Electronic Decision Support System Research Articles

Antimicrobial Stewardship Programs in Latin America and the Caribbean: A Story of Perseverance, Challenges, and Goals.

Antimicrobial resistance is one of the major global health threats. Antimicrobial stewardship (AMS) has been set as a priority within international action plans to combat this issue. The region of Latin America and the Caribbean are recognized for their high antimicrobial resistance rates; nevertheless, a low number of studies describing implemented interventions for this topic have been published. This review aims to provide an overview of the status of AMS in our region, focusing on the main progress achieved and describing the different published efforts made by countries towards the implementation of antimicrobial stewardship programs (ASP). Common areas of intervention included were (a) education approaches, (b) antimicrobial guideline implementation and monitoring, (c) diagnostic stewardship, (d) technological tools: electronic clinical decision support systems in AMS, (e) pharmacy-driven protocols and collaborative practice agreements, and (f) economic impact. The search demonstrated the varied interventions implemented in diverse healthcare settings; the results accentuate their influence on antimicrobial consumption, antimicrobial resistance, clinical outcomes, and direct economic impact. The integration of multiple strategies within each hospital was highlighted as an essential key to ASP success. Even though the literature found demonstrated clear progress, there is still a special need for strengthening leadership from the top down, defining goals based on needs, and gaining support through policy and financing in LAC.

Electronic Tendering and Organizational Performance of Parastatals in Nakuru County

E-tendering plays a key role in ensuring that the best suppliers are selected for a continuous supply of better-quality products and services. The study focused on the role of e-tendering through online registration of suppliers, virtual screening, automatic evaluation and automated supplier selection criteria- through the use of an electronic Decision Support System (e-DSS). The study adopted the null hypothesis that e- tendering had no statistically significant influence on parastatals in Nakuru County. The study population included five (5) selected state-owned organisations in Nakuru municipality with a total population of 236 employees in selected departments where a sample size of 91 employees was drawn by application of Daniel’s (1999) sample size formula. Structured questionnaires were used as the main instrument to collect data, out of which 80 respondents gave their responses, an 87.9% response rate. The regression analysis showed a 4.6% change in organisational performance was described by e-tendering. The study confirmed there was a statistical significance (p=.000) between e-tendering and organisation performance, where e-tendering, as a supplier management tool, was able to account for a positive marginal significant increase (B=.133) in organisational performance. There was a moderate positive correlation between organisational performance and e-tendering at .519. The study recommends that parastatals enhance system integration for compatibility and easy access and flow of information, leverage technology, and facilitate training and educating their suppliers on how to use the organisation’s systems and other ICT-related functions.

Clinical decision-making and the nursing process in digital health systems: An integrated systematic review.

To identify how the nursing process (assessment, planning, intervention and outcome evaluation) has been incorporated into digital health systems (electronic medical records, electronic care plans and clinical decision support systems) to gain an understanding of known benefits and challenges posed to nurses' decision-making processes. Nursing terminologies, including the International Classification for Nursing Practice (ICNP), and Nursing Minimum Data Set's (NMDS), have been developed to improve standardised language integration of components of nursing care into digital systems. However, there is limited evidence regarding whether the complete nursing process is effectively being incorporated into digital health systems. An integrative systematic review following PRISMA guidelines. A search strategy was applied to extract articles from included databases: CINAHL, MEDLINE, SCOPUS and Web of Science Core Collection. Articles were limited to English language and published January 2007-March 2022 and assessed using a pre-determined eligibility criteria. Quality assessment and a narrative synthesis were conducted. A total of 3321 articles were identified, and 27 studies included. There were (n = 10) qualitative, (n = 4) quantitative non-randomised controlled trials, (n = 3) quantitative descriptive studies and (n = 10) mixed methods. Nurse assessment and planning components were the most comprehensive phases incorporated into digital health systems, and interventions and outcome evaluation were scarcely reported. Inadequate capture of nursing work is a problem unresolved by digital health systems. This omission may be hindering nurse clinical decision-making for patient care and limiting the visibility of the nursing role in health care interventions and the associated impact on patient outcomes. Further research is needed on how digital systems can support nurses to apply the full nursing process and to further evaluate patient outcomes. Digital systems can support health-service level evaluation through capturing missed nursing care and the consequences on patients utilising nurse-sensitive-outcomes; however, this is not yet being realised.

Optimising prescribing in older adults with multimorbidity and polypharmacy in primary care (OPTICA): cluster randomised clinical trial

ObjectiveTo study the effects of a primary care medication review intervention centred around an electronic clinical decision support system (eCDSS) on appropriateness of medication and the number of prescribing omissions...

The systematic medical appraisal, referral and treatment (SMART) mental health programme: Formative research informing a cluster randomized controlled trial

BackgroundGaps exist between prevalence and treatment options for mental disorders in India. Limited awareness, poor help-seeking, scarcity of trained mental health professionals, limited mental health services and stigma are few examples of reasons contributing to treatment gap. AimsThis paper highlights findings from formative research of a primary mental healthcare model comprising of a preliminary feasibility testing of the Electronic Decision Support System (EDSS) to provide care using mobile based applications, perceptions of the community towards mental health and incorporating cultural adaptations for pre-existing anti-stigma campaign materials. MethodsA cross-sectional mixed methods approach tested the user acceptability of the electronic decision support system EDSS for accredited social health activists (ASHAs) and Primary Health Centre (PHC) doctors using tablets in two villages and two PHCs in rural Haryana (Northern India). Five focus groups and six in-depth interviews along with non-participant observations were used to ascertain community perceptions about various aspects related to mental health. Findings of the study were analyzed and interpreted against the key themes of Andersen's model. ResultsOut of a total of 553 individuals screened for common mental disorders, 51 (9.2%) were screened positive and 32 visited PHC doctors for treatment. There was limited knowledge about common mental disorders amongst community; need to train primary health workers to identify and treat mental disorders; and incorporate cultural adaptation of anti-stigma awareness materials. ConclusionsThe EDSS was found to be acceptable and feasible by primary and community health workers. The findings guided refining of the intervention prior to implementation of a large-scale cluster randomized controlled trial.

Ensuring Information Security of OLAP-Containing Distributed Electronic Systems using Blockchain Technology

The article outlines the properties of blockchain technology, according to which the content of blockchain blocks is immutable and the use of a peer-to-peer (P2P) network implies decentralized management. It describes the essence and meaning of smart-contracts and smart-views derived from them, which are involved in the process of data analysis and decision making. The article considers the papers devoted to various approaches to the problem of integration of blockchain technology and data storage. To ensure all three key aspects of information security — the integrity, availability and confidentiality of information, which is important for both government and corporate structures, the article proposes to use a private blockchain, instead of a public one. A modification of the model of an electronic decision support system containing an OLAP block, which includes a private blockchain, is developed. It is shown that this DSS model can be used as an electronic demographic DSS, which is an infrastructure for solving state problems in this area, since many of the characteristics of this model correspond to the multisectoral nature of demography.

Clinical decision support to Optimize Care of patients with Atrial Fibrillation or flutter in the Emergency department: protocol of a stepped-wedge cluster randomized pragmatic trial (O’CAFÉ trial)

BackgroundManagement of adults with atrial fibrillation (AF) or atrial flutter in the emergency department (ED) includes rate reduction, cardioversion, and stroke prevention. Different approaches to these components of care may lead to variation in frequency of hospitalization and stroke prevention actions, with significant implications for patient experience, cost of care, and risk of complications. Standardization using evidence-based recommendations could reduce variation in management, preventable hospitalizations, and stroke risk.MethodsWe describe the rationale for our ED-based AF treatment recommendations. We also describe the development of an electronic clinical decision support system (CDSS) to deliver these recommendations to emergency physicians at the point of care. We implemented the CDSS at three pilot sites to assess feasibility and solicit user feedback. We will evaluate the impact of the CDSS on hospitalization and stroke prevention actions using a stepped-wedge cluster randomized pragmatic clinical trial across 13 community EDs in Northern California.DiscussionWe hypothesize that the CDSS intervention will reduce hospitalization of adults with isolated AF or atrial flutter presenting to the ED and increase anticoagulation prescription in eligible patients at the time of ED discharge and within 30 days. If our hypotheses are confirmed, the treatment protocol and CDSS could be recommended to other EDs to improve management of adults with AF or atrial flutter.Trial registrationClinicalTrials.gov NCT05009225. Registered on 17 August 2021.

Enhancing Hepatitis A and B Vaccinations Through Electronic Clinical Decision Support Systems and Staff Education in a Correctional Facility.

Despite the prevalence and risks for hepatitis A virus (HAV) and hepatitis B virus (HBV) infection and the availability of safe and effective vaccines, HAV/HBV vaccinations are disproportionately low in jails. This quality improvement project evaluated the effectiveness of clinical decision support systems: electronic standing orders to nurses, clinical alerts to nurses and healthcare providers, and secondarily staff education in enhancing HAV and HBV vaccination and knowledge of hepatitis infection. We distributed a validated self-report hepatitis knowledge questionnaire (α = 0.7-0.8) before and after an educational presentation to nurses, nurse practitioners, and physicians ( N = 26) at a Northeastern state jail and then embedded electronic clinical alerts and standing orders in the electronic medical record. The questionnaire assessed pre- and posteducation knowledge scores. The number of vaccine status screenings and vaccinations was retrieved from the electronic medical record 3 months pre- and post-implementation. Descriptive statistics and the Wilcoxon signed-ranks test were used for data analysis. Twenty-one participants completed the pretest, 18 attended the educational intervention, and 15 completed the posttest. Vaccine status screening increased by 97.5%, and HAV and HBV vaccinations increased by 8.7%. Knowledge scores improved significantly post-intervention ( p = 0.04), with an effect size of r = 0.67). Using the Donabedian quality of care model, we showed that quality initiatives are feasible in a jail setting. Implementing a clinical decision support system and education improved the vaccination rate, which may decrease HAV/HBV incidence in the jail and prevent community spread.

Clinical decision support automates care gap detection among primary care patients with nonalcoholic fatty liver disease

Although guidelines recommend primary care-driven management of NAFLD, workflow constraints hinder feasibility. Leveraging electronic health records to risk stratify patients proposes a scalable, workflow-integrated strategy. We prospectively evaluated an electronic health record-embedded clinical decision support system's ability to risk stratify patients with NAFLD and detect gaps in care. Patients missing annual laboratory testing to calculate Fibrosis-4 Score (FIB-4) or those missing necessary linkage to further care were considered to have a gap in care. Linkage to care was defined as either referral for elastography-based testing or for consultation in hepatology clinic depending on clinical and biochemical characteristics. Patients with NAFLD often lacked annual screening labs within primary care settings (1129/2154; 52%). Linkage to care was low in all categories, with <3% of patients with abnormal FIB-4 undergoing further evaluation. Significant care gaps exist within primary care for screening and risk stratification of patients with NAFLD and can be efficiently addressed using electronic health record functionality.

Learning meaningful latent space representations for patient risk stratification: Model development and validation for dengue and other acute febrile illness.

Increased data availability has prompted the creation of clinical decision support systems. These systems utilise clinical information to enhance health care provision, both to predict the likelihood of specific clinical outcomes or evaluate the risk of further complications. However, their adoption remains low due to concerns regarding the quality of recommendations, and a lack of clarity on how results are best obtained and presented. We used autoencoders capable of reducing the dimensionality of complex datasets in order to produce a 2D representation denoted as latent space to support understanding of complex clinical data. In this output, meaningful representations of individual patient profiles are spatially mapped in an unsupervised manner according to their input clinical parameters. This technique was then applied to a large real-world clinical dataset of over 12,000 patients with an illness compatible with dengue infection in Ho Chi Minh City, Vietnam between 1999 and 2021. Dengue is a systemic viral disease which exerts significant health and economic burden worldwide, and up to 5% of hospitalised patients develop life-threatening complications. The latent space produced by the selected autoencoder aligns with established clinical characteristics exhibited by patients with dengue infection, as well as features of disease progression. Similar clinical phenotypes are represented close to each other in the latent space and clustered according to outcomes broadly described by the World Health Organisation dengue guidelines. Balancing distance metrics and density metrics produced results covering most of the latent space, and improved visualisation whilst preserving utility, with similar patients grouped closer together. In this case, this balance is achieved by using the sigmoid activation function and one hidden layer with three neurons, in addition to the latent dimension layer, which produces the output (Pearson, 0.840; Spearman, 0.830; Procrustes, 0.301; GMM 0.321). This study demonstrates that when adequately configured, autoencoders can produce two-dimensional representations of a complex dataset that conserve the distance relationship between points. The output visualisation groups patients with clinically relevant features closely together and inherently supports user interpretability. Work is underway to incorporate these findings into an electronic clinical decision support system to guide individual patient management.

A cluster randomized controlled trial of an electronic decision-support system to enhance antenatal care services in pregnancy at primary healthcare level in Telangana, India: trial protocol

BackgroundIndia contributes 15% of the total global maternal mortality burden. An increasing proportion of these deaths are due to Pregnancy Induced Hypertension (PIH), Gestational Diabetes Mellitus (GDM), and anaemia. This study aims to evaluate the effectiveness of a tablet-based electronic decision-support system (EDSS) to enhance routine antenatal care (ANC) and improve the screening and management of PIH, GDM, and anaemia in pregnancy in primary healthcare facilities of Telangana, India. The EDSS will work at two levels of primary health facilities and is customized for three cadres of healthcare providers – Auxiliary Nurse Midwifes (ANMs), staff nurses, and physicians (Medical Officers).MethodsThis will be a cluster randomized controlled trial involving 66 clusters with a total of 1320 women in both the intervention and control arms. Each cluster will include three health facilities—one Primary Health Centre (PHC) and two linked sub-centers (SC). In the facilities under the intervention arm, ANMs, staff nurses, and Medical Officers will use the EDSS while providing ANC for all pregnant women. Facilities in the control arm will continue to provide ANC services using the existing standard of care in Telangana. The primary outcome is ANC quality, measured as provision of a composite of four selected ANC components (measurement of blood pressure, blood glucose, hemoglobin levels, and conducting a urinary dipstick test) by the healthcare providers per visit, observed over two visits. Trained field research staff will collect outcome data via an observation checklist.DiscussionTo our knowledge, this is the first trial in India to evaluate an EDSS, targeted to enhance the quality of ANC and improve the screening and management of PIH, GDM, and anaemia, for multiple levels of health facilities and several cadres of healthcare providers. If effective, insights from the trial on the feasibility and cost of implementing the EDSS can inform potential national scale-up. Lessons learned from this trial will also inform recommendations for designing and upscaling similar mHealth interventions in other low and middle-income countries.Trial Registration.ClinicalTrials.gov, NCT03700034, registered 9 Oct 2018, https://www.clinicaltrials.gov/ct2/show/NCT03700034CTRI, CTRI/2019/01/016857, registered on 3 Mar 2019, http://www.ctri.nic.in/Clinicaltrials/pdf_generate.php?trialid=28627&EncHid=&modid=&compid=%27,%2728627det%27

Challenges of using e-health technologies to support clinical care in rural Africa: a longitudinal mixed methods study exploring primary health care nurses’ experiences of using an electronic clinical decision support system (CDSS) in South Africa

BackgroundElectronic decision-making support systems (CDSSs) can support clinicians to make evidence-based, rational clinical decisions about patient management and have been effectively implemented in high-income settings. Integrated Management of Childhood Illness (IMCI) uses clinical algorithms to provide guidelines for management of sick children in primary health care clinics and is widely implemented in low income countries. A CDSS based on IMCI (eIMCI) was developed in South Africa.MethodsWe undertook a mixed methods study to prospectively explore experiences of implementation from the perspective of newly-trained eIMCI practitioners. eIMCI uptake was monitored throughout implementation. In-depth interviews (IDIs) were conducted with selected participants before and after training, after mentoring, and after 6 months implementation. Participants were then invited to participate in focus group discussions (FGDs) to provide further insights into barriers to eIMCI implementation.ResultsWe conducted 36 IDIs with 9 participants between October 2020 and May 2021, and three FGDs with 11 participants in October 2021. Most participants spoke positively about eIMCI reporting that it was well received in the clinics, was simple to use, and improved the quality of clinical assessments. However, uptake of eIMCI across participating clinics was poor. Challenges reported included lack of computer skills which made simple tasks, like logging in or entering patient details, time consuming. Technical support was provided, but was time consuming to access so that eIMCI was sometimes unavailable. Other challenges included heavy workloads, and the perception that eIMCI took longer and disrupted participant’s work. Poor alignment between recording requirements of eIMCI and other clinic programmes increased participant’s administrative workload. All these factors were a disincentive to eIMCI uptake, frequently leading participants to revert to paper IMCI which was quicker and where they felt more confident.ConclusionDespite the potential of CDSSs to increase adherence to guidelines and improve clinical management and prescribing practices in resource constrained settings where clinical support is scarce, they have not been widely implemented. Careful attention should be paid to the work environment, work flow and skills of health workers prior to implementation, and ongoing health system support is required if health workers are to adopt these approaches (350).

Can Electronic Clinical Decision Support Systems Improve the Diagnosis of Urinary Tract Infections? A Systematic Review and Meta-Analysis.

Urinary tract infection (UTI) is a commonly misdiagnosed infectious syndrome. Diagnostic stewardship interventions can reduce rates of asymptomatic bacteriuria treatment but are often labor intensive, and thus an automated means of reducing unnecessary urine testing is preferred. In this systematic review and meta-analysis, we sought to identify studies describing interventions utilizing clinical decision support (CDS) to optimize UTI diagnosis and to characterize the effectiveness of these interventions. We conducted a comprehensive electronic search and manual reference list review for peer-reviewed articles published before July 2, 2021. Publications describing an intervention intending to enhance UTI diagnosis via CDS were included. The primary outcome was urine culture test rate. The electronic search identified 5013 studies for screening. After screening and full-text review, 9 studies met criteria for inclusion, and a manual reference list review identified 5 additional studies, yielding a total of 14 studies included in the systematic review. The most common CDS intervention was urinalysis with reflex to urine culture based on prespecified urinalysis parameters. All 9 studies that provided statistical comparisons reported a decreased urine culture rate postintervention, 8 of which were statistically significant. A meta-analysis including 4 studies identified a pooled urine culture incidence rate ratio of 0.56 (95% confidence interval, .52-.60) favoring the postintervention versus preintervention group. In this systematic review and meta-analysis, CDS appeared to be effective in decreasing urine culture rates. Prospective trials are needed to confirm these findings and to evaluate their impact on antimicrobial prescribing, patient-relevant outcomes, and potential adverse effects.

790. Can Electronic Clinical Decision Support Systems Improve the Diagnosis of Urinary Tract Infections?: A Systematic Review and Meta-Analysis

Abstract Background Urinary tract infection (UTI) is a commonly misdiagnosed infectious condition. Stewardship interventions which successfully reduce rates of asymptomatic bacteriuria treatment (ASB) are often labor intensive, and thus a systematic solution is desirable. In this study, our objective was to systematically review studies to evaluate the effect of implementing a clinical decision support system on the ordering of urine culture tests for the diagnosis of UTI across diverse clinical settings. Methods We conducted a comprehensive electronic search of 5 databases and manual reference list review for peer-reviewed articles published prior to July 2, 2021. Studies which described an intervention designed to reduce unnecessary or incorrect diagnosis of UTI through utilization of CDS were included. The primary outcome of interest was rate of urine culture tests ordered. Two investigators independently screened studies and extracted and compiled data. Results A total of 5,013 studies were screened, of which 14 met inclusion criteria for the systematic review (Table 1). The most common intervention was urinalysis with reflex to urine culture based on pre-specified urinalysis parameters, such as a threshold level of pyuria. All 9 studies with statistical comparisons reported a decreased urine culture rate post-intervention, 8 of which were statistically significant (Table 2). Overall, a 37% decrease in urine culture rate was detected after CDS implementation (Table 3). Several studies also reported improvements in antimicrobial-related measures such as days of therapy and guideline-concordant therapy. Catheter-associated urinary tract infection rate was decreased in 2 studies and unchanged in 1 study. A limited number of included studies reported no adverse outcomes including increased bloodstream infection and mortality rates. Conclusion Electronic clinical decision support systems appear to be effective in decreasing unnecessary urine culture tests and improving UTI diagnosis. Prospective studies are needed to evaluate the impact on antimicrobial prescribing, patient-relevant outcomes, and potential adverse effects. Disclosures Elie Saade, MD, MPH, Janssen: Advisor/Consultant Curtis Donskey, MD, Pfizer, Clorox, Ecolab, and Professional Disposables International: Grant/Research Support Abhishek Deshpande, MD, PhD, Clorox: Grant/Research Support|Merck &amp; Co., Inc., Kenilworth, NJ, USA: Advisor/Consultant|Merck &amp; Co., Inc., Kenilworth, NJ, USA: Stocks/Bonds|Seres Therapeutics: Grant/Research Support.

An intervention to reduce stigma and improve management of depression, risk of suicide/self-harm and other significant emotional or medically unexplained complaints among adolescents living in urban slums: protocol for the ARTEMIS project

BackgroundThere are around 250 million adolescents in India. Adolescents are vulnerable to common mental disorders with depression and self-harm accounting for a major share of the burden of death and disability in this age group. Around 20% of children and adolescents are diagnosed with/ or live with a disabling mental illness. A national survey has found that suicide is the third leading cause of death among adolescents in India. The authors hypothesise that an intervention involving an anti-stigma campaign co-created by adolescents themselves, and a mobile technology-based electronic decision support system will help reduce stigma, depression, and suicide risk and improve mental health for high-risk adolescents living in urban slums in India.MethodsThe intervention will be implemented as a cluster randomised control trial in 30 slum clusters in each of the cities of Vijayawada and New Delhi in India. Adolescents aged 10 to 19 years will be screened for depression and suicide ideation using the Patient Health Questionnaire (PHQ-9). Two evaluation cohorts will be derived—a high-risk cohort with an elevated PHQ-9 score ≥ 10 and/or a positive response (score ≥ 2) to the suicide risk question on the PHQ-9, and a non-high-risk cohort comprising an equal number of adolescents not at elevated risk based on these scores.DiscussionThe key elements that ARTEMIS will focus on are increasing awareness among adolescents and the slum community on these mental health conditions as well as strengthening the skills of existing primary healthcare workers and promoting task sharing. The findings from this study will provide evidence to governments about strategies with potential for addressing the gaps in providing care for adolescents living in urban slums and experiencing depression, other significant emotional or medically unexplained complaints or increased suicide risk/self-harm and should have relevance not only for India but also for other low- and middle-income countries.Trial statusProtocol version – V7, 20 Dec 2021Recruitment start date: tentatively after 15th July 2022Recruitment end date: tentatively 14th July 2023 (1 year after the trial start date)Trial registrationThe trial has been registered in the Clinical Trial Registry India, which is included in the WHO list of Registries (https://www.who.int/clinical-trials-registry-platform/network/primary-registries) Reference No. CTRI/2022/02/040307. Registered on 18 February 2022.The tentative start date of participant recruitment for the trial will begin after 15th July 2022.

Effectiveness of an electronic clinical decision support system in improving the management of childhood illness in primary care in rural Nigeria: an observational study

ObjectivesTo evaluate the impact of ALgorithm for the MANAgement of CHildhood illness (‘ALMANACH’), a digital clinical decision support system (CDSS) based on the Integrated Management of Childhood Illness, on health...

How much do we need electronic clinical decision support systems to select patients to perform HIV tests in clinical settings?

Infectious Diseases Unit, San Camillo De Lellis Hospital, Rieti/National Institute for Infectious Diseases ‘Lazzaro Spallanzani’, Rome, Italy. Correspondence to Dr Mauro Zaccarelli, Infectious Diseases Unit, San Camillo de Lellis Hospital, Viale J.F. Kennedy, Rieti 02100, Italy. E-mail: [email protected] Received 17 March, 2022 Revised 8 April, 2022 Accepted 8 April, 2022

Development, validation and evaluation of the Goal-directed Medication review Electronic Decision Support System (G-MEDSS)©.

1) To understand and investigate the experiences of accredited clinical pharmacists (ACP) using computerised clinical decision support systems (CCDSS) during medication reviews for older people, including those living with dementia; 2) To design, develop, validate, and evaluate a CCDSS that incorporates pharmacological and other deprescribing tools to aid person-centred management of high-risk medications in older adults living with and without dementia. This study consisted of three phases and was designed on scenario-based methodology: a) the development phase, which included an exploratory survey and prototype building; b) the validation phase, which included qualitative data collection and usability testing with ACPs, general practitioners (GPs) and carers for people living with dementia; and c) the evaluation phase, using mixed-methods analyses. The exploratory survey found that ACPs required a flexible, and reliable CCDSS to support them with clinical decisions regarding high-risk medication use in older adults. The Goal-directed Medication review Electronic Decision Support System (G-MEDSS)© was developed and validated using quantitative and qualitative feedback received from ACPs, GPs and carers for people with dementia. The mean (SD) System Usability Scale score was 69.0 (12.9), which indicated fair-good usability. Involving end-users in the design process refined and improved the design of G-MEDSS, allowing for a person-centred and goal-directed delivery of pharmaceutical care. G-MEDSS allows healthcare practitioners conducting medication reviews for older adults living with and without dementia to tailor pharmaceutical care to meet their goals and preferences. Future studies may explore integration of G-MEDSS with prescribing or dispensing software.

Electronic medical decision support system in achieving sustainable development goal health targets on non-communicable diseases

The epidemic of non-communicable diseases poses devastating consequences on health and Sustainable Development Goal 3 of the 2030 Agenda focuses on reducing mortality from non-communicable diseases. The current study evaluated the impact of Electronic Medical decision Support Systems in the management of non-communicable diseases like diabetes, hypertension. Fifteen studies were included in total in the qualitative analysis. While reviewing the usefulness of Electronic Medical decision Support Systems in the management of non-communicable diseases, both beneficial and less beneficial outcomes were explored. This necessitates a lot more improvisation and standardisation for effective implementation which is highly potential to revolutionize health outcomes.

682-P: Feasibility of CGM Use in Basal-Bolus Insulin Therapy with an Electronic Decision Support System in Hospitalized Patients

Continuous glucose monitoring (CGM) provides a more holistic picture of glycemic control than capillary blood glucose (BG) measurements. We simulated CGM use with a clinical decision support system (cDSS) with a basal-bolus insulin algorithm using CGM values recorded at the same time (CGM0) vs. 15 minutes after the BG measurement (CGM+15) to simulate typical CGM trend information. Data of 30 inpatients with T2D (age: 74.1±10.9 years, female: 60 %, Caucasian: 100 %, BMI: 28.6±5.6 kg/m2, diabetes duration: 13.2±11.6 years, HbA1c: 72±22 mmol/mol, stay duration: 8.2±3.7 days) were used. Simulation results were analysed for insulin doses, overall glycemic control, and potentially avoidable hypoglycemic events (PAHE) : those occurring within 3 hours of a bolus insulin injection when the suggested dose based on CGM was lower. Glucose levels and insulin doses were lower when using CGM. Glucose differences were mainly due to nocturnal hypoglycemia undetected by BG (Table 1) . 36 PAHEs occurred in 17 patients with CGM0 vs. 38 PAHEs in patients with CGM+15. In the simulation, lower CGM readings and undetected nocturnal hypoglycemia resulted in lower insulin doses (single and total daily doses) . Consequently, there were hypoglycemic events that could have been avoided had CGM been used. Combining cDSS and CGM is feasible and can facilitate glycemic control whilst avoiding hypoglycemia. Disclosure K.Bytyqi: None. P.M.Baumann: None. D.A.Hochfellner: None. T.Poettler: None. A.Simic: None. P.Beck: Employee; decide Clinical Software GmbH, Stock/Shareholder; decide Clinical Software GmbH. J.K.Mader: Advisory Panel; Abbott Diabetes, Boehringer Ingelheim International GmbH, Eli Lilly and Company, Medtronic, Merck Sharp &amp; Dohme Corp., Novo Nordisk A/S, Roche Diabetes Care, Sanofi-Aventis Deutschland GmbH, Speaker’s Bureau; Abbott Diabetes, Eli Lilly and Company, Medtronic, Merck Sharp &amp; Dohme Corp., Novo Nordisk A/S, Roche Diabetes Care, Sanofi-Aventis Deutschland GmbH, Servier Laboratories, Stock/Shareholder; decide Clinical Software GmbH.