Realistic Synthetic Data Generation: The ATEN Framework

Abstract

In secondary uses of data, access to real data is problematic due to data being non-existent, incomplete, or avoiding privacy and confidentiality breaches. Synthetic data (SD) are best replacements for real data but must be verifiably realistic. There is little or no investigation into systematically achieving realism in SD. This work investigates this problem, and contributes the ATEN framework, which incorporates three component approaches: (1) THOTH for synthetic data generation (SDG); (2) RA for characterising realism is SD, and (3) HORUS for validating realism in SD. The framework is found promising after its use in generating the realistic synthetic EHR (RS-EHR) for labour and birth. This framework is significant in guaranteeing realism in SDG projects. Future efforts focus on further validation of ATEN in a controlled multi-stream SDG process.

The Health Condition Timeline as a Model for Pregnancy Disease Management

“…Other data were also anonymised, including replacing the date of birth with an age in years, and delta shifting all dates in the patient record using a consistent randomly assigned number of days for each patient. All examples provided in the tables in this work are representative of the real anonymised data collected and used during the project, but were synthetically generated for this paper using the method described in [37]. Table 2 shows an example of raw patient demographics data.…”

Synthetic data & the future of Women’s Health: A synergistic relationship

“…Content models are a modelling method for synthetic data generated via electronic health records (EHR) and was originally proposed by McLachlan and colleagues to develop synthetic EHRs based on publicly available health information statistics coupled with the expertise of clinicians [14].…”

Synthetic data generation for tabular health records: A systematic review

“…The Aten framework was proposed by McLachlan et al in 2019 [43] to generate synthetic Labour and Birth EHRs whilst characterizing and validating its realism by gathering the necessary knowledge, identifying realistic properties from real data and validating the realism of SD.…”