SynthEye: Investigating the Impact of Synthetic Data on Artificial Intelligence-assisted Gene Diagnosis of Inherited Retinal Disease

Veturi, Yoga Advaith; Woof, William; Lazebnik, Teddy; Moghul, Ismail; Woodward-Court, Peter; Wagner, Siegfried; Guimarães, Thales Antonio Cabral de; Varela, Malena Daich; Liefers, Bart; Patel, Praveen J; Beck, Stephan; Webster, Andrew R.; Mahroo, Omar Abdul Rahman; Keane, Pearse Andrew; Michaelides, Michel; Balaskas, Konstantinos; Pontikos, Nikolas

doi:10.1016/j.xops.2022.100258

Cited by 21 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The series of clinical Turing tests that were performed provided a robust validation method to confirm the realism of the synthetic ECG dataset. Whilst Turing tests have been used to validate other forms of synthetic medical imaging data, [27][28][29][30] our iterative methodology is novel as it integrates healthcare professionals' feedback to enhance the realism of the synthetic images. The methodology described in this study presents a framework that can be used by other disciplines to generate large, life-like synthetic patient datasets reducing the requirement to prospectively create new patient datasets.…”

Section: Discussionmentioning

confidence: 99%

“…For each round of Turing Tests, we measured the Accuracy (overall proportion of ECGs correctly identified as ‘real-world’ or ‘synthetic’), True Recognition Rate (proportion of real-world ECGs identified correctly) and False Recognition Rate (proportion of synthetic ECGs identified correctly) using adapted terminology from previous Turing tests used in healthcare research. [28,30] The Fleiss-Kappa score was calculated to evaluate the degree of inter-observer agreement. For the second and third rounds of clinical Turing tests, confidence Likert scale scores were converted to a signed ordinal scale for AUC-ROC score analysis.…”

Section: Methodsmentioning

confidence: 99%

“…A series of visual Turing tests were designed using previously published healthcare research utilising image-based Turing testing [27][28][29][30] and conducted to assess the fidelity of synthetic ECG images via an online survey (Qualtrics, Provo, UT). In all rounds of Turing tests, healthcare professionals were provided with a series of 60 images comprising 30 synthetically created ECGs and 30 photographs of real-world ECGs.…”

Section: Clinical Turing Testsmentioning

confidence: 99%

See 2 more Smart Citations

GenECG: A synthetic image-based ECG dataset to augment artificial intelligence-enhanced algorithm development

Bodagh,

Tun,

Barton

et al. 2023

Preprint

View full text Add to dashboard Cite

Artificial intelligence-enhanced electrocardiogram (AI-ECG) analysis has the potential to transform care of cardiovascular disease patients. Most algorithms rely on digitised signal data and are unable to analyse paper-based ECGs, which remain in use in numerous clinical settings. An image-based ECG dataset incorporating artefacts common to paper-based ECGs, which are typically scanned or photographed into electronic health records, could facilitate development of clinically useful image-based algorithms. This paper describes the creation of GenECG, a high-fidelity, synthetic image-based dataset containing 21,799 ECGs with artefacts encountered in routine care. Iterative clinical Turing tests confirmed the realism of the synthetic ECGs: expert observer accuracy of discrimination between real-world and synthetic ECGs fell from 63.9% (95% CI 58.0%- 69.8%) to 53.3% (95% CI: 48.6%-58.1%) over three rounds of testing, indicating that observers could not distinguish between synthetic and real ECGs. GenECG is the first publicly available synthetic image-based ECG dataset to pass a clinical Turing test. The dataset will enable image-based AI-ECG algorithm development, ensuring the translation of AI-ECG research developments to the clinical workspace.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Clinical Turing Testsmentioning

confidence: 99%

See 1 more Smart Citation

GenECG: A synthetic image-based ECG dataset to augment artificial intelligence-enhanced algorithm development

Bodagh,

Tun,

Barton

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…As such, τ should be a relatively small portion of the original dataset. Recent work shows that integrating up to 25% of synthetic data obtained by an ML model or generative adversarial neural networks can contribute to classification and regression tasks [94][95][96] . Following these results, we suggest setting τ between 5% and 20% of the original data set size.…”

Section: Genetic Algorithm Based Symbolic Regression Componentmentioning

confidence: 99%

A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge

Keren

Liberzon

Lazebnik

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Discovering a meaningful symbolic expression that explains experimental data is a fundamental challenge in many scientific fields. We present a novel, open-source computational framework called Scientist-Machine Equation Detector (SciMED), which integrates scientific discipline wisdom in a scientist-in-the-loop approach, with state-of-the-art symbolic regression (SR) methods. SciMED combines a wrapper selection method, that is based on a genetic algorithm, with automatic machine learning and two levels of SR methods. We test SciMED on five configurations of a settling sphere, with and without aerodynamic non-linear drag force, and with excessive noise in the measurements. We show that SciMED is sufficiently robust to discover the correct physically meaningful symbolic expressions from the data, and demonstrate how the integration of domain knowledge enhances its performance. Our results indicate better performance on these tasks than the state-of-the-art SR software packages , even in cases where no knowledge is integrated. Moreover, we demonstrate how SciMED can alert the user about possible missing features, unlike the majority of current SR systems.

show abstract

“… 4 Furthermore, the performance of the algorithms was highly dependent on demographic and clinical characteristics of the study population, suggesting the need to validate AI models in the intended use populations. Several studies in this special issue discussed algorithm bias, need for independent validations, and need for more training data, especially in rare disease, 5 , 6 , 7 , 8 all of which are important steps forward in our Big Data and AI research.…”

mentioning

confidence: 99%

Entering the Exciting Era of Artificial Intelligence and Big Data in Ophthalmology

Lee,

Brandt,

Lee

2024

Ophthalmology Science

View full text Add to dashboard Cite

SynthEye: Investigating the Impact of Synthetic Data on Artificial Intelligence-assisted Gene Diagnosis of Inherited Retinal Disease

Cited by 21 publications

References 35 publications

GenECG: A synthetic image-based ECG dataset to augment artificial intelligence-enhanced algorithm development

GenECG: A synthetic image-based ECG dataset to augment artificial intelligence-enhanced algorithm development

A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge

Entering the Exciting Era of Artificial Intelligence and Big Data in Ophthalmology

Contact Info

Product

Resources

About