EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Impact of Data Quality Degradation on the Robustness of Clinical Regression Models: A Study on ICU Length of Stay

Nour Idris Pacha, Saber Aloui, Asma Rabaoui, Antony Escudie, Jérémie Riou

Studies in Health Technology and Informatics · 29.06.2026

DOI: 10.3233/shti260903 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 29.06.2026. Verfasst von Nour Idris Pacha und 4 weiteren Autor:innen. Beteiligte Einrichtung: Angers University Hospital, Angers, France. Hauptthemen laut MEDLINE: Length of Stay, Intensive Care Units, Machine Learning, Data Accuracy. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data quality (DQ) directly impacts the reliability of clinical machine learning systems. This study evaluates how degradations across five DQ dimensions (completeness, coherence, validity, precision, and uniqueness) affect regression models predicting ICU length of stay using the MIMIC-IV dataset. Controlled degradations were applied to evaluation data, while models were trained on clean inputs to reflect realistic deployment conditions. Prediction error increases consistently with degradation, with coherence having the strongest impact, in line with clinical intuition. Differences across model families further indicate that robustness depends in part on model architecture.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Length of StayIntensive Care UnitsMachine LearningData AccuracyElectronic Health RecordsHumansRegression AnalysisReproducibility of ResultsPredictive Learning Models

Stichwörter der Autor:innen

Data QualityElectronic Health RecordsICU Length of StayMachine LearningModel RobustnessRegression

Autor:innen und Institutionen

  • Angers University Hospital, Angers, France.
  • Enovacom, Orange Business, France.
  • MINT, INSERM UMR 1066 / CNRS UMR 6021, University of Angers, Angers, France.

Zitieren

APA

Idris Pacha, N., Aloui, S., Rabaoui, A., Escudie, A., & Riou, J. (2026). Impact of Data Quality Degradation on the Robustness of Clinical Regression Models: A Study on ICU Length of Stay. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260903

Vancouver

Idris Pacha N, Aloui S, Rabaoui A, Escudie A, Riou J. Impact of Data Quality Degradation on the Robustness of Clinical Regression Models: A Study on ICU Length of Stay. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260903

BibTeX
@article{IdrisPacha2026,
  author = {Idris Pacha, Nour and Aloui, Saber and Rabaoui, Asma and Escudie, Antony and Riou, Jérémie},
  title = {Impact of Data Quality Degradation on the Robustness of Clinical Regression Models: A Study on ICU Length of Stay},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260903}
}
Kostenlos starten →