Unsupervised Characterization of Temporal Dataset Shifts as an Early Indicator of AI Performance Variations: Evaluation Study Using the Medical Information Mart for Intensive Care-IV Dataset

David Fernández-Narro, Pablo Ferri, Alba Gutiérrez-Sacristán, Juan M García-Gómez, Carlos Sáez

Open source

DOI
10.2196/78309
Published
2025-12-03
Container
JMIR Medical Informatics
Publisher
JMIR Publications Inc.
Open access
unknown

Credibility signals

uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.2196/78309,
  title = {Unsupervised Characterization of Temporal Dataset Shifts as an Early Indicator of AI Performance Variations: Evaluation Study Using the Medical Information Mart for Intensive Care-IV Dataset},
  author = {David Fernández-Narro and Pablo Ferri and Alba Gutiérrez-Sacristán and Juan M García-Gómez and Carlos Sáez},
  year = {2025},
  journal = {JMIR Medical Informatics},
  doi = {10.2196/78309},
  url = {https://doi.org/10.2196/78309}
}

RIS

TY  - JOUR
TI  - Unsupervised Characterization of Temporal Dataset Shifts as an Early Indicator of AI Performance Variations: Evaluation Study Using the Medical Information Mart for Intensive Care-IV Dataset
AU  - David Fernández-Narro
AU  - Pablo Ferri
AU  - Alba Gutiérrez-Sacristán
AU  - Juan M García-Gómez
AU  - Carlos Sáez
PY  - 2025
JO  - JMIR Medical Informatics
DO  - 10.2196/78309
UR  - https://doi.org/10.2196/78309
ER  - 

APA

Fernández-Narro, D., Ferri, P., Gutiérrez-Sacristán, A., García-Gómez, J. M., & Sáez, C. (2025). Unsupervised Characterization of Temporal Dataset Shifts as an Early Indicator of AI Performance Variations: Evaluation Study Using the Medical Information Mart for Intensive Care-IV Dataset. JMIR Medical Informatics. https://doi.org/10.2196/78309

Source records