Data-Driven Approaches to Improve the Quality of Clinical Processes: A Systematic Review

Abstract

Background: Considering the emergence of electronic health records and their related technologies, an increasing attention is paid to data driven approaches like machine learning, data mining, and process mining. The aim of this paper was to identify and classify these approaches to enhance the quality of clinical processes.

Methods: In order to determine the knowledge related to the research question, a systematic literature review was conducted. To this end, the related studies were searched in the web of science documentation database, as a comprehensive and authoritative database covering 1536 scientific publications from 2000 to 2019. The studies found from the initial search were investigated and the relevance of their title with the inclusion and exclusion criteria was determined. As a result, 184 articles were selected. Further investigations resulted in 84 studies that remained after reviewing the abstracts and full texts of these articles. These studies were also evaluated with regard to their field of study and the quality of presented evidence. Consequently, the final synthesis was performed on the evidence extracted from these articles.

Results: Examination of the identified evidences resulted in 4 general categories of "event-based approaches", "process intelligence", "clinical knowledge systems", and "data-driven control and monitoring" as data-driven approaches that can be used to manage the quality of clinical processes.

Conclusion: The findings demonstrated that event-bases approaches had more applications as data driven approaches in the context of health care. Furthermore, process mining is a novel approach that can be used by future studies. The results of this study can be used to complement clinical governance procedures regarding emerging data driven opportunities.