EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Limitations of Retrospective Machine Learning Models for Predicting Tracheostomy After Cardiac Surgery

Felix Wiesmueller iD, Johannes Rösch, Stephan Kersting iD, Thomas Strecker iD

Diagnostics · 04.03.2026 · 16 (5) · 771

DOI: 10.3390/diagnostics16050771 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 04.03.2026. Verfasst von Felix Wiesmueller und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, University Hospital Greifswald, University of Greifswald, 17475 Greifswald, Germany. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Early tracheostomy seems favorable in prolonged ventilated patients after surgery. Hence, predicting tracheostomy after cardiac surgery is essential. Recently proposed prediction models aim to support this decision-making process, but their diagnostic validity across other patient populations remains uncertain.

Methods

A retrospective single-center study was performed at a university hospital. The patient sample included consecutive patients between 2010 and 2020 who underwent cardiac surgery. Patients who underwent tracheostomy after cardiac surgery were assigned to the intervention group. Control group patients, who had not undergone tracheostomy, were randomly assigned to the group. An existing model was evaluated by receiver operating characteristics curve analysis. Four sets of risk features were chosen depending on results from regression analysis, lasso regularization, random forest or clinical domain knowledge. Newly developed models were created using machine learning methods: random forest, naïve Bayes, nearest neighbor and deep learning. Multiple models were trained with either feature set and then assessed using confusion matrices on an independent test set.

Results

A total of 4744 patients were included in this study. One-hundred and eighteen patients were included in the tracheostomy group. Diagnostic accuracy of the existing model showed insufficient discrimination (area under the curve (AUC) = 0.57). Likewise, newly developed models also showed overall poor diagnostic discrimination across all feature sets and algorithms.

Conclusions

This study shows the diagnostic limitations of retrospective clinical data for the diagnostic prediction of tracheostomy, thereby informing the design of future prospective diagnostic studies. Training new models should not rely on retrospective data alone. Instead, prospective data collection and integration of physiological or imaging-based diagnostics could likely contribute to the development of a good classifier.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecardiac surgerydeep learningdiagnostic validationmachine learningprediction modeltracheostomy

Autor:innen und Institutionen

  • Department of Surgery, University Hospital Greifswald, University of Greifswald, 17475 Greifswald, Germany.
  • Department of Cardiac Surgery, University Hospital Erlangen, Friedrich-Alexander-University of Erlangen-Nuremberg (FAU), 91054 Erlangen, Germany.

ORCID-Profile: Felix Wiesmueller, Stephan Kersting, Thomas Strecker

Zitieren

APA

Wiesmueller, F., Rösch, J., Kersting, S., & Strecker, T. (2026). Limitations of Retrospective Machine Learning Models for Predicting Tracheostomy After Cardiac Surgery. Diagnostics, 16(5), 771. https://doi.org/10.3390/diagnostics16050771

Vancouver

Wiesmueller F, Rösch J, Kersting S, Strecker T. Limitations of Retrospective Machine Learning Models for Predicting Tracheostomy After Cardiac Surgery. Diagnostics. 2026;16(5):771. doi:10.3390/diagnostics16050771

BibTeX
@article{Wiesmueller2026,
  author = {Wiesmueller, Felix and Rösch, Johannes and Kersting, Stephan and Strecker, Thomas},
  title = {Limitations of Retrospective Machine Learning Models for Predicting Tracheostomy After Cardiac Surgery},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {5},
  pages = {771},
  doi = {10.3390/diagnostics16050771}
}
Kostenlos starten →