Developing data-driven clinical pathways using electronic health records: The cases of total laparoscopic hysterectomy and rotator cuff tears

Minsu Cho, Kidong Kim, Jungeun Lim, Hyunyoung Baek, Seok Kim, Hee Hwang, Minseok Song, Sooyoung Yoo

Research output: Contribution to journalArticle

Abstract

Objective: A clinical pathway is one of the tools used to support clinical decision making that provides a standardized care process in a specific context. The objective of this research was to develop a method for building data-driven clinical pathways using electronic health record data. Materials and methods: We proposed a matching rate-based clinical pathway mining algorithm that produces the optimal set of clinical orders for each clinical stage by employing matching rates. To validate the approach, we utilized two different datasets of deidentified inpatient records directly related to total laparoscopic hysterectomy (TLH) and rotator cuff tears (RCTs) from a hospital in South Korea. The derived data-driven clinical pathways were evaluated with knowledge-based models by health professionals using a delta analysis. Results: Two different data-driven clinical pathways, i.e., TLH and RCTs, were produced by applying the matching rate-based clinical pathway mining algorithm. We identified that there were significant differences in clinical orders between the data-driven and knowledge-based models. Additionally, the data-driven clinical pathways based on our algorithm outperformed the models by clinical experts, with average matching rates of 82.02% and 79.66%, respectively. Conclusion: The proposed algorithm will be helpful for supporting clinical decisions and directly applicable in medical practices.

Original languageEnglish
Article number104015
JournalInternational Journal of Medical Informatics
Volume133
DOIs
StatePublished - Jan 2020

Fingerprint

Critical Pathways
Electronic Health Records
Hysterectomy
Republic of Korea
Rotator Cuff Injuries
Inpatients
Health
Research

Keywords

  • Clinical pathways
  • Electronic health records(EHR)
  • Evidence-Based approach
  • Matching rates
  • Rotator cuff tears(RCTs)
  • Total laparoscopic hysterectomy(TLH)

Cite this

@article{add5653ebeb0496ea752e21ae4a7b12e,
title = "Developing data-driven clinical pathways using electronic health records: The cases of total laparoscopic hysterectomy and rotator cuff tears",
abstract = "Objective: A clinical pathway is one of the tools used to support clinical decision making that provides a standardized care process in a specific context. The objective of this research was to develop a method for building data-driven clinical pathways using electronic health record data. Materials and methods: We proposed a matching rate-based clinical pathway mining algorithm that produces the optimal set of clinical orders for each clinical stage by employing matching rates. To validate the approach, we utilized two different datasets of deidentified inpatient records directly related to total laparoscopic hysterectomy (TLH) and rotator cuff tears (RCTs) from a hospital in South Korea. The derived data-driven clinical pathways were evaluated with knowledge-based models by health professionals using a delta analysis. Results: Two different data-driven clinical pathways, i.e., TLH and RCTs, were produced by applying the matching rate-based clinical pathway mining algorithm. We identified that there were significant differences in clinical orders between the data-driven and knowledge-based models. Additionally, the data-driven clinical pathways based on our algorithm outperformed the models by clinical experts, with average matching rates of 82.02{\%} and 79.66{\%}, respectively. Conclusion: The proposed algorithm will be helpful for supporting clinical decisions and directly applicable in medical practices.",
keywords = "Clinical pathways, Electronic health records(EHR), Evidence-Based approach, Matching rates, Rotator cuff tears(RCTs), Total laparoscopic hysterectomy(TLH)",
author = "Minsu Cho and Kidong Kim and Jungeun Lim and Hyunyoung Baek and Seok Kim and Hee Hwang and Minseok Song and Sooyoung Yoo",
year = "2020",
month = "1",
doi = "10.1016/j.ijmedinf.2019.104015",
language = "English",
volume = "133",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier Ireland Ltd",

}

Developing data-driven clinical pathways using electronic health records : The cases of total laparoscopic hysterectomy and rotator cuff tears. / Cho, Minsu; Kim, Kidong; Lim, Jungeun; Baek, Hyunyoung; Kim, Seok; Hwang, Hee; Song, Minseok; Yoo, Sooyoung.

In: International Journal of Medical Informatics, Vol. 133, 104015, 01.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Developing data-driven clinical pathways using electronic health records

T2 - The cases of total laparoscopic hysterectomy and rotator cuff tears

AU - Cho, Minsu

AU - Kim, Kidong

AU - Lim, Jungeun

AU - Baek, Hyunyoung

AU - Kim, Seok

AU - Hwang, Hee

AU - Song, Minseok

AU - Yoo, Sooyoung

PY - 2020/1

Y1 - 2020/1

N2 - Objective: A clinical pathway is one of the tools used to support clinical decision making that provides a standardized care process in a specific context. The objective of this research was to develop a method for building data-driven clinical pathways using electronic health record data. Materials and methods: We proposed a matching rate-based clinical pathway mining algorithm that produces the optimal set of clinical orders for each clinical stage by employing matching rates. To validate the approach, we utilized two different datasets of deidentified inpatient records directly related to total laparoscopic hysterectomy (TLH) and rotator cuff tears (RCTs) from a hospital in South Korea. The derived data-driven clinical pathways were evaluated with knowledge-based models by health professionals using a delta analysis. Results: Two different data-driven clinical pathways, i.e., TLH and RCTs, were produced by applying the matching rate-based clinical pathway mining algorithm. We identified that there were significant differences in clinical orders between the data-driven and knowledge-based models. Additionally, the data-driven clinical pathways based on our algorithm outperformed the models by clinical experts, with average matching rates of 82.02% and 79.66%, respectively. Conclusion: The proposed algorithm will be helpful for supporting clinical decisions and directly applicable in medical practices.

AB - Objective: A clinical pathway is one of the tools used to support clinical decision making that provides a standardized care process in a specific context. The objective of this research was to develop a method for building data-driven clinical pathways using electronic health record data. Materials and methods: We proposed a matching rate-based clinical pathway mining algorithm that produces the optimal set of clinical orders for each clinical stage by employing matching rates. To validate the approach, we utilized two different datasets of deidentified inpatient records directly related to total laparoscopic hysterectomy (TLH) and rotator cuff tears (RCTs) from a hospital in South Korea. The derived data-driven clinical pathways were evaluated with knowledge-based models by health professionals using a delta analysis. Results: Two different data-driven clinical pathways, i.e., TLH and RCTs, were produced by applying the matching rate-based clinical pathway mining algorithm. We identified that there were significant differences in clinical orders between the data-driven and knowledge-based models. Additionally, the data-driven clinical pathways based on our algorithm outperformed the models by clinical experts, with average matching rates of 82.02% and 79.66%, respectively. Conclusion: The proposed algorithm will be helpful for supporting clinical decisions and directly applicable in medical practices.

KW - Clinical pathways

KW - Electronic health records(EHR)

KW - Evidence-Based approach

KW - Matching rates

KW - Rotator cuff tears(RCTs)

KW - Total laparoscopic hysterectomy(TLH)

UR - http://www.scopus.com/inward/record.url?scp=85074241287&partnerID=8YFLogxK

U2 - 10.1016/j.ijmedinf.2019.104015

DO - 10.1016/j.ijmedinf.2019.104015

M3 - Article

AN - SCOPUS:85074241287

VL - 133

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

M1 - 104015

ER -