A multi-modal temporal fusion transformer for comprehensive decision support across the emergency care trajectory

Emergency care in the emergency department (ED) requires continuous, multifaceted decision-making based on evolving clinical information. This study aimed to develop and externally validate a comprehensive ED decision-support model based on a Temporal Fusion Transformer (TFT) with multi-modal time-series data to jointly predict testing, treatment, diagnosis, and disposition.

Adult ED visit data from one hospital were used for model development, and data from another hospital for external validation. The static inputs included patient characteristics, ED visit-related information, and triage notes, while the time-varying inputs included vital signs, laboratory results, management, and clinical notes. The primary outcomes were the areas under the receiver operating characteristic curves (AUCs) for predicting computed tomography, magnetic resonance imaging, echocardiography, gastrointestinal endoscopy, mechanical ventilation (MV), antibiotic administration, oxygen therapy, vasopressor use, transfusion, primary diagnosis, and ED disposition. A single TFT model was trained to predict all targets jointly, and separate Random Forest (RF) models were developed for comparison.

The development and external validation datasets included 272,058 and 138,343 patients, respectively (median age, 61-62 years; females, 51.3%-51.7%). Across internal and external validation, the TFT demonstrated strong discrimination for tests (AUC 0.877-0.961), treatments (AUC 0.912-0.990), and disposition outcomes (AUC 0.811-0.905). The top-5 accuracy for diagnosis prediction was 73.7% and 65.4% in the internal and external validation, respectively. The TFT outperformed RF models for most targets and showed comparable performance in predicting MV, oxygen therapy, and vasopressor use.

The TFT model achieved high accuracy across multiple ED decisions, demonstrating its potential as a comprehensive and temporally aware decision-support tool throughout the ED trajectory.