Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2009 Jul-Aug;16(4):590-5.
doi: 10.1197/jamia.M3095. Epub 2009 Apr 23.

A system for classifying disease comorbidity status from medical discharge summaries using automated hotspot and negated concept detection

Kyle H Ambert  1 , Aaron M Cohen
Affiliations

A system for classifying disease comorbidity status from medical discharge summaries using automated hotspot and negated concept detection

Kyle H Ambert et al. J Am Med Inform Assoc. 2009 Jul-Aug.

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 13(th) in the textual task. CONCLUSIONS The system demonstrates that effective comorbidity status classification by an automated system is possible.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Diagrammatic example of our automated hot-spot filtering procedure. In this example, the information gain associated with the word asthma identifies it as a hot-spot feature, so a 100-character window around it is extracted as the hot-spot passage and passed on to the tokenization and vector modeling steps.
Figure 2
Figure 2
Macro-averaged F1 scores across comorbidities for cross-validation studies on the training document collection (black), and training on the training collection, and testing on the test collection (gray), for both the textual (top) and intuitive (bottom) tasks. Bars for which only one color is visible indicate that the difference between training and testing performance was not significant. Abbreviations: AST—Asthma, CAD—Coronary Artery Disease, CHF—Congestive Heart Failure, DEP—Depression, DIA—Diabetes, GST—Gallstones, GRD—Gastroesophogeal Reflux Disease, GT—Gout, HCH—Hypercholesterolemia, HRT—Hypertension, HTR—Hypertriglyceridemia, OA—Osteoarthritis, OBS—Obesity, OSA—Obstructive Sleep Apnea, PVD—Post-viral Depression, VI—Venous Insufficiency.
Figure 3
Figure 3
Macro-averaged F1 scores by comorbidity for 2-, 4-, and 8-way cross-validation using the combined training and testing document collections in both the textual (black) and intuitive (gray) tasks. For most comorbidities, performance decreased with smaller datasets, for a few it remained invariant.
Figure 4
Figure 4
Macro-averaged F1 for the AutoHP (light gray), AutoHP+ NegEx (dark gray), and None (black) preprocessing procedures across comorbidities for the textual (top) and intuitive (bottom) classification tasks. The addition of NegEx only provided small improvement in performance over and above that provided by AutoHP for a few topics, which showed consistent improvements over the system having no pre-processing procedure. See ▶ for abbreviation definitions.
Figure 5
Figure 5
Error rate for the plain NegEx (solid line) regular expressions and Enhanced using Support Vector Machine (SVM) (dashed line) procedures across comorbidities and varying window sizes during 2-way cross-validation on the combined training and testing documents collections for the textual task. For all but one comorbidity, the Automated Negation Finder tended to extract fewer falsely negated terms (negated terms not actually associated with the negative class). For the Hypertriglyceridemia and Venous Insufficiency comorbidities, no NegEx features were found.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Cohen A. Five-way smoking status classification using text hot-spot identification and error-correcting output codes J Am Med Inform Assoc 2008;15:32-35. - PMC - PubMed
    1. Chapman WW, Bridewell W, Hanbury P, Cooper GF, Buchanan BG. A simple algorithm for identifying negated findings and diseases in discharge summaries J Biomed Inform 2001;34:301-310. - PubMed
    1. Aronson AR. Effective mapping of biomedical text to the UMLS metathesaurus: The MetaMap Program Proc AMIA Symp. 2001. pp. 17-21. - PMC - PubMed
    1. Dietterich TG. Ensemble methods in machine learning Lecture Notes in Computer Science 2000(1857):1-15.
    1. Ghani R. Using error-correcting output codes for text classificationIn: Langely P, editor. Proceedings of the 17th International Conference on Maching Learning (ICML)-2000, San Francisco. United States: Morgan Kaufmann Publishers; 2000. pp. 303-310.

Publication types

-