From Data to Text in the Neonatal Intensive Care Unit: Using NLG Technology for Decision Support and Information Management

Albert Gatt, Francois Portet, Ehud Reiter, Jim Hunter, Saad Mahamood, Wendy Moncur, Somayajulu Sripada

Research output: Contribution to journalLiterature review

44 Citations (Scopus)

Abstract

Contemporary Neonatal Intensive Care Units collect vast amounts of patient data in various formats, making efficient processing of information by medical professionals difficult. Moreover, different stakeholders in the neonatal scenario, which include parents as well as staff occupying different roles, have different information requirements. This paper describes recent and ongoing work on building systems that automatically generate textual summaries of neonatal data. Our evaluation results show that the technology is viable and comparable in its effectiveness for decision support to existing presentation modalities. We discuss the lessons learned so far, as well as the major challenges involved in extending current technology to deal with a broader range of data types, and to improve the textual output in the form of more coherent summaries.

Original languageEnglish
Pages (from-to)153-186
Number of pages34
JournalAI Communications
Volume22
Issue number3
DOIs
Publication statusPublished - 2009

Keywords

  • Natural language generation
  • signal analysis
  • signal processing
  • knowledge-based systems
  • medical informatics
  • narrative
  • weather forecasts
  • situation models
  • clinical-data
  • time
  • language
  • systems
  • words
  • trial
  • visualization
  • comprehension

Cite this

From Data to Text in the Neonatal Intensive Care Unit : Using NLG Technology for Decision Support and Information Management. / Gatt, Albert; Portet, Francois; Reiter, Ehud; Hunter, Jim; Mahamood, Saad; Moncur, Wendy; Sripada, Somayajulu.

In: AI Communications, Vol. 22, No. 3, 2009, p. 153-186.

Research output: Contribution to journalLiterature review

@article{aa1d9a9bc205496080d02f5e95a45460,
title = "From Data to Text in the Neonatal Intensive Care Unit: Using NLG Technology for Decision Support and Information Management",
abstract = "Contemporary Neonatal Intensive Care Units collect vast amounts of patient data in various formats, making efficient processing of information by medical professionals difficult. Moreover, different stakeholders in the neonatal scenario, which include parents as well as staff occupying different roles, have different information requirements. This paper describes recent and ongoing work on building systems that automatically generate textual summaries of neonatal data. Our evaluation results show that the technology is viable and comparable in its effectiveness for decision support to existing presentation modalities. We discuss the lessons learned so far, as well as the major challenges involved in extending current technology to deal with a broader range of data types, and to improve the textual output in the form of more coherent summaries.",
keywords = "Natural language generation, signal analysis, signal processing, knowledge-based systems, medical informatics, narrative, weather forecasts, situation models, clinical-data, time, language, systems, words, trial, visualization, comprehension",
author = "Albert Gatt and Francois Portet and Ehud Reiter and Jim Hunter and Saad Mahamood and Wendy Moncur and Somayajulu Sripada",
year = "2009",
doi = "10.3233/AIC-2009-0453",
language = "English",
volume = "22",
pages = "153--186",
journal = "AI Communications",
issn = "0921-7126",
publisher = "IOS Press",
number = "3",

}

TY - JOUR

T1 - From Data to Text in the Neonatal Intensive Care Unit

T2 - Using NLG Technology for Decision Support and Information Management

AU - Gatt, Albert

AU - Portet, Francois

AU - Reiter, Ehud

AU - Hunter, Jim

AU - Mahamood, Saad

AU - Moncur, Wendy

AU - Sripada, Somayajulu

PY - 2009

Y1 - 2009

N2 - Contemporary Neonatal Intensive Care Units collect vast amounts of patient data in various formats, making efficient processing of information by medical professionals difficult. Moreover, different stakeholders in the neonatal scenario, which include parents as well as staff occupying different roles, have different information requirements. This paper describes recent and ongoing work on building systems that automatically generate textual summaries of neonatal data. Our evaluation results show that the technology is viable and comparable in its effectiveness for decision support to existing presentation modalities. We discuss the lessons learned so far, as well as the major challenges involved in extending current technology to deal with a broader range of data types, and to improve the textual output in the form of more coherent summaries.

AB - Contemporary Neonatal Intensive Care Units collect vast amounts of patient data in various formats, making efficient processing of information by medical professionals difficult. Moreover, different stakeholders in the neonatal scenario, which include parents as well as staff occupying different roles, have different information requirements. This paper describes recent and ongoing work on building systems that automatically generate textual summaries of neonatal data. Our evaluation results show that the technology is viable and comparable in its effectiveness for decision support to existing presentation modalities. We discuss the lessons learned so far, as well as the major challenges involved in extending current technology to deal with a broader range of data types, and to improve the textual output in the form of more coherent summaries.

KW - Natural language generation

KW - signal analysis

KW - signal processing

KW - knowledge-based systems

KW - medical informatics

KW - narrative

KW - weather forecasts

KW - situation models

KW - clinical-data

KW - time

KW - language

KW - systems

KW - words

KW - trial

KW - visualization

KW - comprehension

U2 - 10.3233/AIC-2009-0453

DO - 10.3233/AIC-2009-0453

M3 - Literature review

VL - 22

SP - 153

EP - 186

JO - AI Communications

JF - AI Communications

SN - 0921-7126

IS - 3

ER -