A System for Classifying Disease Comorbidity Status from Medical Discharge Summaries Using Automated Hotspot and Negated Concept Detection

Kyle H. Ambert, Aaron Cohen

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Objective: Free-text clinical reports serve as an important part of patient care management and clinical documentation of patient disease and treatment status. Free-text notes are commonplace in medical practice, but remain an under-used source of information for clinical and epidemiological research, as well as personalized medicine. The authors explore the challenges associated with automatically extracting information from clinical reports using their submission to the Integrating Informatics with Biology and the Bedside (i2b2) 2008 Natural Language Processing Obesity Challenge Task. Design: A text mining system for classifying patient comorbidity status, based on the information contained in clinical reports. The approach of the authors incorporates a variety of automated techniques, including hot-spot filtering, negated concept identification, zero-vector filtering, weighting by inverse class-frequency, and error-correcting of output codes with linear support vector machines. Measurements: Performance was evaluated in terms of the macroaveraged F1 measure. Results: The automated system performed well against manual expert rule-based systems, finishing fifth in the Challenge's intuitive task, and 13th in the textual task. Conclusions: The system demonstrates that effective comorbidity status classification by an automated system is possible.

Original languageEnglish (US)
Pages (from-to)590-595
Number of pages6
JournalJournal of the American Medical Informatics Association
Volume16
Issue number4
DOIs
StatePublished - Jul 2009

Fingerprint

Comorbidity
Patient Care Management
Natural Language Processing
Precision Medicine
Informatics
Data Mining
Documentation
Obesity
Research
Therapeutics
Support Vector Machine

ASJC Scopus subject areas

  • Health Informatics

Cite this

@article{f3e8d0a81ea742cf8dbb64acc2a503e0,
title = "A System for Classifying Disease Comorbidity Status from Medical Discharge Summaries Using Automated Hotspot and Negated Concept Detection",
abstract = "Objective: Free-text clinical reports serve as an important part of patient care management and clinical documentation of patient disease and treatment status. Free-text notes are commonplace in medical practice, but remain an under-used source of information for clinical and epidemiological research, as well as personalized medicine. The authors explore the challenges associated with automatically extracting information from clinical reports using their submission to the Integrating Informatics with Biology and the Bedside (i2b2) 2008 Natural Language Processing Obesity Challenge Task. Design: A text mining system for classifying patient comorbidity status, based on the information contained in clinical reports. The approach of the authors incorporates a variety of automated techniques, including hot-spot filtering, negated concept identification, zero-vector filtering, weighting by inverse class-frequency, and error-correcting of output codes with linear support vector machines. Measurements: Performance was evaluated in terms of the macroaveraged F1 measure. Results: The automated system performed well against manual expert rule-based systems, finishing fifth in the Challenge's intuitive task, and 13th in the textual task. Conclusions: The system demonstrates that effective comorbidity status classification by an automated system is possible.",
author = "Ambert, {Kyle H.} and Aaron Cohen",
year = "2009",
month = "7",
doi = "10.1197/jamia.M3095",
language = "English (US)",
volume = "16",
pages = "590--595",
journal = "Journal of the American Medical Informatics Association",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - A System for Classifying Disease Comorbidity Status from Medical Discharge Summaries Using Automated Hotspot and Negated Concept Detection

AU - Ambert, Kyle H.

AU - Cohen, Aaron

PY - 2009/7

Y1 - 2009/7

N2 - Objective: Free-text clinical reports serve as an important part of patient care management and clinical documentation of patient disease and treatment status. Free-text notes are commonplace in medical practice, but remain an under-used source of information for clinical and epidemiological research, as well as personalized medicine. The authors explore the challenges associated with automatically extracting information from clinical reports using their submission to the Integrating Informatics with Biology and the Bedside (i2b2) 2008 Natural Language Processing Obesity Challenge Task. Design: A text mining system for classifying patient comorbidity status, based on the information contained in clinical reports. The approach of the authors incorporates a variety of automated techniques, including hot-spot filtering, negated concept identification, zero-vector filtering, weighting by inverse class-frequency, and error-correcting of output codes with linear support vector machines. Measurements: Performance was evaluated in terms of the macroaveraged F1 measure. Results: The automated system performed well against manual expert rule-based systems, finishing fifth in the Challenge's intuitive task, and 13th in the textual task. Conclusions: The system demonstrates that effective comorbidity status classification by an automated system is possible.

AB - Objective: Free-text clinical reports serve as an important part of patient care management and clinical documentation of patient disease and treatment status. Free-text notes are commonplace in medical practice, but remain an under-used source of information for clinical and epidemiological research, as well as personalized medicine. The authors explore the challenges associated with automatically extracting information from clinical reports using their submission to the Integrating Informatics with Biology and the Bedside (i2b2) 2008 Natural Language Processing Obesity Challenge Task. Design: A text mining system for classifying patient comorbidity status, based on the information contained in clinical reports. The approach of the authors incorporates a variety of automated techniques, including hot-spot filtering, negated concept identification, zero-vector filtering, weighting by inverse class-frequency, and error-correcting of output codes with linear support vector machines. Measurements: Performance was evaluated in terms of the macroaveraged F1 measure. Results: The automated system performed well against manual expert rule-based systems, finishing fifth in the Challenge's intuitive task, and 13th in the textual task. Conclusions: The system demonstrates that effective comorbidity status classification by an automated system is possible.

UR - http://www.scopus.com/inward/record.url?scp=67649342015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649342015&partnerID=8YFLogxK

U2 - 10.1197/jamia.M3095

DO - 10.1197/jamia.M3095

M3 - Article

VL - 16

SP - 590

EP - 595

JO - Journal of the American Medical Informatics Association

JF - Journal of the American Medical Informatics Association

SN - 1067-5027

IS - 4

ER -