Computerized Decision Support Tool Research Articles

Exploring the potential cost-effectiveness of a new computerised decision support tool for identifying fetal compromise during monitored term labours: an early health economic model

BackgroundAround 60% of term labours in the UK are continuously monitored using cardiotocography (CTG) to guide clinical labour management. Interpreting the CTG trace is challenging, leading to some babies suffering adverse outcomes and others unnecessary expedited deliveries. A new data driven computerised tool combining multiple clinical risk factors with CTG data (attentive CTG) was developed to help identify term babies at risk of severe compromise during labour. This paper presents an early health economic model exploring its potential cost-effectiveness.MethodsThe model compared attentive CTG and usual care with usual care alone and simulated clinical events, healthcare costs, and infant quality-adjusted life years over 18 years. It was populated using data from a cohort of term pregnancies, the literature, and administrative datasets. Attentive CTG effectiveness was projected through improved monitoring sensitivity/specificity and potential reductions in numbers of severely compromised infants. Scenario analyses explored the impact of including litigation costs.ResultsNationally, attentive CTG could potentially avoid 10,000 unnecessary alerts in labour and 2400 emergency C-section deliveries through improved specificity. A reduction of 21 intrapartum stillbirths amongst severely compromised infants was also predicted with improved sensitivity. Attentive CTG could potentially lead to cost savings and health gains with a probability of being cost-effective at £25,000 per QALY ranging from 70 to 95%. Potential exists for further cost savings if litigation costs are included.ConclusionsAttentive CTG could offer a cost-effective use of healthcare resources. Prospective patient-level studies are needed to formally evaluate its effectiveness and economic impact in routine clinical practice.

A person-centred consultation intervention to improve shared decision-making about, and uptake of, osteoporosis medicines (iFraP): a pragmatic, parallel-group, individual randomised controlled trial protocol

Background Good quality shared decision-making (SDM) conversations involve people with, or at risk of osteoporosis and clinicians collaborating to decide, where appropriate, which evidence-based medicines best fit the person’s life, beliefs, and values. We developed the improving uptake of Fracture Prevention drug treatments (iFraP) intervention comprising a computerised Decision Support Tool (DST), clinician training package and information resources, for use in UK Fracture Liaison Service consultations. Two primary objectives to determine (1) the effect of the iFraP intervention on patient-reported ease in decision-making about osteoporosis medicines, and (2) cost-effectiveness of iFraP intervention compared to usual NHS care. Secondary objectives are to determine the iFraP intervention effect on patient reported outcome and experience measures, clinical effectiveness (osteoporosis medicine adherence), and to explore intervention acceptability, mechanisms, and processes underlying observed effects, and intervention implementation. Methods The iFraP trial is a pragmatic, parallel-group, individual randomised controlled trial in patients referred to a Fracture Liaison Service, with nested mixed methods process evaluation and health economic analysis. Participants aged ≥50 years (n=380) are randomised (1:1 ratio) to one of two arms: (1) iFraP intervention (iFraP-i) or (2) comparator usual NHS care (iFraP-u) and are followed up at 2-weeks and 3-months. The primary outcome is ease of decision-making assessed 2 weeks after the consultation using the Decisional Conflict Scale (DCS). The primary objectives will be addressed by comparing the mean DCS score in each trial arm (using analysis of covariance) for patients given an osteoporosis medicine recommendation, alongside a within-trial cost-effectiveness and value of information (VoI) analysis. Process evaluation data collection includes consultation recordings, semi-structured interviews, and DST analytics. Discussion The iFraP trial will answer important questions about the effectiveness of the new ‘iFraP’ osteoporosis DST, coupled with clinician training, on SDM and informed initiation of osteoporosis medicines. Trial registration ISRCTN 10606407, 21/11/2022 https://doi.org/10.1186/ISRCTN10606407

Protocol for a trial-based economic evaluation analysis of a complex digital health intervention including a computerised decision support tool: the iFraP intervention

Background Digital health interventions (DHI) are associated with significant promise. In recent years, the need to assess the value of these healthcare technologies has motivated a debate regarding the suitability of existing economic evaluation methods in the context of DHI evaluation. Some have argued that robust economic evaluation methods may not be capable of capturing relevant DHI’s characteristics. Others consider that assessing the value of DHI might not be feasible. This protocol paper challenges that view. More specifically, it describes early Health Technology Assessments (HTA) methods to rigorously assess the value for money of a complex intervention including a digital decision support tool i.e., Improving uptake of Fracture Prevention drug treatments (iFraP) as a tracer intervention. iFraP is a complex intervention consisting of a computerised decision support tool, a clinician training package, and information resources to facilitate shared decision-making, increase informed medicine initiation and reduce levels of medicine discontinuation. iFraP’s development was motivated by a view that good quality shared decision-making conversations have the potential to improve levels of osteoporosis medicine uptake. Methods An early economic evaluation of the iFraP intervention was designed to identify, measure, and evaluate the costs and health benefits of iFraP compared to usual practice in Fracture Liaison Services (FLSs). A within-trial cost-effectiveness from the perspective of the National Health Service and Personal Social Service in England will be conducted using patient’s self-reported health related quality of life (HRQoL) and resource use from the iFraP randomised controlled trial. Microanalysis will be used to estimate iFraP’s intervention cost. Finally, Bayesian Value of Information analysis will allow us to estimate an upper bound for the potential health benefits gained from reducing uncertainty on the impact of the iFraP intervention to support uptake and adherence with osteoporosis medicines. Trial registration ISRCTN10606407 - https://doi.org/10.1186/ISRCTN10606407

A person-centred consultation intervention to improve shared decision-making about, and uptake of, osteoporosis medicines (iFraP): a pragmatic, parallel-group, individual randomised controlled trial protocol.

Good quality shared decision-making (SDM) conversations involve people with, or at risk of osteoporosis and clinicians collaborating to decide, where appropriate, which evidence-based medicines best fit the person's life, beliefs, and values. We developed the improving uptake of Fracture Prevention drug treatments (iFraP) intervention comprising a computerised Decision Support Tool (DST), clinician training package and information resources, for use in UK Fracture Liaison Service consultations.Two primary objectives to determine (1) the effect of the iFraP intervention on patient-reported ease in decision-making about osteoporosis medicines, and (2) cost-effectiveness of iFraP intervention compared to usual NHS care. Secondary objectives are to determine the iFraP intervention effect on patient reported outcome and experience measures, clinical effectiveness (osteoporosis medicine adherence), and to explore intervention acceptability, mechanisms, and processes underlying observed effects, and intervention implementation. The iFraP trial is a pragmatic, parallel-group, individual randomised controlled trial in patients referred to a Fracture Liaison Service, with nested mixed methods process evaluation and health economic analysis. Participants aged ≥50 years (n=380) are randomised (1:1 ratio) to one of two arms: (1) iFraP intervention (iFraP-i) or (2) comparator usual NHS care (iFraP-u) and are followed up at 2-weeks and 3-months. The primary outcome is ease of decision-making assessed 2 weeks after the consultation using the Decisional Conflict Scale (DCS). The primary objectives will be addressed by comparing the mean DCS score in each trial arm (using analysis of covariance) for patients given an osteoporosis medicine recommendation, alongside a within-trial cost-effectiveness and value of information (VoI) analysis. Process evaluation data collection includes consultation recordings, semi-structured interviews, and DST analytics. The iFraP trial will answer important questions about the effectiveness of the new 'iFraP' osteoporosis DST, coupled with clinician training, on SDM and informed initiation of osteoporosis medicines. ISRCTN 10606407, 21/11/2022 https://doi.org/10.1186/ISRCTN10606407.

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

BackgroundDespite 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. MethodsPatients with AF and CHA2DS2−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. ResultsThe 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. ConclusionsAn 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 registrationClinicalTrials.gov Identifier- NCT02958943.

Abstract 10984: Alert-Based Computerized Decision Support for High-Risk Ambulatory Clinic Patients With Atrial Fibrillation Not Prescribed Anticoagulation: A Randomized, Controlled Trial (AF-Alert2)

Introduction: Despite widely available risk stratification tools, safe and effective anticoagulants, and guideline recommendations, antithrombotic therapy for stroke prevention in atrial fibrillation (AF) is under-prescribed in ambulatory clinic patients. Hypothesis: We hypothesized that alert-based computerized decision support (CDS) would increase anticoagulation prescription in ambulatory clinic patients with AF and high-risk for stroke. Methods: We enrolled 798 patients (CHA 2 DS 2- VASc score≥2) with AF who were not prescribed anticoagulant therapy and had an ambulatory clinic visit at Brigham and Women’s Hospital. 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. Patients in the alert group were more likely to be prescribed anticoagulation within 48 hours of the clinic visit (15.4% vs. 7.7%, p&lt;0.001) and at 90 days (17.2% vs. 9.9%, p&lt;0.01). Direct oral anticoagulants (DOACs) comprised the majority of increased prescriptions of anticoagulation at 48 hours and 90 days. No differences in stroke, TIA, or systemic embolic events (0% vs. 0.8%, p=0.09), symptomatic VTE (0.5% vs. 1%, p=0.43), CV mortality (0.5% vs. 0.7%, p=0.99), or a composite of major adverse cardiovascular events (2.8% vs. 2.5%, p=0.79) were observed at 90 days ( Figure ). Conclusions: An alert-based CDS strategy increased anticoagulation in ambulatory clinic patients with AF and high-risk for stroke who were not receiving anticoagulation at the time of the office visit. ClinicalTrials.gov Identifier: NCT02958943

The Use of Multilayer Perceptron Artificial Neural Networks to Detect Dairy Cows at Risk of Ketosis.

Simple SummaryKetosis is a serious metabolic disease in high-yield dairy cows, that affects productive herds throughout the world. Subclinical ketosis is one of the most dominant metabolic disorders in dairy herds during early lactation, so early detection and prevention are important for both economic and animal welfare reasons. Neural networks, which offer a high degree of accuracy in predicting various phenomena and processes where there is no clear causal correlation or there are no rules that allow the establishment of a logical cause-and-effect relationship, can be used to address problems related to prediction, classification, or control. A Multi-Layer perceptron (MLP) is a feedforward artificial neural network model that takes input data for a set of proper output. This study investigated the performance of four algorithms used to train MLP networks. The experimental results demonstrate that the MLP network model improved the accuracy of process recognition of subclinical ketosis in dairy cows. The received artificial model’s results were saved in the predictive model markup language (PMML) and can be used to describe the learning set, the algorithm used in the data mining application and related information.Subclinical ketosis is one of the most dominant metabolic disorders in dairy herds during lactation. Cows suffering from ketosis experience elevated ketone body levels in blood and milk, including β-hydroxybutyric acid (BHB), acetone (ACE) and acetoacetic acid. Ketosis causes serious financial losses to dairy cattle breeders and milk producers due to the costs of diagnosis and management as well as animal welfare reasons. Recent years have seen a growing interest in the use of artificial neural networks (ANNs) in various fields of science. ANNs offer a modeling method that enables the mapping of highly complex functional relationships. The purpose of this study was to determine the relationship between milk composition and blood BHB levels associated with subclinical ketosis in dairy cows, using feedforward multilayer perceptron (MLP) artificial neural networks. The results were verified based on the estimated sensitivity and specificity of selected network models, an optimum cut-off point was identified for the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC). The study demonstrated that BHB, ACE and lactose (LAC) levels, as well as the fat-to-protein ratio in milk, were important input variables in the network training process. For the identification of cows at risk of subclinical ketosis, variables such as BHB and ACE levels in milk were of particular relevance, with a sensitivity and specificity of 0.84 and 0.61, respectively. It was found that the back propagation algorithm offers opportunities to integrate artificial intelligence and dairy cattle welfare within a computerized decision support tool.

Pain Management in Primary Care: A Randomized Controlled Trial of a Computerized Decision Support Tool

BackgroundPrimary care providers manage most patients with chronic pain. Pain is a complex problem, particularly in underserved populations. A technology-enabled, point-of-care decision support tool may improve pain management outcomes. MethodsWe created an electronic health record (EHR)-based decision support tool, the Pain Management Support System–Primary Care (PMSS-PC), and studied the tool-plus-education in 6 Federally Qualified Health Center practices using a randomized, wait-list controlled design. The PMSS-PC generated “best practice alerts,” gave clinicians access to a pain assessment template, psychological distress and substance use measures, guidelines for drug and non-drug therapies, and facilitated referrals. Practices were randomly assigned to early vs delayed (after 6 months) implementation of the intervention, including technical support and 6 webinars. The primary outcome was change in worst pain intensity scores after 6 months, assessed on the Brief Pain Inventory-Short Form. Changes in outcomes were compared between the practices using linear multilevel modeling. The EHR provided clinician data on PMSS-PC utilization. ResultsThe 256 patients in the early implementation practices had significantly improved worst pain (standardized effect size [ES] = −.32) compared with the 272 patients in the delayed implementation practices (ES = −.11). There was very low clinician uptake of the intervention in both conditions. ConclusionsEarly implementation of the PMSS-PC improved worst pain, but this effect cannot be attributed to clinician use of the tool. Further PMSS-PC development is not indicated, but practice-level interventions can improve pain, and studies are needed to identify the determinants of change.

Supporting deprescribing in hospitalised patients: formative usability testing of a computerised decision support tool

BackgroundDespite growing evidence that deprescribing can improve clinical outcomes, quality of life and reduce the likelihood of adverse drug events, the practice is not widespread, particularly in hospital settings. Clinical risk assessment tools, like the Drug Burden Index (DBI), can help prioritise patients for medication review and prioritise medications to deprescribe, but are not integrated within routine care. The aim of this study was to conduct formative usability testing of a computerised decision support (CDS) tool, based on DBI, to identify modifications required to the tool prior to trialling in practice.MethodsOur CDS tool comprised a DBI MPage in the electronic medical record (clinical workspace) that facilitated review of a patient’s DBI and medication list, access to deprescribing resources, and the ability to deprescribe. Two rounds of scenario-based formative usability testing with think-aloud protocol were used. Seventeen end-users participated in the testing, including junior and senior doctors, and pharmacists.ResultsParticipants expressed positive views about the DBI CDS tool but testing revealed a number of clear areas for improvement. These primarily related to terminology used (i.e. what is a DBI and how is it calculated?), and consistency of functionality and display. A key finding was that users wanted the CDS tool to look and function in a similar way to other decision support tools in the electronic medical record. Modifications were made to the CDS tool in response to user feedback.ConclusionUsability testing proved extremely useful for identifying components of our CDS tool that were confusing, difficult to locate or to understand. We recommend usability testing be adopted prior to implementation of any digital health intervention. We hope our revised CDS tool equips clinicians with the knowledge and confidence to consider discontinuation of inappropriate medications in routine care of hospitalised patients. In the next phase of our project, we plan to pilot test the tool in practice to evaluate its uptake and effectiveness in supporting deprescribing in routine hospital care.

Evaluation of Two Approaches for Responding to Allegations of Family Maltreatment in the U.S. Army: Coordinated Community Response Impacts and Costs.

The U.S. Air Force (USAF) conducted a program of research to develop and disseminate reliable and valid criteria for partner and child maltreatment (comprising abuse [physical, emotional/psychological, and sexual] and neglect). These criteria are now used in all branches of the U.S. military. The U.S. Army was the first service outside the USAF to adopt the criteria sets and computerized decision support tool but maintained the original committee composition (the "Case Review Committee" [CRC]) instead of adopting the entire assessment, allegation determination, and treatment planning process (the "Field-tested Assessment, Intervention-planning, and Response" [FAIR] system). The Army commissioned this study to compare the CRC and FAIR processes by testing (1) intra-committee process (i.e., three facets of committee functioning-fidelity to regulations, cohesion and team process, outsized influence of unit representatives); (2) coordinated community response to maltreatment (i.e., perceptions of fairness to alleged offenders and victims, impact on unit representatives, and (3) collaboration between the Family Advocacy Program (FAP, the military's maltreatment response agency) and outside agencies; and (4) the time expended and cost. New York University's Institutional Review Board approved the study protocol, and the Army's Human Research Protection Office provided permission to collect data. The ten Army garrisons with the most annual maltreatment cases participated. Committee members, FAP social workers, unit commanders, and independent observers completed assessments of individual meetings and of their overall impression of the processes. A test of whether the means significantly differed between phases was then performed separately for each outcome, and 95% CIs of the unstandardized mean difference between phases were estimated. Independent observers rated FAIR meetings as significantly more faithful to regulations. Unit representatives (i.e., commanders and/or first sergeants) perceived the committee to function better during FAIR (although other committee members and independent observers did not perceive differences). Unit representatives not only rated FAIR as significantly more fair to both alleged offenders and victims (ratings from other committee members did not differ), but also were more likely to attend FAIR meetings and, when they did, rated their ability to serve soldiers and families higher during FAIR. However, FAP social workers rated their relationships with units as being better during CRC, and outside agencies rated their relationship with FAP as significantly better during CRC. Costs to the Army were nearly identical in the two committee structures. Results indicated that the CRC and FAIR processes cost almost identical amounts to run and that the FAIR system was superior in ways most likely to impact service members: (1) independent observers judged its meetings to be more faithful to Army and DoD Instructions; (2) unit representatives were more likely to attend and believed the FAIR system to be fairer (to both alleged offenders and victims) and better functioning. Care should be taken, however, in nurturing relationships between FAP and (1) unit representatives and (2) outside agencies, which may have weakened during FAIR.

Impact of a Clostridioides Difficile Testing Computerized Clinical Decision Support Tool on an Adult Stem Cell Transplantation and Hematologic Malignancies Unit

Clostridioides difficile infection rates are higher in hospitalized hematopoietic stem cell transplantation (HSCT) recipients and patients with hematologic malignancy (HM) compared with the general population. This is related both to extensive exposure to antibiotics as well as to frequent and often prolonged hospitalization. In this population, with numerous potential causes of diarrhea, a subset of C difficile detected is presumed to represent colonization rather than clinical infection. The use of decision support tools to guide ordering in hospitalized patients has been reported to decrease both C difficile testing and detection rates. Following implementation of a computerized decision support tool on our HSCT/HM unit, we observed a >2-fold decrease in C difficile testing volume and National Healthcare Safety Network-defined laboratory identifications of C difficile. Furthermore, the rate of oral vancomycin use, as well as the incidence of vancomycin-resistant enterococci colonization and bloodstream infection, decreased in the postintervention period.

Impact of a computerized decision support tool deployed in two intensive care units on acute kidney injury progression and guideline compliance: a prospective observational study

BackgroundAcute kidney injury (AKI) affects a large proportion of the critically ill and is associated with worse patient outcomes. Early identification of AKI can lead to earlier initiation of supportive therapy and better management. In this study, we evaluate the impact of computerized AKI decision support tool integrated with the critical care clinical information system (CCIS) on patient outcomes. Specifically, we hypothesize that integration of AKI guidelines into CCIS will decrease the proportion of patients with Stage 1 AKI deteriorating into higher stages of AKI.MethodsThe study was conducted in two intensive care units (ICUs) at University Hospitals Bristol, UK, in a before (control) and after (intervention) format. The intervention consisted of the AKIN guidelines and AKI care bundle which included guidance for medication usage, AKI advisory and dashboard with AKI score. Clinical data and patient outcomes were collected from all patients admitted to the units. AKI stage was calculated using the Acute Kidney Injury Network (AKIN) guidelines. Maximum AKI stage per admission, change in AKI stage and other metrics were calculated for the cohort. Adherence to eGFR-based enoxaparin dosing guidelines was evaluated as a proxy for clinician awareness of AKI.ResultsEach phase of the study lasted a year, and a total of 5044 admissions were included for analysis with equal numbers of patients for the control and intervention stages. The proportion of patients worsening from Stage 1 AKI decreased from 42% (control) to 33.5% (intervention), p = 0.002. The proportion of incorrect enoxaparin doses decreased from 1.72% (control) to 0.6% (intervention), p < 0.001. The prevalence of any AKI decreased from 43.1% (control) to 37.5% (intervention), p < 0.05.ConclusionsThis observational study demonstrated a significant reduction in AKI progression from Stage 1 and a reduction in overall development of AKI. In addition, a reduction in incorrect enoxaparin dosing was also observed, indicating increased clinical awareness. This study demonstrates that AKI guidelines coupled with a newly designed AKI care bundle integrated into CCIS can impact patient outcomes positively.

Real-Time Effort Driven Ventilator Management: A Pilot Study.

Mechanical ventilation of patients with acute respiratory distress syndrome should balance lung and diaphragm protective principles, which may be difficult to achieve in routine clinical practice. Through a Phase I clinical trial, we sought to determine whether a computerized decision support-based protocol (real-time effort-driven ventilator management) is feasible to implement, results in improved acceptance for lung and diaphragm protective ventilation, and improves clinical outcomes over historical controls. Interventional nonblinded pilot study. PICU. Mechanically ventilated children with acute respiratory distress syndrome. A computerized decision support tool was tested which prioritized lung-protective management of peak inspiratory pressure-positive end-expiratory pressure, positive end-expiratory pressure/FIO2, and ventilatory rate. Esophageal manometry was used to maintain patient effort in a physiologic range. Protocol acceptance was reported, and enrolled patients were matched 4:1 with respect to age, initial oxygenation index, and percentage of immune compromise to historical control patients for outcome analysis. Thirty-two patients were included. Acceptance of protocol recommendations was over 75%. One-hundred twenty-eight matched historical controls were used for analysis. Compared with historical controls, patients treated with real-time effort-driven ventilator management received lower peak inspiratory pressure-positive end-expiratory pressure and tidal volume, and higher positive end-expiratory pressure when FIO2 was greater than 0.60. Real-time effort-driven ventilator management was associated with 6 more ventilator-free days, shorter duration until the first spontaneous breathing trial and 3 fewer days on mechanical ventilation among survivors (all p ≤ 0.05) in comparison with historical controls, while maintaining no difference in the rate of reintubation. A computerized decision support-based protocol prioritizing lung-protective ventilation balanced with reduction of controlled ventilation to maintain physiologic levels of patient effort can be implemented and may be associated with shorter duration of ventilation.

Use of an electronic decision support tool to reduce polypharmacy in elderly people with chronic diseases: cluster randomised controlled trial

ObjectiveTo evaluate the effects of a computerised decision support tool for comprehensive drug review in elderly people with polypharmacy.DesignPragmatic, multicentre, cluster randomised controlled trial.Setting359 general practices in Austria, Germany, Italy,...

Improving venous thromboembolism prophylaxis through critical thinking and health informatics

Venous thromboembolism (VTE) is a leading cause of preventable morbidity and mortality in hospitalised patients. Mafraq Hospital, a 450-bed tertiary-level hospital in Abu Dhabi, United Arab Emirates, has identified VTE...

Interaction of Critical Care Practitioners With a Decision Support Tool for Weaning Mechanical Ventilation in Children.

There is evidence that ventilator weaning protocols provide benefit to children receiving mechanical ventilation, but many protocols do not include explicit instructions for decreasing ventilator support from maximal settings. We evaluated care provider opinions on ventilator weaning recommendations made by a computerized decision support tool. Recommendations for ventilator adjustment were generated using a computerized decision support tool based on the ARDSNet protocol using data from children with acute hypoxemic respiratory failure admitted to the pediatric ICU (PICU). Attending physicians, fellows, nurse practitioners, and respiratory therapists (RTs) caring for these patients answered a brief survey to assess whether recommendations were reasonable and whether the practitioner believed they could be implemented. RTs completed 99 surveys and ICU providers completed 96 surveys based on data from 10 patients. RTs and ICU providers found 63.9% and 65.3% of recommendations reasonable, respectively. There were 5 instances of disagreement between RTs and ICU providers. The percent of recommendations that RTs thought could be implemented was 29.9%, whereas this figure for ICU providers was 26.3%, with 4 instances of disagreement. Free-text responses indicated that many RTs and ICU providers were concerned about disrupting current patient stability and low tidal volumes. On initial evaluation, the decision support tool did not appear to be highly acceptable to RTs and ICU providers in our setting because recommendations were rarely implemented. In addition, acceptability did not increase over time as patients generally improved. Most respondents preferred to make no ventilator changes and felt the recommendations were too aggressive. The notable barrier to use was a perception of potential patient instability with weaning.

A Computerized Decision Support Tool To Implement Asthma Guidelines for Children and Adolescents

To evaluate performance of a computerized decision support tool to standardize usual care regimens for asthma management in randomized controlled trials (RCTs).The study included a total of 1443 participants with persistent, uncontrolled asthma who were enrolled in 3 published Inner-City Asthma Consortium multicenter trials; the trials were the Asthma Control Evaluation, the Inner-City Anti-IgE Therapy for Asthma, and the Preventative Omalizumab or Step-Up Therapy for Severe Falls Exacerbations trials. Participants were between 6 and 20 years of age, predominantly black or Hispanic, and highly sensitized to common aeroallergens, and a majority resided in households with annual incomes of <$15 000.Children and adolescents with persistent uncontrolled asthma living in urban areas in the United States were recruited into 3 multicenter RCTs of the Inner-City Asthma Consortium between 2004 and 2014, each with a usual care arm. A computerized decision support tool, the Asthma Control Evaluation and Treatment (ACET) Program, scored asthma control on the basis of parent- and patient-provided answers to questions about daytime and nighttime symptoms, along with forced expiratory volume in 1 second, and assigned an appropriate treatment step on the basis of National Asthma Education and Prevention Program guidelines. Control-level determinants were composed of symptoms, rescue medication use, pulmonary function measure, and adherence estimates; these data were collected at visits and entered into the ACET tool. Changes in control levels and treatment steps were evaluated during the trials.At screening, a majority of participants were assessed as asthma that was not well controlled or poorly controlled. There was a significant increase in the proportion of participants who gained good control between screening and random assignment in all 3 trials. There were 51% to 70% of participants who had symptoms well controlled by random assignment with careful adherence to ACET Program step recommendations, and the proportion of participants with well-controlled asthma remained constant or improved slightly from random assignment until the last posttreatment visit. Nighttime symptoms were the most common control-level determinant contributing to asthma control level compared with daytime symptoms and pulmonary function (forced expiratory volume in 1 second). Study physicians agreed with the ACET step recommendations in 90% or more visits, and there were few instances in which there was a study physician override. Poor medication adherence affected treatment algorithm in 5% to 10% of visits.Investigators in the study found that the application of the ACET computerized decision support tool enabled standardized asthma assessment and treatment in RCTs and was associated with attaining and maintaining good asthma in control in most participants.The study is the largest to examine performance of a computerized decision support tool to standardize usual care regimens for asthma management in RCTs among high-risk populations. This tool allowed for an algorithmic approach based on published guidelines to rate control and assign a treatment step. And furthermore, it allowed monitoring of treatment decisions longitudinally, minimized variability in decision-making across multiple centers, studied the alignment of decision support with clinical judgment, and determined when adjustments were made on the basis of adherence versus symptom or exacerbation occurrences. Although thus far focused on clinical trials, there is no reason that this approach could not eventually be applied clinically, better equipping health care providers to assess asthma control and link with evidence-based guidelines for asthma management, especially if integrated into the electronic health record.

Alert-based computerized decision support for high-risk hospitalized patients with atrial fibrillation not prescribed anticoagulation: a randomized, controlled trial (AF-ALERT).

Despite widely available risk stratification tools, safe and effective anticoagulant options, and guideline recommendations, anticoagulation for stroke prevention in atrial fibrillation (AF) is underprescribed. We created and evaluated an alert-based computerized decision support (CDS) strategy to increase anticoagulation prescription in hospitalized AF patients at high risk for stroke. We enrolled 458 patients (CHA2DS2-VASc score ≥1) with AF who were not prescribed anticoagulant therapy and were hospitalized at Brigham and Women's Hospital. Patients were randomly allocated, according to Attending Physician of record, to intervention (alert-based CDS) vs. control (no notification). The primary efficacy outcome was the frequency of anticoagulant prescription. The CDS tool assigned 248 patients to the alert group and 210 to the control group. Patients in the alert group were more likely to be prescribed anticoagulation during the hospitalization (25.8% vs. 9.5%, P < 0.0001), at discharge (23.8% vs. 12.9%, P = 0.003), and at 90 days (27.7% vs. 17.1%, P = 0.007). The alert reduced the odds of a composite outcome of death, myocardial infarction (MI), cerebrovascular event, and systemic embolic event at 90 days [11.3% vs. 21.9%, P = 0.002; odds ratio (OR) 0.45; 95% confidence interval (CI) 0.27-0.76]. The alert reduced the odds of MI at 90 days by 87% (1.2% vs. 8.6%, P = 0.0002; OR 0.13; 95% CI 0.04-0.45) and cerebrovascular events or systemic embolism at 90 days by 88% (0% vs. 2.4%, P = 0.02; OR 0.12; 95% CI 0.0-0.91). An alert-based CDS strategy increased anticoagulation in high-risk hospitalized AF patients and reduced major adverse cardiovascular events, including MI and stroke. NCT02339493.

Assessment of the Effectiveness of a Computerised Decision-Support Tool for Health Professionals for the Prevention and Treatment of Childhood Obesity. Results from a Randomised Controlled Trial.

We examined the effectiveness of a computerised decision-support tool (DST), designed for paediatric healthcare professionals, as a means to tackle childhood obesity. A randomised controlled trial was conducted with 65 families of 6–12-year old overweight or obese children. Paediatricians, paediatric endocrinologists and a dietitian in two children’s hospitals implemented the intervention. The intervention group (IG) received personalised meal plans and lifestyle optimisation recommendations via the DST, while families in the control group (CG) received general recommendations. After three months of intervention, the IG had a significant change in dietary fibre and sucrose intake by 4.1 and −4.6 g/day, respectively. In addition, the IG significantly reduced consumption of sweets (i.e., chocolates and cakes) and salty snacks (i.e., potato chips) by −0.1 and −0.3 portions/day, respectively. Furthermore, the CG had a significant increase of body weight and waist circumference by 1.4 kg and 2.1 cm, respectively, while Body Mass Index (BMI) decreased only in the IG by −0.4 kg/m2. However, the aforementioned findings did not differ significantly between study groups. In conclusion, these findings indicate the dynamics of the DST in supporting paediatric healthcare professionals to improve the effectiveness of care in modifying obesity-related behaviours. Further research is needed to confirm these findings.

A computerized decision support tool to implement asthma guidelines for children and adolescents

Multicenter randomized controlled trials (RCTs) for asthma management that incorporate usual-care regimens could benefit from standardized application of evidence-based guidelines. We sought to evaluate performance of a computerized decision support tool, the Asthma Control Evaluation and Treatment (ACET) Program, to standardize usual-care regimens for asthma management in RCTs. Children and adolescents with persistent uncontrolled asthma living in urban census tracts were recruited into 3 multicenter RCTs (each with a usual-care arm) between 2004 and 2014. Acomputerized decision support tool scored asthma control and assigned an appropriate treatment step based on published guidelines. Control-level determinants (symptoms, rescue medication use, pulmonary function measure, and adherence estimates) were collected at visits and entered into the ACET Program. Changes in control levels and treatment steps were examined during the trials. At screening, more than half of the participants were rated as having symptoms that were not controlled or poorly controlled. The proportion of participants who gained good control between screening and randomization increased significantly in all 3 trials. Between 51% and 70% had symptoms that were well controlled by randomization. The proportion of well-controlled participants remained constant or improved slightly from randomization until the last posttreatment visit. Nighttime symptoms were the most common control-level determinant; there were few (<1%) instances of complete overlap of factors. FEV1 was the driver of control-level assignment in 30% of determinations. The ACET Program decision support tool facilitated standardized asthma assessment and treatment in multicenter RCTs and was associated with attaining and maintaining good asthma control in most participants.