Method for Generating Synthetic Data Combining Chest Radiography Images with Tabular Clinical Information Using Dual Generative Models
This work addresses privacy and data sharing issues in the medical domain by enabling the release of synthetic datasets without compromising secondary use potential, though it is incremental as it builds on existing GAN methods.
The paper tackled the problem of generating synthetic medical records that combine chest X-ray images with tabular clinical data to address privacy concerns, using dual generative models (alphaGAN and CTGAN) to create a synthetic dataset; the result showed that training models on five times the synthetic data volume achieved classification and regression performance comparable, though slightly inferior, to using the original private dataset.
The generation of synthetic medical records using Generative Adversarial Networks (GANs) is becoming crucial for addressing privacy concerns and facilitating data sharing in the medical domain. In this paper, we introduce a novel method to create synthetic hybrid medical records that combine both image and non-image data, utilizing an auto-encoding GAN (alphaGAN) and a conditional tabular GAN (CTGAN). Our methodology encompasses three primary steps: I) Dimensional reduction of images in a private dataset (pDS) using the pretrained encoder of the αGAN, followed by integration with the remaining non-image clinical data to form tabular representations; II) Training the CTGAN on the encoded pDS to produce a synthetic dataset (sDS) which amalgamates encoded image features with non-image clinical data; and III) Reconstructing synthetic images from the image features using the alphaGAN's pretrained decoder. We successfully generated synthetic records incorporating both Chest X-Rays (CXRs) and thirteen non-image clinical variables (comprising seven categorical and six numeric variables). To evaluate the efficacy of the sDS, we designed classification and regression tasks and compared the performance of models trained on pDS and sDS against the pDS test set. Remarkably, by leveraging five times the volume of sDS for training, we achieved classification and regression results that were comparable, if slightly inferior, to those obtained using the native pDS. Our method holds promise for publicly releasing synthetic datasets without undermining the potential for secondary data usage.