![]() However, nonaggregation techniques still pose the risk of exposing individuals, as shown by multiple reports. Other techniques include pseudoanonymization, in which a coded reference is attached to a record instead of identifying information, and aggregation, in which data are displayed as totals. One approach for preventing identification of personal records is data masking, namely, removal of identifying information from a dataset, so that individual data cannot be linked with specific individuals. Establishing effective anonymization techniques will promote the future release of data for global access, envisioning democratization of data for all researchers, and facilitate the use of real-world data as a base for study. In addition, researchers could apply for a research grant if preliminary data could be extracted and analyzed before making an IRB application, but this is impossible if the data are inaccessible.Ĭonsequently, data anonymization, namely, making reidentification of patients impossible, is required to balance the risk of privacy intrusions with research accessibility. It, therefore, requires approval of the local institutional review board (IRB), but this regulatory process is often time consuming, thereby delaying research and imposing difficulties on data sharing and collaborations. Synthetic data enable broad access to data (eg, for out-of-organization researchers), and rapid, safe, and repeatable analysis of data in hospitals or other health organizations where patient privacy is a primary value.Īccess to large databases of electronic medical records (EMRs) for research purposes is limited by privacy restriction, security laws and regulations, and organizational guidelines imposed because of the assumed value of the data. For studies based on smaller populations that accounted for confounders and modifiers by multivariate models, predictions were of moderate accuracy, yet clear trends were correctly observed.Ĭonclusions: The use of synthetic structured data provides a close estimate to real data results and is thus a powerful tool in shaping research hypotheses and accessing estimated analyses, without risking patient privacy. When the number of patients was large relative to the number of variables used, highly accurate and strongly consistent results were observed between synthetic and real data. Results: This study demonstrated that results derived from synthetic data were predictive of results from real data. In addition, repeatedly generated synthetic datasets were used to estimate the bias and stability of results obtained from synthetic data. For each study, results derived from synthetic data were compared with those based on real data. Methods: A cross-hospital project was conducted to validate results obtained from synthetic data produced for five contemporary studies on various topics. ![]() A comprehensive validation process concerning meaningful clinical questions and various types of data was conducted to assess the accuracy and precision of statistical estimates derived from synthetic patient data. Objective: This paper aimed to validate the results obtained when analyzing synthetic structured data for medical research. A system installed and activated at our institution enables synthetic data generation that mimics data from real electronic medical records, wherein only fictitious patients are listed. Consequently, data anonymization is required to allow researchers data access for initial analysis before granting institutional review board approval.
0 Comments
Leave a Reply. |