Generating Verbal Descriptions from Medical Sensor Data: A Corpus Study on User Preferences

Understanding and interpreting medical sensor data is an essential part of pre-hospital care in medical emergencies, but requires training and previous knowledge. In this paper, we describe on-going work towards a medical decision support tool, which automatically generates textual summaries of underlying sensor data. In particular, we present results from a survey investigating the preferences of individual users and user groups when summarizing medical sensor data. We find that the users' preferences are not necessarily dependent on the user's training level, profession or gender. We therefore use cluster analysis to identify user groups with consistent preferences with regard to 4 different first aid scenarios and 3 types of physiological parameters. In future work, we will utilize these findings to automatically adapt the generated output to personal preferences.