Rationale, aims, and objectives Clinical decision support (CDS) generates excessive alerts that disrupt the workflow of clinicians. Therefore, inefficient clinical processes that contribute to the misfit between CDS alert and workflow must be evaluated. This study evaluates the appropriateness of CDS alerts in supporting clinical workflow from a socio‐technical perspective. Method A qualitative case study evaluation was conducted at a 620‐bed public teaching hospital in Malaysia using interview, observation, and document analysis to investigate the features and functions of alert appropriateness and workflow‐related issues in cardiological and dermatological settings. The current state map for medication prescribing process was also modelled to identify problems pertinent to CDS alert appropriateness. Results The main findings showed that CDS was not well designed to fit into a clinician's workflow due to influencing factors such as technology (usability, alert content, and alert timing), human (training, perception, knowledge, and skills), organizational (rules and regulations, privacy, and security), and processes (documenting patient information, overriding default option, waste, and delay) impeding the use of CDS with its alert function. We illustrated how alert affect workflow in clinical processes using a Lean tool known as value stream mapping. This study also proposes how CDS alerts should be integrated into clinical workflows to optimize their potential to enhance patient safety. Conclusion The design and implementation of CDS alerts should be aligned with and incorporate socio‐technical factors. Process improvement methods such as Lean can be used to enhance the appropriateness of CDS alerts by identifying inefficient clinical processes that impede the fit of these alerts into clinical workflow.

No abstract

A CDSS generates a high number of inappropriate alerts that interrupt the clinical workflow. As a result, clinicians silence, disable, or ignore alerts, thereby undermining patient safety. Therefore, the effectiveness and appropriateness of CDSS alerts need to be evaluated. A systematic review was carried out to identify the factors that affect CDSS alert appropriateness in supporting clinical workflow. Seven electronic databases (PubMed, Scopus, ACM, Science Direct, IEEE, Ovid Medline, and Ebscohost) were searched for English language articles published between 1997 and 2018. Seventy six papers met the inclusion criteria, of which 26, 24, 15, and 11 papers are retrospective cohort, qualitative, quantitative, and mixed-method studies, respectively. The review highlights various factors influencing the appropriateness and efficiencies of CDSS alerts. These factors are categorized into technology, human, organization, and process aspects using a combination of approaches, including socio-technical framework, five rights of CDSS, and Lean. Most CDSS alerts were not properly designed based on human factor methods and principles, explaining high alert overrides in clinical practices. The identified factors and recommendations from the review may offer valuable insights into how CDSS alerts can be designed appropriately to support clinical workflow.

BACKGROUND Clinical decision support systems (CDSS) generate excessive alerts that lead to alert fatigue and override. Alert overrides have resulted in patient death and medical errors. CDSS with its alert function can also disrupt clinical workflow. Therefore, inefficient clinical processes that contribute to the misfit between CDSS alert and workflows must be evaluated. Evaluation findings can serve as input to the process redesign. Redesigning clinical processes can enhance CDSS alert appropriateness and subsequently improve patient safety. OBJECTIVE The paper presents a proposed framework for evaluating CDSS appropriateness in supporting clinical workflow. The paper also discusses the preliminary results of the framework validation. METHODS A subjectivist, qualitative case study evaluation was conducted at a 620-bed public teaching hospital using semi-structured interview, observation, and document analysis methods to investigate the features and functions of alert appropriateness and workflow related issues. The current state map for medication prescription process was also modelled to identify problems pertinent to alert appropriateness. RESULTS The main findings showed that CDSS is not well designed to fit into clinical workflow due to several influencing factors including technology (system design and implementation), human (information analysis and acquisition), organization (clinical tasks, organizational policies & procedures) and process (process analysis, redesign, implementation, monitoring and improvement) impeding the use of CDSS with its alert function. CONCLUSIONS CDSS alerts should be integrated into clinical workflows due to their potentials in enhancing patient safety. Process improvement methods such as Lean can be used to enhance the appropriateness of CDSS alerts by identifying inefficient clinical processes that impede the fit of CDSS alerts with clinical workflow. The validated framework can be used to address alert and workflow related problems in any healthcare setting.