Digital Health Data Imperfection Patterns and Their Manifestations in an Australian Digital Hospital
Location
Online
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2023 12:00 AM
End Date
7-1-2023 12:00 AM
Description
Whilst digital health data provides great benefits for improved and effective patient care and organisational outcomes, the quality of digital health data can sometimes be a significant issue. Healthcare providers are known to spend a significant amount of time on assessing and cleaning data. To address this situation, this paper presents six Digital Health Data Imperfection Patterns that provide insight into data quality issues of digital health data, their root causes, their impact, and how these can be detected. Using the CRISP-DM methodology, we demonstrate the utility and pervasiveness of the patterns at the emergency department of Australia's major tertiary digital hospital. The pattern collection can be used by health providers to identify and prevent key digital health data quality issues contributing to reliable insights for clinical decision making and patient care delivery. The patterns also provide a solid foundation for future research in digital health through its identification of key data quality issues, root causes, detection techniques, and terminology.
Recommended Citation
Goel, Kanika; Sadeghianasl, Sareh; Andrews, Robert; Ter Hofstede, Arthur; Wynn, Moe; Kapugama Geeganage, Dakshi; Leemans, Sander; Mcgree, James; Eden, Rebekah; Staib, Andrew; and Donovan, Raelene, "Digital Health Data Imperfection Patterns and Their Manifestations in an Australian Digital Hospital" (2023). Hawaii International Conference on System Sciences 2023 (HICSS-56). 2.
https://aisel.aisnet.org/hicss-56/hc/process_mining/2
Digital Health Data Imperfection Patterns and Their Manifestations in an Australian Digital Hospital
Online
Whilst digital health data provides great benefits for improved and effective patient care and organisational outcomes, the quality of digital health data can sometimes be a significant issue. Healthcare providers are known to spend a significant amount of time on assessing and cleaning data. To address this situation, this paper presents six Digital Health Data Imperfection Patterns that provide insight into data quality issues of digital health data, their root causes, their impact, and how these can be detected. Using the CRISP-DM methodology, we demonstrate the utility and pervasiveness of the patterns at the emergency department of Australia's major tertiary digital hospital. The pattern collection can be used by health providers to identify and prevent key digital health data quality issues contributing to reliable insights for clinical decision making and patient care delivery. The patterns also provide a solid foundation for future research in digital health through its identification of key data quality issues, root causes, detection techniques, and terminology.
https://aisel.aisnet.org/hicss-56/hc/process_mining/2