Barriers and Facilitators to Implementation of Medication Decision Support Systems in Electronic Medical Records: Mixed Methods Approach Based on Structural Equation Modeling and Qualitative Analysis

Abstract

Background Adverse drug events (ADEs) resulting from medication error are some of the most common causes of iatrogenic injuries in hospitals. With the appropriate use of medication, ADEs can be prevented and ameliorated. Efforts to reduce medication errors and prevent ADEs have been made by implementing a medication decision support system (MDSS) in electronic health records (EHRs). However, physicians tend to override most MDSS alerts. Objective In order to improve MDSS functionality, we must understand what factors users consider essential for the successful implementation of an MDSS into their clinical setting. This study followed the implementation process for an MDSS within a comprehensive EHR system and analyzed the relevant barriers and facilitators. Methods A mixed research methodology was adopted. Data from a structured survey and 15 in-depth interviews were integrated. Structural equation modeling was conducted for quantitative analysis of factors related to user adoption of MDSS. Qualitative analysis based on semistructured interviews with physicians was conducted to collect various opinions on MDSS implementation. Results Quantitative analysis revealed that physicians’ expectations regarding ease of use and performance improvement are crucial. Qualitative analysis identified four significant barriers to MDSS implementation: alert fatigue, lack of accuracy, poor user interface design, and lack of customizability. Conclusions This study revealed barriers and facilitators to the implementation of MDSS. The findings can be applied to upgrade MDSS in the future.

Acceptance, Barriers, and Facilitators to Implementing Artificial Intelligence–Based Decision Support Systems in Emergency Departments: Quantitative and Qualitative Evaluation

“…The convenience sampling and the composition of the clinical experience of participants in this study may have been sources of bias. Nevertheless, our findings are consistent with prior studies in that the user interface and system reliability are key to user acceptance and implementation [ 4 , 33 , 34 ]. Third, the sample size was small for a quantitative analysis and has limited real-world relevance.…”

Clinical Utility and Functionality of an Artificial Intelligence–Based App to Predict Mortality in COVID-19: Mixed Methods Analysis

“…These changes are shown in Figure 4 . Future improvements include model retraining from patient samples across multiple hospital sites, and the potential integration of the app to patient electronic health records to facilitate its use in the context of clinicians’ workflow, although the barriers to integration into electronic medical records are numerous [ 34 ].…”

Factors That Impact the Adoption of Clinical Decision Support Systems (CDSS) for Antibiotic Management

“…The survey questionnaire provided in the Supplementary S1 was designed following an extensive literature review of similar studies [ 9 , 15 , 22 , 23 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 ]. Supplementary S2 (supplementary table) outlines the studies from which the questionnaire constructs were derived.…”

“…Liberati et al report that scientific evidence provided by the system can sometimes challenge deep-rooted beliefs concerning professional autonomy and hierarchies of authority in the clinical setting, resulting in scepticism regarding the use of CDSS [ 13 ]. Many studies have focused on technical appropriateness and users’ experience to understand factors related to CDSS adoption [ 21 , 22 , 23 ], but there is limited information on how end-users’ individual characteristics influence perceptions about adopting CDSS for antibiotic management.…”