BT-Nurse : computer generation of natural language shift summaries from complex heterogeneous medical data

Abstract

Objective: To determine if a computer system can automatically generate a useful natural language nursing shift summary solely from an electronic patient record system, in a neonatal intensive care unit (NICU). Design: A system was built which automatically generates NICU shift summaries, using datato- text technology. The system was tested for two months in the Royal Infirmary of Edinburgh NICU. Measurements: Nurses were asked to rate the understandability, accuracy, and helpfulness of the computer-generated summaries; they were also asked for free-text comments about the summaries. Results: The nurses found the majority of the summaries to be understandable, accurate, and helpful (p < .001 for all measures). However, nurses also pointed out many deficiencies, especially with regard to extra content they wanted to see in the computer-generated summaries. Conclusions: Natural language NICU shift summaries can be automatically generated from an electronic patient record. However our proof-of-concept software needs considerable additional development work.