An innovative artificial intelligence-based method to compress complex models into explainable, model-agnostic and reduced decision support systems with application to healthcare (NEAR)

BACKGROUND AND OBJECTIVE

In everyday clinical practice, medical decision is currently based on clinical guidelines which are often static and rigid, and do not account for population variability, while individualized, patient-oriented decision and/or treatment are the paradigm change necessary to enter into the era of precision medicine. Most of the limitations of a guideline-based system could be overcome through the adoption of Clinical Decision Support Systems (CDSSs) based on Artificial Intelligence (AI) algorithms. However, the black-box nature of AI algorithms has hampered a large adoption of AI-based CDSSs in clinical practice. In this study, an innovative AI-based method to compress AI-based prediction models into explainable, model-agnostic, and reduced decision support systems (NEAR) with application to healthcare is presented and validated.

METHODS

NEAR is based on the Shapley Additive Explanations framework and can be applied to complex input models to obtain the contributions of each input feature to the output. Technically, the simplified NEAR models approximate contributions from input features using a custom library and merge them to determine the final output. Finally, NEAR estimates the confidence error associated with the single input feature contributing to the final score, making the result more interpretable. Here, NEAR is evaluated on a clinical real-world use case, the mortality prediction in patients who experienced Acute Coronary Syndrome (ACS), applying three different Machine Learning/Deep Learning models as implementation examples.

RESULTS

NEAR, when applied to the ACS use case, exhibits performances like the ones of the AI-based model from which it is derived, as in the case of the Adaptive Boosting classifier, whose Area Under the Curve is not statistically different from the NEAR one, even the model's simplification. Moreover, NEAR comes with intrinsic explainability and modularity, as it can be tested on the developed web application platform (https://neardashboard.pythonanywhere.com/).

CONCLUSIONS

An explainable and reliable CDSS tailored to single-patient analysis has been developed. The proposed AI-based system has the potential to be used alongside the clinical guidelines currently employed in the medical setting making them more personalized and dynamic and assisting doctors in taking their everyday clinical decisions.

Validation of Pediatric Emergency Care Applied Research Network (PECARN) rule in children with minor head trauma

The Pediatric Emergency Care Applied Research Network (PECARN) rule is commonly used for predicting the need for computed tomography (CT) scans in children with mild head trauma. The objective of this study was to validate the PECARN rule in Korean children presenting to the pediatric emergency department (PED) with head trauma. This study was a multicenter, retrospective, observational cohort study in two teaching PEDs in Korea between August 2015 and August 2016. In this observational study, 448 patients who visited PEDs were included in the final analysis. Risk stratification was performed with clinical decision support software based on the PECARN rule, and decisions to perform CT scans were subsequently made. Patients were followed-up by phone call between 7 days and 90 days after discharge from the PED. The sensitivity and specificity were analyzed. The sensitivity was 100% for all age groups, and no cases of clinically important traumatic brain injury (ciTBI) were identified in the very-low-risk group. CT scans were performed for 14.7% of patients in this study and for 33.8% in the original PECARN study. The PECARN rule successfully identified low-risk patients, and no cases of ciTBI were missed despite the reduced proportion of patients undergoing CT scans.

Clinical efficacy of a Decision Support Tool (Link-me) to guide intensity of mental health care in primary practice: a pragmatic stratified randomised controlled trial

BACKGROUND

The volume and heterogeneity of mental health problems that primary care patients present with is a substantial challenge for health systems, and both undertreatment and overtreatment are common. We developed Link-me, a patient-completed Decision Support Tool, to predict severity of depression or anxiety, identify priorities, and recommend interventions. In this study, we aimed to examine if Link-me reduces psychological distress among individuals predicted to have minimal/mild or severe symptoms of anxiety or depression.

METHODS

In this pragmatic stratified randomised controlled trial, adults aged 18-75 years reporting depressive or anxiety symptoms or use of mental health medication were recruited from 23 general practices in Australia. Participants completed the Decision Support Tool and were classified into three prognostic groups (minimal/mild, moderate, severe), and those in the minimal/mild and severe groups were eligible for inclusion. Participants were individually and randomly assigned (1:1) by a computer-generated allocation sequence to receive either prognosis-matched care (intervention group) or usual care plus attention control (control group). Participants were not blinded but intervention providers were only notified of those allocated to the intervention group. Outcome assessment was blinded. The primary outcome was the difference in the change in scores between the intervention and control group, and within prognostic groups, on the 10-item Kessler Psychological Distress Scale at 6 months post randomisation. The trial was registered on the Australian and New Zealand Clinical Trials Registry, ACTRN12617001333303.

OUTCOMES

Between Nov 21, 2017, and Oct 31, 2018, 24 616 patients were invited to complete the eligibility screening survey. 1671 of these patients were included and randomly assigned to either the intervention group (n=834) or the control group (n=837). Prognosis-matched care was associated with greater reductions in psychological distress than usual care plus attention control at 6 months (p=0·03), with a standardised mean difference (SMD) of -0·09 (95% CI -0·17 to -0·01). This reduction was also seen in the severe prognostic group (p=0·003), with a SMD of -0·26 (-0·43 to -0·09), but not in the minimal/mild group (p=0·73), with a SMD of 0·04 (-0·17 to 0·24). In the complier average causal effect analysis in the severe prognostic group, differences were larger among those who received some or all aspects of the intervention (SMD range -0·58 to -1·15). No serious adverse effects were recorded.

INTERPRETATION

Prognosis-based matching of interventions reduces psychological distress in patients with anxiety or depressive symptoms, particularly in those with severe symptoms, and is associated with better outcomes when patients access the recommended treatment. Optimisation of the Link-me approach and implementation into routine practice could help reduce the burden of disease associated with common mental health conditions such as anxiety and depression.

FUNDING

Australian Government Department of Health.

Optimizing clinical decision support alerts in electronic medical records: a systematic review of reported strategies adopted by hospitals

OBJECTIVE

To identify and summarize the current internal governance processes adopted by hospitals, as reported in the literature, for selecting, optimizing, and evaluating clinical decision support (CDS) alerts in order to identify effective approaches.

MATERIALS AND METHODS

Databases (Medline, Embase, CINAHL, Scopus, Web of Science, IEEE Xplore Digital Library, CADTH, and WorldCat) were searched to identify relevant papers published from January 2010 to April 2020. All paper types published in English that reported governance processes for selecting and/or optimizing CDS alerts in hospitals were included.

RESULTS

Eight papers were included in the review. Seven papers focused specifically on medication-related CDS alerts. All papers described the use of a multidisciplinary committee to optimize alerts. Other strategies included the use of clinician feedback, alert data, literature and drug references, and a visual dashboard. Six of the 8 papers reported evaluations of their CDS alert modifications following the adoption of optimization strategies, and of these, 5 reported a reduction in alert rate.

CONCLUSIONS

A multidisciplinary committee, often in combination with other approaches, was the most frequent strategy reported by hospitals to optimize their CDS alerts. Due to the limited number of published processes, variation in system changes, and evaluation results, we were unable to compare the effectiveness of different strategies, although employing multiple strategies appears to be an effective approach for reducing CDS alert numbers. We recommend hospitals report on descriptions and evaluations of governance processes to enable identification of effective strategies for optimization of CDS alerts in hospitals.

Systematic Review of Clinical Decision Support Systems for Prehospital Acute Coronary Syndrome Identification

OBJECTIVES

Timely prehospital diagnosis and treatment of acute coronary syndrome (ACS) are required to achieve optimal outcomes. Clinical decision support systems (CDSS) are platforms designed to integrate multiple data and can aid with management decisions in the prehospital environment. The review aim was to describe the accuracy of CDSS and individual components in the prehospital ACS management.

METHODS

This systematic review examined the current literature regarding the accuracy of CDSS for ACS in the prehospital setting, the influence of computer-aided decision-making and of 4 components: electrocardiogram, biomarkers, patient history, and examination findings. The impact of these components on sensitivity, specificity, and positive and negative predictive values was assessed.

RESULTS

A total of 11,439 articles were identified from a search of databases, of which 199 were screened against the eligibility criteria. Eight studies were found to meet the eligibility and quality criteria. There was marked heterogeneity between studies which precluded formal meta-analysis. However, individual components analysis found that patient history led to significant improvement in the sensitivity and negative predictive values. CDSS which incorporated all 4 components tended to show higher sensitivities and negative predictive values. CDSS incorporating computer-aided electrocardiogram diagnosis showed higher specificities and positive predictive values.

CONCLUSIONS

Although heterogeneity precluded meta-analysis, this review emphasizes the potential of ACS CDSS in prehospital environments that incorporate patient history in addition to integration of multiple components. The higher sensitivity of certain components, along with higher specificity of computer-aided decision-making, highlights the opportunity for developing an integrated algorithm with computer-aided decision support.

Artificial Intelligence and Clinical Decision Support for Radiologists and Referring Providers

Recent advances in artificial intelligence (AI) are providing an opportunity to enhance existing clinical decision support (CDS) tools to improve patient safety and drive value-based imaging. We discuss the advantages and potential applications that may be realized with the synergy between AI and CDS systems. From the perspective of both radiologist and ordering provider, CDS could be significantly empowered using AI. CDS enhanced by AI could reduce friction in radiology workflows and can aid AI developers to identify relevant imaging features their tools should be seeking to extract from images. Furthermore, these systems can generate structured data to be used as input to develop machine learning algorithms, which can drive downstream care pathways. For referring providers, an AI-enabled CDS solution could enable an evolution from existing imaging-centric CDS toward decision support that takes into account a holistic patient perspective. More intelligent CDS could suggest imaging examinations in highly complex clinical scenarios, assist on the identification of appropriate imaging opportunities at the health system level, suggest appropriate individualized screening, or aid health care providers to ensure continuity of care. AI has the potential to enable the next generation of CDS, improving patient care and enhancing providers' and radiologists' experience.

Clinical decision support tool and rapid point-of-care platform for determining disease severity in patients with COVID-19

SARS-CoV-2 is the virus that causes coronavirus disease (COVID-19) which has reached pandemic levels resulting in significant morbidity and mortality affecting every inhabited continent. The large number of patients requiring intensive care threatens to overwhelm healthcare systems globally. Likewise, there is a compelling need for a COVID-19 disease severity test to prioritize care and resources for patients at elevated risk of mortality. Here, an integrated point-of-care COVID-19 Severity Score and clinical decision support system is presented using biomarker measurements of C-reactive protein (CRP), N-terminus pro B type natriuretic peptide (NT-proBNP), myoglobin (MYO), D-dimer, procalcitonin (PCT), creatine kinase-myocardial band (CK-MB), and cardiac troponin I (cTnI). The COVID-19 Severity Score combines multiplex biomarker measurements and risk factors in a statistical learning algorithm to predict mortality. The COVID-19 Severity Score was trained and evaluated using data from 160 hospitalized COVID-19 patients from Wuhan, China. Our analysis finds that COVID-19 Severity Scores were significantly higher for the group that died versus the group that was discharged with median (interquartile range) scores of 59 (40-83) and 9 (6-17), respectively, and area under the curve of 0.94 (95% CI 0.89-0.99). Although this analysis represents patients with cardiac comorbidities (hypertension), the inclusion of biomarkers from other pathophysiologies implicated in COVID-19 (e.g., D-dimer for thrombotic events, CRP for infection or inflammation, and PCT for bacterial co-infection and sepsis) may improve future predictions for a more general population. These promising initial models pave the way for a point-of-care COVID-19 Severity Score system to impact patient care after further validation with externally collected clinical data. Clinical decision support tools for COVID-19 have strong potential to empower healthcare providers to save lives by prioritizing critical care in patients at high risk for adverse outcomes.

Confronting challenges to opioid risk mitigation in the U.S. health system: Recommendations from a panel of national experts

BACKGROUND

Amid the ongoing U.S. opioid crisis, achieving safe and effective chronic pain management while reducing opioid-related morbidity and mortality is likely to require multi-level efforts across health systems, including the Military Health System (MHS), Department of Veterans Affairs (VA), and civilian sectors.

OBJECTIVE

We conducted a series of qualitative panel discussions with national experts to identify core challenges and elicit recommendations toward improving the safety of opioid prescribing in the U.S.

DESIGN

We invited national experts to participate in qualitative panel discussions regarding challenges in opioid risk mitigation and how best to support providers in delivery of safe and effective opioid prescribing across MHS, VA, and civilian health systems.

PARTICIPANTS

Eighteen experts representing primary care, emergency medicine, psychology, pharmacy, and public health/policy participated.

APPROACH

Six qualitative panel discussions were conducted via teleconference with experts. Transcripts were coded using team-based qualitative content analysis to identify key challenges and recommendations in opioid risk mitigation.

KEY RESULTS

Panelists provided insight into challenges across multiple levels of the U.S. health system, including the technical complexity of treating chronic pain, the fraught national climate around opioids, the need to integrate surveillance data across a fragmented U.S. health system, a lack of access to non-pharmacological options for chronic pain care, and difficulties in provider and patient communication. Participating experts identified recommendations for multi-level change efforts spanning policy, research, education, and the organization of healthcare delivery.

CONCLUSIONS

Reducing opioid risk while ensuring safe and effective pain management, according to participating experts, is likely to require multi-level efforts spanning military, veteran, and civilian health systems. Efforts to implement risk mitigation strategies at the patient level should be accompanied by efforts to increase education for patients and providers, increase access to non-pharmacological pain care, and support use of existing clinical decision support, including state-level prescription drug monitoring programs.

The Value of the Surgeon Informatician

Clinical informatics is an interdisciplinary specialty that leverages big data, health information technologies, and the science of biomedical informatics within clinical environments to improve quality and outcomes in the increasingly complex and often siloed health care systems. Core competencies of clinical informatics primarily focus on clinical decision making and care process improvement, health information systems, and leadership and change management. Although the broad relevance of clinical informatics is apparent, this review focuses on its application and pertinence to the discipline of surgery, which is less well defined. In doing so, we hope to highlight the importance of the surgeon informatician. Topics covered include electronic health records, clinical decision support systems, computerized order entry, data analytics, clinical documentation, information architectures, implementation science, quality improvement, simulation, education, and telemedicine. The formal pathway for surgeons to become clinical informaticians is also discussed.

Implementation of clinical decision support to manage acute kidney injury in secondary care: an ethnographic study

BACKGROUND

Over the past decade, acute kidney injury (AKI) has become a global priority for improving patient safety and health outcomes. In the UK, a confidential inquiry into AKI led to the publication of clinical guidance and a range of policy initiatives. National patient safety directives have focused on the mandatory establishment of clinical decision support systems (CDSSs) within all acute National Health Service (NHS) trusts to improve the detection, alerting and response to AKI. We studied the organisational work of implementing AKI CDSSs within routine hospital care.

METHODS

An ethnographic study comprising non-participant observation and interviews was conducted in two NHS hospitals, delivering AKI quality improvement programmes, located in one region of England. Three researchers conducted a total of 49 interviews and 150 hours of observation over an 18-month period. Analysis was conducted collaboratively and iteratively around emergent themes, relating to the organisational work of technology adoption.

RESULTS

The two hospitals developed and implemented AKI CDSSs using very different approaches. Nevertheless, both resulted in adaptive work and trade-offs relating to the technology, the users, the organisation and the wider system of care. A common tension was associated with attempts to maximise benefit while minimise additional burden. In both hospitals, resource pressures exacerbated the tensions of translating AKI recommendations into routine practice.

CONCLUSIONS

Our analysis highlights a conflicted relationship between external context (policy and resources), and organisational structure and culture (eg, digital capability, attitudes to quality improvement). Greater consideration is required to the long-term effectiveness of the approaches taken, particularly in light of the ongoing need for adaptation to incorporate new practices into routine work.

Association between GP participation in a primary care group and monitoring of biomedical and lifestyle target indicators in people with type 2 diabetes: a cohort study (ELZHA cohort-1)

OBJECTIVE

Whether care group participation by general practitioners improves delivery of diabetes care is unknown. Using 'monitoring of biomedical and lifestyle target indicators as recommended by professional guidelines' as an operationalisation for quality of care, we explored whether (1) in new practices monitoring as recommended improved a year after initial care group participation (aim 1); (2) new practices and experienced practices differed regarding monitoring (aim 2).

DESIGN

Observational, real-life cohort study.

SETTING

Primary care registry data from Eerstelijns Zorggroep Haaglanden (ELZHA) care group.

PARTICIPANTS

Aim 1: From six new practices (n=538 people with diabetes) that joined care group ELZHA in January 2014, two practices (n=211 people) were excluded because of missing baseline data; four practices (n=182 people) were included. Aim 2: From all six new practices (n=538 people), 295 individuals were included. From 145 experienced practices (n=21 465 people), 13 744 individuals were included.

EXPOSURE

Care group participation includes support by staff nurses on protocolised diabetes care implementation and availability of a system providing individual monitoring information. 'Monitoring as recommended' represented minimally one annual registration of each biomedical (HbA1c, systolic blood pressure, low-density lipoprotein) and lifestyle-related target indicator (body mass index, smoking behaviour, physical exercise).

PRIMARY OUTCOME MEASURES

Aim 1: In new practices, odds of people being monitored as recommended in 2014 were compared with baseline (2013). Aim 2: Odds of monitoring as recommended in new and experienced practices in 2014 were compared.

RESULTS

Aim 1: After 1-year care group participation, odds of being monitored as recommended increased threefold (OR 3.00, 95% CI 1.84 to 4.88, p<0.001). Aim 2: Compared with new practices, no significant differences in the odds of monitoring as recommended were found in experienced practices (OR 1.21, 95% CI 0.18 to 8.37, p=0.844).

CONCLUSIONS

We observed a sharp increase concerning biomedical and lifestyle monitoring as recommended after 1-year care group participation, and subsequently no significant difference between new and experienced practices-indicating that providing diabetes care within a collective approach rapidly improves registration of care.

Tele-Critical Care: An Update From the Society of Critical Care Medicine Tele-ICU Committee

OBJECTIVES

In 2014, the Tele-ICU Committee of the Society of Critical Care Medicine published an article regarding the state of ICU telemedicine, one better defined today as tele-critical care. Given the rapid evolution in the field, the authors now provide an updated review.

DATA SOURCES AND STUDY SELECTION

We searched PubMed and OVID for peer-reviewed literature published between 2010 and 2018 related to significant developments in tele-critical care, including its prevalence, function, activity, and technologies. Search terms included electronic ICU, tele-ICU, critical care telemedicine, and ICU telemedicine with appropriate descriptors relevant to each sub-section. Additionally, information from surveys done by the Society of Critical Care Medicine was included given the relevance to the discussion and was referenced accordingly.

DATA EXTRACTION AND DATA SYNTHESIS

Tele-critical care continues to evolve in multiple domains, including organizational structure, technologies, expanded-use case scenarios, and novel applications. Insights have been gained in economic impact and human and organizational factors affecting tele-critical care delivery. Legislation and credentialing continue to significantly influence the pace of tele-critical care growth and adoption.

CONCLUSIONS

Tele-critical care is an established mechanism to leverage critical care expertise to ICUs and beyond, but systematic research comparing different models, approaches, and technologies is still needed.

Pragmatic trial design of an intervention to reduce cardiovascular risk in people with serious mental illness

BACKGROUND

Cardiovascular (CV) disease is the leading cause of death for people with serious mental illness (SMI), but clinicians are often slow to address this risk.

METHODS/DESIGN

78 Midwestern primary care clinics were randomized to receive or not receive access to a clinical decision support (CDS) tool. Between March 2016 and September 2018, primary care clinicians (PCPs) received CDS alerts during visits with adult patients with SMI who met minimal inclusion criteria and had at least one CV risk factor not at goal. The PCP CDS included a summary of six modifiable CV risk factors and patient-specific treatment recommendations. Psychiatrists received CDS alerts during their next visit with an eligible patient with SMI that alerted them to an elevated body mass index or recent weight gain and the presence of an obesogenic SMI medication. Study outcomes include total modifiable CV risk, six modifiable CV risk factors, and use of obesogenic SMI medications.

DISCUSSION

This cluster-randomized pragmatic trial allowed PCPs and psychiatrists the opportunity to improve CV risk in a timely manner for patients with SMI. Effectiveness will be assessed using an intent-to-treat analysis, and outcomes will be assessed largely through electronic health record data harvested by the CDS tool itself. In total, 10,347 patients with SMI had an index primary care visit in a randomized clinic, and 8937 patients had at least one follow-up visit. Analyses are ongoing, and trial results are expected in mid-2020.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT02451670.

Mixed-methods approach to understanding clinician macrocognition in the design of a clinical decision support tool: a study protocol

INTRODUCTION

The anatomic variants of congenital heart disease (CHD) are multiple. The increased survival of these patients and disposition into communities has led to an increase in their acute presentation to non-CHD experts in primary care clinics and emergency departments. Given the vulnerability and fragility of these patients in the face of acute illness, new clinical decision support systems (CDSS) are urgently needed to better translate the best practice recommendations for the care of these patients. This study aims to understand the perceived confidence and macrocognitive processes of non-CHD experts (emergency medicine physicians) and CHD experts (paediatric cardiac intensivists) when treating children with CHD during acute illness and apply this to optimise the design of a CDSS (MyHeartPass^™) for these patients.

METHODS AND ANALYSIS

The first phase of the study involves a survey of non-CHD experts and CHD experts to understand their perceived confidence as it relates to treating acutely ill patients with CHD. The second phase is a qualitative cognitive task analysis using critical decision method to characterise and compare the macrocognitive processes used by non-CHD experts and CHD experts during the critical decision making. In phases 3 and 4, heuristic evaluation and usability testing of the CDSS will be completed. These results will be used to inform design changes to the chosen CDSS (MyHeartPass^™). In the final phase, a within-participant simulation design will be used to study the effect of the CDSS on clinical decision making compared with baseline (without use of CDSS).

ETHICS AND DISSEMINATION

Ethics approval from The Hospital for Sick Children in Toronto, Ontario, Canada has been obtained for all phases. Results will be published in peer-reviewed journals and presented at relevant conferences. On successful completion of these studies, it is anticipated that there will be a controlled implementation of the redesigned CDSS.

How, in what contexts, and why do quality dashboards lead to improvements in care quality in acute hospitals? Protocol for a realist feasibility evaluation

INTRODUCTION

National audits are used to monitor care quality and safety and are anticipated to reduce unexplained variations in quality by stimulating quality improvement (QI). However, variation within and between providers in the extent of engagement with national audits means that the potential for national audit data to inform QI is not being realised. This study will undertake a feasibility evaluation of QualDash, a quality dashboard designed to support clinical teams and managers to explore data from two national audits, the Myocardial Ischaemia National Audit Project (MINAP) and the Paediatric Intensive Care Audit Network (PICANet).

METHODS AND ANALYSIS

Realist evaluation, which involves building, testing and refining theories of how an intervention works, provides an overall framework for this feasibility study. Realist hypotheses that describe how, in what contexts, and why QualDash is expected to provide benefit will be tested across five hospitals. A controlled interrupted time series analysis, using key MINAP and PICANet measures, will provide preliminary evidence of the impact of QualDash, while ethnographic observations and interviews over 12 months will provide initial insight into contexts and mechanisms that lead to those impacts. Feasibility outcomes include the extent to which MINAP and PICANet data are used, data completeness in the audits, and the extent to which participants perceive QualDash to be useful and express the intention to continue using it after the study period.

ETHICS AND DISSEMINATION

The study has been approved by the University of Leeds School of Healthcare Research Ethics Committee. Study results will provide an initial understanding of how, in what contexts, and why quality dashboards lead to improvements in care quality. These will be disseminated to academic audiences, study participants, hospital IT departments and national audits. If the results show a trial is feasible, we will disseminate the QualDash software through a stepped wedge cluster randomised trial.

A unique framework for the Persian clinical guidelines: addressing an evidence-based CDSS development need

BACKGROUND AND AIM

One of the prerequisites to develop Computerised Decision Support Systems is Clinical Practice Guidelines (CPGs) which provide a systematic aid to make complex medical decisions. In order to provide an automated CPG, it is needed to have a unique structure for the CPGs. This study aims to propose a unique framework for the Persian guidelines.

MATERIALS AND METHODS

20 Persian CPGs were selected and divided into the creation and validation sets (n=10 for each). The first group was studied independently and their headings were listed; wherever possible, the headings were merged into a new heading that was applicable to all the guidelines. The developed framework was validated by the second group of the guidelines.

RESULTS

Studied guidelines had a very heterogeneous structure. The number of original headings was 249; they were reduced to 14 main headings with 16 subheadings in a unique developed framework. The framework is able to represent and cover 100% of the guidelines.

CONCLUSION

The heterogeneity of guidelines was high as they were not developed based on the unique framework. The proposed framework provides a layout for designing the CPGs with a homogeneous structure. Guideline developers can use this framework to develop structured CPGs. This will facilitate the integration of the guidelines into electronic medical records as well as clinical decision support systems.

More Guidelines than states: variations in U.S. lead screening and management guidance and impacts on shareable CDS development

BACKGROUND

Pediatric lead exposure in the United States (U.S.) remains a preventable public health crisis. Shareable electronic clinical decision support (CDS) could improve lead screening and management. However, discrepancies between federal, state and local recommendations could present significant challenges for implementation.

METHODS

We identified publically available guidance on lead screening and management. We extracted definitions for elevated lead and recommendations for screening, follow-up, reporting, and management. We compared thresholds and level of obligation for management actions. Finally, we assessed the feasibility of development of shareable CDS.

RESULTS

We identified 54 guidance sources. States offered different definitions of elevated lead, and recommendations for screening, reporting, follow-up and management. Only 37 of 48 states providing guidance used the Center for Disease Control (CDC) definition for elevated lead. There were 17 distinct management actions. Guidance sources indicated an average of 5.5 management actions, but offered different criteria and levels of obligation for these actions. Despite differences, the recommendations were well-structured, actionable, and encodable, indicating shareable CDS is feasible.

CONCLUSION

Current variability across guidance poses challenges for clinicians. Developing shareable CDS is feasible and could improve pediatric lead screening and management. Shareable CDS would need to account for local variability in guidance.

Results from one-year use of an electronic Clinical Decision Support System in a post-conflict context: An implementation research

BACKGROUND

In 2017, the Adamawa State Primary Healthcare Development Agency introduced ALMANACH, an electronic clinical decision support system based on a modified version of IMCI. The target area was the Federal State of Adamawa (Nigeria), a region recovering after the Boko Haram insurgency. The aim of this implementation research was to assess the improvement in terms of quality care offered after one year of utilization of the tool.

METHODS

We carried out two cross-sectional studies in six Primary Health Care Centres to assess the improvements in comparison with the baseline carried out before the implementation. One survey was carried out inside the consultation room and was based on the direct observation of 235 consultations of children aged from 2 to 59 months old. The second survey questioned 189 caregivers outside the health facility for their opinion about the consultation carried out through using the tablet, the prescriptions and medications given.

RESULTS

In comparison with the baseline, more children were checked for danger signs (60.0% vs. 37.1% at baseline) and in addition, children were actually weighed (61.1% vs. 27.7%) during consultation. Malnutrition screening was performed in 35.1% of children (vs. 12.1%). Through ALMANACH, also performance of preventive measures was significantly improved (p<0.01): vaccination status was checked in 39.8% of cases (vs. 10.6% at baseline), and deworming and vitamin A prescription was increased to 46.5% (vs. 0.7%) and 48.3% (vs. 2.8%) respectively. Furthermore, children received a complete physical examination (58.3% vs. 45.5%, p<0.01) and correct treatment (48.4% vs. 29.5%, p<0.01). Regarding antibiotic prescription, 69.3% patients received at least one antibiotic (baseline 77.7%, p<0.05).

CONCLUSIONS

Our findings highlight major improvements in terms of quality of care despite many questions still pending to be answered in relation to a full integration of the tool in the Adamawa health system.

Availability and usage of clinical decision support systems (CDSSs) in office-based primary care settings in the USA

BACKGROUND

A clinical decision support system (CDSS) covers a broad spectrum of applications, for example, screening reminders, can reduce malpractice, improve preventive services and enable better management of chronic conditions. CDSSs have traditionally been used successfully in large hospitals. The availability (ie, whether the function is provided by the software) and usage (ie, actual use) of a CDSS in office-based primary care settings, however, are less well studied.

OBJECTIVE

To establish a benchmark of CDSS availability and usage in office-based primary care settings, particularly given the large volume of visits in such settings.

METHODS

We used the 2015 Centers for Disease Control and Prevention's National Ambulatory Medical Care Survey to conduct secondary data analysis. We selected preventive services reminders and drug interaction alerts, along with several other variables as examples of a CDSS.

RESULTS

CDSS usage rates ranged from 68.5% to 100% among solo or non-solo primary care practices owned by physicians or physician groups that have electronic medical records (EMRs)/electronic health records (EHRs) and 44.7% to 96.1%, regardless of EMR/EHR status. According to proportion tests, solo practices had significantly lower CDSS usage and availability rates on several measures if the practice is entirely EMR/EHR based and significantly lower (16.3%-28.9%) CDSS usage rates than did non-solo practices on each measure, regardless of EMR/EHR status.

CONCLUSION

In the USA, a CDSS, especially under the categories of basic preventive reminders and drug interaction alerts, is used routinely between 68% and 100% in primary care if a practice is entirely EMR/EHR based. More work is needed, however, to determine the reasons for large usage gaps between solo and non-solo practices and to reduce such gaps.

Merits, features, and desiderata to be considered when developing electronic health records with embedded clinical decision support systems in Palestinian hospitals: a consensus study

BACKGROUND

Electronic health records (EHRs) with embedded clinical decision support systems (CDSSs) have the potential to improve healthcare delivery. This study was conducted to explore merits, features, and desiderata to be considered when planning for, designing, developing, implementing, piloting, evaluating, maintaining, upgrading, and/or using EHRs with CDSSs.

METHODS

A mixed-method combining the Delphi technique and Analytic Hierarchy Process was used. Potentially important items were collected after a thorough search of the literature and from interviews with key contact experts (n = 19). Opinions and views of the 76 panelists on the use of EHRs were also explored. Iterative Delphi rounds were conducted to achieve consensus on 122 potentially important items by a panel of 76 participants. Items on which consensus was achieved were ranked in the order of their importance using the Analytic Hierarchy Process.

RESULTS

Of the 122 potentially important items presented to the panelists in the Delphi rounds, consensus was achieved on 110 (90.2%) items. Of these, 16 (14.5%) items were related to the demographic characteristics of the patient, 16 (14.5%) were related to prescribing medications, 16 (14.5%) were related to checking prescriptions and alerts, 14 (12.7%) items were related to the patient's identity, 13 (11.8%) items were related to patient assessment, 12 (10.9%) items were related to the quality of alerts, 11 (10%) items were related to admission and discharge of the patient, 9 (8.2%) items were general features, and 3 (2.7%) items were related to diseases and making diagnosis.

CONCLUSIONS

In this study, merits, features, and desiderata to be considered when planning for, designing, developing, implementing, piloting, evaluating, maintaining, upgrading, and/or using EHRs with CDSSs were explored. Considering items on which consensus was achieved might promote congruence and safe use of EHRs. Further studies are still needed to determine if these recommendations can improve patient safety and outcomes in Palestinian hospitals.

General Practitioner's use of online resources during medical visits: managing the boundary between inside and outside the clinic

In an increasingly connected world, information about health can be exchanged at any time, in any location or direction, and is no longer dominated by traditional authoritative sources. We consider the ways information and advice given in consultations by doctors transcends the boundary between the clinic and the home. We explore how information that is widely accessible outside the consultation is transformed by General Practitioners (GPs) into a medical offering. Data comprise 18 consultations identified from 144 consultations between unselected patients and five GPs. We use conversation analytic methods to explore four ways in which GPs used online resources; (i) to check information; (ii) as an explanatory tool; (iii) to provide information for patients for outside the consultation; (iv) to signpost further explanation and self-help. We demonstrate the interactional delicacy with which resources from the Internet are introduced and discussed, developing and extending Nettleton's (2004) idea of 'e-scaped medicine' to argue that Internet resources may be 'recaptured' by GPs, with information transformed and translated into a medical offering so as to maintain the asymmetry between patients and practitioners necessary for the successful functioning of medical practice.

A usability study to improve a clinical decision support system for the prescription of antibiotic drugs

OBJECTIVE

A clinical decision support system (CDSS) for empirical antibiotic treatment has the potential to increase appropriate antibiotic use. Before using such a system on a broad scale, it needs to be tailored to the users preferred way of working. We have developed a CDSS for empirical antibiotic treatment in hospitalized adult patients. Here we determined in a usability study if the developed CDSS needed changes.

METHODS

Four prespecified patient cases, based on real life clinical scenarios, were evaluated by 8 medical residents in the study. The "think-aloud" method was used, and sessions were recorded and analyzed afterwards. Usability was assessed by 3 evaluators using an augmented classification scheme, which combines the User Action Framework with severity rating of the usability problems and the assessment of the potential impact of these problems on the final task outcomes.

RESULTS

In total 51 usability problems were identified, which could be grouped into 29 different categories. Most (n = 17/29) of the usability problems were cosmetic problems or minor problems. Eighteen (out of 29) of the usability categories could have an ordering error as a result. Classification of the problems showed that some of the problems would get a low priority based on their severity rating, but got a high priority for their impact on the task outcome. This effectively provided information to prioritize system redesign efforts.

CONCLUSION

Usability studies improve lay-out and functionality of a CDSS for empirical antibiotic treatment, even after development by a multidisciplinary system.

How do general practitioners access guidelines and utilise electronic medical records to make clinical decisions on antibiotic use? Results from an Australian qualitative study

OBJECTIVE

This study aimed to explore how general practitioners (GPs) access and use both guidelines and electronic medical records (EMRs) to assist in clinical decision-making when prescribing antibiotics in Australia.

DESIGN

This is an exploratory qualitative study with thematic analysis interpreted using the Theory of Planned Behaviour (TPB) framework.

SETTING

This study was conducted in general practice in Victoria, Australia.

PARTICIPANTS

Twenty-six GPs from five general practices were recruited to participate in five focus groups between February and April 2018.

RESULTS

GPs expressed that current EMR systems do not provide clinical decision support to assist with antibiotic prescribing. Access and use of guidelines were variable. GPs who had more clinical experience were less likely to access guidelines than younger and less experienced GPs. Guideline use and guideline-concordant prescribing was facilitated if there was a practice culture encouraging evidence-based practice. However, a lack of access to guidelines and perceived patients' expectation and demand for antibiotics were barriers to guideline-concordant prescribing. Furthermore, guidelines that were easy to access and navigate, free, embedded within EMRs and fit into the clinical workflow were seen as likely to enhance guideline use.

CONCLUSIONS

Current barriers to the use of antibiotic guidelines include GPs' experience, patient factors, practice culture, and ease of access and cost of guidelines. To reduce inappropriate antibiotic prescribing and to promote more rational use of antibiotic in the community, guidelines should be made available, accessible and easy to use, with minimal cost to practicing GPs. Integration of evidence-based antibiotic guidelines within the EMR in the form of a clinical decision support tool could optimise guideline use and increase guideline-concordant prescribing.

Association of decision support for hospital discharge disposition with outcomes

OBJECTIVES

To assess the association of a clinical decision support (CDS) algorithm for hospital discharge disposition with spending, readmissions, and postdischarge emergency department (ED) use.

STUDY DESIGN

A retrospective study in a cohort of fee-for-service Medicare patients 65 years or older linked to a database of patients receiving CDS.

METHODS

We evaluated (1) patients whose discharge disposition was concordant with the CDS recommendation versus those whose disposition was not and (2) patients receiving CDS for discharge disposition versus those not receiving CDS, regardless of concordance. Outcomes were spending over a 90-day episode, 90-day readmissions, and postdischarge ED utilization not associated with a readmission.

RESULTS

Analysis of concordant versus discordant cases showed decreased spending for concordant cases ($860 savings; 95% CI, $162-$1558; P = .016), a decrease in readmissions (adjusted odds ratio [OR], 0.920; 95% CI, 0.850-0.995; P = .038), and no change in rate of postdischarge ED use (adjusted OR, 0.990; 95% CI, 0.882-1.110; P = .858). Analysis of patients receiving CDS versus not receiving CDS showed no significant difference in spending ($221 savings; 95% CI, -$115 to $557; P = .198), ED use (adjusted OR, 0.959; 95% CI, 0.908-1.012; P = .128), or readmission rate (adjusted OR, 1.004; 95% CI, 0.966-1.043; P = .840).

CONCLUSIONS

Following the recommendation of a CDS algorithm for hospital discharge disposition was associated with lower spending, fewer readmissions, and no change in ED use over a 90-day episode of care.

The Safer Prescription of Opioids Tool (SPOT): A Novel Clinical Decision Support Digital Health Platform for Opioid Conversion in Palliative and End of Life Care-A Single-Centre Pilot Study

Opioid errors are a leading cause of patient harm. Active failures in opioid dose conversion can contribute to error. Conversion is complex and is currently performed manually using tables of approximate equivalence. Apps that offer opioid dose double-checking are available but there are concerns about their accuracy and clinical validation. This study evaluated a novel opioid dose conversion app, The Safer Prescription of Opioids Tool (SPOT), a CE-marked Class I medical device, as a clinician decision support (CDS) platform. This single-centre prospective clinical utility pilot study followed a mixed methods design. Prescribers completed an initial survey exploring their current opioid prescribing practice. Thereafter prescribers used SPOT for opioid dosage conversions in parallel to their usual clinical practice, then evaluated SPOT through a survey and focus group. SPOT matched the Gold Standard result in 258 of 268 (96.3%) calculations. The 10 instances (3.7%) when SPOT did not match were due to a rounding error. Users had a statistically significant increase in confidence in prescribing opioids after using SPOT. Focus group feedback highlighted benefits in Quality Improvement and Safety when using SPOT. SPOT is a safe, reliable and validated CDS that has potential to reduce harms from opioid dosing errors.

Link-me: Protocol for a randomised controlled trial of a systematic approach to stepped mental health care in primary care

Primary care in Australia is undergoing significant reform, with a particular focus on cost-effective tailoring of mental health care to individual needs. Link-me is testing whether a patient-completed Decision Support Tool (DST), which predicts future severity of depression and anxiety symptoms and triages individuals into care accordingly, is clinically effective and cost-effective relative to usual care. The trial is set in general practices, with English-speaking patients invited to complete eligibility screening in their general practitioner's waiting room. Eligible and consenting patients will then complete the DST assessment and are randomised and stratified according to predicted symptom severity. Participants allocated to the intervention arm will receive feedback on DST responses, select treatment priorities, assess motivation to change, and receive a severity-matched treatment recommendation (information about and links to low intensity services for those with mild symptoms, or assistance from a specially trained health professional (care navigator) for those with severe symptoms). All patients allocated to the comparison arm will receive usual GP care plus attention control. Primary (psychological distress) and secondary (depression, anxiety, quality of life, days out of role) outcomes will be assessed at 6 and 12 months. Differences in outcome means between trial arms both across and within symptom severity group will be examined using intention-to-treat analyses. Within trial and modelled economic evaluations will be conducted to determine the value for money of credentials of Link-me. Findings will be reported to the Federal Government to inform how mental health services across Australia are funded and delivered in the future.

The critical need for clinical decision support systems for identification and management of teratogenic medications

OBJECTIVES

To describe the critical need for clinical decision support systems to identify and manage use of potentially teratogenic medications in women of reproductive potential in the United States.

DATA SOURCES

Medline, CINAHL Plus, Academic Search Complete, International Pharmaceutical Abstracts, and the Cochrane Library databases were searched on November 1, 2018, with the key words (teratogen* OR birth defect OR Category D OR Category X OR (pregnancy or pregnant)) AND (clinical decision support OR decision support OR electronic record) to identify primary literature published in peer-reviewed journals describing clinical decision support systems implemented in outpatient settings in the United States to promote safe prescribing and clinician counseling for teratogenic medications. A hand search of the reference lists of relevant articles, including review articles, found through this search strategy was also performed.

SUMMARY

Despite the great potential for clinical decision support to assist clinicians in minimizing inadvertent fetal exposure to potentially teratogenic medications, there were only seven primary articles meeting the criteria. The results of these studies have shown some evidence of effectiveness yet had several notable limitations. No published clinical decision system showed great success. An eighth article, published in 2017, details the design of an intervention that had been implemented but not yet evaluated.

CONCLUSION

There is a relative paucity of data regarding clinical decision support systems focused on teratogenic medications in the outpatient setting in the United States. Additional clinical decision support systems in this area need to be developed.

A Clinical Decision Support System for Diabetic Retinopathy Screening: Creating a Clinical Support Application

BACKGROUND

The aim of this study was to build a clinical decision support system (CDSS) in diabetic retinopathy (DR), based on type 2 diabetes mellitus (DM) patients.

METHOD

We built a CDSS from a sample of 2,323 patients, divided into a training set of 1,212 patients, and a testing set of 1,111 patients. The CDSS is based on a fuzzy random forest, which is a set of fuzzy decision trees. A fuzzy decision tree is a hierarchical data structure that classifies a patient into several classes to some level, depending on the values that the patient presents in the attributes related to the DR risk factors. Each node of the tree is an attribute, and each branch of the node is related to a possible value of the attribute. The leaves of the tree link the patient to a particular class (DR, no DR).

RESULTS

A CDSS was built with 200 trees in the forest and three variables at each node. Accuracy of the CDSS was 80.76%, sensitivity was 80.67%, and specificity was 85.96%. Applied variables were current age, gender, DM duration and treatment, arterial hypertension, body mass index, HbA1c, estimated glomerular filtration rate, and microalbuminuria.

DISCUSSION

Some studies concluded that screening every 3 years was cost effective, but did not personalize risk factors. In this study, the random forest test using fuzzy rules permit us to build a personalized CDSS.

CONCLUSIONS

We have developed a CDSS that can help in screening diabetic retinopathy programs, despite our results more testing is essential.

BDI personal medical assistant agents: The case of trauma tracking and alerting

Personal assistant agents can have an important role in healthcare as a smart technology to support physicians in their daily work, helping to tackle the increasing complexity of their task environment. In this paper we present and discuss a personal medical assistant agent technology for trauma documentation and management, based on the Belief-Desire-Intention (BDI) architecture. The purpose of the personal assistant agent is twofold: to assist the Trauma Team in doing precision tracking during a trauma resuscitation, so as to (automatically) produce an accurate documentation of the trauma, and to generate alerts at real-time, to be eventually displayed either on smart-glasses or room-display.

Acceptability of a decision-support electronic health record system and its impact on diabetes care goals in South Asia: a mixed-methods evaluation of the CARRS trial

AIMS

To describe physicians' acceptance of decision-support electronic health record system and its impact on diabetes care goals among people with Type 2 diabetes.

METHODS

We analysed data from participants in the Centre for Cardiometabolic Risk Reduction in South Asia (CARRS) trial, who received the study intervention (care coordinators and use of a decision-support electronic health record system; n=575) using generalized estimating equations to estimate the association between acceptance/rejection of decision-support system prompts and outcomes (mean changes in HbA_1c , blood pressure and LDL cholesterol) considering repeated measures across all time points available. We conducted in-depth interviews with physicians to understand the benefits, challenges and value of the decision-support electronic health record system and analysed physicians' interviews using Rogers' diffusion of innovation theory.

RESULTS

At end-of-trial, participants with diabetes for whom glycaemic, systolic blood pressure, diastolic blood pressure and LDL cholesterol decision-support electronic health record prompts were accepted vs rejected, experienced no reduction in HbA_1c [mean difference: -0.05 mmol/mol (95% CI -0.22, 0.13); P=0.599], but statistically significant improvements were observed for systolic blood pressure [mean difference: -11.6 mmHg (95% CI -13.9, -9.3); P ≤ 0.001], diastolic blood pressure [mean difference: -5.2 mmHg (95% CI -6.5, -3.8); P ≤ 0.001] and LDL cholesterol [mean difference: -0.7 mmol/l (95% CI -0.6, -0.8); P ≤0.001], respectively. The relative advantages and compatibility of the decision-support electronic health record system with existing clinic set-ups influenced physicians' acceptance of it. Software complexities and data entry challenges could be overcome by task-sharing.

CONCLUSION

Wider adherence to decision-support electronic health record prompts could potentially improve diabetes goal achievement, particularly when accompanied by assistance from a non-physician health worker.

Nudging physicians and patients with autopend clinical decision support to improve diabetes management

OBJECTIVES

To determine the impact on routine glycated hemoglobin (A1C) laboratory test completion of incorporating an autopend laboratory order functionality into clinical decision support, which (1) routed provider alerts to a separate electronic folder, (2) automatically populated preauthorization forms, and (3) linked the timing and content of electronic patient health maintenance topic (HMT) reminders to the provider authorization.

STUDY DESIGN

Observational pre-post study from November 2011 (1 year before autopend) through June 2014 (1.5 years after).

METHODS

The study included HMT reminders concerning an A1C test for patients with type 1 or type 2 diabetes (N = 15,630 HMT reminders; 8792 patients) in a large multispecialty ambulatory healthcare system. A Cox proportional hazard model, adjusted for patient and provider demographics, estimated the likelihood of laboratory test completion based on 3 HMT reminder characteristics: preautopend versus postautopend period, read versus unread, and the patient's time to reading.

RESULTS

In the postautopend period, the median time for patients to read reminders decreased (1 vs 3 days; P <.001) and the median time to complete laboratory tests decreased (40 vs 48 days; P <.001). Comparing preautopend HMT reminders with a similar time to reading, the likelihood of A1C laboratory test completion increased after autopend by between 21.1% (hazard ratio [HR], 1.211; P = .050), when time to reading was 57 days, and 33.9% (HR, 1.339; P = .003), when time to reading was 0 days. This result included 68% of the reminders. There was no statistical difference in A1C laboratory test completion for unread reminders in the preautopend versus postautopend period.

CONCLUSIONS

Automated patient-centered decision support can improve guideline-concordant monitoring of A1C among patients with diabetes, particularly among patients who read reminders in a timely fashion.

Role of Technology in Antimicrobial Stewardship

Because of the increasing plague of antimicrobial resistance and antibiotic misuse, antimicrobial stewardship programs (ASPs) are now a mandatory entity in all US hospitals. ASPs can use technological advances, such as the electronic medical record and clinical decision support systems, to impact a larger patient population with more efficiency. Additionally, through the use of mobile applications and social media, ASPs can highlight and propagate educational information regarding antimicrobial utilization to patients and providers in a widespread and timely manner. In this article, the authors describe how technology can play an important role in antimicrobial stewardship.

Assessment of the Feasibility of automated, real-time clinical decision support in the emergency department using electronic health record data

BACKGROUND

The use of big data and machine learning within clinical decision support systems (CDSSs) has the potential to transform medicine through better prognosis, diagnosis and automation of tasks. Real-time application of machine learning algorithms, however, is dependent on data being present and entered prior to, or at the point of, CDSS deployment. Our aim was to determine the feasibility of automating CDSSs within electronic health records (EHRs) by investigating the timing, data categorization, and completeness of documentation of their individual components of two common Clinical Decision Rules (CDRs) in the Emergency Department.

METHODS

The CURB-65 severity score and HEART score were randomly selected from a list of the top emergency medicine CDRs. Emergency department (ED) visits with ICD-9 codes applicable to our CDRs were eligible. The charts were reviewed to determine the categorization components of the CDRs as structured and/or unstructured, median times of documentation, portion of charts with all data components documented as structured data, portion of charts with all structured CDR components documented before ED departure. A kappa score was calculated for interrater reliability.

RESULTS

The components of the CDRs were mainly documented as structured data for the CURB-65 severity score and HEART score. In the CURB-65 group, 26.8% of charts had all components documented as structured data, and 67.8% in the HEART score. Documentation of some CDR components often occurred late for both CDRs. Only 21 and 11% of patients had all CDR components documented as structured data prior to ED departure for the CURB-65 and HEART score groups, respectively. The interrater reliability for the CURB-65 score review was 0.75 and 0.65 for the HEART score.

CONCLUSION

Our study found that EHRs may be unable to automatically calculate popular CDRs-such as the CURB-65 severity score and HEART score-due to missing components and late data entry.

The Use of Clinical Decision Support in Reducing Diagnosis of and Treatment of Asymptomatic Bacteriuria

Clinical decision support (CDS) embedded within the electronic health record (EHR) is a potential antibiotic stewardship strategy for hospitalized patients. Reduction in urine testing and treating asymptomatic bacteriuria (ASB) is an important strategy to promote antibiotic stewardship. We created an intervention focused on reducing urine testing for asymptomatic patients at a large tertiary care center. The objective of this study was to design an intervention to reduce unnecessary urinalysis and urine culture (UC) orders as well as the treatment of ASB. We performed a quasiexperimental study among adult inpatients at a single academic institution. We implemented a bundled intervention, including information broadcast in newsletters, hospitalwide screensavers, and passive CDS messages in the EHR. We investigated the impact of this strategy on urinalysis, UC orders, and on the treatment of ASB by using an interrupted time series analysis. Our intervention led to reduced UC order as well as reduced antibiotic orders in response to urinalysis orders and UC results. This easily implementable bundle may play an important role as an antibiotic stewardship strategy.

The Feasibility of Sophisticated Multicriteria Support for Clinical Decisions

BACKGROUND

Multicriteria decision-making (MCDM) methods are well-suited to serve as the foundation for clinical decision support systems. To do so, however, they need to be appropriate for use in busy clinical settings. We compared decision-making processes and outcomes of patient-level analyses done with a range of multicriteria methods that vary in ease of use and intensity of decision support, 2 factors that could affect their ease of implementation into practice.

METHODS

We conducted a series of Internet surveys to compare the effects of 5 multicriteria methods that differ in user interface and required user input format on decisions regarding selection of a preferred method for lowering the risk of cardiovascular disease. The study sample consisted of members of an online Internet panel maintained by Fluidsurveys, an Internet survey company. Study outcomes were changes in preferred option, decision confidence, preparation for decision making, the Values Clarification and Decisional Uncertainty subscales of the Decisional Conflict Scale, and method ease of use.

RESULTS

The frequency of changes in the preferred option ranged from 9% to 38%, P < 0.001, and rose progressively as the level of decision support provided by the MCDM method increased. The proportion of respondents who rated the method as easy ranged from 57% to 79% and differed significantly among MCDM methods, P = 0.003, but was not consistently related to intensity of decision support or ease of use.

CONCLUSION

Decision support based on MCDM methods is not necessarily limited by decreases in ease of use. This result suggests that it is possible to develop decision support tools using sophisticated multicriteria techniques suitable for use in routine clinical care settings.

A kidney offer acceptance decision tool to inform the decision to accept an offer or wait for a better kidney

We developed a kidney offer acceptance decision tool to predict the probability of graft survival and patient survival for first-time kidney-alone candidates after an offer is accepted or declined, and we characterized the effect of restricting the donor pool with a maximum acceptable kidney donor profile index (KDPI). For accepted offers, Cox proportional hazards models estimated these probabilities using transplanted kidneys. For declined offers, these probabilities were estimated by considering the experience of similar candidates who declined offers and the probability that declining would lead to these outcomes. We randomly selected 5000 declined offers and estimated these probabilities 3 years post-offer had the offers been accepted or declined. Predicted outcomes for declined offers were well calibrated (<3% error) with good predictive accuracy (area under the curve: graft survival, 0.69; patient survival, 0.69). Had the offers been accepted, the probabilities of graft survival and patient survival were typically higher. However, these advantages attenuated or disappeared with higher KDPI, candidate priority, and local donor supply. Donor pool restrictions were associated with worse 3-year outcomes, especially for candidates with high allocation priority. The kidney offer acceptance decision tool could inform offer acceptance by characterizing the potential risk-benefit trade-off associated with accepting or declining an offer.

"I Never Would Have Caught That Before": Pharmacist Perceptions of Using Clinical Decision Support for Antimicrobial Stewardship in the United States

To systematically improve the appropriateness of antibiotic prescribing, antimicrobial stewardship programs have been developed. There is a paucity of literature examining how pharmacists perform antimicrobial stewardship using a clinical decision support system in a hospital setting. The purpose of this qualitative study was to develop a model exploring how pharmacists perform antimicrobial stewardship to identify areas for programmatic improvement. Semistructured interviews were conducted across a health care system until saturation of themes was reached. Pharmacists identified that self-efficacy and time were vital for antimicrobial stewardship to be performed, while culture of the hospital and attitude facilitated the process of stewardship. Antimicrobial stewardship programs using clinical decision support tools should ensure pharmacists have adequate time to address rules, provide easy-to-use resources and training to support self-efficacy, and engage influential physicians to support a culture of collaboration.

The Effect of a Clinical Decision Support System on Improving Adherence to Guideline in the Treatment of Atrial Fibrillation: An Interrupted Time Series Study

To evaluate the effect of a computerized Decision Support System (CDSS) on improving adherence to an anticoagulation guideline for the treatment of atrial fibrillation (AF). This study had an interrupted time series design. The adherence to the guideline was assessed at fortnightly (two weeks) intervals from January 2016 to January 2017, 6 months before and 6 months after intervention. Newly diagnosed patients with AF were included in the offices of ten cardiologists. Stroke and major bleeding risks were calculated by the CDSS which was implemented via a mobile application. Treatment recommendations based on the guideline were shown to cardiologists. The segmented regression model was used to evaluate the effect of CDSS on level and trend of guideline adherence for the treatment of AF. In our analysis, 373 patients were included. The trend of adherence to the anticoagulation guideline for the treatment of AF was stable in the pre-intervention phase. After the CDSS intervention, mean of the adherence to the guideline significantly increased from 48% to 65.5% (P-value < 0.0001). The trend of adherence to the guideline was stable in the post-intervention phase. Our results showed that the CDSS can improve adherence to the anticoagulation guideline for the treatment of AF. Registration ID: IRCT2016052528070N1.

Economic and organizational impact of a clinical decision support system on laboratory test ordering

BACKGROUND

We studied the impact of a clinical decision support system (CDSS) implemented in a few wards of two Italian health care organizations on the ordering of redundant laboratory tests under different perspectives: (1) analysis of the volume of tests, (2) cost analysis, (3) end-user satisfaction before and after the installation of the CDSS.

METHODS

(1) and (2) were performed by comparing the ordering of laboratory tests between an intervention group of wards where a CDSS was in use and a second (control) group where a CDSS was not in use; data were compared during a 3-month period before (2014) and a 3-month period after (2015) CDSS installation. To measure end-user satisfaction (3), a questionnaire based on POESUS was administered to the medical staff.

RESULTS

After the introduction of the CDSS, the number of laboratory tests requested decreased by 16.44% and costs decreased by 16.53% in the intervention group, versus an increase in the number of tests (+3.75%) and of costs (+1.78%) in the control group. Feedback from practice showed that the medical staff was generally satisfied with the CDSS and perceived its benefits, but they were less satisfied with its technical performance in terms of slow response time.

CONCLUSIONS

The implementation of CDSSs can have a positive impact on both the efficiency of care provision and health care costs. The experience of using a CDSS can also result in good practice to be implemented by other health care organizations, considering the positive result from the first attempt to gather the point of view of end-users in Italy.

The hospital tech laboratory: quality innovation in a new era of value-conscious care

For decades, the healthcare industry has been incentivized to develop new diagnostic technologies, but this limitless progress fueled rapidly growing expenditures. With an emphasis on value, the future will favor information synthesis and processing over pure data generation, and hospitals will play a critical role in developing these systems. A Michigan Medicine, IBM, and AirStrip partnership created a robust streaming analytics platform tasked with creating predictive algorithms for critical care with the potential to support clinical decisions and deliver significant value.

Healthcare provider education to support integration of pharmacogenomics in practice: the eMERGE Network experience

Ten organizations within the Electronic Medical Records and Genomics Network developed programs to implement pharmacogenomic sequencing and clinical decision support into clinical settings. Recognizing the importance of informed prescribers, a variety of strategies were used to incorporate provider education to support implementation. Education experiences with pharmacogenomics are described within the context of each organization's prior involvement, including the scope and scale of implementation specific to their Electronic Medical Records and Genomics projects. We describe common and distinct education strategies, provide exemplars and share challenges. Lessons learned inform future perspectives. Future pharmacogenomics clinical implementation initiatives need to include funding toward implementing provider education and evaluating outcomes.

Studying Readiness for Clinical Decision Support for Worker Health Using the Rapid Assessment Process and Mixed Methods Interviews

To determine how the Rapid Assessment Process (RAP) can be adapted to evaluate the readiness of primary care clinics for acceptance and use of computerized clinical decision support (CDS) related to clinical management of working patients, we used a unique blend of ethnographic methods for gathering data. First, knowledge resources, which were prototypes of CDS content areas (diabetes, lower back pain, and asthma) containing evidence-based information, decision logic, scenarios and examples of use, were developed by subject matter experts. A team of RAP researchers then visited five clinic settings to identify barriers and facilitators to implementing CDS about the health of workers in general and the knowledge resources specifically. Methods included observations, semi-structured qualitative interviews and graphic elicitation interviews about the knowledge resources. We used both template and grounded hermeneutic approaches to data analysis. Preliminary results indicate that the methods succeeded in generating specific actionable recommendations for CDS design.

Using Best Practices to Extract, Organize, and Reuse Embedded Decision Support Content Knowledge Rules from Mature Clinical Systems

Clinical decision support (CDS) knowledge, embedded over time in mature medical systems, presents an interesting and complex opportunity for information organization, maintenance, and reuse. To have a holistic view of all decision support requires an in-depth understanding of each clinical system as well as expert knowledge of the latest evidence. This approach to clinical decision support presents an opportunity to unify and externalize the knowledge within rules-based decision support. Driven by an institutional need to prioritize decision support content for migration to new clinical systems, the Center for Knowledge Management and Health Information Technology teams applied their unique expertise to extract content from individual systems, organize it through a single extensible schema, and present it for discovery and reuse through a newly created Clinical Support Knowledge Acquisition and Archival Tool (CS-KAAT). CS-KAAT can build and maintain the underlying knowledge infrastructure needed by clinical systems.

Representation of People's Decisions in Health Information Systems.* A Complementary Approach for Understanding Health Care Systems and Population Health

OBJECTIVES

In this study, we aimed: 1) to conceptualize the theoretical challenges facing health information systems (HIS) to represent patients' decisions about health and medical treatments in everyday life; 2) to suggest approaches for modeling these processes.

METHODS

The conceptualization of the theoretical and methodological challenges was discussed in 2015 during a series of interdisciplinary meetings attended by health informatics staff, epidemiologists and health professionals working in quality management and primary and secondary prevention of chronic diseases of the Hospital Italiano de Buenos Aires, together with sociologists, anthropologists and e-health stakeholders.

RESULTS

HIS are facing the need and challenge to represent social human processes based on constructivist and complexity theories, which are the current frameworks of human sciences for understanding human learning and socio-cultural changes. Computer systems based on these theories can model processes of social construction of concrete and subjective entities and the interrelationships between them. These theories could be implemented, among other ways, through the mapping of health assets, analysis of social impact through community trials and modeling of complexity with system simulation tools.

CONCLUSIONS

This analysis suggested the need to complement the traditional linear causal explanations of disease onset (and treatments) that are the bases for models of analysis of HIS with constructivist and complexity frameworks. Both may enlighten the complex interrelationships among patients, health services and the health system. The aim of this strategy is to clarify people's decision making processes to improve the efficiency, quality and equity of the health services and the health system.

Discussion of "Representation of People's Decisions in Health Information Systems: A Complementary Approach for Understanding Health Care Systems and Population Health"

This article is part of a For-Discussion-Section of Methods of Information in Medicine about the paper "Representation of People's Decisions in Health Information Systems: A Complementary Approach for Understanding Health Care Systems and Population Health" written by Fernan Gonzalez Bernaldo de Quiros, Adriana Ruth Dawidowski, and Silvana Figar. It is introduced by an editorial. This article contains the combined commentaries invited to independently comment on the paper of de Quiros, Dawidowski, and Figar. In subsequent issues the discussion can continue through letters to the editor.

The Use of Automated SNOMED CT Clinical Coding in Clinical Decision Support Systems for Preventive Care

OBJECTIVE

The objective of this study is to discuss and analyze the use of automated SNOMED CT clinical coding in clinical decision support systems (CDSSs) for preventive care. The central question that this study seeks to answer is whether the utilization of SNOMED CT in CDSSs can improve preventive care.

METHOD

PubMed, Google Scholar, and Cochrane Library were searched for articles published in English between 2001 and 2012 on SNOMED CT, CDSS, and preventive care.

OUTCOME MEASURES

Outcome measures were the sensitivity or specificity of SNOMED CT coded data and the positive predictive value or negative predictive value of SNOMED CT coded data. Additionally, we documented the publication year, research question, study design, results, and conclusions of these studies.

RESULTS

The reviewed studies suggested that SNOMED CT successfully represents clinical terms and negated clinical terms.

CONCLUSION

The use of SNOMED CT in CDSS can be considered to provide an answer to the problem of medical errors as well as for preventive care in general. Enhancement of the modifiers and synonyms found in SNOMED CT will be necessary to improve the expected outcome of the integration of SNOMED CT with CDSS. Moreover, the application of the tree-augmented naïve (TAN) Bayesian network method can be considered the best technique to search SNOMED CT data and, consequently, to help improve preventive health services.

Reducing Excessive Medication Administration in Hospitalized Adults With Renal Dysfunction

Medication errors are common and harm hospitalized patients. The authors designed and implemented an automated system to complement an existing computerized order entry system by detecting the administration of excessive doses of medication to adult in-patients with renal insufficiency. Its impact, in combination with feedback to prescribers, was evaluated in 3 participating nursing units and compared with the remainder of a tertiary care academic medical center. The baseline rate of excessive dosing was 23.2% of administered medications requiring adjustment for renal insufficiency given to patients with renal impairment on the participating units and 23.6% in the rest of the hospital. The rate fell to 17.3% with nurse feedback and 16.8% with pharmacist feedback in the participating units (P<.05 for each, relative to baseline). The rates of excessive dosing for the same time periods were 26.1% and 24.8% in the rest of the hospital. Automated detection and routine feedback can reduce the rate of excessive administration of medication in hospitalized adults with renal insufficiency.