Automated triage in pandemics: Support vector machine for efficient patient classification - 01/05/26
, Anahi Flores-Pérez e, Debbie Hernández f, Eli Abraham Vázquez-Orduña gHighlights |
• | Before the COVID-19 pandemic emergency departments around the world were already overcrowded. |
• | Triage protocols can improve and physicians may override algorithms with experience to prevent under-triage. |
• | This SVM-based system replicates triage decisions and physician criteria used to prevent under-triage. |
• | SVM system identifies green/red patients with 94% accuracy using 96 samples, replicating triage for new pathogens. |
• | SVM triage systems can address COVID-19 respiratory cases and all emergencies covered by conventional algorithms. |
Abstract |
Introduction |
We aimed to develop tools to ease the burden on medical staff while improving patient care. The central question is whether Support Vector Machines (SVMs), trained solely on patients’ self-reported data (symptoms, demographics, comorbidities), can achieve triage accuracy comparable to or surpassing traditional score-based systems in emergency departments under pandemic conditions.
Methods |
We propose an SVM-based approach to replicate COVID-19 triage using patient-provided information rather than laboratory tests. The system automates triage scoring, classifying patients into red, yellow, or green categories. A computer program records patient data and calculates scores, while physicians have the ability to override results based on their clinical judgment.
Results |
The system integrates clinical expertise, enhancing rather than replacing physicians’ roles. It achieved over 98% accuracy in red-triage classification using less than 2.8% of training data.
Conclusions |
This SVM-based triage model shows promise for improving emergency department processes, accuracy, and patient outcomes in high-demand situations.
Le texte complet de cet article est disponible en PDF.Keywords : COVID-19, Pandemics, Resource allocation, InfectiousDiseases, SupportVector Machines
Plan
Vol 56 - N° 3
Article 105267- avril 2026 Retour au numéro
Article précédent
- HIV reservoir dynamics according to the timing of antiretroviral therapy initiation or modification
- Pierre Gantner, Christine Cheneau, Jakub Kowalczyk, Jean-Pierre Faller, Martin Martinot, Mahsa Mosheni-Zadeh, Anne Fuchs, David Rey, Samira Fafi-Kremer
- Transcriptomic insights into nosocomial infection bacteria in conflict-affected Northeast Syria
- Haidar Saify Nabiabad, Massoume Amini
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?