What question did this study set out to answer?

December 13, 2025Scientific ReportsOpen Access

AI-powered models for overcrowding prediction at TUMS hospitals

View Full Paper

Ask AI

Bookmark

The research aims to enhance overcrowding prediction in emergency departments at TUMS hospitals using AI models.
Utilized a time series dataset across 5 hospitals.
Employed feature selection using minimum redundancy maximum relevance (mRMR).
Applied multiple base learners including linear regression, SVM, and LSTM with Bayesian tuning.
Combined models using ensemble methods such as VP-BMA.
Feature selection significantly improved modeling performance.
SVM and LSTM showed the most reliable performance across emergency departments.
ED A performed consistently well; EDs B and D showed poor performance.

No takes yet. Share an insight, caveat, or question.

This research demonstrates improved overcrowding prediction in emergency departments, highlighting feature selection impacts on modeling.

Shaibani et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark