The effects of clinical decision support systems on insulin use: A systematic review

Abstract

BackgroundA clinical decision support system (CDSS) is a computerized system using case‐based reasoning to assist clinicians in assessing disease status, in selecting appropriate therapy or in making other clinical decisions. Previous randomized controlled trials (RCTs or trials) have shown that CDSSs have the potential to improve the insulin use, but the evidence was conflicting and uncertain. The purpose of our study was to determine whether a CDSS improves the use of insulin.MethodPubMed, Embase, Cochrane Central Register of Controlled Trials, and ClinicalTrials.gov were searched from their inception to October 2018. The quality assessment was based on the risk of bias criteria of the Cochrane Handbook.ResultsTwenty‐four RCTs, involving 7653 participants, were included. Thirteen of those trials (54.2%) used a computerized algorithm or a computer‐assisted insulin protocol for insulin dose and therapy adjustment, of which 30.8% (four of 13) found significant changes. Of 10 trials that measured mean blood glucose levels and the 11 trials reported HbA1c, the computerized insulin dose adjustment resulted in lower mean blood glucose levels in 70.0% (seven of 10) and 36.4% (four of 11) of RCTs, respectively. Additionally, a significant reduction of hyperglycaemia events was reported in three of six RCTs. The evidence in a majority of the 24 RCTs was of moderate quality.ConclusionsCDSSs have the potential to improve the insulin use and blood glucose control in a clinical setting. The methodologies in these studies were of mixed quality. Better designed and longer‐term studies are required to ensure a larger and more reliable evidence base on the effects of CDSS intervention on insulin use.

Implementation of a clinical decision support system for the optimization of antidiabetic drug orders by pharmacists

“…A number of studies have shown that CDSSs are relevant for particularly complex insulin therapy and the general management of T2DM (e.g. glycaemia control and glycated haemoglobin levels) 20–22,25 . The use of a CDSS to improve antidiabetic drug prescriptions is poorly documented, despite the fact that this drug class is often involved in preventable ADRs—mainly because of inappropriate use 31 .…”

“…insulin use and glycaemia control). [20][21][22][23][24] A literature review has suggested that the use of a CDSS is associated with an overall improvement in the care process. 25 However, these studies analysed the overall management of patients with T2DM and did not focus on drug management; none of the studied outcomes was related to the appropriateness of antidiabetic drug prescriptions.…”

“…glycaemia control and glycated haemoglobin levels). [20][21][22]25 The use of a CDSS to improve antidiabetic drug prescriptions is poorly documented, despite the fact that this drug class is often involved in preventable ADRs-mainly because of inappropriate use. 31 In the study by Gagnon et al, 7 56% of older patients with T2DM had at least one potentially inappropriate medication, and endocrine system drugs corresponded to the third most frequent type of potentially inappropriate medication.…”

How are ontologies implemented to represent clinical practice guidelines in clinical decision support systems: protocol for a systematic review

“…According to EBHC pyramid 5.0 for accessing pre-appraised evidence, CDSSs rest at the top of the pyramid, and they are designed based on information sources such as clinical practice guidelines (CPG), systematic reviews, and evidence summaries [2]. The literature shows the potential positive impact of CDSSs on physicians' decision-making [3][4][5][6][7]. However, a recent meta-analysis shows that the pooled impact of CDSSs on guideline adherence during patient care is relatively low [8].…”

Evaluation Framework for Successful Artificial Intelligence–Enabled Clinical Decision Support Systems: Mixed Methods Study

“…These systems provide services ranging from simple reminders to complex risk prediction [ 3 ] and support health care providers in diagnosis, treatment decisions, and population health management. Clinical decision support systems assist one or more levels of decision making: alerting, interpreting, critiquing, assisting, diagnosing, and managing [ 4 ]. Diagnostic support systems are a subset of clinical decision support systems that are specifically designed to support clinician in diagnosing patients [ 5 ].…”