Do computerized clinical decision support systems improve the prescribing of oral anticoagulants? A systematic review

Clinical decision support systems to optimize adherence to anticoagulant guidelines in patients with atrial fibrillation: a systematic review and meta-analysis of randomized controlled trials

BACKGROUND

Clinical decision support systems (CDSS) have been utilized as a low-cost intervention to improve healthcare process measures. Thus, we aim to estimate CDSS efficacy to optimize adherence to oral anticoagulant guidelines in eligible patients with atrial fibrillation (AF).

METHODS

A systematic review and meta-analysis of randomized controlled trials (RCTs) retrieved from PubMed, WOS, SCOPUS, EMBASE, and CENTRAL through August 2023. We used RevMan V. 5.4 to pool dichotomous data using risk ratio (RR) with a 95% confidence interval (CI).

PROSPERO ID

CRD42023471806.

RESULTS

We included nine RCTs with a total of 25,573 patients. There was no significant difference, with the use of CDSS compared to routine care, in the number of patients prescribed anticoagulants (RR: 1.06, 95% CI [0.98, 1.14], P = 0.16), the number of patients prescribed antiplatelets (RR: 1.01 with 95% CI [0.97, 1.06], P = 0.59), all-cause mortality (RR: 1.19, 95% CI [0.31, 4.50], P = 0.80), major bleeding (RR: 0.84, 95% CI [0.21, 3.45], P = 0.81), and clinically relevant non-major bleeding (RR: 1.05, 95% CI [0.52, 2.16], P = 0.88). However, CDSS was significantly associated with reduced incidence of myocardial infarction (RR: 0.18, 95% CI [0.06, 0.54], P = 0.002) and cerebral or systemic embolic event (RR: 0.11, 95% CI [0.01, 0.83], P = 0.03).

CONCLUSION

We report no significant difference with the use of CDSS compared to routine care in anticoagulant or antiplatelet prescription in eligible patients with AF. CDSS was associated with a reduced incidence of myocardial infarction and cerebral or systemic embolic events.

Physicians' Perspectives on AI in Clinical Decision Support Systems: Interview Study of the CURATE.AI Personalized Dose Optimization Platform

BACKGROUND

Physicians play a key role in integrating new clinical technology into care practices through user feedback and growth propositions to developers of the technology. As physicians are stakeholders involved through the technology iteration process, understanding their roles as users can provide nuanced insights into the workings of these technologies that are being explored. Therefore, understanding physicians' perceptions can be critical toward clinical validation, implementation, and downstream adoption. Given the increasing prevalence of clinical decision support systems (CDSSs), there remains a need to gain an in-depth understanding of physicians' perceptions and expectations toward their downstream implementation. This paper explores physicians' perceptions of integrating CURATE.AI, a novel artificial intelligence (AI)-based and clinical stage personalized dosing CDSSs, into clinical practice.

OBJECTIVE

This study aims to understand physicians' perspectives of integrating CURATE.AI for clinical work and to gather insights on considerations of the implementation of AI-based CDSS tools.

METHODS

A total of 12 participants completed semistructured interviews examining their knowledge, experience, attitudes, risks, and future course of the personalized combination therapy dosing platform, CURATE.AI. Interviews were audio recorded, transcribed verbatim, and coded manually. The data were thematically analyzed.

RESULTS

Overall, 3 broad themes and 9 subthemes were identified through thematic analysis. The themes covered considerations that physicians perceived as significant across various stages of new technology development, including trial, clinical implementation, and mass adoption.

CONCLUSIONS

The study laid out the various ways physicians interpreted an AI-based personalized dosing CDSS, CURATE.AI, for their clinical practice. The research pointed out that physicians' expectations during the different stages of technology exploration can be nuanced and layered with expectations of implementation that are relevant for technology developers and researchers.

Electronic alerts for ambulatory patients with atrial fibrillation not prescribed anticoagulation: A randomized, controlled trial (AF-ALERT2)

BACKGROUND

Despite widely available risk stratification tools, safe and effective anticoagulants, and guideline recommendations, anticoagulation for stroke prevention in atrial fibrillation (AF) is under-prescribed in ambulatory patients. To assess the impact of alert-based computerized decision support (CDS) on anticoagulation prescription in ambulatory patients with AF and high-risk for stroke, we conducted this randomized controlled trial.

METHODS

Patients with AF and CHA₂DS_2-VASc score ≥ 2 who were not prescribed anticoagulation and had a clinic visit at Brigham and Women's Hospital were enrolled. Patients were randomly allocated, according to Attending Physician of record, to intervention (alert-based CDS) versus control (no notification). The primary efficacy outcome was the frequency of anticoagulant prescription.

RESULTS

The CDS tool assigned 395 and 403 patients to the alert and control groups, respectively. Alert patients were more likely to be prescribed anticoagulation within 48 h of the clinic visit (15.4 % vs. 7.7 %, p < 0.001) and at 90 days (17.2 % vs. 9.9 %, p < 0.01). Direct oral anticoagulants were the predominantly prescribed form of anticoagulation. No significant differences were observed in stroke, TIA, or systemic embolic events (0 % vs. 0.8 %, p = 0.09), symptomatic VTE (0.5 % vs. 1 %, p = 0.43), all-cause mortality (2 % vs. 0.7 %, p = 0.12), or major adverse cardiovascular events (2.8 % vs. 2.5 %, p = 0.79) at 90 days.

CONCLUSIONS

An alert-based CDS strategy increased a primary efficacy outcome of anticoagulation in clinic patients with AF and high-risk for stroke who were not receiving anticoagulation at the time of the office visit. The study was likely underpowered to assess an impact on clinical outcomes.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier- NCT02958943.

Using a Clinical Decision Support System to Improve Anticoagulation in Patients with Nonvalve Atrial Fibrillation in China's Primary Care Settings: A Feasibility Study

BACKGROUND

To primarily investigate the effect of using a clinical decision support system (CDSS) in community health centers in Shanghai, China, on the proportion of patients prescribed guideline-directed antithrombotic therapy. This study also gauged the general practitioner (GP)'s acceptance of the CDSS who worked in the atrial fibrillation (AF) special consulting room of the CDSS group.

METHODS

This was a prospective cohort study that included a semistructured interview and a feasibility study for a cluster-randomized controlled trial. Eligible patients who sought medical care in the AF special consulting rooms in two community health centers in Shanghai, China, between April 1, 2020, and October 1, 2020, were enrolled, and their medical records from the enrollment date, up to October 1, 2021, were extracted. Based on whether the GPs in the AF special consulting rooms of the two sites used the CDSS or not, we classified the two sites as a software group and a control group. The CDSS could automatically assess the risks of stroke and bleeding and provide suggestions on treatment, follow-up, adjustment of anticoagulants or dosage, and other items. The primary outcome was the proportion of patients prescribed guideline-directed antithrombotic therapy. We also conducted a semistructured interview with the GP in the AF special consulting rooms of the software group regarding the acceptance of the CDSS and suggestions on the optimization of the CDSS and the study protocol of the cluster-randomized controlled trial in the future.

RESULTS

Eighty-four patients completed the follow-up. The mean age of these subjects was 75.71 years, the median time of clinical visits was six times per person, and the follow-up duration was 15 months. The basic demographics were similar between the two groups, except for age (t = 2.109, p = 0.038) and the HAS-BLED score (χ ² = 4.363, p = 0.037). The primary outcome in the software group was 8.071 times higher than that in the control group (adjusted odds ratio (OR) = 8.071, 95% confidence interval (2.570-25.344), p < 0.001). The frequency of consultation between groups was not significantly different (p = 0.981). It seemed that the incidence of adverse clinical events in the software group was lower than that in the control group. The main reason for dropouts in both groups was "following up in other hospitals." The GP in the AF special consulting rooms of the software group accepted the CDSS well.

CONCLUSIONS

The findings indicated that it was feasible to further promote the CDSS in the study among community health centers in China. The use of the CDSS might improve the proportion of patients prescribed guideline-directed antithrombotic therapy. The GP in the AF special consulting room of the software group showed a positive attitude toward the CDSS.

Computerized clinical decision support systems for prescribing in primary care: main characteristics and implementation impact-protocol of an evidence and gap map

BACKGROUND

Computerized clinical decision support systems are used by clinicians at the point of care to improve quality of healthcare processes (prescribing error prevention, adherence to clinical guidelines, etc.) and clinical outcomes (preventive, therapeutic, and diagnostics). Attempts to summarize results of computerized clinical decision support systems to support prescription in primary care have been challenging, and most systematic reviews and meta-analyses failed due to an extremely high degree of heterogeneity present among the included primary studies. The aim of our study will be to synthesize the evidence, considering all methodological factors that could explain these differences, and build an evidence and gap map to identify important remaining research questions.

METHODS

A literature search will be conducted from January 2010 onwards in MEDLINE, Embase, the Cochrane Library, and Web of Science databases. Two reviewers will independently screen all citations, full text, and abstract data. The study methodological quality and risk of bias will be appraised using appropriate tools if applicable. A flow diagram with the screened studies will be presented, and all included studies will be displayed using interactive evidence and gap maps. Results will be reported in accordance with recommendations from the Campbell Collaboration on the development of evidence and gap maps.

DISCUSSION

Evidence behind computerized clinical decision support systems to support prescription use in primary care has so far been difficult to be synthesized. Evidence and gap maps represent an innovative approach that has emerged and is increasingly being used to address a broader research question, where multiple types of intervention and outcomes reported may be evaluated. Broad inclusion criteria have been chosen with regard to study designs, in order to collect all available information. Regarding the limitations, we will only include English and Spanish language studies from the last 10 years, we will not perform a grey literature search, and we will not carry out a meta-analysis due to the predictable heterogeneity of available studies.

SYSTEMATIC REVIEW REGISTRATION

This study is registered in Open Science Framework https://bit.ly/2RqKrWp.

An e-Delphi study to obtain expert consensus on the level of risk associated with preventable e-prescribing events

Aims

We aim to seek expert opinion and gain consensus on the risks associated with a range of prescribing scenarios, preventable using e‐prescribing systems, to inform the development of a simulation tool to evaluate the risk and safety of e‐prescribing systems (ePRaSE).

Methods

We conducted a two‐round e‐Delphi survey where expert participants were asked to score pre‐designed prescribing scenarios using a five‐point Likert scale to ascertain the likelihood of occurrence of the prescribing event, likelihood of occurrence of harm and the severity of the harm.

Results

Twenty‐four experts consented to participate with 15 pand 13 participants completing rounds 1 and 2, respectively. Experts agreed on the level of risk associated with 136 out of 178 clinical scenarios with 131 scenarios categorised as high or extreme risk.

Conclusion

We identified 131 extreme or high‐risk prescribing scenarios that may be prevented using e‐prescribing clinical decision support. The prescribing scenarios represent a variety of categories, with drug–disease contraindications being the most frequent, representing 37 (27%) scenarios, and antimicrobial agents being the most common drug class, representing 28 (21%) of the scenarios. Our e‐Delphi study has achieved expert consensus on the risk associated with a range of clinical scenarios with most of the scenarios categorised as extreme or high risk. These prescribing scenarios represent the breadth of preventable prescribing error categories involving both basic and advanced clinical decision support. We will use the findings of this study to inform the development of the e‐prescribing risk and safety evaluation tool.

Improving appropriate use of anticoagulants in hospitalised patients: a pharmacist-led Check of Medication Appropriateness intervention

AIM

Inappropriate anticoagulant use increases the risk of bleeding and thrombotic events. We implemented clinical decision rules to promote judicious medication use, as part of the 'Check of Medication Appropriateness' (CMA). The CMA concerns a pharmacist-led review service, targeting potentially inappropriate prescriptions (PIPs). In this analysis, we aimed to evaluate the impact of the CMA on anticoagulant prescribing.

METHODS

The number of anticoagulant-related PIPs was evaluated before and after implementation of the intervention in a quasi-experimental interrupted time series analysis. The pre-implementation cohort received usual care. The anticoagulant-focused CMA, comprising 13 clinical rules pertaining to anticoagulation therapies, was implemented in the post-implementation cohort. Segmented regression analysis was used to assess the impact of the intervention on the number of residual PIPs. A residual PIP was defined as a PIP which persisted up to 48h after the CMA intervention. Total number of recommendations and acceptance rate were documented for the 2-year post-implementation period.

RESULTS

Pre-implementation, we observed 501 PIPs in 466 inpatients on 36 days, with a median proportion of 78.5% (range: 46.2%-100%) residual PIPs per day. Post-implementation, 538 PIPs were detected in 485 patients over the same number of days. The CMA intervention reduced the median proportion to 18.2% (range: 0-100%) per day. The effect coincided with an immediate relative reduction of 70% (95%CI 0.19-0.46) in anticoagulant-related residual PIPs. Post-implementation, 2778 recommendations were provided and 75.1% were accepted.

CONCLUSION

Our CMA approach significantly reduced anticoagulant-related PIPs. Implementing a pharmacist-led intervention, based on clinical rules, may support safer prescribing of anticoagulants.

Cochrane's risk of bias tool for non-randomized studies (ROBINS-I) is frequently misapplied: A methodological systematic review

OBJECTIVES

We aimed to review how 'Risk of Bias In Non-randomized Studies-of Interventions' (ROBINS-I), a Cochrane risk of bias assessment tool, has been used in recent systematic reviews.

STUDY DESIGN AND SETTING

Database and citation searches were conducted in March 2020 to identify recently published reviews using ROBINS-I. Reported ROBINS-I assessments and data on how ROBINS-I was used were extracted from each review. Methodological quality of reviews was assessed using AMSTAR 2 ('A MeaSurement Tool to Assess systematic Reviews').

RESULTS

Of 181 hits, 124 reviews were included. Risk of bias was serious/critical in 54% of assessments on average, most commonly due to confounding. Quality of reviews was mostly low, and modifications and incorrect use of ROBINS-I were common, with 20% reviews modifying the rating scale, 20% understating overall risk of bias, and 19% including critical-risk of bias studies in evidence synthesis. Poorly conducted reviews were more likely to report low/moderate risk of bias (predicted probability 57% [95% CI: 47-67] in critically low-quality reviews, 31% [19-46] in high/moderate-quality reviews).

CONCLUSION

Low-quality reviews frequently apply ROBINS-I incorrectly, and may thus inappropriately include or give too much weight to uncertain evidence. Readers should be aware that such problems can lead to incorrect conclusions in reviews.

Clinical decision support systems with team-based care on type 2 diabetes improvement for Medicaid patients: A quality improvement project

BACKGROUND

The prevalence of clinical inertia, the failure of appropriate treatment intensification in diabetes treatment, is a well-documented worldwide phenomenon. This project addresses the problem of clinical inertia through three interrelated activities, clinical decision support (CDSS), team-based care, and patient engagement in diabetes management.

OBJECTIVES

The purpose of this research is to provide analysis under the State-University Partnership Learning Network regarding the impact of an electronic decision support tool combined with team-based care workflow on provider decision-making and patient outcomes for the treatment of poorly controlled diabetes mellitus (diabetes) among patients receiving Kentucky Medicaid. The objectives of this study are to 1) assess clinical outcomes of type 2 diabetes in the Medicaid population with team-based care using CDSS, 2) evaluate physicians' and pharmacists' experience on CDSS.

METHODS

This is a quality improvement project using a mixed-method - longitudinal and control group comparison of outcomes based upon clinical measures and online surveys of providers and pharmacists involved in this project.

RESULTS

Patients treated by providers who changed the treatment regimen to one that either fully or partially followed the recommendation of the CDSS tool had a statistically significant reduction in HbA1c with an average initial HbA1c of 10.1 and the final HbA1c of 8. The online survey of physicians shows that more than 80% of physicians agree the use of CDSS will support improved patient outcomes. The use of a team-based care approach that includes pharmacists in implementing treatment changes was broadly supported by both physicians and pharmacists.

CONCLUSION

CDSS combined with team-based care can be effective in reducing HbA1c to targeted therapeutic levels. The use of CDSS provides a way to efficiently assess more than 160 potential frontline drugs and properly accelerate treatment. Consistent with the research literature, the inclusion of pharmacists can play a key role in team-based care to assess treatment alternatives and provide for improvement in outcomes and patient adherence for diabetes. The user surveys show both physicians and pharmacists have a positive attitude toward CDSS.

[Heart failure care in a digitalized future : A discourse on resource-sparing structures and self-determined patients]

Digital health solutions, applications of artificial intelligence (AI) and new technologies, such as cardiac magnetic resonance imaging and cardiac human genetics are currently being validated in cardiac healthcare pathways. They show promising approaches for improving existing healthcare structures in the future by strengthening the focus on predictive, preventive and personalized medicine. In addition, the accompanying use of digital health applications will become increasingly more important in the future healthcare, especially in patients with chronic diseases. In this article, the authors describe a case of chronic heart failure (HF) as an example to provide an overview of how digitalized healthcare can be efficiently designed across sectors and disciplines in the future. Moreover, the importance of a self-determined patient management for the treatment process itself is underlined. Since HF is frequently accompanied by various comorbidities during the course of the disease that are often recognized only after a delay, the necessity for a timely simultaneous and preventive treatment of multiple comorbidities in cardiovascular diseases is emphasized. Against this background the currently separately applied disease management programs (DMP) are critically questioned. The development of a holistic DMP encompassing all indications for the treatment of chronic diseases may pave the way to a more efficient medical care system.

Inappropriate Use of Oral Antithrombotic Combinations in an Outpatient Setting and Associated Risks: A French Nationwide Cohort Study

With the increase in prevalence of cardiovascular diseases, multimorbidity, and medical progress, oral antithrombotic (AT) combinations are increasingly prescribed. The aims of this study were to estimate the incidence of oral AT combinations, their appropriateness (defined as indications compliant with guidelines), and the related risk of major bleeding (i.e., leading to hospitalization) or death, among new users. We conducted a 5-year historical cohort study, using the French national healthcare database, including all individuals ≥ 45 years old with a first delivery of oral ATs between 1 January 2013 and 31 December 2017. The cumulative incidence of oral AT combinations was estimated with the Fine and Gray method, taking into account the competitive risk of death. We compared the cumulative incidence of major bleeding according to the type of oral AT treatment initiated at study entry (monotherapy or oral AT combinations). During the study period, 22,220 individuals were included (mean (SD) age 68 (12) years). The cumulative incidence of oral AT combinations at 5 years was 27.8% (95% confidence interval (CI) 26.8–28.9). Overall, 64% of any oral AT combinations did not comply with guidelines. The cumulative incidence of major bleeding and death in the whole cohort at 5 years was 4.1% (95% CI 3.7–4.6) and 10.8% (95% CI 10.1–11.6), respectively. Risk of major bleeding increased among individuals with oral AT combinations versus oral AT monotherapy at study entry (subdistribution hazard ratio sHR: 2.16 (1.01–4.63)); with no difference in terms of death. The use of oral AT combinations among oral AT users is frequent, often inappropriately prescribed, and associated with an increased risk of major bleeding.

Impact of a machine learning based decision support for Urinary Tract Infections: Prospective observational study in 36 primary care practices (Preprint)

Background

There is increasing attention on machine learning (ML)-based clinical decision support systems (CDSS), but their added value and pitfalls are very rarely evaluated in clinical practice. We implemented a CDSS to aid general practitioners (GPs) in treating patients with urinary tract infections (UTIs), which are a significant health burden worldwide.

Objective

This study aims to prospectively assess the impact of this CDSS on treatment success and change in antibiotic prescription behavior of the physician. In doing so, we hope to identify drivers and obstacles that positively impact the quality of health care practice with ML.

Methods

The CDSS was developed by Pacmed, Nivel, and Leiden University Medical Center (LUMC). The CDSS presents the expected outcomes of treatments, using interpretable decision trees as ML classifiers. Treatment success was defined as a subsequent period of 28 days during which no new antibiotic treatment for UTI was needed. In this prospective observational study, 36 primary care practices used the software for 4 months. Furthermore, 29 control practices were identified using propensity score-matching. All analyses were performed using electronic health records from the Nivel Primary Care Database. Patients for whom the software was used were identified in the Nivel database by sequential matching using CDSS use data. We compared the proportion of successful treatments before and during the study within the treatment arm. The same analysis was performed for the control practices and the patient subgroup the software was definitely used for. All analyses, including that of physicians’ prescription behavior, were statistically tested using 2-sided z tests with an α level of .05.

Results

In the treatment practices, 4998 observations were included before and 3422 observations (of 2423 unique patients) were included during the implementation period. In the control practices, 5044 observations were included before and 3360 observations were included during the implementation period. The proportion of successful treatments increased significantly from 75% to 80% in treatment practices (z=5.47, P<.001). No significant difference was detected in control practices (76% before and 76% during the pilot, z=0.02; P=.98). Of the 2423 patients, we identified 734 (30.29%) in the CDSS use database in the Nivel database. For these patients, the proportion of successful treatments during the study was 83%—a statistically significant difference, with 75% of successful treatments before the study in the treatment practices (z=4.95; P<.001).

Conclusions

The introduction of the CDSS as an intervention in the 36 treatment practices was associated with a statistically significant improvement in treatment success. We excluded temporal effects and validated the results with the subgroup analysis in patients for whom we were certain that the software was used. This study shows important strengths and points of attention for the development and implementation of an ML-based CDSS in clinical practice.

Trial Registration

ClinicalTrials.gov NCT04408976; https://clinicaltrials.gov/ct2/show/NCT04408976