Use abstracted patient-specific features to assist an information-theoretic measurement to assess similarity between medical cases

Hui Cao; Genevieve B. Melton; Marianthi Markatou; George Hripcsak

doi:10.1016/j.jbi.2008.03.006

Use abstracted patient-specific features to assist an information-theoretic measurement to assess similarity between medical cases

Hui Cao, Genevieve B. Melton, Marianthi Markatou, George Hripcsak

Surgery

Research output: Contribution to journal › Article › peer-review

22 Scopus citations

Abstract

Inter-case similarity metrics can potentially help find similar cases from a case base for evidence-based practice. While several methods to measure similarity between cases have been proposed, developing an effective means for measuring patient case similarity remains a challenging problem. We were interested in examining how abstracting could potentially assist computing case similarity. In this study, abstracted patient-specific features from medical records were used to improve an existing information-theoretic measurement. The developed metric, using a combination of abstracted disease, finding, procedure and medication features, achieved a correlation between 0.6012 and 0.6940 to experts.

Original language	English (US)
Pages (from-to)	882-888
Number of pages	7
Journal	Journal of Biomedical Informatics
Volume	41
Issue number	6
DOIs	https://doi.org/10.1016/j.jbi.2008.03.006
State	Published - Dec 2008

Bibliographical note

Funding Information:
This research was funded by National Library of Medicine R01 LM06910 “Discovering and applying knowledge in clinical databases”. Dr. Markatou was supported by Grant NSF-DMS-0504957 from the National Science Foundation. We acknowledge Dr. Pamela Tarrazona-Yu at Western Queens Health Associates for her help in the reliability study for the evaluation of metrics.

Keywords

Abstracting
Case similarity
Case-based reasoning
Patient feature

Access

10.1016/j.jbi.2008.03.006

OpenUrl availability

Full text

Cite this

@article{fc68b348342e4536892019204de6a866,

title = "Use abstracted patient-specific features to assist an information-theoretic measurement to assess similarity between medical cases",

abstract = "Inter-case similarity metrics can potentially help find similar cases from a case base for evidence-based practice. While several methods to measure similarity between cases have been proposed, developing an effective means for measuring patient case similarity remains a challenging problem. We were interested in examining how abstracting could potentially assist computing case similarity. In this study, abstracted patient-specific features from medical records were used to improve an existing information-theoretic measurement. The developed metric, using a combination of abstracted disease, finding, procedure and medication features, achieved a correlation between 0.6012 and 0.6940 to experts.",

keywords = "Abstracting, Case similarity, Case-based reasoning, Patient feature",

author = "Hui Cao and Melton, {Genevieve B.} and Marianthi Markatou and George Hripcsak",

note = "Funding Information: This research was funded by National Library of Medicine R01 LM06910 “Discovering and applying knowledge in clinical databases”. Dr. Markatou was supported by Grant NSF-DMS-0504957 from the National Science Foundation. We acknowledge Dr. Pamela Tarrazona-Yu at Western Queens Health Associates for her help in the reliability study for the evaluation of metrics.",

year = "2008",

month = dec,

doi = "10.1016/j.jbi.2008.03.006",

language = "English (US)",

volume = "41",

pages = "882--888",

journal = "Journal of Biomedical Informatics",

issn = "1532-0464",

publisher = "Academic Press Inc.",

number = "6",

}

TY - JOUR

T1 - Use abstracted patient-specific features to assist an information-theoretic measurement to assess similarity between medical cases

AU - Cao, Hui

AU - Melton, Genevieve B.

AU - Markatou, Marianthi

AU - Hripcsak, George

N1 - Funding Information: This research was funded by National Library of Medicine R01 LM06910 “Discovering and applying knowledge in clinical databases”. Dr. Markatou was supported by Grant NSF-DMS-0504957 from the National Science Foundation. We acknowledge Dr. Pamela Tarrazona-Yu at Western Queens Health Associates for her help in the reliability study for the evaluation of metrics.

PY - 2008/12

Y1 - 2008/12

N2 - Inter-case similarity metrics can potentially help find similar cases from a case base for evidence-based practice. While several methods to measure similarity between cases have been proposed, developing an effective means for measuring patient case similarity remains a challenging problem. We were interested in examining how abstracting could potentially assist computing case similarity. In this study, abstracted patient-specific features from medical records were used to improve an existing information-theoretic measurement. The developed metric, using a combination of abstracted disease, finding, procedure and medication features, achieved a correlation between 0.6012 and 0.6940 to experts.

AB - Inter-case similarity metrics can potentially help find similar cases from a case base for evidence-based practice. While several methods to measure similarity between cases have been proposed, developing an effective means for measuring patient case similarity remains a challenging problem. We were interested in examining how abstracting could potentially assist computing case similarity. In this study, abstracted patient-specific features from medical records were used to improve an existing information-theoretic measurement. The developed metric, using a combination of abstracted disease, finding, procedure and medication features, achieved a correlation between 0.6012 and 0.6940 to experts.

KW - Abstracting

KW - Case similarity

KW - Case-based reasoning

KW - Patient feature

UR - http://www.scopus.com/inward/record.url?scp=55749116316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55749116316&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2008.03.006

DO - 10.1016/j.jbi.2008.03.006

M3 - Article

C2 - 18487093

AN - SCOPUS:55749116316

SN - 1532-0464

VL - 41

SP - 882

EP - 888

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

IS - 6

ER -

Use abstracted patient-specific features to assist an information-theoretic measurement to assess similarity between medical cases

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this