Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review

Hond, Anne de; Leeuwenberg, Artuur; Hooft, Lotty; Kant, Ilse; Nijman, Steven W J; Os, Hendrikus J.A. van; Aardoom, Jiska J; Debray, Thomas P A; Schuit, Ewoud; Smeden, Maarten van; Reitsma, Johannes B.; Steyerberg, Ewout W.; Chavannes, Niels H.; Moons, Karel G.M.

doi:10.1038/s41746-021-00549-7

Cited by 214 publications

(190 citation statements)

References 73 publications

Supporting

Mentioning

155

Contrasting

Order By: Relevance

“…The importance of error auditing in AI cannot be underestimated to identify and prevent algorithmic bias both inside and outside of healthcare. 29 30 …”

Section: Discussionmentioning

confidence: 99%

Diagnostic accuracy of code-free deep learning for detection and evaluation of posterior capsule opacification

et al. 2022

View full text Add to dashboard Cite

ObjectiveTo train and validate a code-free deep learning system (CFDLS) on classifying high-resolution digital retroillumination images of posterior capsule opacification (PCO) and to discriminate between clinically significant and non-significant PCOs.Methods and analysisFor this retrospective registry study, three expert observers graded two independent datasets of 279 images three separate times with no PCO to severe PCO, providing binary labels for clinical significance. The CFDLS was trained and internally validated using 179 images of a training dataset and externally validated with 100 images. Model development was through Google Cloud AutoML Vision. Intraobserver and interobserver variabilities were assessed using Fleiss kappa (κ) coefficients and model performance through sensitivity, specificity and area under the curve (AUC).ResultsIntraobserver variability κ values for observers 1, 2 and 3 were 0.90 (95% CI 0.86 to 0.95), 0.94 (95% CI 0.90 to 0.97) and 0.88 (95% CI 0.82 to 0.93). Interobserver agreement was high, ranging from 0.85 (95% CI 0.79 to 0.90) between observers 1 and 2 to 0.90 (95% CI 0.85 to 0.94) for observers 1 and 3. On internal validation, the AUC of the CFDLS was 0.99 (95% CI 0.92 to 1.0); sensitivity was 0.89 at a specificity of 1. On external validation, the AUC was 0.97 (95% CI 0.93 to 0.99); sensitivity was 0.84 and specificity was 0.92.ConclusionThis CFDLS provides highly accurate discrimination between clinically significant and non-significant PCO equivalent to human expert graders. The clinical value as a potential decision support tool in different models of care warrants further research.

show abstract

“…The importance of error auditing in AI cannot be underestimated to identify and prevent algorithmic bias both inside and outside of healthcare. 29 30 …”

Section: Discussionmentioning

confidence: 99%

Diagnostic accuracy of code-free deep learning for detection and evaluation of posterior capsule opacification

et al. 2022

View full text Add to dashboard Cite

show abstract

“… AI – artificial intelligence, AUC – Area under the receiver operating characteristic curve, CRC – colorectal carcinoma *Phase I – Data collection and processing, Phase II – Model construction, Phase III – Model validation, Phase IV – Software application development, Phase V – Impact and efficiency analysis, Phase VI – Model implementation in daily oncology practices [ 21 ]. …”

Section: Implementation and Potential Refinements For Cancer-based Ar...mentioning

confidence: 99%

Artificial intelligence-based prediction for cancer-related outcomes in Africa: Status and potential refinements

et al. 2022

View full text Add to dashboard Cite

“…Covariate shift is common in medical imaging, examples include changes to imaging protocols, imaging software or equipment updates, and changing patient demographics. After a covariate shift, a deployed model may be operating in an untested or poorly validated environment wherein performance degradation becomes an obvious concern [20]. When a significant time gap exists between contemporary data and model deployment, the likelihood of drift and consequently, classification errors increases [11].…”

Section: Datamentioning

confidence: 99%

CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI

Soin¹,

Merkow²,

Jin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Background/Motivation: Rapidly expanding Clinical AI applications worldwide have the potential to impact to all areas of medical practice. Medical imaging applications constitute a vast majority of approved clinical AI applications with more than 150 to date. Though healthcare systems are eager to adopt AI solutions after initial successes in model validation and deployment for clinical workflows, fundamental questions remain: Is the model still working as expected?, What is causing the change?, Is it time to intervene? While infrastructure and local validation barriers are addressed during implementation, the larger problem looms regarding how to monitor input data and track model performance in real-time production systems. Real-world healthcare data environments are dynamic which can disrupt AI model performance, referred to as "drift". For example, medical equipment updates, new imaging workflows, changes in patient and disease characteristics, and more, can change over time and cause drift. While there are dozens of tools for monitoring drift, all lack functionality for image-based deep learning model architectures, cannot use healthcare medical imaging data, and require contemporaneous ground truth which is rarely available in healthcare settings. As a result, healthcare systems are left without insight for ongoing medical imaging model performance which poses serious safety concerns for healthcare system leadership, government regulators, and patients.Methods: In this study, we utilize the CheXpert and PadChest open datasets to build, design, and test a medical imaging AI drift monitoring workflow that can track data and model drift in the absence of contemporaneous ground truth for a chest X-ray use case. Ten pathology labels were chosen and reconciled between the two datasets in order to fine-tune a densely connected convolutional neural network on PadChest after being pre-trained on frontal-only CheXpert images. The PadChest dataset and accompanying ground truth labels were chronologically arranged and split such that all finetuning and validation used only data between 2007-2013 while tests were performed on data between 2014-2017. To test the robustness of our approach, we simulate drift in a variety of experiments and observe measured performance and drift within a data stream. We measure performance using ground truth labels and compare our drift metric with actual model performance over time in the test dataset and identify correlative signals. Drift evaluation used DICOM metadata, image appearance, and model output scores as input. Variational autoencoders (VAE) were used to capture an appearance feature encoding by using the underlying latent space representation. For continuous features (e.g.

show abstract

Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review

Cited by 214 publications

References 73 publications

Diagnostic accuracy of code-free deep learning for detection and evaluation of posterior capsule opacification

Diagnostic accuracy of code-free deep learning for detection and evaluation of posterior capsule opacification

Artificial intelligence-based prediction for cancer-related outcomes in Africa: Status and potential refinements

CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI

Contact Info

Product

Resources

About