Patient record linkage for data quality assessment based on time series matching

Alphons Eggerth; Dieter Hayn; Karl Kreiner; Sai Veeranki; Heimo Traninger; Robert Modre-Osprian; Günter Schreier

doi:10.3233/978-1-61499-971-3-210

Patient record linkage for data quality assessment based on time series matching

Alphons Eggerth^*, Dieter Hayn, Karl Kreiner, Sai Veeranki, Heimo Traninger, Robert Modre-Osprian, Günter Schreier

^*Corresponding author for this work

Institute of Neural Engineering (7090)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

Background: Huge amounts of data are collected by healthcare providers and other institutions. However, there are data protection regulations, which limit their utilisation for secondary use, e.g. research. In scenarios, where several data sources are obtained without universal identifiers, record linkage methods need to be applied to obtain a comprehensive dataset. Objectives: In this study, we had the objective to link two datasets comprising data from ergometric performance tests in order to have reference values to free text annotations for assessing their data quality. Methods: We applied an iterative, distance-based time series record linkage algorithm to find corresponding entries in the two given datasets. Subsequently, we assessed the resulting matching rate. The implementation was done in Matlab. Results: The matching rate of our record linkage algorithm was 74.5% for matching patients’ records with their ergometry records. The highest rate of appropriate free text annotations was 87.9%. Conclusion: For the given scenario, our algorithm matched 74.5% of the patients. However, we had no gold standard for validating our results. Most of the free text annotations contained the expected values.

Original language	English
Title of host publication	dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference
Editors	Dieter Hayn, Alphons Eggerth, Gunter Schreier
Publisher	IOS Press
Pages	210-217
Number of pages	8
ISBN (Electronic)	9781614999706
DOIs	https://doi.org/10.3233/978-1-61499-971-3-210
Publication status	Published - 1 Jan 2019
Event	13th Annual Conference Health Informatics Meets Digital Health - Schönbrunn Palace, Wien, Austria Duration: 28 May 2019 → 29 May 2019 http://www.ehealth2017.at

Publication series

Name	Studies in Health Technology and Informatics
Volume	260
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	13th Annual Conference Health Informatics Meets Digital Health
Abbreviated title	dHealth 2019
Country/Territory	Austria
City	Wien
Period	28/05/19 → 29/05/19
Internet address	http://www.ehealth2017.at

Keywords

Cardiac rehabilitation
Data analysis
Ergometry
Exercise test
Medical record linkage

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/978-1-61499-971-3-210

Cite this

Eggerth, A., Hayn, D., Kreiner, K., Veeranki, S., Traninger, H., Modre-Osprian, R., & Schreier, G. (2019). Patient record linkage for data quality assessment based on time series matching. In D. Hayn, A. Eggerth, & G. Schreier (Eds.), dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference (pp. 210-217). (Studies in Health Technology and Informatics; Vol. 260). IOS Press. https://doi.org/10.3233/978-1-61499-971-3-210

Patient record linkage for data quality assessment based on time series matching. / Eggerth, Alphons; Hayn, Dieter; Kreiner, Karl et al.
dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference. ed. / Dieter Hayn; Alphons Eggerth; Gunter Schreier. IOS Press, 2019. p. 210-217 (Studies in Health Technology and Informatics; Vol. 260).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Eggerth, A, Hayn, D, Kreiner, K, Veeranki, S, Traninger, H, Modre-Osprian, R & Schreier, G 2019, Patient record linkage for data quality assessment based on time series matching. in D Hayn, A Eggerth & G Schreier (eds), dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference. Studies in Health Technology and Informatics, vol. 260, IOS Press, pp. 210-217, 13th Annual Conference Health Informatics Meets Digital Health , Wien, Austria, 28/05/19. https://doi.org/10.3233/978-1-61499-971-3-210

Eggerth A, Hayn D, Kreiner K, Veeranki S, Traninger H, Modre-Osprian R et al. Patient record linkage for data quality assessment based on time series matching. In Hayn D, Eggerth A, Schreier G, editors, dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference. IOS Press. 2019. p. 210-217. (Studies in Health Technology and Informatics). doi: 10.3233/978-1-61499-971-3-210

Eggerth, Alphons ; Hayn, Dieter ; Kreiner, Karl et al. / Patient record linkage for data quality assessment based on time series matching. dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference. editor / Dieter Hayn ; Alphons Eggerth ; Gunter Schreier. IOS Press, 2019. pp. 210-217 (Studies in Health Technology and Informatics).

@inproceedings{50f638d7212c4fa0b05b359c5f2644a3,

title = "Patient record linkage for data quality assessment based on time series matching",

abstract = "Background: Huge amounts of data are collected by healthcare providers and other institutions. However, there are data protection regulations, which limit their utilisation for secondary use, e.g. research. In scenarios, where several data sources are obtained without universal identifiers, record linkage methods need to be applied to obtain a comprehensive dataset. Objectives: In this study, we had the objective to link two datasets comprising data from ergometric performance tests in order to have reference values to free text annotations for assessing their data quality. Methods: We applied an iterative, distance-based time series record linkage algorithm to find corresponding entries in the two given datasets. Subsequently, we assessed the resulting matching rate. The implementation was done in Matlab. Results: The matching rate of our record linkage algorithm was 74.5% for matching patients{\textquoteright} records with their ergometry records. The highest rate of appropriate free text annotations was 87.9%. Conclusion: For the given scenario, our algorithm matched 74.5% of the patients. However, we had no gold standard for validating our results. Most of the free text annotations contained the expected values.",

keywords = "Cardiac rehabilitation, Data analysis, Ergometry, Exercise test, Medical record linkage",

author = "Alphons Eggerth and Dieter Hayn and Karl Kreiner and Sai Veeranki and Heimo Traninger and Robert Modre-Osprian and G{\"u}nter Schreier",

year = "2019",

month = jan,

day = "1",

doi = "10.3233/978-1-61499-971-3-210",

language = "English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "210--217",

editor = "Dieter Hayn and Alphons Eggerth and Gunter Schreier",

booktitle = "dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference",

address = "Netherlands",

note = "13th Annual Conference Health Informatics Meets Digital Health , dHealth 2019 ; Conference date: 28-05-2019 Through 29-05-2019",

url = "http://www.ehealth2017.at",

}

TY - GEN

T1 - Patient record linkage for data quality assessment based on time series matching

AU - Eggerth, Alphons

AU - Hayn, Dieter

AU - Kreiner, Karl

AU - Veeranki, Sai

AU - Traninger, Heimo

AU - Modre-Osprian, Robert

AU - Schreier, Günter

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: Huge amounts of data are collected by healthcare providers and other institutions. However, there are data protection regulations, which limit their utilisation for secondary use, e.g. research. In scenarios, where several data sources are obtained without universal identifiers, record linkage methods need to be applied to obtain a comprehensive dataset. Objectives: In this study, we had the objective to link two datasets comprising data from ergometric performance tests in order to have reference values to free text annotations for assessing their data quality. Methods: We applied an iterative, distance-based time series record linkage algorithm to find corresponding entries in the two given datasets. Subsequently, we assessed the resulting matching rate. The implementation was done in Matlab. Results: The matching rate of our record linkage algorithm was 74.5% for matching patients’ records with their ergometry records. The highest rate of appropriate free text annotations was 87.9%. Conclusion: For the given scenario, our algorithm matched 74.5% of the patients. However, we had no gold standard for validating our results. Most of the free text annotations contained the expected values.

AB - Background: Huge amounts of data are collected by healthcare providers and other institutions. However, there are data protection regulations, which limit their utilisation for secondary use, e.g. research. In scenarios, where several data sources are obtained without universal identifiers, record linkage methods need to be applied to obtain a comprehensive dataset. Objectives: In this study, we had the objective to link two datasets comprising data from ergometric performance tests in order to have reference values to free text annotations for assessing their data quality. Methods: We applied an iterative, distance-based time series record linkage algorithm to find corresponding entries in the two given datasets. Subsequently, we assessed the resulting matching rate. The implementation was done in Matlab. Results: The matching rate of our record linkage algorithm was 74.5% for matching patients’ records with their ergometry records. The highest rate of appropriate free text annotations was 87.9%. Conclusion: For the given scenario, our algorithm matched 74.5% of the patients. However, we had no gold standard for validating our results. Most of the free text annotations contained the expected values.

KW - Cardiac rehabilitation

KW - Data analysis

KW - Ergometry

KW - Exercise test

KW - Medical record linkage

UR - http://www.scopus.com/inward/record.url?scp=85066466189&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-971-3-210

DO - 10.3233/978-1-61499-971-3-210

M3 - Conference paper

C2 - 31118340

AN - SCOPUS:85066466189

T3 - Studies in Health Technology and Informatics

SP - 210

EP - 217

BT - dHealth 2019 - From eHealth to dHealth - Proceedings of the 13th Health Informatics Meets Digital Health Conference

A2 - Hayn, Dieter

A2 - Eggerth, Alphons

A2 - Schreier, Gunter

PB - IOS Press

T2 - 13th Annual Conference Health Informatics Meets Digital Health

Y2 - 28 May 2019 through 29 May 2019

ER -

Patient record linkage for data quality assessment based on time series matching

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this