Finding Indicator Diseases of Psychiatric Disorders in BigData using Clustered Association Rule Mining

Markus Bertl; Mahtab Shahin; Peeter Ross; Dirk Draheim

doi:10.1145/3555776.3577594

Finding Indicator Diseases of Psychiatric Disorders in BigData using Clustered Association Rule Mining

Markus Bertl
, Mahtab Shahin
, Peeter Ross
, Dirk Draheim

Publication: Chapter in book/Conference proceeding › Contribution to conference proceedings

Abstract

Psychiatric disorders represent critical non-communicable diseases of the 21st century and are ranked as the leading cause of years lived with disabilities. Nevertheless, data that could be used to improve our understanding of psychiatric diseases remain underutilized. In this research, we apply clustered association rule mining to find comorbidities and indicator diseases for patients with psychiatric illnesses. The model was trained with health insurance billing data from 60,115 patients with a total of 904,821 ICD-10 coded diseases. Nine association rules were found without clustering, 40 with clustering of F diagnoses. The approach proves suitable for further use in the implementation of indicator-based digital decision support systems in psychiatry.

Original language	English
Title of host publication	SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing
Subtitle of host publication	Tallinn, Estonia, March 27-31 2023
Place of Publication	New York
Publisher	Association for Computing Machinery
Pages	826-833
Number of pages	8
ISBN (Electronic)	978-1-4503-9517-5
DOIs	https://doi.org/10.1145/3555776.3577594
Publication status	Published - 27 Mar 2023
Externally published	Yes
Event	38th Annual ACM Symposium on Applied Computing, SAC 2023 - Tallinn, Estonia Duration: 27 Mar 2023 → 31 Mar 2023

Conference

Conference	38th Annual ACM Symposium on Applied Computing, SAC 2023
Country/Territory	Estonia
City	Tallinn
Period	27/03/23 → 31/03/23

Bibliographical note

Publisher Copyright:
© 2023 ACM.

Keywords

artificial intelligence (AI)
association rule mining (ARM)
comorbidity
decision support systems (DSS)
electronic health record (EHR)
explainable artificial intelligence (XAI)
health insurance data
indicator diseases
machine learning (ML)
psychiatry

Access to Document

10.1145/3555776.3577594Licence: Unspecified

Cite this

@inproceedings{ac87fea1bab4474ba06a50a2131891ec,

title = "Finding Indicator Diseases of Psychiatric Disorders in BigData using Clustered Association Rule Mining",

abstract = "Psychiatric disorders represent critical non-communicable diseases of the 21st century and are ranked as the leading cause of years lived with disabilities. Nevertheless, data that could be used to improve our understanding of psychiatric diseases remain underutilized. In this research, we apply clustered association rule mining to find comorbidities and indicator diseases for patients with psychiatric illnesses. The model was trained with health insurance billing data from 60,115 patients with a total of 904,821 ICD-10 coded diseases. Nine association rules were found without clustering, 40 with clustering of F diagnoses. The approach proves suitable for further use in the implementation of indicator-based digital decision support systems in psychiatry.",

keywords = "artificial intelligence (AI), association rule mining (ARM), comorbidity, decision support systems (DSS), electronic health record (EHR), explainable artificial intelligence (XAI), health insurance data, indicator diseases, machine learning (ML), psychiatry",

author = "Markus Bertl and Mahtab Shahin and Peeter Ross and Dirk Draheim",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 38th Annual ACM Symposium on Applied Computing, SAC 2023 ; Conference date: 27-03-2023 Through 31-03-2023",

year = "2023",

month = mar,

day = "27",

doi = "10.1145/3555776.3577594",

language = "English",

pages = "826--833",

booktitle = "SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing",

publisher = "Association for Computing Machinery",

address = "United States",

}

Bertl, M, Shahin, M, Ross, P & Draheim, D 2023, Finding Indicator Diseases of Psychiatric Disorders in BigData using Clustered Association Rule Mining. in SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing: Tallinn, Estonia, March 27-31 2023. Association for Computing Machinery, New York, pp. 826-833, 38th Annual ACM Symposium on Applied Computing, SAC 2023, Tallinn, Estonia, 27/03/23. https://doi.org/10.1145/3555776.3577594

Finding Indicator Diseases of Psychiatric Disorders in BigData using Clustered Association Rule Mining. / Bertl, Markus; Shahin, Mahtab; Ross, Peeter et al.
SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing: Tallinn, Estonia, March 27-31 2023. New York: Association for Computing Machinery, 2023. p. 826-833.

Publication: Chapter in book/Conference proceeding › Contribution to conference proceedings

TY - GEN

T1 - Finding Indicator Diseases of Psychiatric Disorders in BigData using Clustered Association Rule Mining

AU - Bertl, Markus

AU - Shahin, Mahtab

AU - Ross, Peeter

AU - Draheim, Dirk

PY - 2023/3/27

Y1 - 2023/3/27

N2 - Psychiatric disorders represent critical non-communicable diseases of the 21st century and are ranked as the leading cause of years lived with disabilities. Nevertheless, data that could be used to improve our understanding of psychiatric diseases remain underutilized. In this research, we apply clustered association rule mining to find comorbidities and indicator diseases for patients with psychiatric illnesses. The model was trained with health insurance billing data from 60,115 patients with a total of 904,821 ICD-10 coded diseases. Nine association rules were found without clustering, 40 with clustering of F diagnoses. The approach proves suitable for further use in the implementation of indicator-based digital decision support systems in psychiatry.

AB - Psychiatric disorders represent critical non-communicable diseases of the 21st century and are ranked as the leading cause of years lived with disabilities. Nevertheless, data that could be used to improve our understanding of psychiatric diseases remain underutilized. In this research, we apply clustered association rule mining to find comorbidities and indicator diseases for patients with psychiatric illnesses. The model was trained with health insurance billing data from 60,115 patients with a total of 904,821 ICD-10 coded diseases. Nine association rules were found without clustering, 40 with clustering of F diagnoses. The approach proves suitable for further use in the implementation of indicator-based digital decision support systems in psychiatry.

KW - artificial intelligence (AI)

KW - association rule mining (ARM)

KW - comorbidity

KW - decision support systems (DSS)

KW - electronic health record (EHR)

KW - explainable artificial intelligence (XAI)

KW - health insurance data

KW - indicator diseases

KW - machine learning (ML)

KW - psychiatry

UR - https://www.scopus.com/pages/publications/85162905543

U2 - 10.1145/3555776.3577594

DO - 10.1145/3555776.3577594

M3 - Contribution to conference proceedings

AN - SCOPUS:85162905543

SP - 826

EP - 833

BT - SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing

PB - Association for Computing Machinery

CY - New York

T2 - 38th Annual ACM Symposium on Applied Computing, SAC 2023

Y2 - 27 March 2023 through 31 March 2023

ER -

Finding Indicator Diseases of Psychiatric Disorders in BigData using Clustered Association Rule Mining

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this