FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387083732> ?p ?o ?g. }

• W4387083732 abstract "ABSTRACT A number of challenges hinder artificial intelligence (AI) models from effective clinical translation. Foremost among these challenges are: (1) reproducibility or repeatability, which is defined as the ability of a model to make consistent predictions on repeat images from the same patient taken under identical conditions; (2) the presence of clinical uncertainty or the equivocal nature of certain pathologies, which needs to be acknowledged in order to effectively, accurately and meaningfully separate true normal from true disease cases; and (3) lack of portability or generalizability, which leads AI model performance to differ across axes of data heterogeneity. We recently investigated the development of an AI pipeline on digital images of the cervix, utilizing a multi-heterogeneous dataset (“SEED”) of 9,462 women (17,013 images) and a multi-stage model selection and optimization approach, to generate a diagnostic classifier able to classify images of the cervix into “normal”, “indeterminate” and “precancer/cancer” (denoted as “precancer+”) categories. In this work, we investigated the performance of this multiclass classifier on external data (“EXT”) not utilized in training and internal validation, to assess the portability of the classifier when moving to new settings. We assessed both the repeatability and classification performance of our classifier across the two axes of heterogeneity present in our dataset: image capture device and geography, utilizing both out-of-the-box inference and retraining with “EXT”. Our results indicate strong repeatability of our multiclass model utilizing Monte-Carlo (MC) dropout, which carries over well to “EXT” (95% limit of agreement range = 0.2 - 0.4) even in the absence of retraining, as well as strong classification performance of our model on “EXT” that is achieved with retraining (% extreme misclassifications = 4.0% for n = 26 “EXT” individuals added to “SEED” in a 2n normal : 2n indeterminate : n precancer+ ratio), and incremental improvement of performance following retraining with images from additional individuals. We additionally find that device-level heterogeneity affects our model performance more than geography-level heterogeneity. Our work supports both (1) the development of comprehensively designed AI pipelines, with design strategies incorporating multiclass ground truth and MC dropout, on multi-heterogeneous data that are specifically optimized to improve repeatability, accuracy, and risk stratification; and (2) the need for optimized retraining approaches that address data heterogeneity (e.g., when moving to a new device) to facilitate effective use of AI models in new settings. AUTHOR SUMMARY Artificial intelligence (AI) model robustness has emerged as a pressing issue, particularly in medicine, where model deployment requires rigorous standards of approval. In the context of this work, model robustness refers to both the reproducibility of model predictions across repeat images, as well as the portability of model performance to external data. Real world clinical data is often heterogeneous across multiple axes, with distribution shifts in one or more of these axes often being the norm. Current deep learning (DL) models for cervical cancer and in other domains exhibit poor repeatability and overfitting, and frequently fail when evaluated on external data. As recently as March 2023, the FDA issued a draft guidance on effective implementation of AI/DL models, proposing the need for adapting models to data distribution shifts. To surmount known concerns, we conducted a thorough investigation of the generalizability of a deep learning model for cervical cancer screening, utilizing the distribution shifts present in our large, multi-heterogenous dataset. We highlight optimized strategies to adapt an AI-based clinical test, which in our case was a cervical cancer screening triage test, to external data from a new setting. Given the severe clinical burden of cervical cancer, and the fact that existing screening approaches, such as visual inspection with acetic acid (VIA), are unreliable, inaccurate, and invasive, there is a critical need for an automated, AI-based pipeline that can more consistently evaluate cervical lesions in a minimally invasive fashion. Our work represents one of the first efforts at generating and externally validating a cervical cancer diagnostic classifier that is reliable, consistent, accurate, and clinically translatable, in order to triage women into appropriate risk categories." @default.
• W4387083732 created "2023-09-28" @default.
• W4387083732 creator A5001020883 @default.
• W4387083732 creator A5005550476 @default.
• W4387083732 creator A5006466185 @default.
• W4387083732 creator A5007169506 @default.
• W4387083732 creator A5019058409 @default.
• W4387083732 creator A5025470510 @default.
• W4387083732 creator A5028194259 @default.
• W4387083732 creator A5028424622 @default.
• W4387083732 creator A5040414468 @default.
• W4387083732 creator A5042502745 @default.
• W4387083732 creator A5044173766 @default.
• W4387083732 creator A5047356212 @default.
• W4387083732 creator A5059951020 @default.
• W4387083732 creator A5062329858 @default.
• W4387083732 creator A5072259448 @default.
• W4387083732 creator A5075288631 @default.
• W4387083732 creator A5076073861 @default.
• W4387083732 creator A5078163436 @default.
• W4387083732 creator A5084312100 @default.
• W4387083732 date "2023-09-27" @default.
• W4387083732 modified "2023-10-17" @default.
• W4387083732 title "Assessing generalizability of an AI-based visual test for cervical cancer screening" @default.
• W4387083732 cites W2035097569 @default.
• W4387083732 cites W2095753131 @default.
• W4387083732 cites W2177429266 @default.
• W4387083732 cites W2289463038 @default.
• W4387083732 cites W2963037989 @default.
• W4387083732 cites W3087507349 @default.
• W4387083732 cites W4309563912 @default.
• W4387083732 cites W4323045941 @default.
• W4387083732 cites W4387079777 @default.
• W4387083732 doi "https://doi.org/10.1101/2023.09.26.23295263" @default.
• W4387083732 hasPublicationYear "2023" @default.
• W4387083732 type Work @default.
• W4387083732 citedByCount "0" @default.
• W4387083732 crossrefType "posted-content" @default.
• W4387083732 hasAuthorship W4387083732A5001020883 @default.
• W4387083732 hasAuthorship W4387083732A5005550476 @default.
• W4387083732 hasAuthorship W4387083732A5006466185 @default.
• W4387083732 hasAuthorship W4387083732A5007169506 @default.
• W4387083732 hasAuthorship W4387083732A5019058409 @default.
• W4387083732 hasAuthorship W4387083732A5025470510 @default.
• W4387083732 hasAuthorship W4387083732A5028194259 @default.
• W4387083732 hasAuthorship W4387083732A5028424622 @default.
• W4387083732 hasAuthorship W4387083732A5040414468 @default.
• W4387083732 hasAuthorship W4387083732A5042502745 @default.
• W4387083732 hasAuthorship W4387083732A5044173766 @default.
• W4387083732 hasAuthorship W4387083732A5047356212 @default.
• W4387083732 hasAuthorship W4387083732A5059951020 @default.
• W4387083732 hasAuthorship W4387083732A5062329858 @default.
• W4387083732 hasAuthorship W4387083732A5072259448 @default.
• W4387083732 hasAuthorship W4387083732A5075288631 @default.
• W4387083732 hasAuthorship W4387083732A5076073861 @default.
• W4387083732 hasAuthorship W4387083732A5078163436 @default.
• W4387083732 hasAuthorship W4387083732A5084312100 @default.
• W4387083732 hasBestOaLocation W43870837321 @default.
• W4387083732 hasConcept C105795698 @default.
• W4387083732 hasConcept C119857082 @default.
• W4387083732 hasConcept C153180895 @default.
• W4387083732 hasConcept C154020017 @default.
• W4387083732 hasConcept C154945302 @default.
• W4387083732 hasConcept C27158222 @default.
• W4387083732 hasConcept C2776214188 @default.
• W4387083732 hasConcept C33923547 @default.
• W4387083732 hasConcept C41008148 @default.
• W4387083732 hasConcept C95623464 @default.
• W4387083732 hasConceptScore W4387083732C105795698 @default.
• W4387083732 hasConceptScore W4387083732C119857082 @default.
• W4387083732 hasConceptScore W4387083732C153180895 @default.
• W4387083732 hasConceptScore W4387083732C154020017 @default.
• W4387083732 hasConceptScore W4387083732C154945302 @default.
• W4387083732 hasConceptScore W4387083732C27158222 @default.
• W4387083732 hasConceptScore W4387083732C2776214188 @default.
• W4387083732 hasConceptScore W4387083732C33923547 @default.
• W4387083732 hasConceptScore W4387083732C41008148 @default.
• W4387083732 hasConceptScore W4387083732C95623464 @default.
• W4387083732 hasLocation W43870837321 @default.
• W4387083732 hasOpenAccess W4387083732 @default.
• W4387083732 hasPrimaryLocation W43870837321 @default.
• W4387083732 hasRelatedWork W2167582322 @default.
• W4387083732 hasRelatedWork W2556319748 @default.
• W4387083732 hasRelatedWork W2563096758 @default.
• W4387083732 hasRelatedWork W2742991909 @default.
• W4387083732 hasRelatedWork W2961085424 @default.
• W4387083732 hasRelatedWork W2972035100 @default.
• W4387083732 hasRelatedWork W3196298017 @default.
• W4387083732 hasRelatedWork W4200511449 @default.
• W4387083732 hasRelatedWork W4386053843 @default.
• W4387083732 hasRelatedWork W3158004940 @default.
• W4387083732 isParatext "false" @default.
• W4387083732 isRetracted "false" @default.
• W4387083732 workType "article" @default.