Electronic Medical Record Integration Research Articles

A Multi-step Integrative Workflow Implementation to Improve Documentation of Point of Care Ultrasound in Medical Intensive Care Unit.

Point of care ultrasound (POCUS) provides quick bedside assessment for diagnosing and managing life-threatening conditions in critical care medicine. There has been increasing interest in developing infrastructure to archive images, record clinical interpretation, assess quality, and recoup revenue for POCUS. We present a simple workflow by systems integration of electronic medical record, ultrasound machines, picture archiving, and communication system to facilitate POCUS documentation and billing. We recorded a trend on the number of POCUS performed before and after introduction of the structured integration. We observed and recorded a linear increase over time post-intervention. Our innovative and integrated POCUS workflow is an effective way to document and bill POCUS.

Reporting of asthma mobile health data for clinical practice: a qualitative study of pediatric provider perspectives

Objective Mobile health (mHealth), defined as the use of mobile phones or applications in healthcare, has been developed to enhance asthma care; yet implementation is inconsistent, and few studies have focused on provider perspectives on use in daily practice. The purpose of this study was to explore primary care pediatric provider perspectives regarding mHealth use in clinical practice for children with asthma. Methods A qualitative, descriptive approach was utilized to perform semi-structured interviews on asthma mHealth use with providers caring for children with asthma. Interview transcripts were coded by two independent investigators and any differences were reconciled. Interviews continued until thematic saturation was achieved. Results and Conclusions Seventeen pediatric providers were recruited and interviewed. Three themes identified included implementation benefits, implementation barriers, and reporting desires, with 11 subthemes. Many subthemes were consistent across providers (e.g. self-management benefits and electronic medical record integration), while others such as provider clinical burden and approach to integrating mHealth data reports into daily workflow demonstrated variability. Provider perspectives highlight the potential of mHealth applications in asthma self-management while offering challenges related to clinical burden and suggestions for reporting and workflow integration. These results provide valuable perspectives on mHealth use and reporting to ensure provider efficiency and technology-enhanced asthma care. This study investigates pediatric provider perspectives on asthma mobile health use and reporting in daily practice, a topic that has not sufficiently been explored within the literature. Results can guide best practices, encourage more consistent use, and maximize the benefits of asthma mHealth tools by providers.

A simple electronic medical record-based predictors of illness severity in sepsis (sepsis) score.

Current scores for predicting sepsis outcomes are limited by generalizability, complexity, and electronic medical record (EMR) integration. Here, we validate a simple EMR-based score for sepsis outcomes in a large multi-centre cohort. A simple electronic medical record-based predictor of illness severity in sepsis (SEPSIS) score was developed (4 additive lab-based predictors) using a population-based retrospective cohort study. Internal medicine services across four academic teaching hospitals in Toronto, Canada from April 2010-March 2015 (primary cohort) and 2015-2019 (secondary cohort). We identified patients admitted with sepsis based upon receipt of antibiotics and positive cultures. The primary outcome was in-hospital mortality and secondary outcomes were ICU admission at 72 hours, and hospital length of stay (LOS). We calculated the area under the receiver operating curve (AUROC) for the SEPSIS score, qSOFA, and NEWS2. We then evaluated the SEPSIS score in a secondary cohort (2015-2019) of hospitalized patients receiving antibiotics. Our primary cohort included 1,890 patients with a median age of 72 years (IQR: 56-83). 9% died during hospitalization, 18.6% were admitted to ICU, and mean LOS was 12.7 days (SD: 21.5). In the primary and secondary (2015-2019, 4811 patients) cohorts, the AUROCs of the SEPSIS score for predicting in-hospital mortality were 0.63 and 0.64 respectively, which were similar to NEWS2 (0.62 and 0.67) and qSOFA (0.62 and 0.68). AUROCs for predicting ICU admission at 72 hours, and length of stay > 14 days, were similar between scores, in the primary and secondary cohorts. All scores had comparable calibration for predicting mortality. An EMR-based SEPSIS score shows a similar ability to predict important clinical outcomes compared with other validated scores (qSOFA and NEWS2). Because of the SEPSIS score's simplicity, it may prove a useful tool for clinical and research applications.

The Effect of an Oxytocin Decision Support Checklist on Oxytocin Use and Maternal and Neonatal Outcomes: A Retrospective Cohort Study.

To assess the association between use of an oxytocin decision support checklist with oxytocin usage and clinical outcomes. We conducted a retrospective cohort study of patients with singleton gestations at 370/7 weeks or greater who received oxytocin during labor from October 2012 to February 2017 at an integrated community health care system during three exposure periods: (1) pre-checklist; (2) after paper checklist implementation; and (3) after checklist integration into the electronic medical record (EMR). The checklist was a clinical decision support tool to standardize the dosing and management of oxytocin. Thus, our primary outcomes included oxytocin infusion rates and cumulative dose. Secondary outcomes included maternal and neonatal outcomes. We controlled for maternal risk factors with multivariable regression analysis and stratified by mode of delivery. A total of 34,269 deliveries were included. Unadjusted analyses showed that compared with pre-checklist, deliveries during the paper and EMR-integrated periods had a lower cumulative dose (4,670 ± 6,174 vs. 4,318 ± 5,719 and 4,286 ± 5,579 mU, p < 0.001 for both), lower maximal infusion rate (9.9 ± 6.8 vs. 8.7 ± 5.8 and 8.4 ± 5.6 mU/min, p < 0.001 for both), and longer duration of oxytocin use (576 ± 442 vs. 609 ± 476 and 627 ± 488 minutes, p < 0.001 and p = 0.01, respectively). The unadjusted rates of cesarean, 5-minute Apgar <7, mechanical ventilation, and neonatal hospital length of stay were similar between periods. The adjusted mean difference in time from admission to delivery was longer during the EMR-integrated period compared with pre-checklist (3.0 [95% confidence interval: 2.7-3.3] hours, p < 0.001). Oxytocin checklist use was associated with decreased oxytocin use patterns at the expense of longer labor times. Findings were more pronounced with EMR integration. · An oxytocin decision support checklist is associated with reduced amounts of oxytocin used.. · However, checklists were associated with longer duration of oxytocin use and of labor.. · Results were more pronounced in the EMR-integrated checklist compared with paper checklist..

Integrated Digital Mental Health Care: A Vision for Addressing Population Mental Health Needs.

The unmet need for mental health care continues to rise across the world. This article synthesizes the evidence supporting the components of a hypothetical model of integrated digital mental health care to meet population-wide mental health needs. This proposed model integrates two approaches to broadening timely access to effective care: integrated, primary care-based mental health services and digital mental health tools. The model solves for several of the key challenges historically faced by digital health, through promoting digital literacy and access, the curation of evidence-based digital tools, integration into clinical practice, and electronic medical record integration. This model builds upon momentum toward the integration of mental health services within primary care and aligns with the principles of the Collaborative Care Model. Finally, the authors present the major next steps toward implementation of integrated digital mental health care at scale.

Comprehensive adolescent healthcare transition program for congenital adrenal hyperplasia: A quality improvement initiative

Background and significanceCongenital adrenal hyperplasia (CAH) is a genetic condition impairing adrenal steroid production, requiring lifelong steroid replacement, leading to decreased quality of life and a shortened lifespan. Preparing and supporting adolescents with CAH to develop health-related knowledge, skills, and decision-making during the pediatric-to-adult healthcare transition (HCT) is a priority. Many adolescents with CAH do not receive adequate HCT and do not attend follow-up care after transfer to an adult setting. The Comprehensive Adolescent Healthcare Transition (CAH-T) program was developed using CAH care guidelines and the Got Transition Six Core Elements of Healthcare Transition approach. PurposeThis quality improvement (QI) initiative aimed to evaluate clinicians’ utilization and acceptance of the CAH-T program for addressing the HCT needs of adolescents with CAH in a southeastern United States pediatric endocrine clinic. InterventionBaseline demographics, the Health Care Transition Feedback Survey for Clinicians, and the Current Assessment of Healthcare Transition Activities were measured using surveys adopted from Got Transition. Clinicians were educated on the CAH-T program and patient education materials. Following implementation, clinicians documented all CAH-T program-recommended interventions provided in the clinic. Surveys were reassessed using repeated measures. EvaluationTwenty-nine clinicians participated. Eight separate patients received 53 total CAH-T program-recommended interventions during the three-month observation period. Paired assessment of the Current Assessment of Healthcare Transition Activities scores increased from 15.29 ± 8.32 to 24.00 ± 6.11 (p = 0.018; r = 0.63). The Health Care Transition Feedback Survey for Clinicians mean scores increased from 2.75 ± 0.26 to 3.30 ± 0.43 (p = 0.018; r = 0.59). These measures indicate increased utilization of HCT services and acceptance of HCT value. Clinicians suggested that time limitations, English-only transition education materials, and lack of electronic medical record integration were significant barriers to HCT support. Implications for practiceA structured HCT program ensures clinicians provide adolescents with CAH support and guideline-based care. The CAH-T program offers an example of developing and implementing an HCT program for adolescents with CAH. Integration in the electronic medical record will ultimately increase program sustainability.

Post-Hospitalization Home Monitoring Programs During the COVID-19 Pandemic: Survey Results from the Hospital Medicine Re-engineering Network (HOMERuN).

During the coronavirus disease 2019 (COVID-19) pandemic, hospitals and healthcare systems launched innovative responses to emerging needs. The creation and use of programs to remotely follow patient clinical status and recovery after COVID-19 hospitalization has not been thoroughly described. To characterize deployment of remotepost-hospital discharge monitoring programs during the COVID-19 pandemic METHODS: Electronic surveys were administered to leaders of 83 US academic hospitals in the Hospital Medicine Re-engineering Network (HOMERuN). An initial survey was completed in March 2021 with follow-up survey completed in July 2022. There were 35 responses to the initial survey (42%) and 15 responses to the follow-up survey (43%). Twenty-two (63%) sites reported a post-discharge monitoring program, 16 of which were newly developed for COVID-19. Physiologic monitoring devices such as pulse oximeters were often provided. Communication with medical teams was often via telephone, with moderate use of apps or electronic medical record integration. Programs launched most commonly between January and June 2020. Only three programs were still active at the time of follow-up survey. Our findings demonstrate rapid, ad hoc development of post-hospital discharge monitoring programs during the COVID-19 pandemic but with little standardization or evaluation. Additional study could identify the benefits of these programs, instruct their potential application to other disease processes, and inform further development as part of emergency preparedness for upcoming crises.

Personalized medicine in a community health system: the NorthShore experience.

Genomic and personalized medicine implementation efforts have largely centered on specialty care in tertiary health systems. There are few examples of fully integrated care systems that span the healthcare continuum. In 2014, NorthShore University HealthSystem launched the Center for Personalized Medicine to catalyze the delivery of personalized medicine. Successful implementation required the development of a scalable family history collection tool, the Genetic and Wellness Assessment (GWA) and Breast Health Assessment (BHA) tools; integrated pharmacogenomics programming; educational programming; electronic medical record integration; and robust clinical decision support tools. To date, more than 225,000 patients have been screened for increased hereditary conditions, such as cancer risk, through these tools in primary care. More than 35,000 patients completed clinical genetic testing following GWA or BHA completion. An innovative program trained more than 100 primary care providers in genomic medicine, activated with clinical decision support and access to patient genetic counseling services and digital healthcare tools. The development of a novel bioinformatics platform (FLYPE) enabled the incorporation of genomics data into electronic medical records. To date, over 4,000 patients have been identified to have a pathogenic or likely pathogenic variant in a gene with medical management implications. Over 33,000 patients have clinical pharmacogenomics data incorporated into the electronic health record supported by clinical decision support tools. This manuscript describes the evolution, strategy, and successful multispecialty partnerships aligned with health system leadership that enabled the implementation of a comprehensive personalized medicine program with measurable patient outcomes through a genomics-enabled learning health system model that utilizes implementation science frameworks.

New insights on oncologist use of genomic testing.

e18741 Background: As the indications and complexity of precision medicine in oncology increase, we sought information about current provider needs and experiences. Methods: In early 2023, we conducted qualitative interviews with medical oncologists who reported treating patients with lung, breast, and/or colorectal cancer. Questions focused on use, concerns, patient communication, resources, and needs related to genomic testing and precision medicine. Results: A total of 24 oncologists were interviewed (50% in practice &gt; 20 years, 71% at community sites, 88% general oncology). Three patterns of tumor genomic testing emerged: (1) Frequent use and an exploratory mindset; (2) measured use, often with a limited set of alterations tested initially, focused on actionable findings; and (3) infrequent use, requiring availability of effective and affordable treatment. Concerns included turnaround time (particularly for lung cancer), workflow and electronic medical record (EMR) non-integration, non-actionable results, cost, and tissue adequacy. Most respondents find test results easy to use, focusing on the first two pages; some use the entire report. Respondents identified problems securing patient access to indicated targeted therapies, particularly oral agents with costly copays requiring substantial staff administrative effort, with the greatest challenges faced by underinsured rather than uninsured patients. Recommendations included improving EMR integration, shortening time-to-result, reflex performance so results are available at initial oncology appointment, standardizing result presentation, and addressing cost issues. In addition, some suggested that centralized collection and analysis of patient outcome data would inform questions of actionability and access. Conclusions: This qualitative work identifies several major challenges practicing oncologists face in delivering precision medicine. Notably, downstream issues related to treatment access may influence decisions regarding tumor genomic profiling. Further investigation of barriers and potential solutions is needed.

Addressing barriers to increased adoption of DPYD genotyping at a large multisite cancer center.

To describe the implementation of an in-house genotyping program to detect genetic variants linked to impaired dihydropyrimidine dehydrogenase (DPD) metabolism at a large multisite cancer center, including barriers to implementation and mechanisms to overcome barriers to facilitate test adoption. Fluoropyrimidines, including fluorouracil and capecitabine, are commonly used chemotherapy agents in the treatment of solid tumors, such as gastrointestinal cancers. DPD is encoded by the DPYD gene, and individuals classified as DPYD intermediate and poor metabolizers due to certain genetic variations in DPYD can experience reduced fluoropyrimidine clearance and an increased risk of fluoropyrimidine-related adverse events. Although pharmacogenomic guidelines provide evidence-based recommendations for DPYD genotype-guided dosing, testing has not been widely adopted in the United States for numerous reasons, including limited education/awareness of clinical utility, lack of testing recommendations by oncology professional organizations, testing cost, lack of accessibility to a comprehensive in-house test and service, and prolonged test turnaround time. Based on stakeholder feedback regarding barriers to testing, we developed an in-house DPYD test and workflow to facilitate testing in multiple clinic locations at Levine Cancer Institute. Across 2 gastrointestinal oncology clinics from March 2020 through June 2022, 137 patients were genotyped, and 13 (9.5%) of those patients were heterozygous for a variant and identified as DPYD intermediate metabolizers. Implementation of DPYD genotyping at a multisite cancer center was feasible due to operationalization of workflows to overcome traditional barriers to testing and engagement from all stakeholders, including physicians, pharmacists, nurses, and laboratory personnel. Future directions to scale and sustain testing in all patients receiving a fluoropyrimidine across all Levine Cancer Institute locations include electronic medical record integration (eg, interruptive alerts), establishment of a billing infrastructure, and further refinement of workflows to improve the rate of pretreatment testing.

The Real-World Global Use of Patient-Reported Outcomes for the Care of Patients With Inflammatory Bowel Disease.

Many patient-reported outcomes (PROs) have been developed for inflammatory bowel disease (IBD) without recommendations for clinical use. PROs differ from physician-reported disease activity indices; they assess patients' perceptions of their symptoms, functional status, mental health, and quality of life, among other areas. We sought to investigate the current global use and barriers to using PROs in clinical practice for IBD. A cross-sectional survey was performed. An electronic questionnaire was sent to an international group of providers who care for patients with IBD. There were 194 respondents, including adult/pediatric gastroenterologists, advanced practice providers, and colorectal surgeons from 5 continents. The majority (80%) use PROs in clinical practice, 65% frequently found value in routine use, and 50% frequently found PROs influenced management. Thirty-one different PROs for IBD were reportedly used. Barriers included not being familiar with PROs, not knowing how to incorporate PRO results into clinical practice, lack of electronic medical record integration, and time constraints. Most (91%) agreed it would be beneficial to have an accepted set of consistently used PROs. The majority (60%) thought that there should be some cultural differences in PROs used globally but that PROs for IBD should be consistent around the world. PROs are used frequently in clinical practice with wide variation in which are used and how they influence management. Education about PROs and how to use and interpret an accepted set of PROs would decrease barriers for use and allow for global harmonization.

1747. Emergency Department Antimicrobial Stewardship Intervention Bundle to Optimize Antibiotic Prescribing in Urinary Tract Infections and Skin and Soft Tissue Infections

Abstract Background Emerging literature has demonstrated a positive impact of emergency department (ED)-focused antimicrobial stewardship initiatives on antibiotic prescribing. To date, the majority of interventions focus on urinary tract infections (UTI) and few evaluate electronic medical record (EMR) integration. Methods This retrospective, quasi-experimental study was conducted at five EDs within a large-community health system. An antimicrobial stewardship intervention bundle was implemented in February 2022, consisting of ED-specific discharge antibiotic order sets for UTI and skin and soft tissue infections (SSTI) and education to ED prescribers and pharmacists. Adult patients receiving an ED discharge antibiotic prescription associated with a UTI or SSTI ICD10 code were included. The primary outcome was the percentage of prescriptions matching discharge order set antibiotic regimens for UTI and SSTI in the 2-month pre- and post-implementation periods. Secondary outcomes included evaluation of primary outcome indications (UTI or SSTI), use of recommended agents or durations of therapy, use of combination therapy (SSTI only), and rate of 30-day hospital admission. Results The implementation of this multi-intervention stewardship bundle was associated with a significant initial improvement in the percentage of prescriptions matching discharge order set recommendations for UTI and SSTI (30.9% vs. 35%, P = 0.04). There was a significant improvement in UTI prescribing (54.9% vs. 61.7%, P = 0.01), but the same benefit was not demonstrated for SSTI (6.2% vs. 3.6%, P = 0.04). A significant improvement was also observed in the use of recommended durations of therapy (34% vs. 38.5%, P = 0.023). No significant difference was observed in use of indication recommended agents (75.7% vs. 77.1%, P = 0.43), use of inappropriate combination therapy for SSTI (31.7% vs.26.3%, P = 0.07), or 30-day hospital admission (6% vs. 5%, P = 0.33). Conclusion This novel multi-intervention ED antimicrobial stewardship bundle was associated with overall immediate improvements in antibiotic prescribing for discharged patients. Future directions of research will include evaluation of methods to improve SSTI prescribing, implementation of prescriber data feedback, and expansion to additional indications. Disclosures All Authors: No reported disclosures.

Cardiovascular Disease Prevention in Persons with Hemophilia

Background: Advances in the treatment of hemophilia have resulted in a nearly normal life expectancy for persons with hemophilia (PwH). As a result of this improved life expectancy the aging hemophilia population is now experiencing age-related complications including cardiovascular disease (CVD), which is the leading cause of death in the US general population. Several studies have shown that the CVD risk profile among PwH is less favorable than that in the general population (Fransen van de Putte et al., 2013; Sood et al., 2018). Despite higher rates of hypertension among PwH, rates of treatment are lower than in the general population (Sood et al., 2018). We also know that atherosclerosis develops at the same rate among PwH as in the general population (Biere-Rafi et al., 2012; Zwiers et al., 2012). When CVD occurs in PwH, the management is more complicated due to the requirement for clotting factor concentrates to offset anticoagulant and antiplatelet therapies and prevent serious bleeding complications (Martin & Key, 2016). Recent prospective data indicate that the incidence of cardiovascular endpoints in PwH is lower than would be predicted by the QRISK-2011 score, but the use of novel therapies was not analyzed in that study, and we do not know how widespread use of these therapies will impact the development of CVD among PwH (Van Der Valk et al., 2022). Primary prevention of CVD through risk factor management is essential to prevent cardiovascular complications in the era of novel therapies for hemophilia. Study Design and Methods: This multicenter observational cohort study will utilize quality improvement science informed by frequent data sampling to improve the management of hypertension and dyslipidemia in PwH. Ten large hemophilia treatment centers will contribute 100 PwH each and will be stratified by age such that 25% of the population will be age 18-29, 30-44, 45-59, and 60-89. PwH will be eligible for inclusion if they have hemophilia A or B of any severity, are age 18-89, have been seen in the last 2 years, and do not anticipate relocating in the next 3 years. Men and women with hemophilia will be included. Individual consent will not be required as the dataset will be completely deidentified and the quality improvement interventions will be applied broadly to the hemophilia population at each center. Data will be collected from routine clinical care records. The primary outcome will be the prevalence of diagnosed and undiagnosed hypertension in this cohort. Secondary outcomes will be prevalence of dyslipidemia and rates of treatment for hypertension and dyslipidemia. Exploratory and descriptive statistical analyses will be performed. Deidentified data will be entered into a database via electronic medical record integration. This will allow for collection of 5 years of retrospective data, and subsequent monthly prospective data collection for 3 years. The automated nature of the data collection is novel and will allow for rapid record collection with minimal manual data entry, which can introduce errors and delay analysis. As such, a substantial number of records and timepoints can be collected. Conventional manual data entry of this scale would not be feasible for many independent academic studies. Table 1 contains the most relevant variables that will be collected. Retrospective data will be analyzed to determine the prevalence of hypertension, dyslipidemia, and established CVD. Rates of hypertension and dyslipidemia meeting criteria for diagnosis, but without an official diagnosis will also be determined along with rates of treatment in those who have been diagnosed. Investigators will be trained on the latest guidelines from the American College of Cardiology for the management of hypertension and dyslipidemia as part of this initiative. A survey will be distributed to participating investigators to determine barriers to control of vascular risk factors. This data be used by a steering committee to guide quality improvement efforts at each site. Monthly reports will inform investigators on the progress of their quality improvement initiatives. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

Developing a standardized EMR workflow for medical students and preceptors

ObjectivesThe electronic medical record (EMR) is an integral component of clinical encounters. However, there is no standardized curriculum for EMR education in medical school. This study aimed to create a standardized EMR workflow model for medical students in clinic. It was hypothesized that this workflow would be effectively implemented and increase physician productivity. MethodsAn outpatient clinic workflow model was created to integrate students into clinical visits as active participants in EMR documentation. 240 third and fourth-year medical students on their Neurology clerkship at a U.S. medical institution and 34 outpatient neurologists were trained on the workflow (student EMR integration training; SEIT). A total of 733 Neurology outpatient clinic days were analyzed (473 pre-SEIT and 251 post-SEIT). Productivity metrics included average lag time, average Relative Value Units (RVUs) per day, and average invoices per day. ResultsThere was a statistically significant difference in documentation time, with a pre-SEIT lag time of 14.7 days (SD 13.1 days, 95% CI 9.4–20.0) compared to 10.3 days post-SEIT (SD 10.2 days, 95% CI 6.2–14.5; p-value = 0.001). The average RVUs per day were 18.5 pre-SEIT (SD 7.8, 95% CI 15.4–21.7) and 17.8 post-SEIT (SD 8.0, 95% CI 14.6–21.0; p-value = 0.7). The average invoices per day were 7.5 pre-SEIT (SD 2.6, 95% CI 6.5–8.6) and 7.3 post-SEIT (SD 3.0, 95% CI 6.1–8.5; p-value = 0.5). ConclusionsThe workflow model utilizes medical student EMR documentation in the clinical note and decreases physician documentation time.

PSUN221 Implementation of Scheduled Mealtimes for Improved Glycemic Control among Hospitalized Patients with Diabetic Meal Plans

Abstract Objective To improve inpatient glycemic control through implementation of scheduled diabetic mealtimes in coordination with standardized bedside glucose checks and insulin administration times Methods We performed a plan-do-study-act (PDSA) trial in which we modified our standard diabetic diet from on-demand service to scheduled mealtimes with a goal to complete bedside glucose monitoring, meal delivery, and insulin administration all within a one-hour window for each meal. Both patients and clinical staff were actively educated regarding the rationale for this approach; prominent visual cues were implemented, and the menu was modified to include patient-centered information regarding mealtime practices. Low-carbohydrate snacks were offered between meals. Electronic medical record integration included defaulting to scheduled insulin dosing rather than as-needed dosing. Results Early PDSA analysis demonstrated a 98% rate of pre-prandial glucose measurement with a 96% rate of correctional insulin doses ordered, while 91% of overall mealtimes successfully coordinated tray delivery, glucose testing, and insulin administration within one hour. Analysis of glycemic data from before and after our intervention demonstrated decreased overall mean daily glucose (167 to 164mg/dL, p = 0.001), fewer patients with any daily glucose greater than 250mg/dL (from 51% to 47%, p=0.001), and more for whom all glucose readings were between 70 and 249mg/dL (from 43% to 47%, p=0.001). Average pre-prandial blood sugars significantly improved before breakfast (156 to 152mg/dL, p=0.003) and dinner (173 to 165mg/dL, p&amp;lt; 0.001), while no effect was noted with pre-prandial lunchtime measurements. Evening blood sugars declined from 186 to 180mg/dL (p&amp;lt; 0.001). Subgroup analyses demonstrated that patients who presented with baseline poor glycemic control (admission blood sugar &amp;gt;250mg/dL) improved the percentage of patients with all glucose readings between 70 and 249mg/dL (from 12% to 19%, p=0.001), as well as the number of patients with any subsequent glucose &amp;gt;250mg/dL (from 85% to 77%, p=0.003). Patients who presented with better initial blood glucose control still improved their mean daily glucose (161 to 158mg/dL, p=0.005). The percentage of patients who had any glucose less than 70mg/dL did not significantly change throughout the intervention overall or with any subgroup analysis. Discussion/Conclusion The implementation of scheduled mealtimes within a diabetic meal plan contributes to improved glycemic control when compared with on-demand meal availability by streamlining the coordination of blood glucose measurement, meal delivery, and insulin administration. Presentation: Sunday, June 12, 2022 12:30 p.m. - 2:30 p.m.

34 How online care plans promote partnership, trust, and cohesive care for children with medical complexity

Abstract Background Children with medical complexity (CMC) require care coordination across hospital, home, and community settings. The use of a medical care plan supports care coordination; however, the content of the care plan is often controlled by the health care team, limiting the ability of parents to edit in real time. It has been suggested that these limitations could be improved by using online care plans shared between parents of CMC and care team members (CTM). Objectives The objective of this study was to explore the perspectives of parents and care team members of children with medical complexity following the use of an online care plan. Design/Methods This qualitative study utilized grounded theory (GT) to explore parent and CTM experiences using an online editable medical care plan. Parents of CMC were invited to use a novel online patient-facing platform to coordinate their child’s care and edit/share their child’s care plan. They were also able to invite any of their child’s CTM to use the platform. Parents could make changes to the care plan including adding, editing, or deleting information. After 6 months, parents and CTM participated in semi-structured interviews aimed at exploring their experiences using the online care plan. Consistent with GT, constant comparative analysis was used as data analysis occurred concurrently with interviews, which allowed for theoretical sampling and theory generation. Results Thirty-five semi-structured interviews with parents (n=15) and CTM (n=20) were conducted. Interviews revealed three major themes (9 sub-themes): 1) navigation of uncharted roles (trust, role sharing, responsibility), 2) requirements for success (collaborative review, electronic medical record integration, online access), and 3) cohesive care (autonomy, accessibility and convenience, same page). These themes informed the creation of a theory outlining how and why a robust online shared care plan can improve care for CMC. Both parents and CTM identified the uniqueness of this care plan located on the online platform as it promoted collaboration and trust whilst allowing for increased autonomy and convenience. Conclusion Online shared care plans, implemented in a safe and thoughtful manner, promote cohesive partnering between parents and care team members while allowing easy access to information. This facilitates care coordination and a cohesive partnering between parents and care team members involved in the care of CMC.

Improving routine use of clinical pathway decision support through EMR integration.

432 Background: There has been an explosive growth in oncology with an evolution of precision oncology based on molecular profiling. Providing evidence-based, high quality, equitable care is a foundational mission for Kaiser Permanente (KP). Thus, KP created a systematic approach toward oncology care pathways that incorporated organizational leadership, structured participation and feedback, novel integration of clinical decision support (CDS) tools, and evaluation of efficacy, safety, and value. Our goal was to make it easy and preferable for physicians to access clinical decision support for every patient, every time. Methods: KP’s inter-regional oncology chiefs, supported by relevant teams in evidence analysis, pharmacy, and other clinical specialties, convened monthly meetings in 10 oncology sub-specialties to synthesize evidence and create care pathways for priority conditions. The pathways are published to KP’s Clinical Library (CL), a trusted, curated resource of clinical knowledge guidance and tools, available via KP’s Epic Systems electronic medical record (EMR). The pathways are represented as intuitive, graphical, clickable process diagrams, with additional clinical content available as hover text. CL uses standard Epic interfaces to receive contextual information when accessed from a patient encounter. When the physician browses the CL oncology pathway and selects a treatment recommendation, CL returns to the EMR with the specific treatment plan queued up for ordering. We began initial deployment of these inter-regional pathways in Feb 2020. We combined EMR data with CL data to understand the impact of this clinical decision support. Results: We experienced dramatic uptake of oncology clinical pathways despite offering minimal training and no external incentives. KP orders over Beacon treatment plans annually in the clinical conditions supported by our pathways. In the first quarter of deployment, clinicians ordered 9% of these protocols through clicking on CDS in CL. Over the course of 2 years, we saw pathway-based ordering grow to over 75% of eligible patients. Conclusions: We find that we have made considerable progress toward our goal of having physician users consult clinical pathways decision support before ordering oncology drug treatment protocols. As with all clinical guidance, we would not expect 100% of patients to follow the recommendation, due to clinical variation and co-morbidity, but we find that by making clinical pathways easily accessible and actionable within normal clinical workflow, physicians are consulting the latest evidence in their treatment.

Development and validation of interpretable machine learning models for inpatient fall events and electronic medical record integration.

Falls are one of the most frequently occurring adverse events among hospitalized patients. The Morse Fall Scale, which has been widely used for fall risk assessment, has the two limitations of low specificity and difficulty in practical implementation. The aim of this study was to develop and validate an interpretable machine learning model for prediction of falls to be integrated in an electronic medical record (EMR) system. This was a retrospective study involving a tertiary teaching hospital in Seoul, Korea. Based on the literature, 83 known predictors were grouped into seven categories. Interpretable fall event prediction models were developed using multiple machine learning models including gradient boosting and Shapley values. Overall, 191,778 cases with 272 fall events (0.1%) were included in the analysis. With the validation cohort of 2020, the area under the receiver operating curve (AUROC) of the gradient boosting model was 0.817 (95% confidence interval [CI], 0.720-0.904), better performance than random forest (AUROC, 0.801; 95% CI, 0.708-0.890), logistic regression (AUROC, 0.802; 95% CI, 0.721-0.878), artificial neural net (AUROC, 0.736; 95% CI, 0.650-0.821), and conventional Morse fall score (AUROC, 0.652; 95% CI, 0.570-0.715). The model's interpretability was enhanced at both the population and patient levels. The algorithm was later integrated into the current EMR system. We developed an interpretable machine learning prediction model for inpatient fall events using EMR integration formats.

Feasibility Of An Evidence-based Exercise Intervention With Electronic Medical Record Integration For Testicular Cancer Survivors

Feasibility Of An Evidence-based Exercise Intervention With Electronic Medical Record Integration For Testicular Cancer Survivors

COVID-19 telehealth preparedness: a cross-sectional assessment of cardiology practices in the USA.

Aim: The COVID-19 pandemic forced medical practices to augment healthcare delivery to remote and virtual services. We describe the results of a nationwide survey of cardiovascular professionals regarding telehealth perspectives. Materials & methods: A 31-question survey was sent early in the pandemic to assess the impact of COVID-19 on telehealth adoption & reimbursement. Results: A total of342 clinicians across 42 states participated. 77% were using telehealth, with the majority initiating usage 2 months after the COVID-19 shutdown. A variety of video-based systems were used. Telehealth integration requirements differed, with electronic medical record integration being mandated in more urban than rural practices (70vs 59%;p<0.005). Many implementation barriers surfaced, with over 75% of respondents emphasizing reimbursement uncertainty and concerns for telehealth generalizability given the complexity of cardiovascular diseases. Conclusion: Substantial variation exists in telehealth practices. Further studies and legislation are needed to improve access, reimbursementand the quality of telehealth-based cardiovascular care.