Synthetic Data in Healthcare

arXiv 2304.03243 ↗First posted 6 Apr 2023cs.AI cs.LG stat.APcited by 8

Not on the map. Why?

Abstract (arXiv)

Synthetic data are becoming a critical tool for building artificially intelligent systems. Simulators provide a way of generating data systematically and at scale. These data can then be used either exclusively, or in conjunction with real data, for training and testing systems. Synthetic data are particularly attractive in cases where the availability of ``real'' training examples might be a bottleneck. While the volume of data in healthcare is growing exponentially, creating datasets for novel tasks and/or that reflect a diverse set of conditions and causal relationships is not trivial. Furthermore, these data are highly sensitive and often patient specific. Recent research has begun to illustrate the potential for synthetic data in many areas of medicine, but no systematic review of the literature exists. In this paper, we present the cases for physical and statistical simulations for creating data and the proposed applications in healthcare and medicine. We discuss that while synthetics can promote privacy, equity, safety and continual and causal learning, they also run the risk of introducing flaws, blind spots and propagating or exaggerating biases.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 44 of its 110 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

44 of 110 references.

References · 44

2020Denoising Diffusion Probabilistic Modelscited by 20,851
2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
2022Generative Adversarial Networkscited by 5,603
2013Auto-Encoding Variational Bayescited by 3,980
2016Equality of Opportunity in Supervised Learningcited by 2,000
2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
2018Model Cards for Model Reportingcited by 1,068
2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 996
2016Semantics derived automatically from language corpora contain human-like biasescited by 894
2020COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Imagescited by 264

32 more

2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
2015Doctor AI: Predicting Clinical Events via Recurrent Neural Networkscited by 205
2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 146
2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
2018Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Networkcited by 97
2022DataPerf: Benchmarks for Data-Centric AI Developmentcited by 89
2019Bias Correction of Learned Generative Models using Likelihood-Free Importance Weightingcited by 70
2018A Review of Challenges and Opportunities in Machine Learning for Healthcited by 67
2021CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detectioncited by 64
2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 58
2017Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Trainingcited by 57
2021Camera Measurement of Physiological Vital Signscited by 49
2022A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Modelscited by 43
2017Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Recordscited by 36
2019DermGAN: Synthetic Generation of Clinical Skin Images with Pathologycited by 33
2020SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classificationcited by 32
2022SCAMPS: Synthetics for Camera Measurement of Physiological Signalscited by 28
2016Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Explorationcited by 26
2019Characterizing Bias in Classifiers using Generative Modelscited by 23
2021CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoningcited by 23
2020Endo-Sim2Real: Consistency learning-based domain adaptation for instrument segmentationcited by 20
2020Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Datacited by 16
2020Advancing Non-Contact Vital Sign Measurement using Synthetic Avatarscited by 15
2020XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantomscited by 11
2022Virtual Histological Staining of Label-Free Total Absorption Photoacoustic Remote Sensing (TA-PARS)cited by 10
2019Visual Physics: Discovering Physical Laws from Videoscited by 9
2020Hide-and-Seek Privacy Challengecited by 8
2022Decouple-and-Sample: Protecting sensitive information in task agnostic data releasecited by 4
2015Model Validation for Vision Systems via Graphics Simulationcited by 3
2022MIME: Minority Inclusion for Majority Group Enhancement of AI Performancecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 3; 2026: 2.

8 papers.