Systematic Review Registration: [http://www.crd.york.ac.uk/prospero], identifier [CRD42021228200].

BackgroundImpairment of bowel, urogenital and fertility-related function in patients treated for rectal cancer is common. While the rate of rectal cancer in the young (

BackgroundA regular task by developers and users of synthetic data generation (SDG) methods is to evaluate and compare the utility of these methods. Multiple utility metrics have been proposed and used to evaluate synthetic data. However, they have not been validated in general or for comparing SDG methods. ObjectiveThis study evaluates the ability of common utility metrics to rank SDG methods according to performance on a specific analytic workload. The workload of interest is the use of synthetic data for logistic regression prediction models, which is a very frequent workload in health research. MethodsWe evaluated 6 utility metrics on 30 different health data sets and 3 different SDG methods (a Bayesian network, a Generative Adversarial Network, and sequential tree synthesis). These metrics were computed by averaging across 20 synthetic data sets from the same generative model. The metrics were then tested on their ability to rank the SDG methods based on prediction performance. Prediction performance was defined as the difference between each of the area under the receiver operating characteristic curve and area under the precision-recall curve values on synthetic data logistic regression prediction models versus real data models. ResultsThe utility metric best able to rank SDG methods was the multivariate Hellinger distance based on a Gaussian copula representation of real and synthetic joint distributions. ConclusionsThis study has validated a generative model utility metric, the multivariate Hellinger distance, which can be used to reliably rank competing SDG methods on the same data set. The Hellinger distance metric can be used to evaluate and compare alternate SDG methods.

Abstract Background TNF-α plays a role in angiogenesis and collagen synthesis, both essential in the wound healing process. There are concerns that pre-operative anti-TNF-α treatment may influence the surgical stress response and increase the risk of surgical complications. The aim of this study was to describe the surgical stress response in patients with inflammatory bowel disease (IBD) and to investigate whether the pre-operative administration of anti-tumor necrosis factor alpha (anti-TNF-α) agents modify the surgical stress response. Methods This was a prospective, multi-center cohort pilot study. The primary outcome was the change in concentration of immunological biomarkers of the surgical stress response (TNF-α, IL-6, and IL-10). Secondary outcome measures were changes in IL-8, IL-17A, C-reactive protein, white blood cells, cortisol, transferrin, ferritin, and D-Dimer in addition to 30 days’ post-operative complications and length of post-operative stay in the hospital (LOS). Results Forty-six patients with IBD undergoing major abdominal surgery were included, and 18 received anti-TNF- α treatment pre-operatively. Peak increase of most of the immunological biomarkers occurred 6 hours after surgical incision. Then the concentration decreased after 24 h followed by a plateau at 48 h. After adjusting for confounders including detectable blood concentrations, no difference in the concentrations of immunological, endocrinological or haematological biomarkers of stress was found between anti-TNF-α treated and anti-TNF-α naïve patients. No increase in post-operative complications or LOS was noticed in patients who received anti-TNF-α treatment. Conclusions Anti-TNF-α did not affect surgical stress response in this pilot study. Withdrawal of anti-TNF-α drugs prior to surgical intervention in IBD patients might not be justified without measurement of drug concentration and drug antibodies. Trial registration Clinicaltrails.gov.: NCT01974869.