EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Moving beyond the empty cell: The threat of decontextualized healthcare data

Aya El Mir iD, Eric Bezerra de Sousa iD, Ignacio Mesina-Estarrón, Leo Anthony Celi, Moad Hani, Mohammed Benjelloun, Neha Nageswaran, Saïd Mahmoudi, Shaheen Siddiqui, Sreeram Sadasivam, William Greig Mitchell iD

PLOS Digital Health · 13.01.2026 · 5 (1) · e0001194

DOI: 10.1371/journal.pdig.0001194 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift PLOS Digital Health, online erschienen am 13.01.2026. Verfasst von Aya El Mir und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Missing, inaccurate, or poorly documented data in healthcare is often treated as a technical problem to be statistically resolved via imputation, deletion, or modeling assumptions about randomness. However, such inaccuracies relate to far more complex socioeconomic and geopolitical issues, rather than “errors of data entry” to be ameliorated with statistical modeling techniques. We outline that what is really missing or inaccurate is the context in which the data is collected—and that only by understanding this context can we begin to prevent artificial intelligence’s (AIs) amplification of misleading, decontextualized data. We critically examine how traditional modeling methods fail to account for the factors that influence what data gets recorded, and for whom. We show how AI systems trained on decontextualized data reinforce health inequities at scale. And, we review recent literature on context-aware approaches to understanding data, that incorporate metadata, social determinants of health, fairness constraints, and participatory governance to build more ethical and representative systems. Our analysis urges the AI and healthcare communities to move beyond the traditional emphasis on statistical convenience, toward socially grounded and interdisciplinary strategies for handling decontextualized data.

Autor:innen und Institutionen

  • Department of Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates.
  • Faculty of Medicine, University of Sao Paulo, Sao Paulo, Brazil.
  • Department of Neurosurgery, Children's Hospital of Orange County, Orange, California, United States of America.
  • Laboratory for Computational Physiology, Massachusetts Institute of Technology, Massachusetts, United States of America.
  • Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, United States of America.
  • Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, United States of America.

ORCID-Profile: Aya El Mir, Eric Bezerra de Sousa, William Greig Mitchell

Zitieren

APA

El Mir, A., de Sousa, E. B., Mesina-Estarrón, I., Celi, L. A., Hani, M., Benjelloun, M., Nageswaran, N., Mahmoudi, S., Siddiqui, S., Sadasivam, S., & Mitchell, W. G. (2026). Moving beyond the empty cell: The threat of decontextualized healthcare data. PLOS Digital Health, 5(1), e0001194. https://doi.org/10.1371/journal.pdig.0001194

Vancouver

El Mir A, de Sousa EB, Mesina-Estarrón I, Celi LA, Hani M, Benjelloun M, et al. Moving beyond the empty cell: The threat of decontextualized healthcare data. PLOS Digital Health. 2026;5(1):e0001194. doi:10.1371/journal.pdig.0001194

BibTeX
@article{ElMir2026,
  author = {El Mir, Aya and de Sousa, Eric Bezerra and Mesina-Estarrón, Ignacio and Celi, Leo Anthony and Hani, Moad and Benjelloun, Mohammed and Nageswaran, Neha and Mahmoudi, Saïd and Siddiqui, Shaheen and Sadasivam, Sreeram and Mitchell, William Greig},
  title = {Moving beyond the empty cell: The threat of decontextualized healthcare data},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {1},
  pages = {e0001194},
  doi = {10.1371/journal.pdig.0001194}
}
Kostenlos starten →