Multimodal Attention-based Deep Learning for Emergency Triage with Electronic Health Records
Machine Learning
Summary
The authors created a computer model that helps doctors decide how urgent a patient's situation is when they arrive in the emergency room. This model looks at both the patient's main complaints written as text and their vital signs recorded as numbers. To do this well, they used a special technique called self-attention that helps the model understand important details from both types of information. Testing on real patient data showed their model made slightly better predictions than older versions. This suggests their approach could help improve emergency triage decisions.
Authors
Hazqeel Afyq Athaillah Kamarul Aryffin, Kamarul Aryffin Baharuddin, Mohd Halim Mohd Noor
Abstract
Accurate emergency triage decision is critical to avoid clinical deterioration, morbidity, and mortality. Machine learning-based triage system involves acquiring the main presenting complaint in text form and assessing vital signs in numerical data, enabling an automated and efficient analysis of patient information for timely and accurate prioritization of medical attention. However, modelling the intricacies of both data types requires a comprehensive understanding of the temporal structure and dependencies within the data. Thus, the aim of this study is to propose a multimodal deep learning architecture that can effectively handle both tabular and textual data. Furthermore, the proposed model exploits self-attention to to capture both local and global relationships between the features. A dataset consisting of 11,102 triage data collected from emergency department of Hospital Universiti Sains Malaysia is used for model development and validation. The proposed model demonstrated an increase of 1.95% in accuracy, 2.49% in F1-score, and 1.41% in ROC AUC compared to the baseline model. The experimental results demonstrated the potential of the proposed model in predicting triage decisions.