Existing Electronic Health Record Research Articles

Improving cardiovascular risk prediction through machine learning modelling of irregularly repeated electronic health records.

Existing electronic health records (EHRs) often consist of abundant but irregular longitudinal measurements of risk factors. In this study, we aim to leverage such data to improve the risk prediction of atherosclerotic cardiovascular disease (ASCVD) by applying machine learning (ML) algorithms, which can allow automatic screening of the population. A total of 215 744 Chinese adults aged between 40 and 79 without a history of cardiovascular disease were included (6081 cases) from an EHR-based longitudinal cohort study. To allow interpretability of the model, the predictors of demographic characteristics, medication treatment, and repeatedly measured records of lipids, glycaemia, obesity, blood pressure, and renal function were used. The primary outcome was ASCVD, defined as non-fatal acute myocardial infarction, coronary heart disease death, or fatal and non-fatal stroke. The eXtreme Gradient boosting (XGBoost) algorithm and Least Absolute Shrinkage and Selection Operator (LASSO) regression models were derived to predict the 5-year ASCVD risk. In the validation set, compared with the refitted Chinese guideline-recommended Cox model (i.e. the China-PAR), the XGBoost model had a significantly higher C-statistic of 0.792, (the differences in the C-statistics: 0.011, 0.006-0.017, P < 0.001), with similar results reported for LASSO regression (the differences in the C-statistics: 0.008, 0.005-0.011, P < 0.001). The XGBoost model demonstrated the best calibration performance (men: Dx = 0.598, P = 0.75; women: Dx = 1.867, P = 0.08). Moreover, the risk distribution of the ML algorithms differed from that of the conventional model. The net reclassification improvement rates of XGBoost and LASSO over the Cox model were 3.9% (1.4-6.4%) and 2.8% (0.7-4.9%), respectively. Machine learning algorithms with irregular, repeated real-world data could improve cardiovascular risk prediction. They demonstrated significantly better performance for reclassification to identify the high-risk population correctly.

System-wide approach on biosimilars adoption in oncology: Strategic plan on switching and cost savings.

1600 Background: Biosimilars provide competitive, lower-cost alternatives to biologic drugs in cancer treatment. As more agents become available in the US, institutions have to implement a strategy for successful adoption that is feasible, safe and provide price competition among biosimilar manufacturers. Methods: We aimed to standardize biosimilar utilization across the Cedars-Sinai Health System (CSHS) by integrating institutionally developed clinical pathways and insurance prior-authorization into the existing electronic health record (EHR). The initial study was limited to bevacizumab, rituximab and trastuzumab. To align with CSHS guideline recommendations, biosimilar indications for use were reviewed by each disease related group (DRG). Biosimilar brands for each drug were selected through a formulary process vetted by the Pharmacy &amp; Therapeutics Committee. Physicians were permitted to opt-out of switching via an option provided within the electronic order set. To test feasibility of this approach, patients were divided into two groups as 1) main medical center (Cedars Sinai Medical Center) and 2) Cedars-Sinai Cancer affiliated sites. Feasibility was defined as a compliance rate of 80% or greater at the main medical center and 75% or greater at the affiliated sites. This study was powered to detect a minimum difference at 5.7% and 8.9%, respectively. Results: Between January 2021 to September 2022, a total of 1,139 cancer patients who initiated treatment with bevacizumab, rituximab or trastuzumab were identified through the EHR, of whom 650 were eligible (age 18-96; 61% female, 39% male). Using our approach, the compliance rate was 86% at the main site (p&lt;0.001, 95%CI: 82.5-89.1) and 88% (p&lt;0.001, 95%CI: 82.1-91.7) at the affiliated sites, resulting in a 56% improvement from baseline (86% vs. 55%, p&lt;0.001). Among 14% of patients who did not switch to institutional-preferred biosimilar brands, the most common reasons for this were payer mandated use of an alternate brand (5%), off-label indication (4%), enrolled in patient assistance program (3%) and physician preference (2%). Five patients (&lt;1%) did not switch to biosimilars due to history of infusion reactions. Insurance type (HMO, PPO, Medicare, others) was not associated with non-compliance (p=0.876). Cost savings were projected to be over $4 million over a duration of two years. Conclusions: Enterprise-wide switching to one specific biosimilar brand is feasible and facilitated through leveraging of the EHR. This approach optimized exiting organizational infrastructure to standardize biosimilar utilization and promote substantial cost savings.[Table: see text]

An alternative model for assessing mortality risk in Stevens Johnson syndrome/toxic epidermal necrolysis using a random forests classifier: A pilot study.

Mortality risk prediction is an important part of the clinical assessment in the Stevens-Johnson syndrome and toxic epidermal necrolysis (SJS/TEN) patient. The SCORTEN and ABCD-10 scoring systems have been used as predictive clinical tools for assessing this risk. However, some of the metrics required in calculating these scores, such as the total body surface area (TBSA) involvement, are difficult to calculate. In addition, TBSA involvement is calculated in a variety of ways and is observer dependent and subjective. The goal of this study was to develop an alternative method to predict mortality in patients with SJS/TEN. Data was split into training and test datasets and preprocessed. Models were trained using five-fold cross validation. Out of several possible candidates, a random forests model was evaluated as being the most robust in predictive power for this dataset. Upon feature selection, a final random forests model was developed which was used for comparison against SCORTEN. The differences in both accuracy (p = 0.324) and area under the receiver operating characteristic curve (AUROC) (p = 0.318) between the final random forests model and the SCORTEN and ABCD-10 models were not statistically significant. As such, this alternative method performs similarly to SCORTEN while only requiring simple laboratory tests from the day of admission. This new alternative can make the mortality prediction process more efficient, along with providing a seamless implementation of the patient laboratory tests directly into the model from existing electronic health record (EHR) systems. Once the model was developed, a web application was built to deploy the model which integrates with the Epic EHR system on the Fast Healthcare Interoperability Resources (FHIR) Application Programming Interface (API); this only requires the patient medical record number and a date of the lab tests as parameters. This model ultimately allows clinicians to calculate patient mortality risk with only a few clicks. Further studies are needed for validation of this tool.

Providers’ Experience with Artificial Intelligence-Based System During the COVID-19 Pandemic

Abstract Background As the pandemic continues to spread worldwide, many of healthcare facilities are exploring new methods to keep their patients safe from potential hospital-acquired infections (HAIs) during the pandemic. This study explored the attitudes about artificial intelligence (AI) among providers who utilized AI-based hand hygiene monitoring system (HHMS) at a rural medical center during the pandemic. Methods A self-administered questionnaire was mailed to 48 healthcare providers at a rural medical center in north Texas, with a 75% percent response rate (n = 36). The survey collected information on providers attitudes about AI-based HHMS use. In addition, the study also examined the relationship between provider’s well-being and the level of satisfaction with the AI-based HHMS use. The lessons learned from this study will be used to determine important factors to consider when attempting to advance and expand AI technologies in rural healthcare settings. Results Results revealed that the integration of AI technology within the existing electronic health record (EHR) system remains a challenge for many providers. Plus, the lack of user-centered design approaches to incorporate the AI tool into existing workflows has reduced providers satisfaction about the new technology. Conclusions The findings suggested that although AI technology has great promise to reduce the number of hospital-acquired infections (HAIs), successfully implement of an AI-based tool that meets the expectations of users requires significant levels of consolidation to ensure that it fits within the existing workflows and is accepted by users. Key messages • AI application indirectly affects the well-being of providers, particularly in rural healthcare settings. • A better AI application interface design that meets the expectations of providers is needed.

Needs assessment survey of healthcare providers' perceptions and practices regarding delirium prevention at a university medical center.

Background: Despite the high prevalence and serious implications of delirium, identification, tracking, and documentation of the condition remain a challenge for the health care team, impeding management of patients. This survey is the first phase of a qualitative study to build a conversational agent-based tool for screening and managing delirium-prone patients. Objectives: To assess healthcare providers’ perceptions of delirium management, focusing on patient assessment, therapeutic interventions, and subsequent communication and documentation. Design: An electronic web-based survey was distributed to healthcare providers identified as caring for inpatient acutely ill older adults admitted for medical and orthopedic surgery needs. Respondent contact information was removed to preserve anonymity. Setting: A 1,000 bed university-affiliated teaching hospital in an urban setting. Participants: 23 residents in family practice, 36 residents in internal medicine, and a total of 492 advanced care nurses, nurses, and clinical staff. Approach: The analysis of survey responses provided insight into providers’ current experiences with delirium assessment tools including computerized documentation, as well as their perceptions and attitudes toward delirium prevention. Key results: Most respondents (89%) thought delirium could be prevented, and 85% thought targeting delirium risk factors was helpful. Fifty one percent reported patients’ loneliness and need for companionship, and 65% believed delirium was linked to higher mortality. Only 14% of respondents thought existing Electronic Health Record (EHR) alerts to identify high-risk delirium patients were useful, and 38% thought current delirium assessment protocols were helpful. In addition, 33% of nurses never received formal delirium prevention training, and 48% indicated that they needed improved systems to assess and manage patients at risk for delirium. Conclusion: A majority of providers affirmed that current delirium protocols are helpful; however, existing screening instruments and methods for documentation are cumbersome, resulting in incomplete or limited documentation of episodes. These barriers lead to an understatement of evidence available for continuous improvement of the patient management process.

Disparities in Psychosocial Distress Screening and Management of Lung and Ovarian Cancer Survivors.

Since 2016, the American College of Surgeons' Commission on Cancer (CoC) has required routine distress screening (DS) of cancer survivors treated in their accredited facilities to facilitate early identification of survivors with psychosocial concerns. Lung and ovarian cancer survivors have relatively low 5-year survival rates and may experience high levels of distress. We examined the extent to which ovarian and lung cancer survivors received CoC-mandated DS and whether DS disparities exist on the basis of diagnosis, sociodemographic factors, or facility geography (urban/rural). This study included a quantitative review of DS documentation and follow-up services provided using existing electronic health records (EHRs). We worked with 21 CoC-accredited facilities across the United States and examined EHRs of 2,258 survivors from these facilities (1,618 lung cancer survivors and 640 ovarian cancer survivors) diagnosed in 2016 or 2017. Documentation of DS was found in half (54.8%) of the EHRs reviewed. Disparities existed across race/ethnicity, cancer type and stage, and facility characteristics. Hispanic/Latino and Asian/Pacific Islander survivors were screened at lower percentages than other survivors. Patients with ovarian cancer, those diagnosed at earlier stages, and survivors in urban facilities had relatively low percentages of DS. Non-Hispanic Black survivors were more likely than non-Hispanic White survivors to decline further psychosocial services. Despite the mandate for routine DS in CoC-accredited oncology programs, gaps remain in how many and which survivors are screened for distress. Improvements in DS processes to enhance access to DS and appropriate psychosocial care could benefit cancer survivors. Collaboration with CoC during this study led to improvement of their processes for collecting DS data for measuring standard adherence.

Information extraction from free text for aiding transdiagnostic psychiatry: constructing NLP pipelines tailored to clinicians’ needs

BackgroundDeveloping predictive models for precision psychiatry is challenging because of unavailability of the necessary data: extracting useful information from existing electronic health record (EHR) data is not straightforward, and available clinical trial datasets are often not representative for heterogeneous patient groups. The aim of this study was constructing a natural language processing (NLP) pipeline that extracts variables for building predictive models from EHRs. We specifically tailor the pipeline for extracting information on outcomes of psychiatry treatment trajectories, applicable throughout the entire spectrum of mental health disorders (“transdiagnostic”).MethodsA qualitative study into beliefs of clinical staff on measuring treatment outcomes was conducted to construct a candidate list of variables to extract from the EHR. To investigate if the proposed variables are suitable for measuring treatment effects, resulting themes were compared to transdiagnostic outcome measures currently used in psychiatry research and compared to the HDRS (as a gold standard) through systematic review, resulting in an ideal set of variables. To extract these from EHR data, a semi-rule based NLP pipeline was constructed and tailored to the candidate variables using Prodigy. Classification accuracy and F1-scores were calculated and pipeline output was compared to HDRS scores using clinical notes from patients admitted in 2019 and 2020.ResultsAnalysis of 34 questionnaires answered by clinical staff resulted in four themes defining treatment outcomes: symptom reduction, general well-being, social functioning and personalization. Systematic review revealed 242 different transdiagnostic outcome measures, with the 36-item Short-Form Survey for quality of life (SF36) being used most consistently, showing substantial overlap with the themes from the qualitative study. Comparing SF36 to HDRS scores in 26 studies revealed moderate to good correlations (0.62—0.79) and good positive predictive values (0.75—0.88). The NLP pipeline developed with notes from 22,170 patients reached an accuracy of 95 to 99 percent (F1 scores: 0.38 – 0.86) on detecting these themes, evaluated on data from 361 patients.ConclusionsThe NLP pipeline developed in this study extracts outcome measures from the EHR that cater specifically to the needs of clinical staff and align with outcome measures used to detect treatment effects in clinical trials.

DETECT: Development of Technologies for Early HCC Detection

DETECT: Development of Technologies for Early HCC Detection

A privacy-preserving National Clinical Data Warehouse: Architecture and analysis

A centralized clinical data repository is essential for inspecting patients’ medical history, disease analysis, population-wide disease research, treatment decision support, and improving existing healthcare policies and services. Bangladesh, a rapidly developing country, poses several unusual challenges for developing such a centralized clinical data repository as the existing Electronic Health Records (EHR) are stored in unconnected, heterogeneous sources with no unique patient identifier and consistency. Data integration with secure record linkage, privacy preservation, quality control, and data standardization are the main challenges for developing a consistent and interoperable centralized clinical data repository. Based on the findings from our previous researches, we have designed an anonymous National Clinical Data Warehouse (NCDW) framework to reinforce research and analysis. The architecture of NCDW is divided into five stages to overcome the challenges: (1) Wrapper-based anonymous data acquisition; (2) Data loading and staging; (3) Transformation, standardization, and uploading to the data warehouse; (4) Management and monitoring; (5) Data Mart design, OLAP server, data mining, and applications. A prototype of NCDW has been developed with a complete pipeline from data collection to analytics by integrating three data sources. The proposed NCDW model facilitates regional and national decision support, intelligent disease analysis, knowledge discovery, and data-driven research. We have inspected the analytical efficacy of the framework by qualitative evaluation of the national decision support from two derived disease data marts. The experimental result based on the analysis is satisfactory to extend the NCDW on a large scale.

A New Approach for Secure Cloud-Based Electronic Health Record and its Experimental Testbed

The tremendous development of the Internet of Things (IoT) technology in the last decades has fostered advancement in automatic medical assistive devices to support the existing Electronic Health Record (EHR) system. As an integral part of the EHR electronic model, public cloud servers store medical data. Unfortunately, public cloud servers are prone to security and privacy breach. This paper introduces a novel non-cryptographic approach to preserve electrocardiograph (ECG) data confidentiality and integrity in the EHR environment. The main objective of the proposed anonymization algorithm is to obscure the patient’s cardiac information during transmission and to protect information stored in the cloud database. Although we focus on ECG data, generalization to other types of clinical data can be derived using the proposed method. Performance evaluation of the proposed scheme showed that the algorithm conceals both fiducial and non-fiducial features of the data. Therefore, confidentiality feature is preserved. This paper examined confidentiality of the anonymized data using the Percentage Residual Difference (PRD) and investigated the integrity of the reconstructed data in terms of cross-correlation. Security analysis carried out using the PRD, brute force attack, and performance comparison between the proposed algorithm and existing methods. Evaluation showed that the proposed scheme offers a secure non-cryptographic model for transmission and storing clinical data in the cloud. Moreover, in terms of processing time, the proposed algorithm is ten times faster than the existing wavelet packet method when processing long ECG data, 65,536 sample points. In a real-time experimental testbed, the implemented proposed system was successful.

Point-of-care dashboards promote coproduction of healthcare services for patients with inflammatory bowel disease.

Coproduction of healthcare services by patients and professionals is seen as an increasingly important mechanism to support person-centred care delivery. Coproduction invites a deeper understanding of what persons sometimes called 'patients' bring to development of a service. Yet, little is known about tools that may help elicit that information. Our objective was to explore potential benefits and limitations of an electronic pre-visit survey (PVS) and dashboard by studying uptake and experiences within the inflammatory bowel disease (IBD) community. We conducted a mixed-method evaluation of patients and clinicians using the IBD Qorus PVS and dashboard at 24 programmes participating in the IBD Qorus learning health system. We analysed (i) descriptive statistics and thematic analyses of 537 patient surveys, (ii) semi-structured interviews with seven patients and six care teams and (iii) usage data collected between 25 March 2019 and 26 April 2020. Nearly two-thirds (64%; n = 38) of clinicians enrolled ≥25 patients into IBD Qorus; 59% (n = 29) of clinicians received ≥25 electronic PVS, with 3834 PVS received during the study period. Post-visit evaluation surveys were completed by patients following 26% (n = 993) of PVS completions. Among patients who reported using the dashboard for 1 or more months (n = 537), two-thirds (65%, n = 344) used the dashboard at a clinic visit and one-third used it outside the clinic (33%, n = 176). Most patients who used the dashboard during a clinic visit said it was helpful in discussions with their clinician (82%), in talking about what matters most (76%) and in making healthcare decisions (71%). Patients using the dashboard during the clinic visit reported higher levels of shared decision-making than those who did not use the dashboard (82% vs. 65%, P < 0.001). This relationship remained significant after controlling for receipt of care at a clinic with the highest levels of patient-reported shared decision-making (odds ratio: 2.1; confidence interval: 1.3-3.3). Patients and clinicians found the greatest value in using the PVS and dashboard to share concerns and symptoms, prepare for a visit and support discussions during the visit. The lack of integration with existing electronic health records (EHRs) limited clinician usage of the PVS and dashboard. The PVS and dashboard created a shared language, which supported coproduction and shared decision-making and facilitated a shared understanding of goals, concerns, symptoms and well-being. To support uptake, future systems should reduce implementation burden for healthcare professionals and integrate seamlessly with existing EHR systems and workflows.

Introduction of Systematized Nomenclature of Medicine–Clinical Terms Coding Into an Electronic Health Record and Evaluation of its Impact: Qualitative and Quantitative Study

BackgroundThis study describes the conversion within an existing electronic health record (EHR) from the International Classification of Diseases, Tenth Revision coding system to the SNOMED-CT (Systematized Nomenclature of Medicine–Clinical Terms) for the collection of patient histories and diagnoses. The setting is a large acute hospital that is designing and building its own EHR. Well-designed EHRs create opportunities for continuous data collection, which can be used in clinical decision support rules to drive patient safety. Collected data can be exchanged across health care systems to support patients in all health care settings. Data can be used for research to prevent diseases and protect future populations.ObjectiveThe aim of this study was to migrate a current EHR, with all relevant patient data, to the SNOMED-CT coding system to optimize clinical use and clinical decision support, facilitate data sharing across organizational boundaries for national programs, and enable remodeling of medical pathways.MethodsThe study used qualitative and quantitative data to understand the successes and gaps in the project, clinician attitudes toward the new tool, and the future use of the tool.ResultsThe new coding system (tool) was well received and immediately widely used in all specialties. This resulted in increased, accurate, and clinically relevant data collection. Clinicians appreciated the increased depth and detail of the new coding, welcomed the potential for both data sharing and research, and provided extensive feedback for further development.ConclusionsSuccessful implementation of the new system aligned the University Hospitals Birmingham NHS Foundation Trust with national strategy and can be used as a blueprint for similar projects in other health care settings.

174 Modeling the Value of an Emergency Department Influenza Vaccination Program

Seasonal Influenza continues to present a significant annual burden as the vaccination rate for all persons six months and older in the United States is 51.8%. Emergency Department (ED) based influenza programs have been successfully implemented and improve vaccine uptake, reduce incidence and costs, as well as improve outcomes. We modeled the process of implementing an ED based vaccination program for a large health system’s Medicare (65+) and Medicaid populations. We utilized existing electronic health records (EHR) and evaluated the impact on the patient population and expenditures to health system.

Monitoring Diagnostic Safety Risks in Emergency Departments: Protocol for a Machine Learning Study.

BackgroundDiagnostic decision making, especially in emergency departments, is a highly complex cognitive process that involves uncertainty and susceptibility to errors. A combination of factors, including patient factors (eg, history, behaviors, complexity, and comorbidity), provider-care team factors (eg, cognitive load and information gathering and synthesis), and system factors (eg, health information technology, crowding, shift-based work, and interruptions) may contribute to diagnostic errors. Using electronic triggers to identify records of patients with certain patterns of care, such as escalation of care, has been useful to screen for diagnostic errors. Once errors are identified, sophisticated data analytics and machine learning techniques can be applied to existing electronic health record (EHR) data sets to shed light on potential risk factors influencing diagnostic decision making.ObjectiveThis study aims to identify variables associated with diagnostic errors in emergency departments using large-scale EHR data and machine learning techniques.MethodsThis study plans to use trigger algorithms within EHR data repositories to generate a large data set of records that are labeled trigger-positive or trigger-negative, depending on whether they meet certain criteria. Samples from both data sets will be validated using medical record reviews, upon which we expect to find a higher number of diagnostic safety events in the trigger-positive subset. Machine learning will be used to evaluate relationships between certain patient factors, provider-care team factors, and system-level risk factors and diagnostic safety signals in the statistically matched groups of trigger-positive and trigger-negative charts.ResultsThis federally funded study was approved by the institutional review board of 2 academic medical centers with affiliated community hospitals. Trigger queries are being developed at both organizations, and sample cohorts will be labeled using the triggers. Machine learning techniques such as association rule mining, chi-square automated interaction detection, and classification and regression trees will be used to discover important variables that could be incorporated within future clinical decision support systems to help identify and reduce risks that contribute to diagnostic errors.ConclusionsThe use of large EHR data sets and machine learning to investigate risk factors (related to the patient, provider-care team, and system-level) in the diagnostic process may help create future mechanisms for monitoring diagnostic safety.International Registered Report Identifier (IRRID)DERR1-10.2196/24642

The Influence of Selection Bias on Identifying an Association between Allergy Medication Use and SARS-CoV-2 Infection

Background: Medications to prevent and treat SARS-CoV-2 infection are needed to complement emerging vaccinations. Recent in vitro studies suggested that certain allergy medications could prevent SARS-CoV-2 infection so we sought to characterize this relationship using existing electronic health record (EHR) data.Methods: We analyzed associations of three allergy medications (cetirizine, diphenhydramine or hydroxyzine) with testing negative for SARS-CoV-2 infection, and measuring also the potential effect of selection bias on these associations. We used EHR data from 230,376 patients (18 years+) who visited outpatient clinicians in a single, large academic center at least once but were never hospitalized (10/1/2020-6/1/2020). Main exposures included EHR documentation of three allergy medications and allergy, with intermediate outcome of receipt of a SARS-CoV-2 test, and the primary outcome as testing negative. Findings: Testing rates varied by sex, age, race/ethnicity and insurance type. Higher age categories and public insurance were associated with a higher adjusted odds of a negative test, while being Black or Hispanic was significantly associated with test positivity. Allergy diagnosis and use of any of three allergy medications were each associated with a higher likelihood of receiving a test (e.g. diphenhydramine - Odds Ratio (OR) 2.99, 95% Confidence Interval (CI) 2.73, 3.28; cetirizine 1.75 (95% CI 1.60, 1.92)). Among those who were tested, only use of diphenhydramine was associated with a negative SARS-CoV-2 test (adjusted OR = 2.23, 95% CI 1.10, 4.55). However, further analyses revealed that selection bias was likely responsible for the apparent protective effect of diphenhydramine.Interpretation: While EHR-based observational studies can inform a need for interventional trials, this study highlights their limitations. The finding that diphenhydramine was associated with a higher odds of testing negative for SARS-CoV-2 must be interpreted with caution due to selection bias.Funding: The Children’s Miracle Network of the University of Florida partially funded this study.Declaration of Interests: Dr. Rasmussen has served on advisory committees for the Teva Pregnancy Registry and Solriamfetol Pregnancy Registry and has consulted for F. Hoffmann-La Roche AG as a litigation expert. Dr. Ostrov has a patent pending for compounds to prevent and treat COVID-19 and methods of using the same. All other authors have nothing to declare. Ethics Approval Statement: We received human subjects approval from the University of Florida Institutional Review Board.

A Secure Signcryption Scheme for Electronic Health Records Sharing in Blockchain

In the existing Electronic Health Records (EHRs), the medical information of patients is completely controlled by various medical institutions. As such, patients have no dominant power over their own EHRs. These personal data are not only inconvenient to access and share, but are also prone to cause privacy disclosure. The blockchain technology provides a new development direction in the medical field. Blockchain-based EHRs are characterized by decentralization, openness and non-tampering of records, which enable patients to better manage their own EHRs. In order to better protect the privacy of patients, only designated receivers can access EHRs, and receivers can authenticate the sharer to ensure that the EHRs are real and effective. In this study, we propose an identity-based signcryption scheme with multiple authorities for multiple receivers, which can resist N-1 collusion attacks among N authorities. In addition, the identity information of receivers is anonymous, so the relationship between them and the sharer is not disclosed. Under the random oracle model, it was proved that our scheme was secure and met the unforgeability and confidentiality requirements of signcryption. Moreover, we evaluated the performance of the scheme and found that it had the moderate signcryption efficiency and excellent signcryption attributes.

COVID-19 Outcomes in Individuals with Sickle Cell Disease and Sickle Cell Trait Compared to Blacks without Sickle Cell Disease or Trait

Introduction: By August 1, 2020 in the United States, more than 3 million cases of Coronavirus disease 2019 (COVID-19) had been reported with more than 150,000 deaths due to this disease. Growing evidence suggests that individuals with the pre-existing conditions of hypertension, diabetes, cardiovascular disease and obesity are at a higher risk of more serious COVID-19 illness. However, the impact of COVID-19 on individuals with sickle cell disease and sickle cell trait as compared to those without sickle cell disease or trait is not known. The objective of this study was to determine the rate of hospitalization, disease symptoms and deaths due to COVID-19, in patients with sickle cell disease and sickle cell trait compared to Blacks without sickle cell disease or trait.Methods: We leveraged existing electronic health record (EHR) data from multiple sites that contribute data to a research network, TriNetX. TriNetX query platform was used to identify patients with COVID-19 infection based on ICD diagnoses codes or a positive COVID-19 result from a nucleic acid amplification with probe-based detection test, present any time after January 20, 2020 (this is when the first COVID-19 case was detected in the United States) within the patients’ EHR data. We report rates of specific COVID-19 related outcomes among individuals with sickle cell disease and trait, calculated as % of patients in cohort with the particular outcome. Our outcomes of interest included COVD-19 related symptoms, hospitalization, and death, which occurred within 2 weeks of COVID diagnosis. We used propensity score matching (greedy nearest-neighbor matching algorithm with a caliper of 0.1 pooled standard deviations) to create balanced cohorts for comparing outcomes between individuals with sickle cell disease or trait and Blacks without sickle cell disease or trait. Risk ratios and risk differences are reported along with 95% confidence intervals. Given multiple outcomes of interest, we considered a more stringent two-sided alpha of less than <0.01, based on a z-test, to determine statistical significance for differences in outcome rates.Results: As of July 15, 2020, there were 122 COVID-19 patients who had sickle cell disease and 172 COVID-19 patients who had sickle cell trait. Our comparator groups included 15,762 Blacks who were diagnosed with COVID-19 but did not have sickle cell trait/disease. COVID-19 patients with sickle cell disease were significantly younger and a higher proportion had asthma, type 1 diabetes and pre-existing liver conditions compared to Blacks without sickle cell trait/disease (Table 1). COVID-19 patients with sickle cell trait were significantly younger, a higher proportion were females, overweight/obese, and a higher proportion had asthma or type 1 diabetes compared to Blacks without sickle cell trait/disease (Table 1). The rate of respective outcomes for the three groups is shown in Figure 1. Propensity score matching yielded a cohort of patients such that there were no significant differences in demographic and clinical characteristics between patients with sickle cell disease/trait compared to Blacks without sickle cell trait/disease. After matching, COVID patients with sickle cell disease remained at a higher risk of hospitalization, pneumonia and pain compared to Blacks without sickle cell trait/disease (Table 2). The case fatality rates were not significantly different between those with sickle cell disease compared to Blacks. There were no significant differences in COVID outcomes between sickle cell trait and Blacks without sickle cell trait/disease, within the matched cohort.Conclusions: These data provide evidence that sickle cell disease imposes additional risk of severe COVID-19 illness and hospitalization, after balancing for age, gender and other preexisting conditions. The death rate between sickle cell disease and Blacks without sickle cell trait/disease was not significantly different. There are no significant differences in COVID-19 outcomes between sickle cell trait and Blacks without sickle cell trait/disease, after balancing for age, gender and other pre-existing conditions.DisclosuresBrandow:NIH / NHLBI: Research Funding; Greater Milwaukee Foundation: Research Funding. Panepinto:HRSA: Research Funding; NINDS: Research Funding; NINDS: Research Funding; NHLBI: Research Funding.

Modernizing health information technology: lessons from healthcare delivery systems.

ObjectiveTo identify recurrent themes, insights, and process recommendations from stakeholders in US organizations during the health information technology (HIT) modernization of an existing electronic health record (EHR) to a commercial-off-the-shelf product in both resource-plentiful settings and in a resource-constrained environment, the US Indian Health Service.Materials and MethodsThirteen qualitative interviews with stakeholders in various organizations were conducted about HIT modernization efforts. Using a Theory of Change framework, recurring themes were identified and analyzed.ResultsThe interviewees emphasized the importance of organizational and process revision during modernization, converting historical data, and clinical and leadership involvement. HIT implementation required technological and infrastructure redesign, additional training, and workflow reconfiguration. Motivations for modernization included EHR usability dissatisfaction, revenue enhancements, and improved clinical operations. Decision-making strategies, primarily during HIT selection, included meetings with stakeholders. Successful modernization resulted in improvements in clinical operations, patient experience, and financial outlay.DiscussionExisting implementation frameworks fail to provide experiential feedback, such as implementation challenges, like data conversion, regulatory, functionality, and interoperability requirements. Regardless of the healthcare environment, HIT modernization requires the engagement of leadership and end-users during HIT selection and through all stages of the implementation to prepare people, processes, and technology. Organizations must iteratively define the technological, infrastructure, organizational, and workflow changes required for a successful HIT modernization effort.ConclusionsHIT modernization is an opportunity for organizational and technological change. Successful modernization requires a comprehensive, intentional, well-communicated, and multidisciplinary approach. Resource-constrained environments have the additional challenges of financial burdens, limited staffing, and unstable infrastructure.

Building a survivorship care plan delivery process: Experience in an academic center.

69 Background: The Institute of Medicine endorses delivery of survivorship care plans (SCPs) to the growing number of cancer survivors in order to improve the coordination of care between oncologists and primary care providers (PCPs). In response, the Commission on Cancer (COC) has increased the SCP delivery requirement to &gt;50% of eligible patients, a goal that is difficult to meet given limited resources. Here we outline the initiatives taken to achieve this goal at the University of New Mexico Comprehensive Cancer Center (UNMCCC). Methods: Prior to 2017, SCPs were not routinely delivered. Beginning 2017, providers were tasked to complete and deliver printed SCPs , resulting in a 17% rate of SCP completion. However, there was general lack of provider support and enthusiasm as the process was time consuming with no method for identifying eligible patients and tracking SCP delivery. In 2018, designated staff was assigned to partially complete the SCPs to assist providers, resulting in an increase in SCP delivery rate to 41%. However, the same barriers existed. SCP softwares, although available, were expensive. A cost effective process therefore was needed. A committee was then formed to create a system-wide process utilizing the existing electronic health record (EHR) MOSAIQ. ASCO based SCPs were created. Once providers identify eligible patients, an SCP electronic order was initiated. Designated staff then partially completes the SCPs based on review of medical records. The EHR extracts data items including demographics, PCP information, cancer type and stage. The EHR is programmed to flag SCPs ready for delivery which the provider then edits and approves. This system tracks multiple time points including referral, completion and delivery of SCPs. This new process was implemented in April 2019. Quarterly reviews are set to assess metrics. Results: Utilizing existing EHR (MOSAIQ), a new SCP delivery process was created that allows tracking of assembly, completion and timing of delivery. Conclusions: To overcome existing barriers to SCP completion and delivery, a new cost effective process was created utilizing existing staff and EHR resources. Institutional support is key to the success of this initiative.

SYNERGY-AI: Artificial intelligence-based precision oncology clinical trial matching and registry.

22 Background: Precision oncology encompasses the implementation of high level of evidence disease-specific and biomarker-driven diagnostic and treatment recommendations for optimized cancer care. Artificial Intelligence (AI), telemedicine and value-based care may optimize clinical trial enrollment (CTE) and overall cost-benefit. This ongoing, international registry for cancer pts evaluates the feasibility and clinical utility of an AI-based precision oncology clinical trial matching tool, powered by a virtual tumor boards (VTB) program, and its clinical impact on pts with advanced cancer to facilitate CTE, as well as the financial impact, and potential outcomes of the intervention. Methods: The SYNERGY-AI Registry is an international prospective, observational cohort study of eligible adult and pediatric pts with advanced solid and hematological malignancies, for whom the decision to consider CTE has already been made by their primary providers (PP). Using a proprietary application programming interface (API) linked to existing electronic health records (EHR) platforms, individual clinical data is extracted, analyzed and matched to a parametric database of existing institutional and non-institutional CTs. Machine learning algorithms allow for dynamic matching based on CT allocation and availability for optimized matching. Patients voluntarily enroll into registry, which is non-interventional with no protocol-mandated tests/procedures—all treatment decisions are made at the discretion of PP in consultation with their pts, based on the AI CT matching report, and VTB support. CTE will be assessed on variables including biomarkers, barriers to enrollment. Study duration anticipated as ~36 mo. The impact time to initiation of CTE on PFS and OS will be estimated by Kaplan-Meier and Cox multivariable survival analysis. Enrollment is ongoing, with a target of ≥ 1500 patients. Key inclusion criteria: Pts with solid and hematological malignancies; Pts cancer-related biomarkers. Key exclusion: ECOG PS &gt; 2; abnormal organ function; hospice. Results: To be presented. Conclusions: AI-based, patient-driven CTE is feasible, highly effective and paradigm-changing. Clinical trial information: NCT03452774.