Real-Time Multimodal Cognitive Assistant for Emergency Medical Services
Preprint
Abstract
Emergency Medical Services (EMS) responders often operate under time-sensitive conditions, facing cognitive overload and inherent risks, requiring essential skills in critical thinking and rapid decision-making. This paper presents CognitiveEMS, an end-to-end wearable cognitive assistant system that can act as a collaborative virtual partner engaging in the real-time acquisition and analysis of multimodal data from an emergency scene and interacting with EMS responders through Augmented Reality (AR) smart glasses. CognitiveEMS processes the continuous streams of data in real-time and leverages edge computing to provide assistance in EMS protocol selection and intervention recognition. We address key technical challenges in real-time cognitive assistance by introducing three novel components: (i) a Speech Recognition model that is fine-tuned for real-world medical emergency conversations using simulated EMS audio recordings, augmented with synthetic data generated by large language models (LLMs); (ii) an EMS Protocol Prediction model that combines state-of-the-art (SOTA) tiny language models with EMS domain knowledge using graph-based attention mechanisms; (iii) an EMS Action Recognition module which leverages multimodal audio and video data and protocol predictions to infer the intervention/treatment actions taken by the responders at the incident scene. Our results show that for speech recognition we achieve superior performance compared to SOTA (WER of 0.290 vs. 0.618) on conversational data. Our protocol prediction component also significantly outperforms SOTA (top-3 accuracy of 0.800 vs. 0.200) and the action recognition achieves an accuracy of 0.727, while maintaining an end-to-end latency of 3.78s for protocol prediction on the edge and 0.31s on the server.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Lightweight transformers for clinical natural language processingNatural Language Engineering, 2024
- Human Action Recognition for Dynamic Scenes of Emergency Rescue Based on Spatial-Temporal Fusion NetworkElectronics, 2023
- Human Action Recognition and Prediction: A SurveyInternational Journal of Computer Vision, 2022
- SynthASR: Unlocking Synthetic Data for Speech Recognition2021
- Conformer: Convolution-augmented Transformer for Speech Recognition2020
- A survey on video-based Human Action Recognition: recent updates, datasets, challenges, and applicationsArtificial Intelligence Review, 2020
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- Speech Recognition for Medical Conversations2018
- Explainable Prediction of Medical Codes from Clinical Text2018
- User Datagram Protocol1980