Deep continual learning for medical call incidents text classification under the presence of dataset shifts.
Computers in Biology and Medicine · 2024-05-01 · Method & validation
Abstract
The aim of this work is to develop and evaluate a deep classifier that can effectively prioritize Emergency Medical Call Incidents (EMCI) according to their life-threatening level under the presence of dataset shifts. We utilized a dataset consisting of 1982746 independent EMCI instances obtained from the Health Services Department of the Region of Valencia (Spain), with a time span from 2009 to 2019 (excluding 2013). The dataset includes free text dispatcher observations recorded during the call, as well as a binary variable indicating whether the event was life-threatening. To evaluate the presence of dataset shifts, we examined prior probability shifts, covariate shifts, and concept shifts. Subsequently, we designed and implemented four deep Continual Learning (CL) strategies-cumulative learning, continual fine-tuning, experience replay, and synaptic intelligence-alongside three deep CL baselines-joint training, static approach, and single fine-tuning-based on DistilBERT models. Our results demonstrated evidence of prior probability shifts, covariate shifts, and concept shifts in the data. Applying CL techniques had a statistically significant (α=0.05) positive impact on both backward and forward knowledge transfer, as measured by the F1-score, compared to non-continual approaches. We can argue that the utilization of CL techniques in the context of EMCI is effective in adapting deep learning classifiers to changes in data distributions, thereby maintaining the stability of model performance over time. To our knowledge, this study represents the first exploration of a CL approach using real EMCI data.
Abstract © the authors or publisher, via PubMed. Reuse and removal
Tags
Dispatchers & call takers · Decision support tools
Related articles
- An end-to-end solution for out-of-hospital emergency medical dispatch triage based on multimodal and continual deep learning. (Artif Intell Med, 2025)
- Deep ensemble multitask classification of emergency medical call incidents combining multimodal data improves emergency medical dispatch. (Artif Intell Med, 2021)
- Ambulance dispatch prioritisation for traffic crashes using machine learning: A natural language approach. (Int J Med Inform, 2022)
- trIAje project: protocol for a retrospective cohort study to optimise AI-assisted telephone triage of time-sensitive conditions in emergency medical services. (BMJ Open, 2026)
- Machine learning models predicting undertriage in telephone triage. (Ann Med, 2022)
- Improving emergency medical dispatching with emphasis on mass-casualty incidents. (Stud Health Technol Inform, 2014)