Applying Artificial Neural Networks to Determine Effective Factors on Triage Level of Digestive System Disorders in the Emergency Unit

Abstract

Digestive system disorders are among the most frequent causes of emergency department (ED) visits worldwide and present a wide range of clinical severity. This study aimed to identify the most influential factors affecting triage levels of digestive disorders in EC using an artificial neural network (ANN) model. A cross-sectional study was conducted in one emergency unit in Mashhad, Iran. Data from 17,062 patients were extracted from the hospital information system. The findings identified several significant predictors of triage level: age, referral type, admission type, sex, insurance organization, referral month, and referral cause. The ANN model revealed that referral month and referral cause were the most impactful variables. Hematemesis was the predominant reason for urgent triage classification. Seasonal analysis indicated a higher incidence of nausea, vomiting, and diarrhea during the summer months in this city, highlighting the influence of travel and environmental factors on ED utilization. The ANN model validated conventional statistical analysis by elucidating complex interactions among predictors, demonstrating its potential to enhance patient prioritization for digestive system conditions and support ED triage decisions.

Received: 9 January 2026 | Revised: 13 May 2026 | Accepted: 25 May 2026

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The data that support this work are available upon reasonable request to the corresponding author.

Author Contribution Statement

Zakiyeh Balouchzehi: Writing – original draft, Writing – review & editing, Visualization. Mohaddeseh Badpeyma: Writing – original draft, Writing – review & editing, Visualization. Tahmineh Aldaghi: Writing – original draft, Writing – review & editing, Visualization, Project administration. Hamed Tabesh: Conceptualization, Methodology, Validation, Formal analysis, Investigation, Resources. Reza Akhavan: Software, Data curation. Zahra Ebnehoseini: Validation, Formal analysis, Investigation, Resources. Elham Nazari: Conceptualization, Methodology, Supervision, Project administration, Funding acquisition.