September 10, 2025Applied SciencesOpen Access

Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study

View Full Paper

Ask AI

Bookmark

Authors

ÉAÉ. Arnaud PMPedro A. Moreno-SánchezTampere University MEMahmoud ElbattahUniversity of the West of England

Discussion

Member takes

Implication

Retrospective study demonstrated an explainable artificial intelligence model that predicts admissions in emergency departments, indicating improved patient management.

Key Points

The ANN model achieved an AUROC of 83.2% during internal validation, highlighting its predictive accuracy for emergency department admissions.
Current metrics showed that the optimal threshold for F1 score was 0.35, yielding a recall of 75.7% and precision of 59.7%.
SHAP and PDP XAI techniques identified critical factors like patient age and heart rate influencing admissions, providing valuable insights for operational efficiency.
The 3P-U model enhances decision-making in emergency departments, potentially reducing crowding and improving patient flow management.

Cite This Study

Arnaud et al. (2025) studied this question.

synapsesocial.com/papers/68c23e02b210217d647905a0 https://doi.org/10.3390/app15158449

View Full Paper

Ask AI

Bookmark

Implication

Retrospective study demonstrated an explainable artificial intelligence model that predicts admissions in emergency departments, indicating improved patient management.

Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study

Discussion

Member takes

Implication

Key Points

Cite This Study

Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider