Applying Natural Language Processing, Information Retrieval and Machine Learning to Decision Support in Medical Coordination in an Emergency Medicine Context

Abstract

The Medical Coordination, which is the application of logistics techniques to emergency context, is responsible for providing appropriate resources, in appropriate conditions to appropriate patients. A system for medical coordination of emergency requests was developed in 2009, although some activities related to medical coordination decision making are extremely subjective. Aiming to decrease subjectivity on activities like prioritization of requests and coordination flow, new technologies of decision support were incorporated to that system. These technologies include textual and semantic processing of clinical summaries and machine learning tools. Results indicate that automated tools could support decision on medical coordination process, allowing coordinators to focus attention on critical cases. These features may streamline the medical coordination, avoiding mistakes and increasing the chances of saving lives.