Stakeholder Perspectives of Clinical Artificial Intelligence Implementation: Systematic Review of Qualitative Evidence.

BACKGROUND: The rhetoric surrounding clinical artificial intelligence (AI) often exaggerates its effect on real-world care. Limited understanding of the factors that influence its implementation can perpetuate this. OBJECTIVE: In this qualitative systematic review, we aimed to identify key stakeholders, consolidate their perspectives on clinical AI implementation, and characterize the evidence gaps that future qualitative research should target. METHODS: Ovid-MEDLINE, EBSCO-CINAHL, ACM Digital Library, Science Citation Index-Web of Science, and Scopus were searched for primary qualitative studies on individuals' perspectives on any application of clinical AI worldwide (January 2014-April 2021). The definition of clinical AI includes both rule-based and machine learning-enabled or non-rule-based decision support tools. The language of the reports was not an exclusion criterion. Two independent reviewers performed title, abstract, and full-text screening with a third arbiter of disagreement. Two reviewers assigned the Joanna Briggs Institute 10-point checklist for qualitative research scores for each study. A single reviewer extracted free-text data relevant to clinical AI implementation, noting the stakeholders contributing to each excerpt. The best-fit framework synthesis used the Nonadoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework. To validate the data and improve accessibility, coauthors representing each emergent stakeholder group codeveloped summaries of the factors most relevant to their respective groups. RESULTS: The initial search yielded 4437 deduplicated articles, with 111 (2.5%) eligible for inclusion (median Joanna Briggs Institute 10-point checklist for qualitative research score, 8/10). Five distinct stakeholder groups emerged from the data: health care professionals (HCPs), patients, carers and other members of the public, developers, health care managers and leaders, and regulators or policy makers, contributing 1204 (70%), 196 (11.4%), 133 (7.7%), 129 (7.5%), and 59 (3.4%) of 1721 eligible excerpts, respectively. All stakeholder groups independently identified a breadth of implementation factors, with each producing data that were mapped between 17 and 24 of the 27 adapted Nonadoption, Abandonment, Scale-up, Spread, and Sustainability subdomains. Most of the factors that stakeholders found influential in the implementation of rule-based clinical AI also applied to non-rule-based clinical AI, with the exception of intellectual property, regulation, and sociocultural attitudes. CONCLUSIONS: Clinical AI implementation is influenced by many interdependent factors, which are in turn influenced by at least 5 distinct stakeholder groups. This implies that effective research and practice of clinical AI implementation should consider multiple stakeholder perspectives. The current underrepresentation of perspectives from stakeholders other than HCPs in the literature may limit the anticipation and management of the factors that influence successful clinical AI implementation. Future research should not only widen the representation of tools and contexts in qualitative research but also specifically investigate the perspectives of all stakeholder HCPs and emerging aspects of non-rule-based clinical AI implementation. TRIAL REGISTRATION: PROSPERO (International Prospective Register of Systematic Reviews) CRD42021256005; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=256005. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/33145.

Surgeons' risk perception in ASD surgery: The value of objective risk assessment on decision making and patient counselling.

BACKGROUND: Surgeons often rely on their intuition, experience and published data for surgical decision making and informed consent. Literature provides average values that do not allow for individualized assessments. Accurate validated machine learning (ML) risk calculators for adult spinal deformity (ASD) patients, based on 10 year multicentric prospective data, are currently available. The objective of this study is to assess surgeon ASD risk perception and compare it to validated risk calculator estimates. METHODS: Nine ASD complete (demographics, HRQL, radiology, surgical plan) preoperative cases were distributed online to 100 surgeons from 22 countries. Surgeons were asked to determine the risk of major complications and reoperations at 72 h, 90 d and 2 years postop, using a 0-100% risk scale. The same preoperative parameters circulated to surgeons were used to obtain ML risk calculator estimates. Concordance between surgeons' responses was analyzed using intraclass correlation coefficients (ICC) (poor < 0.5/excellent > 0.85). Distance between surgeons' and risk calculator predictions was assessed using the mean index of agreement (MIA) (poor < 0.5/excellent > 0.85). RESULTS: Thirty-nine surgeons (74.4% with > 10 years' experience), from 12 countries answered the survey. Surgeons' risk perception concordance was very low and heterogeneous. ICC ranged from 0.104 (reintervention risk at 72 h) to 0.316 (reintervention risk at 2 years). Distance between calculator and surgeon prediction was very large. MIA ranged from 0.122 to 0.416. Surgeons tended to overestimate the risk of major complications and reintervention in the first 72 h and underestimated the same risks at 2 years postop. CONCLUSIONS: This study shows that expert surgeon ASD risk perception is heterogeneous and highly discordant. Available validated ML ASD risk calculators can enable surgeons to provide more accurate and objective prognosis to adjust patient expectations, in real time, at the point of care.

Patients with perceived high-bleeding risk and computerized decision support for stroke prevention in atrial fibrillation: an AF-ALERT substudy : Piazza: outcomes of high-bleeding risk AF patients.

A perceived increased risk of bleeding is one of the most frequent reasons for withholding anticoagulation for stroke prevention in atrial fibrillation (AF). We previously conducted a randomized controlled trial of alert-based computerized decision support to increase prescription of anticoagulation in hospitalized patients with AF. To determine the clinical characteristics and outcomes of those patients whose inpatient health care providers received a computer alert, we analyzed all 248 patients in the alert group. Patients for whom providers elected to omit anticoagulation and provided a rationale of a perceived high risk of bleeding were compared with those who were not designated as high-risk. Perceived high risk of bleeding was the most common reason (77%) for omitting anticoagulation. Median HAS-BLED scores were similar in these patients compared with those who were not deemed to have an increased bleeding risk (3 vs. 3, p = 0.44). Despite being categorized as too high-risk for bleeding to receive antithrombotic therapy at the time of the alert, nearly 12% of these patients were ultimately prescribed anticoagulation by 90 days. The frequency of major and clinically-relevant non-major bleeding was similar between the groups. The frequency of death, myocardial infarction, stroke, or systemic embolic event was similar in both groups (10.2% vs. 12.4%, p = 0.59). In conclusion, a perceived high risk of bleeding was the most common reason for omission of anticoagulation in patients with AF after a computerized alert. Perceived high risk of bleeding was not reflected in a higher HAS-BLED score.Clinical trial registration: ClinicalTrials.gov Identifier: NCT02339493 https://clinicaltrials.gov/ct2/show/NCT02339493 In a randomized controlled trial of computerized decision support to increase prescription of antithrombotic therapy in hospitalized patients with atrial fibrillation (AF), a perceived high risk of bleeding was the most common reason (77%) for omitting antithrombotic therapy after an on-screen alert. Median HAS-BLED scores were similar in these patients compared with those who were not deemed to have an increased bleeding risk (3 vs. 3, p = 0.44). Despite being categorized as too high-risk for bleeding to receive antithrombotic therapy for stroke prevention at the time of the alert, nearly 12% of these patients were ultimately prescribed anticoagulation over the ensuing 90 days.

Optimizing pharmacists' detection of prescribing errors: Comparison of on-ward and central pharmacy services.

WHAT IS KNOWN AND OBJECTIVE: Prescribing errors are the leading cause of adverse drug events in hospitalized patients. Pharmaceutical validation, defined as the review of drug orders by a pharmacist, associated with clinical decision support (CDS) systems, significantly reduces these errors and adverse drug events. In Belgium, because clinical pharmacy services have limited public financial support, most pharmaceutical validations are performed at the central pharmacy instead of on-ward, by hospital pharmacists doing dispensing activities. In that context, we aimed at evaluating whether the strategy of CDS-guided central validation was the most appropriate method to improve the quality and safety of medicines' use compared to an on-ward pharmaceutical validation. METHODS: Our retrospective observational study was conducted in a Belgian tertiary care hospital, in 2018-2019. Data were extracted from our validation software and pharmacists' charts. The outcomes of the study were the number of pharmaceutical interventions due to the detection of prescribing errors, reasons for interventions, their acceptance rate and their potential clinical impact (according to two blinded experts) in the central pharmacy and on-ward validation groups. RESULTS AND DISCUSSION: Despite the use of the same CDS, a pharmaceutical intervention following the detection of a prescribing error was made for 2.9% (20/698) of central group patients and 13.3% (93/701) of on-ward patients (χ2  = 49.97, p < 0.001). Interventions made at the central pharmacy (n = 20) mostly relied on CDS-alerts (i.e. drug-drug interaction [25%] or overdosing [20%]) while interventions made on-ward (n = 93) were also for pharmacotherapy optimization (i.e. no valid indication [25%] or inappropriate drug's choice [11%]). The on-ward validation group showed a higher acceptance rate compared to the central group (84% and 65%, respectively [Fisher's test, p = 0.053]). Proportions of interventions with significant or very significant clinical impact were similar between the two groups but as fewer interventions were made centrally, a significant proportion of errors were probably not detected by the central validation. WHAT IS NEW AND CONCLUSION: On-ward pharmaceutical validation leads to a higher rate of prescribing error detection. Pharmaceutical interventions made by on-ward pharmacists are also better accepted and more relevant, going further than CDS-alerts.

A framework for validating AI in precision medicine: considerations from the European ITFoC consortium.

BACKGROUND: Artificial intelligence (AI) has the potential to transform our healthcare systems significantly. New AI technologies based on machine learning approaches should play a key role in clinical decision-making in the future. However, their implementation in health care settings remains limited, mostly due to a lack of robust validation procedures. There is a need to develop reliable assessment frameworks for the clinical validation of AI. We present here an approach for assessing AI for predicting treatment response in triple-negative breast cancer (TNBC), using real-world data and molecular -omics data from clinical data warehouses and biobanks. METHODS: The European "ITFoC (Information Technology for the Future Of Cancer)" consortium designed a framework for the clinical validation of AI technologies for predicting treatment response in oncology. RESULTS: This framework is based on seven key steps specifying: (1) the intended use of AI, (2) the target population, (3) the timing of AI evaluation, (4) the datasets used for evaluation, (5) the procedures used for ensuring data safety (including data quality, privacy and security), (6) the metrics used for measuring performance, and (7) the procedures used to ensure that the AI is explainable. This framework forms the basis of a validation platform that we are building for the "ITFoC Challenge". This community-wide competition will make it possible to assess and compare AI algorithms for predicting the response to TNBC treatments with external real-world datasets. CONCLUSIONS: The predictive performance and safety of AI technologies must be assessed in a robust, unbiased and transparent manner before their implementation in healthcare settings. We believe that the consideration of the ITFoC consortium will contribute to the safe transfer and implementation of AI in clinical settings, in the context of precision oncology and personalized care.

Consistency of decision support software-integrated telephone triage and associated factors: a systematic review.

BACKGROUND: In the recent decades, the use of computerized decision support software (CDSS)-integrated telephone triage (TT) has become an important tool for managing rising healthcare demands and overcrowding in the emergency department. Though these services have generally been shown to be effective, large gaps in the literature exist with regards to the overall quality of these systems. In the current systematic review, we aim to document the consistency of decisions that are generated in CDSS-integrated TT. Furthermore, we also seek to map those factors in the literature that have been identified to have an impact on the consistency of generated triage decisions. METHODS: As part of the TRANS-SENIOR international training and research network, a systematic review of the literature was conducted in November 2019. PubMed, Web of Science, CENTRAL, and the CINAHL database were searched. Quantitative articles including a CDSS component and addressing consistency of triage decisions and/or factors associated with triage decisions were eligible for inclusion in the current review. Studies exploring the use of other types of digital support systems for triage (i.e. web chat, video conferencing) were excluded. Quality appraisal of included studies were performed independently by two authors using the Methodological Index for Non-Randomized Studies. RESULTS: From a total of 1551 records that were identified, 39 full-texts were assessed for eligibility and seven studies were included in the review. All of the studies (n = 7) identified as part of our search were observational and were based on nurse-led telephone triage. Scientific efforts investigating our first aim was very limited. In total, two articles were found to investigate the consistency of decisions that are generated in CDSS-integrated TT. Research efforts were targeted largely towards the second aim of our study-all of the included articles reported factors related to the operator- (n = 6), patient- (n = 1), and/or CDSS-integrated (n = 2) characteristics to have an influence on the consistency of CDSS-integrated TT decisions. CONCLUSION: To date, some efforts have been made to better understand how the use of CDSS-integrated TT systems may vary across settings. In general, however, the evidence-base surrounding this field of literature is largely inconclusive. Further evaluations must be prompted to better understand this area of research. PROTOCOL REGISTRATION: The protocol for this study is registered in the PROSPERO database (registration number: CRD42020146323).

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

AIMS: 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. METHODS AND RESULTS: 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). CONCLUSION: An alert-based CDS strategy increased anticoagulation in high-risk hospitalized AF patients and reduced major adverse cardiovascular events, including MI and stroke. CLINICALTRIALS.GOV IDENTIFIER: NCT02339493.

The effect of a computerized best practice alert system in an outpatient setting on metabolic monitoring in patients on second-generation antipsychotics.

WHAT IS KNOWN AND OBJECTIVE: Metabolic syndrome is a well-documented adverse effect of second-generation antipsychotics (SGAs). Patients with metabolic syndrome are at an increased risk of potentially fatal cardiovascular events, including myocardial infarction and stroke. This elevated risk prompted the creation of a national guideline on metabolic monitoring for patients on SGAs in 2004. However, monitoring practices remained low at our clinic. To address this concern, a clinical decision support system was developed to alert providers of monitoring requirements. The purpose of this study is to determine the effect of the best practice alert (BPA), and to assess the impact of provider and patient characteristics on metabolic laboratory (lab) order rates. METHODS: A retrospective chart review was conducted at a large outpatient psychiatric clinic. Data were collected from all adult patients who were prescribed an SGA and triggered the BPA (indicating lab monitoring is needed for the patient). Data collection included a variety of patient, provider and alert variables. The primary outcome was a composite of fasting blood glucose (FBG), haemoglobin A1c (HbA1c) and/or fasting lipid panel order rates. Secondary outcomes included the rate of valid response, which considered appropriate reasons for not ordering labs (ie monitoring already completed during recent primary care visit), as well as order rates of individual labs. RESULTS AND DISCUSSION: Data from 1112 patients were collected and analysed. Patients with a thought disorder diagnosis had significantly more labs ordered than those without. No other patient factors affected order rates. Resident psychiatrists and nurse practitioners ordered significantly more labs and had significantly more valid responses than attending psychiatrists. An active alert, which fired during medication order entry, was associated with a higher rate of lab ordering and valid response compared to a passive alert, which fired whenever a prescribing healthcare provider opened the chart. WHAT IS NEW AND CONCLUSION: Prescribers may associate metabolic syndrome with schizophrenia or with use of SGAs specifically in thought disorders, even though these medications pose a risk for all indications. Higher rates of monitoring by resident physicians may have been due to spending more time with patients during the encounter and in documentation. Lastly, the active BPA was an effective tool to increase metabolic monitoring in patients taking SGAs. Continued education on the importance of regular metabolic monitoring should be implemented for all providers.

A Conceptual Framework to Study the Implementation of Clinical Decision Support Systems (BEAR): Literature Review and Concept Mapping.

BACKGROUND: The implementation of clinical decision support systems (CDSSs) as an intervention to foster clinical practice change is affected by many factors. Key factors include those associated with behavioral change and those associated with technology acceptance. However, the literature regarding these subjects is fragmented and originates from two traditionally separate disciplines: implementation science and technology acceptance. OBJECTIVE: Our objective is to propose an integrated framework that bridges the gap between the behavioral change and technology acceptance aspects of the implementation of CDSSs. METHODS: We employed an iterative process to map constructs from four contributing frameworks-the Theoretical Domains Framework (TDF); the Consolidated Framework for Implementation Research (CFIR); the Human, Organization, and Technology-fit framework (HOT-fit); and the Unified Theory of Acceptance and Use of Technology (UTAUT)-and the findings of 10 literature reviews, identified through a systematic review of reviews approach. RESULTS: The resulting framework comprises 22 domains: agreement with the decision algorithm; attitudes; behavioral regulation; beliefs about capabilities; beliefs about consequences; contingencies; demographic characteristics; effort expectancy; emotions; environmental context and resources; goals; intentions; intervention characteristics; knowledge; memory, attention, and decision processes; patient-health professional relationship; patient's preferences; performance expectancy; role and identity; skills, ability, and competence; social influences; and system quality. We demonstrate the use of the framework providing examples from two research projects. CONCLUSIONS: We proposed BEAR (BEhavior and Acceptance fRamework), an integrated framework that bridges the gap between behavioral change and technology acceptance, thereby widening the view established by current models.

Large-scale implementation of electronic Integrated Management of Childhood Illness (eIMCI) at the primary care level in Burkina Faso: a qualitative study on health worker perception of its medical content, usability and impact on antibiotic prescription and resistance.

BACKGROUND: Electronic clinical decision algorithms (eCDAs) that guide clinicians during patient management are being deployed in resource-limited settings to improve the quality of care and rational use of medicines (especially antimicrobials). Little is known on how local clinicians perceive the use and impact of these tools in their daily practice. This study investigates clinician insights on an eIMCI tool. Specifically, we report their views on its medical content, assess their knowledge on microbes, antimicrobials and the development of resistance. METHODS: This qualitative study was conducted in the frame of a large-scale implementation in Burkina Faso of an eIMCI tool developed by the Swiss NGO Terre des hommes. Twelve in-depth interviews and 2 focus-group discussions were conducted including 21 health workers from 10 primary care facilities. Emerging themes were identified using qualitative data analysis software. RESULTS: eIMCI users expressed a high level of satisfaction, slowness of the tablet was perceived as the major inconvenience limiting uptake. Several frequent illnesses were identified as missing in the algorithm along with guidance for fever without focus. When asked about existing types of microbes, 9 and 4 out of 21 participants could mention bacteria and virus respectively; only 5 correctly answered that antibiotics had no action on viral disease and 6 mentioned the risk of antibiotic resistance. Level of knowledge was higher in nurses than in less trained health workers. The tool was perceived as improving patient management and the rational use of antibiotics. Positive changes in health facility organisation were reported, such as task shifting and improved triage. eIMCI was also perceived as a learning tool, and users expressed a strong desire to expand the geographic and temporal scope of the intervention. CONCLUSION: The use of eICMI was widely accepted and perceived as a powerful tool guiding daily practice. Findings suggest that it has positive effects on the health care system beyond the quality of consultation. To support large uptake and sustainability, better training of health workers in infectiology is essential and the medical content of eIMCI should be optimized to include frequent diseases and, for each of them, the appropriate management plan.

Reducing Potentially Inappropriate Prescriptions for Older Patients Using Computerized Decision Support Tools: Systematic Review.

BACKGROUND: Older adults are more vulnerable to polypharmacy and prescriptions of potentially inappropriate medications. There are several ways to address polypharmacy to prevent its occurrence. We focused on computerized decision support tools. OBJECTIVE: The available literature was reviewed to understand whether computerized decision support tools reduce potentially inappropriate prescriptions or potentially inappropriate medications in older adult patients and affect health outcomes. METHODS: Our systematic review was conducted by searching the literature in the MEDLINE, CENTRAL, EMBASE, and Web of Science databases for interventional studies published through February 2018 to assess the impact of computerized decision support tools on potentially inappropriate medications and potentially inappropriate prescriptions in people aged 65 years and older. RESULTS: A total of 3756 articles were identified, and 16 were included. More than half (n=10) of the studies were randomized controlled trials, one was a crossover study, and five were pre-post intervention studies. A total of 266,562 participants were included; of those, 233,144 participants were included and assessed in randomized controlled trials. Intervention designs had several different features. Computerized decision support tools consistently reduced the number of potentially inappropriate prescriptions started and mean number of potentially inappropriate prescriptions per patient. Computerized decision support tools also increased potentially inappropriate prescriptions discontinuation and drug appropriateness. However, in several studies, statistical significance was not achieved. A meta-analysis was not possible due to the significant heterogeneity among the systems used and the definitions of outcomes. CONCLUSIONS: Computerized decision support tools may reduce potentially inappropriate prescriptions and potentially inappropriate medications. More randomized controlled trials assessing the impact of computerized decision support tools that could be used both in primary and secondary health care are needed to evaluate the use of medication targets defined by the Beers or STOPP (Screening Tool of Older People's Prescriptions) criteria, adverse drug reactions, quality of life measurements, patient satisfaction, and professional satisfaction with a reasonable follow-up, which could clarify the clinical usefulness of these tools. TRIAL REGISTRATION: International Prospective Register of Systematic Reviews (PROSPERO) CRD42017067021; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42017067021.

The effect of computerized decision support systems on cardiovascular risk factors: a systematic review and meta-analysis.

BACKGROUND: Cardiovascular risk management (CVRM) is notoriously difficult because of multi-morbidity and the different phenotypes and severities of cardiovascular disease. Computerized decision support systems (CDSS) enable the clinician to integrate the latest scientific evidence and patient information into tailored strategies. The effect on cardiovascular risk factor management is yet to be confirmed. METHODS: We performed a systematic review and meta-analysis evaluating the effects of CDSS on CVRM, defined as the change in absolute values and attainment of treatment goals of systolic blood pressure (SBP), low density lipoprotein cholesterol (LDL-c) and HbA1c. Also, CDSS characteristics related to more effective CVRM were identified. Eligible articles were methodologically appraised using the Cochrane risk of bias tool. We calculated mean differences, relative risks, and if appropriate (I2 < 70%), pooled the results using a random-effects model. RESULTS: Of the 14,335 studies identified, 22 were included. Four studies reported on SBP, 3 on LDL-c, 10 on CVRM in patients with type II diabetes and 5 on guideline adherence. The CDSSs varied considerably in technical performance and content. Heterogeneity of results was such that quantitative pooling was often not appropriate. Among CVRM patients, the results tended towards a beneficial effect of CDSS, but only LDL-c target attainment in diabetes patients reached statistical significance. Prompting, integration into the electronical health record, patient empowerment, and medication support were related to more effective CVRM. CONCLUSION: We did not find a clear clinical benefit from CDSS in cardiovascular risk factor levels and target attainment. Some features of CDSS seem more promising than others. However, the variability in CDSS characteristics and heterogeneity of the results - emphasizing the immaturity of this research area - limit stronger conclusions. Clinical relevance of CDSS in CVRM might additionally be sought in the improvement of shared decision making and patient empowerment.

What do healthcare professionals need to turn risk models for type 2 diabetes into usable computerized clinical decision support systems? Lessons learned from the MOSAIC project.

BACKGROUND: To understand user needs, system requirements and organizational conditions towards successful design and adoption of Clinical Decision Support Systems for Type 2 Diabetes (T2D) care built on top of computerized risk models. METHODS: The holistic and evidence-based CEHRES Roadmap, used to create eHealth solutions through participatory development approach, persuasive design techniques and business modelling, was adopted in the MOSAIC project to define the sequence of multidisciplinary methods organized in three phases, user needs, implementation and evaluation. The research was qualitative, the total number of participants was ninety, about five-seventeen involved in each round of experiment. RESULTS: Prediction models for the onset of T2D are built on clinical studies, while for T2D care are derived from healthcare registries. Accordingly, two set of DSSs were defined: the first, T2D Screening, introduces a novel routine; in the second case, T2D Care, DSSs can support managers at population level, and daily practitioners at individual level. In the user needs phase, T2D Screening and solution T2D Care at population level share similar priorities, as both deal with risk-stratification. End-users of T2D Screening and solution T2D Care at individual level prioritize easiness of use and satisfaction, while managers prefer the tools to be available every time and everywhere. In the implementation phase, three Use Cases were defined for T2D Screening, adapting the tool to different settings and granularity of information. Two Use Cases were defined around solutions T2D Care at population and T2D Care at individual, to be used in primary or secondary care. Suitable filtering options were equipped with "attractive" visual analytics to focus the attention of end-users on specific parameters and events. In the evaluation phase, good levels of user experience versus bad level of usability suggest that end-users of T2D Screening perceived the potential, but they are worried about complexity. Usability and user experience were above acceptable thresholds for T2D Care at population and T2D Care at individual. CONCLUSIONS: By using a holistic approach, we have been able to understand user needs, behaviours and interactions and give new insights in the definition of effective Decision Support Systems to deal with the complexity of T2D care.

The effect of ICU-tailored drug-drug interaction alerts on medication prescribing and monitoring: protocol for a cluster randomized stepped-wedge trial.

BACKGROUND: Drug-drug interactions (DDIs) can cause patient harm. Between 46 and 90% of patients admitted to the Intensive Care Unit (ICU) are exposed to potential DDIs (pDDIs). This rate is twice as high as patients on general wards. Clinical decision support systems (CDSSs) have shown their potential to prevent pDDIs. However, the literature shows that there is considerable room for improvement of CDSSs, in particular by increasing the clinical relevance of the pDDI alerts they generate and thereby reducing alert fatigue. However, consensus on which pDDIs are clinically relevant in the ICU setting is lacking. The primary aim of this study is to evaluate the effect of alerts based on only clinically relevant interactions for the ICU setting on the prevention of pDDIs among Dutch ICUs. METHODS: To define the clinically relevant pDDIs, we will follow a rigorous two-step Delphi procedure in which a national expert panel will assess which pDDIs are perceived clinically relevant for the Dutch ICU setting. The intervention is the CDSS that generates alerts based on the clinically relevant pDDIs. The intervention will be evaluated in a stepped-wedge trial. A total of 12 Dutch adult ICUs using the same patient data management system, in which the CDSS will operate, were invited to participate in the trial. Of the 12 ICUs, 9 agreed to participate and will be enrolled in the trial. Our primary outcome measure is the incidence of clinically relevant pDDIs per 1000 medication administrations. DISCUSSION: This study will identify pDDIs relevant for the ICU setting. It will also enhance our understanding of the effectiveness of alerts confined to clinically relevant pDDIs. Both of these contributions can facilitate the successful implementation of CDSSs in the ICU and in other domains as well. TRIAL REGISTRATION: Nederlands Trial register Identifier: NL6762 . Registered November 26, 2018.

Computer-Aided Diagnosis System for Detection of Stomach Cancer with Image Processing Techniques.

Stomach cancer is a type of cancer that is hard to detect at an early stage because it gives almost no symptoms at the beginning. Stomach cancer is an increasing incidence of cancer both in the World as well as in Turkey. The most common method used worldwide for gastric cancer diagnosis is endoscopy. However, definitive diagnosis is made with endoscopic biopsy results. Diagnosis with endoscopy is a very specific and sensitive method. With high-resolution endoscopy it is possible to detect mild discolorations, bulges and structural changes of the surface of the mucosa. However, because the procedures are performed with the eye of a doctor, it is possible that the cancerous areas may be missed and / or incompletely detected. Because of the fact that the cancerous area cannot be completely detected may cause the problem of cancer recurrence after a certain period of surgical intervention. In order to overcome this problem, a computerized decision support system (CDS) has been implemented with the help of specialist physicians and image processing techniques. The performed CDS system works as an assistant to doctors of gastroenterology, helping to identify the cancerous area in the endoscopic images of the scaffold, to take biopsies from these areas and to make a better diagnosis. We believe that gastric cancer will be helpful in determining the area and biopsy samples taken from the patient will be useful in determining the area. It is therefore considered a useful model.

Registered nurses' use of computerised decision support in medication reviews.

Purpose The purpose of this paper is to explore the implications of registered nurses' (RNs) use of a computerized decision support system (CDSS) in medication reviews. Design/methodology/approach The paper employs a quasi-experimental, one-group pre-test/post-test design with three- and six-month follow-ups subsequent to the introduction of a CDSS. In total, 11 RNs initiated and prepared a total of 54 medication reviews. The outcome measures were the number of drug-related problems (DRPs) as reported by the CDSS and the RNs, respectively, the RNs' views on the CDSS, and changes in the quality of drug treatment. Findings The CDSS significantly indicated more DRPs than the RNs did, such as potential adverse drug reactions (ADRs). The RNs detected additional problems, outside the scope of the CDSS, such as lack of adherence. They considered the CDSS beneficial and wanted to continue using it. Only minor changes were found in the quality of drug treatments, with no significant changes in the drug-specific quality indicators (e.g. inappropriate drugs). However, the use of renally excreted drugs in reduced renal function decreased. Practical implications The RNs' use of a CDSS in medication reviews is of value in detecting potential ADRs and interactions. Yet, in order to have an impact on outcomes in the quality of drug treatment, further measures are needed. These may involve development of inter-professional collaboration, such as established procedures for the implementation of medication reviews, including the use of CDSS. Originality/value This is, to the best of the authors' knowledge, the first study to explore the implications of medication reviews, initiated and prepared by RNs who use a CDSS. The paper adds further insight into the RNs' role in relation to quality of drug treatments.

Community-acquired pneumonia management and outcomes in the era of health information technology.

Pneumonia continues to be a leading cause of hospitalization and mortality. Implementation of health information technology (HIT) can lead to cost savings and improved care. In this review, we examine the literature on the use of HIT in the management of community-acquired pneumonia. We also discuss barriers to adoption of technology in managing pneumonia, the reliability and quality of electronic health data in pneumonia research, how technology has assisted pneumonia diagnosis and outcomes research. The goal of using HIT is to develop and deploy generalizable, real-time, computerized clinical decision support integrated into usual pneumonia care. A friendly user interface that does not disrupt efficiency and demonstrates improved clinical outcomes should result in widespread adoption.

A tailored online safety and health intervention for women experiencing intimate partner violence: the iCAN Plan 4 Safety randomized controlled trial protocol.

BACKGROUND: Intimate partner violence (IPV) threatens the safety and health of women worldwide. Safety planning is a widely recommended, evidence-based intervention for women experiencing IPV, yet fewer than 1 in 5 Canadian women access safety planning through domestic violence services. Rural, Indigenous, racialized, and immigrant women, those who prioritize their privacy, and/or women who have partners other than men, face unique safety risks and access barriers. Online IPV interventions tailored to the unique features of women's lives, and to maximize choice and control, have potential to reduce access barriers, and improve fit and inclusiveness, maximizing effectiveness of these interventions for diverse groups. METHODS/DESIGN: In this double blind randomized controlled trial, 450 Canadian women who have experienced IPV in the previous 6 months will be randomized to either a tailored, interactive online safety and health intervention (iCAN Plan 4 Safety) or general online safety information (usual care). iCAN engages women in activities designed to increase their awareness of safety risks, reflect on their plans for their relationships and priorities, and create a personalize action plan of strategies and resources for addressing their safety and health concerns. Self-reported outcome measures will be collected at baseline and 3, 6, and 12 months post-baseline. Primary outcomes are depressive symptoms (Center for Epidemiological Studies Depression Scale, Revised) and PTSD Symptoms (PTSD Checklist, Civilian Version). Secondary outcomes include helpful safety actions, safety planning self-efficacy, mastery, and decisional conflict. In-depth qualitative interviews with approximately 60 women who have completed the trial and website utilization data will be used to explore women's engagement with the intervention and processes of change. DISCUSSION: This trial will contribute timely evidence about the effectiveness of online safety and health interventions appropriate for diverse life contexts. If effective, iCAN could be readily adopted by health and social services and/or accessed by women to work through options independently. This study will produce contextualized knowledge about how women engage with the intervention; its strengths and weaknesses; whether specific groups benefit more than others; and the processes explaining any positive outcomes. Such information is critical for effective scale up of any complex intervention. TRIAL REGISTRATION: Clinicaltrials.gov ID NCT02258841 (Registered on Oct 2, 2014).

Clinical decision support systems differ in their ability to identify clinically relevant drug interactions of immunosuppressants in kidney transplant patients.

WHAT IS KNOWN AND OBJECTIVE: In kidney transplant patients, clinically relevant drug-drug interactions (DDIs) with immunosuppressants potentially lead to serious adverse drug events (ADEs). The aim of this study was (i) to show that five clinical decision support systems (CDSSs) differ in their ability to identify clinically relevant potential DDIs (pDDIs) of immunosuppressants in kidney transplant patients and (ii) to compare CDSSs in terms of their ability to identify clinically relevant pDDIs in this context. METHODS: All pDDIs being possible between nine immunosuppressants and 234 comedication drugs were identified for 264 intensive care unit (ICU) kidney transplant patients from 1999 to 2010. For pDDI identification, five CDSSs were used: DRUG-REAX® , ID PHARMA CHECK® , Lexi-Interact, mediQ and Meona. PDDIs from high severity categories were defined as clinically relevant. Classification of pDDIs as clinically relevant/non-clinically relevant by a clinical pharmacist using Stockley's Drug Interactions was employed as benchmark. We analysed inter-rater agreement, sensitivity, specificity, positive predictive value and negative predictive value. RESULTS AND DISCUSSION: Clinical decision support systems generated a total of 759 pDDI alerts. A total of 240 pDDI alerts were in high severity categories. A total of 391 different pDDIs were identified. Only 5% (n = 35) of different pDDIs were identified by all CDSSs. A total of 49 pDDIs were classified as clinically relevant by clinical pharmacists' rating using Stockley's Drug Interactions. Meona (0·72) has the highest inter-rater agreement with the benchmark for clinically relevant pDDIs. ID PHARMA CHECK® and mediQ show highest sensitivities (0·74, respectively). Meona has the highest specificity (0·99) and positive predictive value (0·89). WHAT IS NEW AND CONCLUSION: Five CDSSs differ in their ability to identify clinically relevant pDDIs of immunosuppressants in kidney transplant patients. Data may assist in selecting CDSSs for kidney transplant patients in the ICU. Using CDSSs to identify clinically relevant pDDIs could prevent ADEs and contribute to the overall goal of avoiding patient harm and increasing patient safety.

A Computer Prescribing Order Entry-Clinical Decision Support system designed for neonatal care: results of the 'preselected prescription' concept at the bedside.

WHAT IS KNOWN: The neonatal intensive care units (NICUs) are at the highest risk of drug dose error of all hospital wards. NICUs also have the most complicated prescription modalities. The computerization of the prescription process is currently recommended to decrease the risk of preventable adverse drug effects (pADEs) in NICUs. However, Computer Prescribing Order Entry-Clinical Decision Support (C.P.O.E./C.D.S.) systems have been poorly studied in NICUs, and their technical compatibility with neonatal specificities has been limited. OBJECTIVES: We set up a performance study of the preselected prescription of drugs for neonates, which limited the role of the prescriber to choosing the drugs and their indications. METHODS: A single 29 bed neonatal ward used this neonatal C.P.O.E./C.D.S. system for all prescriptions of all hospitalized newborns over an 18-month period. The preselected prescription of drugs was based on the indication, gestational age, body weight and post-natal age. The therapeutic protocols were provided by a formulary reference (330 drugs) that had been specifically designed for newborns. The preselected prescription also gave complete information about preparation and administration of drugs by nurses. The prescriber was allowed to modify the preselected prescription but alarms provided warning when the prescription was outside the recommended range. The main clinical characteristics and all items of each line of prescription were stored in a data warehouse, thus enabling this study to take place. RESULTS: Seven hundred and sixty successive newborns (from 24 to 42 weeks' gestation) were prescribed 52 392 lines of prescription corresponding to 65 drugs; About 30·4% of neonates had at least one out of licensed prescription; A prescription out of the recommended range for daily dose was recorded for 1·0% of all drug prescriptions. WHAT IS NEW?: The C.P.O.E./C.D.S. systems can currently provide a complete preselected prescription in NICUs according to dose rules, which are specific to newborns and also comply with local specificities (therapeutic protocols and formulation of drugs). The role of the prescriber is limited to the choice of drugs and their indications. The prescriber still retains the possibility of modifying each item of the prescription, with all other prescription items being calculated by the C.P.O.E. system. In these conditions, the prescribers rarely modified the preselected prescription and the rate of out of range prescription was low. A multicentric study is required to confirm and extend these observations. CONCLUSIONS: This study showed the feasibility of preselected prescription in NICUs and a low rate of out of range prescriptions. The preselected prescription could play a key role in lowering the dose error rate in NICUs.