Clustering demographics and sequences of diagnosis codes

Haodi Zhong; Grigorios Loukides; Solon P Pissis

doi:10.1109/JBHI.2021.3129461

Clustering demographics and sequences of diagnosis codes

Haodi Zhong, Grigorios Loukides^*, Solon P Pissis

^*Corresponding author for this work

Centrum Wiskunde en Informatica

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

1 Citation (Scopus)

90 Downloads (Pure)

Abstract

A Relational-Sequential dataset (or RS-dataset for short) contains records comprised of a patients values in demographic attributes and their sequence of diagnosis codes. The task of clustering an RS-dataset is helpful for analyses ranging from pattern mining to classification. However, existing methods are not appropriate to perform this task. Thus, we initiate a study of how an RS-dataset can be clustered effectively and efficiently. We formalize the task of clustering an RS-dataset as an optimization problem. At the heart of the problem is a distance measure we design to quantify the pairwise similarity between records of an RS-dataset. Our measure uses a tree structure that encodes hierarchical relationships between records, based on their demographics, as well as an edit-distance-like measure that captures both the sequentiality and the semantic similarity of diagnosis codes. We also develop an algorithm which first identifies k representative records (centers), for a given k, and then constructs clusters, each containing one center and the records that are closer to the center compared to other centers. Experiments using two Electronic Health Record datasets demonstrate that our algorithm constructs compact and well-separated clusters, which preserve meaningful relationships between demographics and sequences of diagnosis codes, while being efficient and scalable.

Original language	English
Journal	IEEE Journal of Biomedical and Health Informatics
DOIs	https://doi.org/10.1109/JBHI.2021.3129461
Publication status	Accepted/In press - 19 Nov 2021

Access to Document

10.1109/JBHI.2021.3129461

Clustering demographics and sequences of diagnosis codesAccepted author manuscript, 18.9 MBLicence: Unspecified

Cite this

@article{bc75697298ce4b81bf635b75b231130d,

title = "Clustering demographics and sequences of diagnosis codes",

abstract = "A Relational-Sequential dataset (or RS-dataset for short) contains records comprised of a patients values in demographic attributes and their sequence of diagnosis codes. The task of clustering an RS-dataset is helpful for analyses ranging from pattern mining to classification. However, existing methods are not appropriate to perform this task. Thus, we initiate a study of how an RS-dataset can be clustered effectively and efficiently. We formalize the task of clustering an RS-dataset as an optimization problem. At the heart of the problem is a distance measure we design to quantify the pairwise similarity between records of an RS-dataset. Our measure uses a tree structure that encodes hierarchical relationships between records, based on their demographics, as well as an edit-distance-like measure that captures both the sequentiality and the semantic similarity of diagnosis codes. We also develop an algorithm which first identifies k representative records (centers), for a given k, and then constructs clusters, each containing one center and the records that are closer to the center compared to other centers. Experiments using two Electronic Health Record datasets demonstrate that our algorithm constructs compact and well-separated clusters, which preserve meaningful relationships between demographics and sequences of diagnosis codes, while being efficient and scalable.",

author = "Haodi Zhong and Grigorios Loukides and Pissis, {Solon P}",

year = "2021",

month = nov,

day = "19",

doi = "10.1109/JBHI.2021.3129461",

language = "English",

journal = "IEEE Journal of Biomedical and Health Informatics",

issn = "2168-2194",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Clustering demographics and sequences of diagnosis codes

AU - Zhong, Haodi

AU - Loukides, Grigorios

AU - Pissis, Solon P

PY - 2021/11/19

Y1 - 2021/11/19

N2 - A Relational-Sequential dataset (or RS-dataset for short) contains records comprised of a patients values in demographic attributes and their sequence of diagnosis codes. The task of clustering an RS-dataset is helpful for analyses ranging from pattern mining to classification. However, existing methods are not appropriate to perform this task. Thus, we initiate a study of how an RS-dataset can be clustered effectively and efficiently. We formalize the task of clustering an RS-dataset as an optimization problem. At the heart of the problem is a distance measure we design to quantify the pairwise similarity between records of an RS-dataset. Our measure uses a tree structure that encodes hierarchical relationships between records, based on their demographics, as well as an edit-distance-like measure that captures both the sequentiality and the semantic similarity of diagnosis codes. We also develop an algorithm which first identifies k representative records (centers), for a given k, and then constructs clusters, each containing one center and the records that are closer to the center compared to other centers. Experiments using two Electronic Health Record datasets demonstrate that our algorithm constructs compact and well-separated clusters, which preserve meaningful relationships between demographics and sequences of diagnosis codes, while being efficient and scalable.

AB - A Relational-Sequential dataset (or RS-dataset for short) contains records comprised of a patients values in demographic attributes and their sequence of diagnosis codes. The task of clustering an RS-dataset is helpful for analyses ranging from pattern mining to classification. However, existing methods are not appropriate to perform this task. Thus, we initiate a study of how an RS-dataset can be clustered effectively and efficiently. We formalize the task of clustering an RS-dataset as an optimization problem. At the heart of the problem is a distance measure we design to quantify the pairwise similarity between records of an RS-dataset. Our measure uses a tree structure that encodes hierarchical relationships between records, based on their demographics, as well as an edit-distance-like measure that captures both the sequentiality and the semantic similarity of diagnosis codes. We also develop an algorithm which first identifies k representative records (centers), for a given k, and then constructs clusters, each containing one center and the records that are closer to the center compared to other centers. Experiments using two Electronic Health Record datasets demonstrate that our algorithm constructs compact and well-separated clusters, which preserve meaningful relationships between demographics and sequences of diagnosis codes, while being efficient and scalable.

UR - http://www.scopus.com/inward/record.url?scp=85120052998&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2021.3129461

DO - 10.1109/JBHI.2021.3129461

M3 - Article

C2 - 34797768

SN - 2168-2194

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

ER -

Clustering demographics and sequences of diagnosis codes

Abstract

Access to Document

Other files and links

Fingerprint

Cite this