Metraipolis › archive › dc_73be62374e73

Assessing generalizability of an AI-based visual test for cervical cancer screening — Europe PMC PMID:39356713

Source
Europe PMC (en)
Original
https://europepmc.org/article/MED/39356713
DOI
10.1371/journal.pdig.0000364
License (as archived)
CC0-1.0
Archived
2026-10-06T15:19:16.267Z
SHA-256 of the archived text
47c2911f05253de3281ea331e6da932cb18d657cfdd13424a22dad3bf263436c
Stable URL of this page
https://metraipolis.com/documento/dc_73be62374e73

How to cite

Assessing generalizability of an AI-based visual test for cervical cancer screening — Europe PMC PMID:39356713 — Europe PMC (en), https://europepmc.org/article/MED/39356713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73be62374e73 (Metraipolis archive dc_73be62374e73, sha256 47c2911f05253de3281ea331e6da932cb18d657cfdd13424a22dad3bf263436c)
BibTeX
@misc{dc73be62374e73,
  title = {Assessing generalizability of an AI-based visual test for cervical cancer screening — Europe PMC PMID:39356713},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/39356713},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73be62374e73; sha256 47c2911f05253de3281ea331e6da932cb18d657cfdd13424a22dad3bf263436c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/39356713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A number of challenges hinder artificial intelligence (AI) models from effective clinical translation. Foremost among these challenges is the lack of generalizability, which is defined as the ability of a model to perform well on datasets that have different characteristics from the training data. We recently investigated the development of an AI pipeline on digital images of the cervix, utilizing a multi-heterogeneous dataset 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 investigate the performance of this multiclass classifier on external data not utilized in training and internal validation, to assess the generalizability of the classifier when moving to new settings. We assessed both the classification performance and repeatability of our classifier model 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 external data. Our results demonstrate that device-level heterogeneity affects our model performance more than geography-level heterogeneity. Classification performance of our model is strong on images from a new geography without retraining, while incremental retraining with inclusion of images from a new device progressively improves classification performance on that device up to a point of saturation. Repeatability of our model is relatively unaffected by data heterogeneity and remains strong throughout. Our work supports 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.

Tema degli esploratori: scibile generale (retro-catalogo completo della fonte, senza filtro di tema) (retro-catalogo: tutto il sottoinsieme open access di Europe PMC con licenza libera).
Pubblicazione: PLOS digital health, 2024 (prima pubblicazione 2024-10-02).
Identificativi: PMID 39356713 · PMCID PMC11446437 · DOI 10.1371/journal.pdig.0000364.
Pagina: https://europepmc.org/article/MED/39356713 — https://doi.org/10.1371/journal.pdig.0000364. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0.
Letto il 2026-10-06T15:11:56.380Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.