Automatic generation of textual summaries from neonatal intensive care data

摘要

Effective presentation of data for decision support is a major issue when large volumes of data are generated as happens in the Intensive Care Unit (ICU). Although the most common approach is to present the data graphically, it has been shown that textual summarisation can lead to improved decision making. As part of the BabyTalk project, we present a prototype, called BT-45, which generates textual summaries of about 45 minutes of continuous physiological signals and discrete events (e.g.: equipment settings and drug administration). Its architecture brings together techniques from the different areas of signal processing, medical reasoning, knowledge engineering, and natural language generation. A clinical off-ward experiment in a Neonatal ICU (NICU) showed that human expert textual descriptions of NICU data lead to better decision making than classical graphical visualisation, whereas texts generated by BT-45 lead to similar quality decision-making as visualisations. Textual analysis showed that BT-45 texts were inferior to human expert texts in a number of ways, including not reporting temporal information as well and not producing good narratives. Despite these deficiencies, our work shows that it is possible for computer systems to generate effective textual summaries of complex continuous and discrete temporal clinical data.