Abstract
Abstract
Purpose
Synthetic data has garnered heightened attention in contemporary research due to confidentiality barriers and its capacity to simulate variables challenging to obtain, notably in cases where premature death prevents adequate follow-up. Indeed, a significant challenge in clinical neuro-oncology research is the limited availability of data pertinent to rapid-onset conditions with relatively poor prognoses. This study aimed to evaluate the reliability and validity of synthetic data in the context of neuro-oncology research, comparing findings from two published studies with results from synthetic datasets.
Materials and Methods
Two published neuro-oncology studies focusing on prognostic factors were selected, and their methodologies were replicated using MDClone Platform to generate five synthetic datasets for each. These datasets were assessed for inter-variability and compared against the original study results.
Results
Findings from synthetic data consistently matched outcomes from both original articles. Reported findings, demographic trends and survival outcomes showed significant similarity (P < 0.05) with synthetic datasets. Moreover, synthetic data produced consistent results across multiple datasets.
Conclusion
Integrating synthetic data into clinical research offers excellent potential for providing accurate predictive insights without compromising patient privacy. In neuro-oncology, where data fragmentation and patient follow-up pose significant challenges, the adoption of synthetic datasets can be transformative.
Publisher
Research Square Platform LLC
Reference10 articles.
1. Synthetic data in health care: A narrative review;Gonzales A;PLOS Digit Health,2023
2. Preserving Data Publishing;Mohan;J Sci Technol Res,2017
3. Analyzing Medical Research Results Based on Synthetic Data and Their Relation to Real Data Results: Systematic Comparison From Five Observational Studies;Reiner;JMIR Med Inform,2020
4. Construction and validation of synthetic electronic medical records;Moniz L;Online J Public Health Inform,2009
5. Spot the difference: comparing results of analyses from real patient data and synthetic derivatives;Foraker RE;JAMIA Open,2020
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献