TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency Dialogues

Telemedicine in emergency contexts presents unique challenges, particularly in multilingual and low-resource settings where accurate, clinical understanding and triage decision support are critical. This paper introduces TriagE-NLU, a novel multilingual natural language understanding system designed...

Full description

Saved in:
Bibliographic Details
Main Authors: Béatrix-May Balaban, Ioan Sacală, Alina-Claudia Petrescu-Niţă
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/7/314
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078337417871360
author Béatrix-May Balaban
Ioan Sacală
Alina-Claudia Petrescu-Niţă
author_facet Béatrix-May Balaban
Ioan Sacală
Alina-Claudia Petrescu-Niţă
author_sort Béatrix-May Balaban
collection DOAJ
description Telemedicine in emergency contexts presents unique challenges, particularly in multilingual and low-resource settings where accurate, clinical understanding and triage decision support are critical. This paper introduces TriagE-NLU, a novel multilingual natural language understanding system designed to perform both semantic parsing and clinical intervention classification from emergency dialogues. The system is built on a federated learning architecture to ensure data privacy and adaptability across regions and is trained using TriageX, a synthetic, clinically grounded dataset covering five languages (English, Spanish, Romanian, Arabic, and Mandarin). TriagE-NLU integrates fine-tuned multilingual transformers with a hybrid rules-and-policy decision engine, enabling it to parse structured medical information (symptoms, risk factors, temporal markers) and recommend appropriate interventions based on recognized patterns. Evaluation against strong multilingual baselines, including mT5, mBART, and XLM-RoBERTa, demonstrates superior performance by TriagE-NLU, achieving F1 scores of 0.91 for semantic parsing and 0.89 for intervention classification, along with 0.92 accuracy and a BLEU score of 0.87. These results validate the system’s robustness in multilingual emergency telehealth and its ability to generalize across diverse input scenarios. This paper establishes a new direction for privacy-preserving, AI-assisted triage systems.
format Article
id doaj-art-5aa3dc41d3db47f3b9d17840685c8da5
institution DOAJ
issn 1999-5903
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-5aa3dc41d3db47f3b9d17840685c8da52025-08-20T02:45:34ZengMDPI AGFuture Internet1999-59032025-07-0117731410.3390/fi17070314TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency DialoguesBéatrix-May Balaban0Ioan Sacală1Alina-Claudia Petrescu-Niţă2Faculty of Automatic Control and Computers, National University of Science and Technology Politehnica of Bucharest, Splaiul Independentei, No. 313, 060042 Bucharest, RomaniaFaculty of Automatic Control and Computers, National University of Science and Technology Politehnica of Bucharest, Splaiul Independentei, No. 313, 060042 Bucharest, RomaniaFaculty of Applied Sciences, National University of Science and Technology Politehnica of Bucharest, Splaiul Independentei, No. 313, 060042 Bucharest, RomaniaTelemedicine in emergency contexts presents unique challenges, particularly in multilingual and low-resource settings where accurate, clinical understanding and triage decision support are critical. This paper introduces TriagE-NLU, a novel multilingual natural language understanding system designed to perform both semantic parsing and clinical intervention classification from emergency dialogues. The system is built on a federated learning architecture to ensure data privacy and adaptability across regions and is trained using TriageX, a synthetic, clinically grounded dataset covering five languages (English, Spanish, Romanian, Arabic, and Mandarin). TriagE-NLU integrates fine-tuned multilingual transformers with a hybrid rules-and-policy decision engine, enabling it to parse structured medical information (symptoms, risk factors, temporal markers) and recommend appropriate interventions based on recognized patterns. Evaluation against strong multilingual baselines, including mT5, mBART, and XLM-RoBERTa, demonstrates superior performance by TriagE-NLU, achieving F1 scores of 0.91 for semantic parsing and 0.89 for intervention classification, along with 0.92 accuracy and a BLEU score of 0.87. These results validate the system’s robustness in multilingual emergency telehealth and its ability to generalize across diverse input scenarios. This paper establishes a new direction for privacy-preserving, AI-assisted triage systems.https://www.mdpi.com/1999-5903/17/7/314multilingual NLPemergency telemedicinesemantic parsingintervention classificationfederated learninglow-resource languages
spellingShingle Béatrix-May Balaban
Ioan Sacală
Alina-Claudia Petrescu-Niţă
TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency Dialogues
Future Internet
multilingual NLP
emergency telemedicine
semantic parsing
intervention classification
federated learning
low-resource languages
title TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency Dialogues
title_full TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency Dialogues
title_fullStr TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency Dialogues
title_full_unstemmed TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency Dialogues
title_short TriagE-NLU: A Natural Language Understanding System for Clinical Triage and Intervention in Multilingual Emergency Dialogues
title_sort triage nlu a natural language understanding system for clinical triage and intervention in multilingual emergency dialogues
topic multilingual NLP
emergency telemedicine
semantic parsing
intervention classification
federated learning
low-resource languages
url https://www.mdpi.com/1999-5903/17/7/314
work_keys_str_mv AT beatrixmaybalaban triagenluanaturallanguageunderstandingsystemforclinicaltriageandinterventioninmultilingualemergencydialogues
AT ioansacala triagenluanaturallanguageunderstandingsystemforclinicaltriageandinterventioninmultilingualemergencydialogues
AT alinaclaudiapetrescunita triagenluanaturallanguageunderstandingsystemforclinicaltriageandinterventioninmultilingualemergencydialogues