Improving coded data entry by an electronic patient record system

J. H. Hohnloser, F. Puerner, Hooman Soltanian

Research output: Contribution to journalArticle

Abstract

Data are presented on the use of a browsing and encoding utility to improve coded data entry for an electronic patient record system. Traditional and computerized discharge summaries were compared: during three phases of coding ICD-9 diagnoses phase I, no coding; phase II, manual coding, and phase III, computerized semiautomatic coding. Our data indicate that (1) only 50% of all diagnoses in a discharge summary are encoded manually; (2) using a computerized browsing and encoding utility this percentage may increase by 64%; (3) when forced to encode manually, users may 'shift' as much as 84% of relevant diagnoses from the appropriate coding section to other sections thereby 'bypassing' the need to encode, this was reduced by up to 41% with the computerized approach, and (4) computerized encoding can improve completeness of data encoding, from 46 to 100%. We conclude that the use of a computerized browsing and encoding tool can increase data quality and the percentage of documented data. Mechanisms bypassing the need to code can be avoided.

Original languageEnglish (US)
Pages (from-to)108-111
Number of pages4
JournalMethods of Information in Medicine
Volume35
Issue number2
StatePublished - Aug 1 1996
Externally publishedYes

Fingerprint

International Classification of Diseases
Data Accuracy

Keywords

  • browser
  • computerized
  • electronic patient record
  • encoding
  • ICD-9
  • natural language processing

ASJC Scopus subject areas

  • Health Informatics
  • Advanced and Specialized Nursing
  • Health Information Management

Cite this

Improving coded data entry by an electronic patient record system. / Hohnloser, J. H.; Puerner, F.; Soltanian, Hooman.

In: Methods of Information in Medicine, Vol. 35, No. 2, 01.08.1996, p. 108-111.

Research output: Contribution to journalArticle

@article{52700ec218df4a75aa10155faadc7960,
title = "Improving coded data entry by an electronic patient record system",
abstract = "Data are presented on the use of a browsing and encoding utility to improve coded data entry for an electronic patient record system. Traditional and computerized discharge summaries were compared: during three phases of coding ICD-9 diagnoses phase I, no coding; phase II, manual coding, and phase III, computerized semiautomatic coding. Our data indicate that (1) only 50{\%} of all diagnoses in a discharge summary are encoded manually; (2) using a computerized browsing and encoding utility this percentage may increase by 64{\%}; (3) when forced to encode manually, users may 'shift' as much as 84{\%} of relevant diagnoses from the appropriate coding section to other sections thereby 'bypassing' the need to encode, this was reduced by up to 41{\%} with the computerized approach, and (4) computerized encoding can improve completeness of data encoding, from 46 to 100{\%}. We conclude that the use of a computerized browsing and encoding tool can increase data quality and the percentage of documented data. Mechanisms bypassing the need to code can be avoided.",
keywords = "browser, computerized, electronic patient record, encoding, ICD-9, natural language processing",
author = "Hohnloser, {J. H.} and F. Puerner and Hooman Soltanian",
year = "1996",
month = "8",
day = "1",
language = "English (US)",
volume = "35",
pages = "108--111",
journal = "Methods of Information in Medicine",
issn = "0026-1270",
publisher = "Schattauer GmbH",
number = "2",

}

TY - JOUR

T1 - Improving coded data entry by an electronic patient record system

AU - Hohnloser, J. H.

AU - Puerner, F.

AU - Soltanian, Hooman

PY - 1996/8/1

Y1 - 1996/8/1

N2 - Data are presented on the use of a browsing and encoding utility to improve coded data entry for an electronic patient record system. Traditional and computerized discharge summaries were compared: during three phases of coding ICD-9 diagnoses phase I, no coding; phase II, manual coding, and phase III, computerized semiautomatic coding. Our data indicate that (1) only 50% of all diagnoses in a discharge summary are encoded manually; (2) using a computerized browsing and encoding utility this percentage may increase by 64%; (3) when forced to encode manually, users may 'shift' as much as 84% of relevant diagnoses from the appropriate coding section to other sections thereby 'bypassing' the need to encode, this was reduced by up to 41% with the computerized approach, and (4) computerized encoding can improve completeness of data encoding, from 46 to 100%. We conclude that the use of a computerized browsing and encoding tool can increase data quality and the percentage of documented data. Mechanisms bypassing the need to code can be avoided.

AB - Data are presented on the use of a browsing and encoding utility to improve coded data entry for an electronic patient record system. Traditional and computerized discharge summaries were compared: during three phases of coding ICD-9 diagnoses phase I, no coding; phase II, manual coding, and phase III, computerized semiautomatic coding. Our data indicate that (1) only 50% of all diagnoses in a discharge summary are encoded manually; (2) using a computerized browsing and encoding utility this percentage may increase by 64%; (3) when forced to encode manually, users may 'shift' as much as 84% of relevant diagnoses from the appropriate coding section to other sections thereby 'bypassing' the need to encode, this was reduced by up to 41% with the computerized approach, and (4) computerized encoding can improve completeness of data encoding, from 46 to 100%. We conclude that the use of a computerized browsing and encoding tool can increase data quality and the percentage of documented data. Mechanisms bypassing the need to code can be avoided.

KW - browser

KW - computerized

KW - electronic patient record

KW - encoding

KW - ICD-9

KW - natural language processing

UR - http://www.scopus.com/inward/record.url?scp=0029898137&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029898137&partnerID=8YFLogxK

M3 - Article

C2 - 8755383

AN - SCOPUS:0029898137

VL - 35

SP - 108

EP - 111

JO - Methods of Information in Medicine

JF - Methods of Information in Medicine

SN - 0026-1270

IS - 2

ER -