Search

Lung nodules are frequently detected on low‐dose computed tomography scans performed for lung cancer screening and incidentally detected on imaging performed for other reasons. There is wide variability in how lung nodules are managed by general practitioners and subspecialists, with high rates of guideline‐discordant care. This may be due in part to the level of evidence underlying current practice guideline recommendations (primarily based on findings from uncontrolled studies of diagnostic accuracy). The primary aims of lung nodule management are to minimize harms of diagnostic evaluations while expediting the evaluation, diagnosis, and treatment of lung cancer. Potentially useful tools such as lung cancer probability calculators, automated methods to identify patients with nodules in the electronic health record, and multidisciplinary team evaluation are often underused due to limited availability, accessibility, and/or provider knowledge. Finally, relatively little attention has been paid to identifying and reducing disparities among individuals with screening‐detected or incidentally detected lung nodules. This contribution to the American Cancer Society National Lung Cancer Roundtable Strategic Plan aims to identify and describe these knowledge gaps in lung nodule management and propose recommendations to advance clinical practice and research. Major themes that are addressed include improving the quality of evidence supporting lung nodule evaluation guidelines, strategically leveraging information technology, and placing emphasis on equitable approaches to nodule management. The recommendations outlined in this strategic plan, when carried out through interdisciplinary efforts with a focus on health equity, ultimately aim to improve early detection and reduce the morbidity and mortality of lung cancer. Plain Language Summary: Lung nodules may be identified on chest scans of individuals who undergo lung cancer screening (screening‐detected nodules) or among patients for whom a scan was performed for another reason (incidental nodules).Although the vast majority of lung nodules are not lung cancer, it is important to have evidence‐based, standardized approaches to the evaluation and management of a lung nodule.The primary aims of lung nodule management are to diagnose lung cancer while it is still in an early stage and to avoid unnecessary procedures and other harms. Given the need to balance the benefits of early‐detection of lung cancer and the risks of diagnostic tests, it is imperative to develop evidence‐based strategies for lung nodule management. This report identifies six gaps in knowledge about lung nodule management and proposes six recommendations to improve the management approaches described in clinical practice guidelines. [ABSTRACT FROM AUTHOR]

Purpose: To describe the development and integration of an electronic health record‐driven, student dashboard that displays real‐time data relative to the students' patient management and clinic experiences at the University of Illinois Chicago, College of Dentistry. Materials and methods: Following development and implementation of the student dashboard, various objective metrics were evaluated to identify any improvements in the clinical patient management. A cross‐sectional retrospective chart review was completed of the electronic health record (axiUm, Exan, Coquitlam, BC, Canada) from January 2019 to April 2022 evaluating four performance metrics: student lockouts, note/code violations, overdue active patients, and overdue recall patients. Descriptive statistics were analyzed. The Kolmogorov–Smirnov test was applied to assess the normal distribution of data. Data were analyzed by the Kruskal–Wallis tests for potential differences between pre‐dashboard and post‐dashboard implementation years with the mean overdue active/recall patient to student ratio variables. Mann–Whitney U‐tests for between‐groups comparisons with Bonferroni correction for multiple comparisons were performed (α = 0.05). Descriptive statistics were performed to analyze the student utilization frequency of the dashboard. Results: Post‐implementation analysis indicated a slight decrease in the number of lockouts and note/code violation; and a statistically significant decrease in overdue active patients post‐dashboard (P < 0.001). On average, students accessed their dashboards 3.3 times a week. Conclusions: Implementation of a student dashboard through the electronic health record platform within an academic dental practice has the potential to assist students with patient management and is utilized regularly by the students. [ABSTRACT FROM AUTHOR]

Introduction: Competent navigation of an electronic health record (EHR) has become a critical skill for health professionals, and pharmacists need to be adept in EHR utilization given the extent of EHR involvement in routine medication management. Limited data exists related to current approaches to teaching EHR skills in pre‐Advanced Pharmacy Practice Experiences (pre‐APPE) pharmacy curricula. Objectives: The purpose of this study was to describe activities, utilization, and barriers to implementation of teaching EHRs (tEHRs) into pharmacy curricula in skills‐based courses. Methods: Faculty members of the Big Ten Academic Alliance Skills‐Based Education and Assessment Collaborative (BTAA‐SBEAC) were surveyed. The questionnaire included open‐ended questions related to tEHR type, curriculum placement, and current use of tEHRs, as well as barriers to incorporation of tEHRs in the curriculum. Inductive content analysis was used to evaluate qualitative responses. Results: A representative from all 10 colleges within the BTAA responded. Most programs focused on EHR teaching in the second and third years of the curriculum. All respondents reported having access to a tEHR for internal case building. The tEHR was used by all institutions to allow students to practice in gathering patient information as the first step in the Pharmacists' Patient Care Process. Other activities commonly performed using the tEHR included patient care documentation, medication order verification, prescription processing, and medication reconciliation. Faculty time and cost were barriers identified for successful tEHR implementation. Conclusion: Multiple skills are taught through the utilization of a tEHR among the colleges within the BTAA. These activities vary between institutions, and barriers exist that limit expansion and consistent integration across a skills‐based curriculum. Recognition of EHR utilization as an essential pharmacy skill can allow for development of formalized learning outcomes, leading to better support and integration throughout skills‐based courses. [ABSTRACT FROM AUTHOR]

The integration of genetic information (GI) into the electronic health record (EHR) seems inevitable as the mainstreaming of genomics continues. Such newly provided accessibility to GI could be beneficial for improving health care, as well as for supporting clinical decision‐making and health management. Notwithstanding these promising benefits, the automatic integration of GI into the EHR, allowing unrestricted access to one's GI through patient portals, carries various knowledge‐related risks for patients. This article is focused on the potential case of inadvertently revealing misattributed parentage through such practice. The article aims to identify key clinical and ethical implications of such revelation for adult patients. Clinical implications include, for example, altering the physician‐patient interaction and the need to enhance physician's genetic literacy to improve genetic‐information‐specific communication skills. Ethical implications yield arguments supporting disclosure of MP, such as autonomy, individuals' right to know medical information pertaining to them, and the right to know one's genetic origins. Arguments opposing disclosure of MP centre on the right not to know GI and concerns for post‐disclosure family relationships. Following the clinical and ethical analyses of these respective implications, we consider how such integration of GI into the EHR ought to be carried out, ethically. We therefore suggest a solution, featuring an autonomy‐based approach, built around EHR users' right not to know. Our solution of nuanced consent options (including a 'genetic ignorance option') is designed to enable patients' informed exposure to GI through the EHR, allowing them some control over their self‐ and familial narrative. [ABSTRACT FROM AUTHOR]

Aims: Heart failure (HF) is a clinical syndrome with no definitive diagnostic tests. HF registries are often based on manual reviews of medical records of hospitalized HF patients identified using International Classification of Diseases (ICD) codes. However, most HF patients are not hospitalized, and manual review of big electronic health record (EHR) data is not practical. The US Department of Veterans Affairs (VA) has the largest integrated healthcare system in the nation, and an estimated 1.5 million patients have ICD codes for HF (HF ICD‐code universe) in their VA EHR. The objective of our study was to develop artificial intelligence (AI) models to phenotype HF in these patients. Methods and results: The model development cohort (n = 20 000: training, 16 000; validation 2000; testing, 2000) included 10 000 patients with HF and 10 000 without HF who were matched by age, sex, race, inpatient/outpatient status, hospital, and encounter date (within 60 days). HF status was ascertained by manual chart reviews in VA's External Peer Review Program for HF (EPRP‐HF) and non‐HF status was ascertained by the absence of ICD codes for HF in VA EHR. Two clinicians annotated 1000 random snippets with HF‐related keywords and labelled 436 as HF, which was then used to train and test a natural language processing (NLP) model to classify HF (positive predictive value or PPV, 0.81; sensitivity, 0.77). A machine learning (ML) model using linear support vector machine architecture was trained and tested to classify HF using EPRP‐HF as cases (PPV, 0.86; sensitivity, 0.86). From the 'HF ICD‐code universe', we randomly selected 200 patients (gold standard cohort) and two clinicians manually adjudicated HF (gold standard HF) in 145 of those patients by chart reviews. We calculated NLP, ML, and NLP + ML scores and used weighted F scores to derive their optimal threshold values for HF classification, which resulted in PPVs of 0.83, 0.77, and 0.85 and sensitivities of 0.86, 0.88, and 0.83, respectively. HF patients classified by the NLP + ML model were characteristically and prognostically similar to those with gold standard HF. All three models performed better than ICD code approaches: one principal hospital discharge diagnosis code for HF (PPV, 0.97; sensitivity, 0.21) or two primary outpatient encounter diagnosis codes for HF (PPV, 0.88; sensitivity, 0.54). Conclusions: These findings suggest that NLP and ML models are efficient AI tools to phenotype HF in big EHR data to create contemporary HF registries for clinical studies of effectiveness, quality improvement, and hypothesis generation. [ABSTRACT FROM AUTHOR]

Aims Methods Results Conclusion Computerized decision support systems (CDSSs) aim to prevent adverse drug events. However, these systems generate an overload of alerts that are not always clinically relevant. Anticoagulants are frequently involved in these alerts. The aim of this study was to investigate the efficiency of CDSS alerts on anticoagulants in Dutch hospital pharmacies.A multicentre, single‐day, cross‐sectional study was conducted using a flashmob design in Dutch hospital pharmacies, which have CDSSs that operate on both a national medication surveillance database and on self‐developed clinical rules. Hospital pharmacists and pharmacy technicians collected data on the number and type of alerts and time needed for assessing these alerts. The primary outcome was the CDSS efficiency on anticoagulants, defined as the percentage of alerts on anticoagulants that led to an intervention. Secondary outcomes where among other CDSSs efficiency related to any medications and the time expenditure. Descriptive data‐analysis was used.Of the 69 hospital pharmacies invited, 42 (61%) participated. The efficiency of CDSS alerts on anticoagulants was 4.0% (interquartile range [IQR] 14.0%) for the national medication surveillance database alerts and 14.3% (IQR 40.0%) for alerts from clinical rules. For any medication, the efficiency was lower: 1.8% (IQR 7.5%) and 13.4% (IQR 21.5%) respectively. The median time for assessing the relevance of all alerts was 2 (IQR 1:21) h/day for pharmacists and 6 (IQR 5:01) h/day for pharmacy technicians.CDSS efficiency is generally low, both for anticoagulants and any medication, while the time investment is high. Optimization of CDSSs is needed. [ABSTRACT FROM AUTHOR]

Aims: Although tick‐borne disease (TBD) incidence has increased in the United States (U.S.) in the past decade, new evidence suggests that notifiable diseases surveillance records may not accurately reflect the true magnitude of TBD diagnoses. Furthermore, while regional electronic health records (EHR) are readily accessible their potential use as a more stable and consistent source of TBD diagnoses data has remained largely unexplored. Methods and Results: In this study, we used EHR from a database of more than 100 hospitals, healthcare networks, and insurance providers in Indiana, U.S., to better understand incidence, spatio‐temporal and demographic distribution of TBD Diagnoses from 2009–2018. Our results revealed that in Indiana, from 2009 to 2018, there were 5173 unique TBD Diagnoses across three diagnoses categories: Lyme disease (72.5%, n = 3751), Rickettsioses (12.0%, n = 623) and Other TBD Diagnoses (15.4%, n = 799). Using EHR, the average yearly Lyme disease diagnoses was more than double the cases obtained using notifiable disease surveillance data for the same period. Patients with a TBD Diagnoses were generally older (ages 45–59) and less racially diverse (96.3% white). Rickettsiosis diagnoses were reported more among male patients (55.2%), while Lyme disease diagnoses were higher among female patients (57.1%). Temporal data illustrated higher frequencies of diagnoses from May to July. Hot spot analysis identified a Lyme disease hot spot in northwest Indiana, while hotspots of Rickettsiosis and Other TBD Diagnoses category were identified in southwest Indiana. Extrapolated to the Indiana population, chi‐squared (χ2) tests of independence revealed that the observed distribution of TBD diagnoses in our data was significantly different from the expected distribution in the Indiana population‐based race, gender and age groups. Conclusions: Our study findings demonstrate that in Indiana, EHR provide a stable data source for elucidating TBD disease burden and for monitoring spatio‐temporal trends in TBD diagnoses. [ABSTRACT FROM AUTHOR]

Objectives: This work describes the process by which the quality of electronic health care data for a public health study was determined. The objectives were to adapt, develop, and implement data quality assessments (DQAs) based on the National Institutes of Health Pragmatic Trials Collaboratory (NIHPTC) data quality framework within the three domains of completeness, accuracy, and consistency, for an investigation into oral health care disparities of a preventive care program. Methods: Electronic health record data for eligible children in a dental accountable care organization of 30 offices, in Oregon, were extracted iteratively from January 1, 2014, through March 31, 2022. Baseline eligibility criteria included: children ages 0–18 with a baseline examination, Oregon home address, and either Medicaid or commercial dental benefits at least once between 2014 and 2108. Using the NIHPTC framework as a guide, DQAs were conducted throughout data element identification, extraction, staging, profiling, review, and documentation. Results: The data set included 91,487 subjects, 11 data tables comprising 75 data variables (columns), with a total of 6,861,525 data elements. Data completeness was 97.2%, the accuracy of EHR data elements in extracts was 100%, and consistency between offices was strong; 29 of 30 offices within 2 standard deviations of the mean (s = 94%). Conclusions: The NIHPTC framework proved to be a useful approach, to identify, document, and characterize the dataset. The concepts of completeness, accuracy, and consistency were adapted by the multidisciplinary research team and the overall quality of the data are demonstrated to be of high quality. [ABSTRACT FROM AUTHOR]

Pharmacogenomics (PGx) results can potentially guide the prescribing of dozens of medications; however, use of such results is often limited by the prescriber's awareness of results and knowledge of drug–gene interactions. Integration of PGx results with corresponding clinical decision support (CDS) in the electronic health record (EHR) is critical to facilitate genotype‐guided medication prescribing among all clinicians in an integrated health system. We describe our experience with developing an infrastructure to house PGx results and ensure actionable findings can be used at the point of care in real time using CDS. Upon transitioning to a new EHR, PGx‐related CDS alerts for more than 50 medications were developed using a systematic and multidisciplinary process where clinical pharmacist input was key. Multiple strategies were required to enable the storage of PGx results as discrete data from any laboratory source to drive CDS. EHR features were leveraged to link results from external laboratories to CDS and a homegrown translational software platform was developed to integrate results from the in‐house genomics laboratory directly into the EHR. These processes enabled PGx result integration for 2342 patients. As an example, among 356 patients who were genotyped for CYP2C19 to guide voriconazole dosing as part of a standard protocol in bone marrow transplant, 114 (32%) had CDS alerts for medications other than voriconazole presented to a clinician. For 50 of these patients, alerts were presented to a clinician of a different specialty who likely was not aware the patient had PGx results. Clinical pharmacists at institutions performing PGx testing are encouraged to champion the integration of PGx results and CDS in the EHR to maximize clinician awareness and evidence‐based use of PGx results. [ABSTRACT FROM AUTHOR]

Introduction Methods Results Conclusion In medical radiation science (MRS), radiology information systems (RISs) record patient information such as name, gender and birthdate. The purpose of RISs is to ensure the safety and well‐being of patients by recording patient data accurately. However, not all RISs appropriately capture gender, sex or other related information of transgender and gender‐diverse (TGD) patients, resulting in non‐inclusive and discriminatory care. This review synthesises the research surrounding the limitations of RISs preventing inclusivity and the features required to support inclusivity and improve health outcomes.Studies were retrieved from three electronic databases (Scopus, PubMed and Embase). A quality assessment was performed using the Johns Hopkins Nursing Evidence‐Based Practice Research and Non‐Research Evidence Appraisal Tools. A thematic analysis approach was used to synthesise the included articles.Eighteen articles were included based on the predetermined eligibility criteria. The pool of studies included in this review comprised primarily of non‐research evidence and reflected the infancy of this research field and the need for further empirical evidence. The key findings of this review emphasise how current systems do not record the patient's name and pronouns appropriately, conflate sex and gender and treat sex and gender as a binary concept.For current systems to facilitate inclusivity, they must implement more comprehensive information and data models incorporating sex and gender and be more flexible to accommodate the transient and fluid nature of gender. However, implementation of these recommendations is not without challenges. Additionally, further research focused on RISs is required to address the unique challenges MRS settings present to TGD patients. [ABSTRACT FROM AUTHOR]

Aims: To assess the predictive value of early‐stage physiological time‐series (PTS) data and non‐interrogative electronic health record (EHR) signals, collected within 24 h of ICU admission, for traumatic brain injury (TBI) patient outcomes. Methods: Using data from TBI patients in the multi‐center eICU database, we focused on in‐hospital mortality, neurological status based on the Glasgow Coma Score (mGCS) motor subscore at discharge, and prolonged ICU stay (PLOS). Three machine learning (ML) models were developed, utilizing EHR features, PTS signals collected 24 h after ICU admission, and their combination. External validation was performed using the MIMIC III dataset, and interpretability was enhanced using the Shapley Additive Explanations (SHAP) algorithm. Results: The analysis included 1085 TBI patients. Compared to individual models and existing scoring systems, the combination of EHR and PTS features demonstrated comparable or even superior performance in predicting in‐hospital mortality (AUROC = 0.878), neurological outcomes (AUROC = 0.877), and PLOS (AUROC = 0.835). The model's performance was validated in the MIMIC III dataset, and SHAP algorithms identified six key intervention points for EHR features related to prognostic outcomes. Moreover, the EHR results (All AUROC >0.8) were translated into online tools for clinical use. Conclusion: Our study highlights the importance of early‐stage PTS signals in predicting TBI patient outcomes. The integration of interpretable algorithms and simplified prediction tools can support treatment decision‐making, contributing to the development of accurate prediction models and timely clinical intervention. [ABSTRACT FROM AUTHOR]

INTRODUCTION: Alzheimer's disease (AD) is often misclassified in electronic health records (EHRs) when relying solely on diagnosis codes. This study aimed to develop a more accurate, computable phenotype (CP) for identifying AD patients using structured and unstructured EHR data. METHODS: We used EHRs from the University of Florida Health (UFHealth) system and created rule‐based CPs iteratively through manual chart reviews. The CPs were then validated using data from the University of Texas Health Science Center at Houston (UTHealth) and the University of Minnesota (UMN). RESULTS: Our best‐performing CP was "patient has at least 2 AD diagnoses and AD‐related keywords in AD encounters," with an F1‐score of 0.817 at UF, 0.961 at UTHealth, and 0.623 at UMN, respectively. DISCUSSION: We developed and validated rule‐based CPs for AD identification with good performance, which will be crucial for studies that aim to use real‐world data like EHRs. Highlights: Developed a computable phenotype (CP) to identify Alzheimer's disease (AD) patients using EHR data.Utilized both structured and unstructured EHR data to enhance CP accuracy.Achieved a high F1‐score of 0.817 at UFHealth, and 0.961 and 0.623 at UTHealth and UMN.Validated the CP across different demographics, ensuring robustness and fairness. [ABSTRACT FROM AUTHOR]

In a large academic medical center, processes for ordering and receiving biomarker testing to inform cancer treatment in non–small cell lung cancer varied by whether tests were conducted internally or externally. Lack of standardization in biomarker testing processes, despite the availability of electronic health record solutions, contributes to clinician burden and may increase risk of delays in receipt of testing results; therefore, efforts to streamline ordering processes may benefit health systems. [ABSTRACT FROM AUTHOR]

Introduction: Shared decision‐making (SDM) is a method of care by which patients and clinicians work together to co‐create a plan of care. Electronic health record (EHR) integration of SDM tools may increase adoption of SDM. We conducted a "lightweight" integration of a freely available electronic SDM tool, CV Prevention Choice, within the EHRs of three healthcare systems. Here, we report how the healthcare systems collaborated to achieve integration. Methods: This work was conducted as part of a stepped wedge randomized pragmatic trial. CV Prevention Choice was developed using guidelines for HTML5‐based web applications. Healthcare systems integrated the tool in their EHR using documentation the study team developed and refined with lessons learned after each system integrated the electronic SDM tool into their EHR. CV Prevention Choice integration populates the tool with individual patient data locally without sending protected health information between the EHR and the web. Data abstraction and secure transfer systems were developed to manage data collection to assess tool implementation and effectiveness outcomes. Results: Time to integrate CV Prevention Choice in the EHR was 12.1 weeks for the first system, 10.4 weeks for the second, and 9.7 weeks for the third. One system required two 1‐hour meetings with study team members and two healthcare systems required a single 1‐hour meeting. Healthcare system information technology teams collaborated by sharing information and offering improvements to documentation. Challenges included tracking CV Prevention Choice use for reporting and capture of combination medications. Data abstraction required refinements to address differences in how each healthcare system captured data elements. Conclusion: Targeted documentation on tool features and resource mapping supported collaboration of IT teams across healthcare systems, enabling them to integrate a web‐based SDM tool with little additional research team effort or oversight. Their collaboration helped overcome difficulties integrating the web application and address challenges to data harmonization for trial outcome analyses. [ABSTRACT FROM AUTHOR]

Background and Objectives: Use of algorithms to identify patients with high data‐continuity in electronic health records (EHRs) may increase study validity. Practical experience with this approach remains limited. Methods: We developed and validated four algorithms to identify patients with high data continuity in an EHR‐based data source. Selected algorithms were then applied to a pharmacoepidemiologic study comparing rates of COVID‐19 hospitalization in patients exposed to insulin versus noninsulin antidiabetic drugs. Results: A model using a short list of five EHR‐derived variables performed as well as more complex models to distinguish high‐ from low‐data continuity patients. Higher data continuity was associated with more accurate ascertainment of key variables. In the pharmacoepidemiologic study, patients with higher data continuity had higher observed rates of the COVID‐19 outcome and a large unadjusted association between insulin use and the outcome, but no association after propensity score adjustment. Discussion: We found that a simple, portable algorithm to predict data continuity gave comparable performance to more complex methods. Use of the algorithm significantly impacted the results of an empirical study, with evidence of more valid results at higher levels of data continuity. Plain Language Summary: When doing research using electronic health records, one big problem is that sometimes information is missing or not consistently recorded. There are methods (algorithms) that can help identify which patients' records are more complete and reliable. However, it's not clear how much these methods actually improve the results of studies about how drugs affect populations (pharmacoepidemiologic studies). This manuscript demonstrates that using a straightforward and easy‐to‐use method seems to make the results of such a drug study more accurate. [ABSTRACT FROM AUTHOR]

Purpose Data sources Data synthesis Conclusions Implications for nursing practice To identify and synthesize evidence regarding the documented relationship between the standardized nursing terminologies and the unfinished nursing care phenomenon.A systematic review according to the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses guidelines. PubMed, Scopus, and Cumulative Index to Nursing and Allied Health Literature Complete databases were last consulted on November 27, 2023. The review included primary quantitative studies that reported an association between recognized standardized nursing terminologies and unfinished nursing care. Two researchers completedtitle and abstract and full‐text screening.Our search identified 149 citations. A full‐text review of one paper was undertaken. No studies met our inclusion criteria. We report an empty review.Standardized nursing terminologies and Unfinished Care are two sides of the same coin: despite their potential commonalities, no studies have documented their potential links. Digital systems, such as electronic health records and decision support systems, could foster this linkage.This review suggests that linking the conceptual frameworks can promote the diffusion of standardized nursing terminologies in clinical practice and increase accuracy in the measurement of Unfinished Care. This synergy could promote the contribution of nursing knowledge to patient care, nursing visibility, and be beneficial to clinical nurses, managers, and healthcare systems to international level. [ABSTRACT FROM AUTHOR]

Turner syndrome (TS) is a genetic condition occurring in ~1 in 2000 females characterized by the complete or partial absence of the second sex chromosome. TS research faces similar challenges to many other pediatric rare disease conditions, with homogenous, single‐center, underpowered studies. Secondary data analyses utilizing electronic health record (EHR) have the potential to address these limitations; however, an algorithm to accurately identify TS cases in EHR data is needed. We developed a computable phenotype to identify patients with TS using PEDSnet, a pediatric research network. This computable phenotype was validated through chart review; true positives and negatives and false positives and negatives were used to assess accuracy at both primary and external validation sites. The optimal algorithm consisted of the following criteria: female sex, ≥1 outpatient encounter, and ≥3 encounters with a diagnosis code that maps to TS, yielding an average sensitivity of 0.97, specificity of 0.88, and C‐statistic of 0.93 across all sites. The accuracy of any estradiol prescriptions yielded an average C‐statistic of 0.91 across sites and 0.80 for transdermal and oral formulations separately. PEDSnet and computable phenotyping are powerful tools in providing large, diverse samples to pragmatically study rare pediatric conditions like TS. [ABSTRACT FROM AUTHOR]

Purpose: As the first step in monitoring and evaluating day‐to‐day glaucoma care, this study reports all real‐world data recorded during the first full year after the implementation of a prototype for glaucoma‐specific structured electronic healthcare record (EHR). Methods: In 2019, 4618 patients visited Tays Medical Glaucoma Clinic at Tays Eye Centre, Tampere University Hospital, Finland, that serves a population of 0.53 M. Patient data were entered into a glaucoma‐specific EHR by trained nurses to be checked by glaucoma specialists. Tays Eye Centre follows the Finnish Current Care Guideline for glaucoma in which glaucoma is defined using a '2 out of 3' rule, that is, ≥2 findings evaluated as glaucomatous in optic nerve head (ONH), retinal nerve fibre layer (RNFL) and visual field (VF). Results: The clinical evaluations of ONH, RNFL and VF were recorded in 95%–100% of all eyes. ONH was evaluated as glaucomatous more often (44%) than RNFL (33%) and VF tests (30%). Progressive changes in any of the three tests were recorded in 35% of the '≥2/3 glaucoma group' compared to 2%–9% in the other groups. The mean IOP at visit was 15 mmHg. The mean target IOP was 17 mmHg, and it was recorded in 94% of eyes. Conclusion: The developed structured data presentation enables comparisons between different population‐based real‐world glaucoma data sets and glaucoma clinics. Compared to a data set from the UK, the proportion of glaucoma suspicion‐related visits was smaller in Tays Eye Centre and test intervals were longer. [ABSTRACT FROM AUTHOR]

Objective: Social risks complicate patients' ability to manage their conditions and access healthcare, but their association with health expenditures is not well established. To identify patient‐reported social risk, behavioral, and health factors associated with health expenditures in Veterans Affairs (VA) patients at high risk for hospitalization or death. Data Sources, Study Setting, and Study Design: Prospective cohort study among high‐risk Veterans obtaining VA care. Patient‐reported social risk, function, and other measures derived from a 2018 survey sent to 10,000 VA patients were linked to clinical and demographic characteristics extracted from VA data. Response‐weighted generalized linear and marginalized two‐part models were used to examine VA expenditures (total, outpatient, medication, inpatient) 1 year after survey completion in adjusted models. Principal Findings: Among 4680 survey respondents, the average age was 70.9 years, 6.3% were female, 16.7% were African American, 20% had body mass index ≥35, 42.4% had difficulty with two or more basic or instrumental activities of daily living, 19.3% reported transportation barriers, 12.5% reported medication insecurity and 21.8% reported food insecurity. Medication insecurity was associated with lower outpatient expenditures (−$1859.51 per patient per year, 95% confidence interval [CI]: −3200.77 to −518.25) and lower total expenditures (−$4304.99 per patient per year, 95% CI: −7564.87 to −1045.10). Transportation barriers were negatively associated with medication expenditures (−$558.42, 95% CI: −1087.93 to −31.91). Patients with one functional impairment had higher outpatient expenditures ($2997.59 per patient year, 95% CI: 1185.81–4809.36) than patients without functional impairments. No social risks were associated with inpatient expenditures. Conclusions: In this study of VA patients at high risk for hospitalization and mortality, few social and functional measures were independently associated with the costs of VA care. Individuals with functional limitations and those with barriers to accessing medications and transportation may benefit from targeted interventions to ensure that they are receiving the services that they need. [ABSTRACT FROM AUTHOR]

The Ending the HIV Epidemic initiative is poised to eradicate HIV through increasing screening and linkage to care. Despite this, the rate of HIV testing remains inadequate, and effective preventive measures like pre‐exposure prophylaxis (PrEP) are not adequately prescribed. A retrospective chart review was conducted to include 2017 through July 2022 from a large nonprofit health care system in the Midwest. Inclusion criteria included an HIV‐negative diagnosis between 2017 and July 2022. Additional information includes gender, age, race/ethnicity, the primary payment method, the facility where screening occurred, history of PrEP prescription, and the provider who documented sexual health screening. Most patients were female (73%, n = 3366), followed by 27% (n = 1242) who identified as male. The majority identified as white (52.4%, n = 2415), and patients who identified as Black represented 45.3% (n = 2087) of the sample. Of the participants in the sample, n = 3030 (65.8%) did not have a documented sexual health assessment at the time of HIV screening. Black patients were 0.40 times less likely to report a PrEP prescription than their white counterparts. Patients screened by the provider and identified with infectious disease via a sexual mode of transmission demonstrated three times increased odds of being prescribed PrEP. This research highlights the importance of updating medical records systems to capture salient sexual health factors. Ongoing professional development should be made readily available so providers can conduct comprehensive sexual health assessments. [ABSTRACT FROM AUTHOR]

Purpose: To develop a natural language processing (NLP) tool to extract forced vital capacity (FVC) values from electronic health record (EHR) notes in patients with rheumatoid arthritis‐interstitial lung disease (RA‐ILD). Methods: We selected RA‐ILD patients (n = 7485) in the Veterans Health Administration (VA) between 2000 and 2020 using validated ICD‐9/10 codes. We identified numeric values in proximity to FVC string patterns from clinical notes in the EHR. Subsequently, we performed processing steps to account for variability in note structure, related pulmonary function test (PFT) output, and values copied across notes, then assigned dates from linked administrative procedure records. NLP‐derived FVC values were compared to values recorded directly from PFT equipment available on a subset of patients. Results: We identified 5911 FVC values (n = 1844 patients) from PFT equipment and 15 383 values (n = 4982 patients) by NLP. Among 2610 date‐matched FVC values from NLP and PFT equipment, 95.8% of values were within 5% predicted. The mean (SD) difference was 0.09% (5.9), and values strongly correlated (r = 0.94, p < 0.001), with a precision of 0.87 (95% CI 0.86, 0.88). NLP captured more patients with longitudinal FVC values (n = 3069 vs. n = 1164). Mean (SD) change in FVC %‐predicted per year was similar between sources (−1.5 [30.0] NLP vs. −0.9 [16.6] PFT equipment; standardized response mean = 0.05 for both). Conclusions: NLP of EHR notes increases the capture of accurate, longitudinal FVC values by three‐fold over PFT equipment. Use of this NLP tool can facilitate pharmacoepidemiologic research in RA‐ILD and other lung diseases by capturing this critical measure of disease severity. [ABSTRACT FROM AUTHOR]

Objective: Pediatric status epilepticus is one of the most frequent pediatric emergencies, with high mortality and morbidity. Utilizing electronic health records (EHRs) permits analysis of care approaches and disease outcomes at a lower cost than prospective research. However, reviewing EHR manually is time intensive. We aimed to compare refractory status epilepticus (rSE) cases identified by human EHR review with a natural language processing (NLP)‐assisted rSE screen followed by a manual review. Methods: We used the NLP screening tool Document Review Tool (DrT) to generate regular expressions, trained a bag‐of‐words NLP classifier on EHRs from 2017 to 2019, and then tested our algorithm on data from February to December 2012. We compared results from manual review to NLP‐assisted search followed by manual review. Results: Our algorithm identified 1528 notes in the test set. After removing notes pertaining to the same event by DrT, the user reviewed a total number of 400 notes to find patients with rSE. Within these 400 notes, we identified 31 rSE cases, including 12 new cases not found in manual review, and 19 of the 20 previously identified cases. The NLP‐assisted model found 31 of 32 cases, with a sensitivity of 96.88% (95% CI = 82%–99.84%), whereas manual review identified 20 of 32 cases, with a sensitivity of 62.5% (95% CI = 43.75%–78.34%). Significance: DrT provided a highly sensitive model compared to human review and an increase in patient identification through EHRs. The use of DrT is a suitable application of NLP for identifying patients with a history of recent rSE, which ultimately contributes to the implementation of monitoring techniques and treatments in near real time. [ABSTRACT FROM AUTHOR]

INTRODUCTION: Care partners are at the forefront of dementia care, yet little is known about patient portal use in the context of dementia diagnosis. METHODS: We conducted an observational cohort study of date/time‐stamped patient portal use for a 5‐year period (October 3, 2017–October 2, 2022) at an academic health system. The cohort consisted of 3170 patients ages 65+ with diagnosed dementia with 2+ visits within 24 months. Message authorship was determined by manual review of 970 threads involving 3065 messages for 279 patients. RESULTS: Most (71.20%) older adults with diagnosed dementia were registered portal users but far fewer (10.41%) had a registered care partner with shared access. Care partners authored most (612/970, 63.09%) message threads, overwhelmingly using patient identity credentials (271/279, 97.13%). DISCUSSION: The patient portal is used by persons with dementia and their care partners. Organizational efforts that facilitate shared access may benefit the support of persons with dementia and their care partners. Highlights: Patient portal registration and use has been increasing among persons with diagnosed dementia.Two thirds of secure messages from portal accounts of patients with diagnosed dementia were identified as being authored by care partners, primarily using patient login credentials.Care partners who accessed the patient portal using their own identity credentials through shared access demonstrate similar levels of activity to patients without dementia.Organizational initiatives should recognize and support the needs of persons with dementia and their care partners by encouraging awareness, registration, and use of proper identity credentials, including shared, or proxy, portal access. [ABSTRACT FROM AUTHOR]

Introduction: Unhoused individuals have high rates of suicidal ideation (SI) and suicidal behaviors (SB), but few have studied the relative timing of homelessness and SI/SB. Our study examines the potential to use state‐wide electronic health record data from Rhode Island's health information exchange (HIE) to identify temporal relationships, service utilization, and associations of SI/SB among unhoused individuals. Methods: We use timestamped HIE data for 5368 unhoused patients to analyze service utilization and the relative timing of homelessness versus SI/SB onset. Multivariable models identified associations of SI/SB, hospitalization, and repeat acute care utilization within 30 days from clinical features representing 10,000+ diagnoses captured within the HIE. Results: The onset of SI typically precedes homelessness onset, while the onset of SB typically follows. Weekly rates of suicide‐related service utilization increased over 25 times the baseline rate during the week before and after homelessness onset. Over 50% of encounters involving SI/SB result in hospitalization. Of those engaging in acute care for suicide‐related reasons, we found high rates of repeat acute care encounters. Conclusion: HIEs are a particularly valuable resource for understudied populations. Our study demonstrates how longitudinal, multi‐institutional data from an HIE can be used to characterize temporal associations, service utilization, and clinical associations of SI and behaviors among a vulnerable population at scale. Increasing access to services that address co‐occurring SI/SB, mental health, and substance use is needed. [ABSTRACT FROM AUTHOR]

Objective: To examine trends in diagnosis of headache and migraine in a large pediatric neurology cohort, and test whether an electronic health record (EHR)‐integrated headache questionnaire can increase specificity of diagnosis and likelihood of prescribing migraine treatment. Background: Under‐diagnosis of migraine contributes to the burden of disease. As we founded our Pediatric Headache Program in 2013, we recognized that the proportion of patients with headache who were given a diagnosis of migraine was much lower than expected. Methods: We developed a patient headache questionnaire, initially on paper (2013–2014), then in an electronic database (2014–2016), and finally integrated into our electronic health record (pilot: 2016, full: May 2017). We compared diagnoses and prescribed treatments for new patients who were given a headache diagnosis, looking at trends in the proportion of patients given specific diagnoses (migraine, etc.) versus the non‐specific diagnosis, "headache." Next, we conducted a prospective cohort study to test for association between provider use of the form and the presence of a specific diagnosis, then for an association between specific diagnosis and prescription of migraine treatment. Results: Between July 2011 and December 2022 the proportion of new headache patients who were given a diagnosis of migraine increased 9.7% and non‐specific headache diagnoses decreased 21.0%. In the EHR cohort (June 2017–December 2022, n = 15,122), use of the provider form increased the rate of specific diagnosis to 87.2% (1839/2109) compared to 75.5% (5708/7560) without a patient questionnaire, nearly doubling the odds of making a specific diagnosis (odds ratio [OR] 1.90, 95% confidence interval [CI]: 1.65–2.19). Compared to those given only a non‐specific headache diagnosis who were prescribed a migraine therapy 53.7% (1766/3286) of the time, 75.3% (8914/11836) of those given a specific diagnosis received a migraine therapy, more than doubling the odds of prescription (OR 2.39, 95% CI: 2.20–2.60). Conclusions: Interventions to improve specificity of diagnosis were effective and led to increased rates of prescription of migraine treatments. These results have been sustained over several years. This headache questionnaire was adapted into the Foundation system of EpicCare, so it is broadly available as a clinical and research tool for institutions that use this EHR software. [ABSTRACT FROM AUTHOR]

Purpose: Improved hypereosinophilic syndrome (HES) ascertainment in electronic health record (EHR) databases may improve disease understanding and management. An algorithm to ascertain and characterize this rare condition was therefore developed and validated. Methods: Using the UK clinical practice research datalink (CPRD)‐Aurum database linked to the hospital episode statistics database (Admitted Patient Care data) from Jan 2012 to June 2019, this cross‐sectional study ascertained patients with a specific HES code (index). Patients with HES were matched (age, sex and index date) 1:29 with a non‐HES cohort. An algorithm was developed by identifying pre‐defined variables differing between cohorts; model‐fitting using Firth logistic regression and statistical determination of the top‐five performing models; and internal validation using Leave‐One‐Out Cross Validation. Final model sensitivity and specificity were determined at an 80% probability threshold. Results: The HES and non‐HES cohorts included 88 and 2552 patients, respectively; 270 models with four variables each (treatment used for HES, asthma code, white blood cell condition code, and blood eosinophil count [BEC] code) plus age and sex variables were tested. Of the top five models, the sensitivity model performed best (sensitivity, 69% [95% CI: 59%, 79%]; specificity, >99%). The strongest predictors of HES versus non‐HES cases (odds >1000 times greater) were an ICD‐10 code for white blood cell disorders and a BEC ≥1500 cells/μL in the 24 months pre‐index. Conclusions: Using a combination of medical codes, prescribed treatments data and laboratory results, the algorithm can help ascertain patients with HES from EHR databases; this approach may be useful for other rare diseases. [ABSTRACT FROM AUTHOR]

Objective: The main purposes of this study were to validate the epilepsy diagnosis in incident epilepsy cases in the Danish National Patient Registry (DNPR), which contains information on nearly 9 000 000 individuals, and to identify persons in the validated cohort who fulfilled the International League Against Epilepsy (ILAE) criteria for drug‐resistant epilepsy (DRE). Methods: We reviewed a random sample of medical records from all individuals registered with a first diagnosis of epilepsy (International Classification of Diseases, 10th Revision [ICD‐10]: G40) or seizures (ICD‐10: G41, R56, or F445) in the Central Denmark Region from 2010 to 2019. In persons with a validated incident epilepsy diagnosis, we determined the proportion with DRE at the latest contact. We performed logistic regression analyses to identify clinical factors that correlated with risk of DRE. Results: Of 20 723 persons with a first diagnosis of epilepsy (n = 11 812) or seizures (n = 8911), we reviewed the medical records of n = 1067 with incident epilepsy and n = 610 with incident seizures. Among those with a register diagnosis of epilepsy, the diagnosis was confirmed in 838 cases (45% females, mean age at onset = 42.4 years), providing a positive predictive value (PPV) of 79% (95% confidence interval [CI] = 76%–81%). The PPV of focal epilepsy was 86% (95% CI = 82%–89%), and the PPV of generalized epilepsy was 71% (95% CI = 61%–80%). Of 740 patients with confirmed incident epilepsy and ≥1 year of follow‐up, 103 (14%) fulfilled the definition of DRE, 476 (64%) were drug responsive, and 161 (22%) had undefined responsiveness. In multivariable logistic regression analysis, early age at epilepsy onset, cognitive impairment, and a history of status epilepticus were associated with DRE. Significance: In the DNPR, we found a PPV of the epilepsy diagnosis of 79%. Among persons with confirmed epilepsy, 14% fulfilled ILAE criteria for DRE. Early age at epilepsy onset, cognitive impairment, and a history of status epilepticus were independently associated with drug resistance. [ABSTRACT FROM AUTHOR]

Objective: We designed a quality improvement (QI) project to improve rates of documented folic acid supplementation counseling for adolescent females with epilepsy, consistent with a quality measure from the American Academy of Neurology and American Epilepsy Society. Our SMART aim was to increase the percentage of visits at which folic acid counseling was addressed from our baseline rate of 23% to 50% by July 1, 2020. Methods: This initiative was conducted in female patients ≥12 years old with epilepsy who were prescribed daily antiseizure medication and were seen by the 13 providers in our Neurology QI Program. Using provider interviews, we undertook a root cause analysis of low counseling rates and identified the following main factors: insufficient time during clinic visit to counsel, lack of provider knowledge, and forgetting to counsel. Countermeasures were designed to address these main root causes and were implemented through iterative plan–do–study–act (PDSA) cycles. Interventions included provider education and features within the electronic health record, which were introduced sequentially, culminating in the creation of a best practice advisory (BPA). We performed biweekly chart reviews of visits for applicable patients to establish baseline performance rate and track progress over time. We used a statistical process control p‐chart to analyze the outcome measure of documented counseling. As a balancing measure, clinicians were surveyed using the Technology Adoption Model survey to assess acceptance of the BPA. Results: From September 2019 to August 2022, the QI team improved rates of documented folic acid counseling from 23% to 73% through several PDSA cycles. This level of performance has been sustained over time. The most successful and sustainable intervention was the BPA. Provider acceptance of the BPA was overall positive. Significance: We successfully used QI methodology to improve and sustain our rates of documented folic acid supplementation counseling for adolescent females with epilepsy. [ABSTRACT FROM AUTHOR]

Background: We investigated the association between body mass index (BMI) and obesity‐related cancer risk among individuals with/without incident hypertension (HTN), type 2 diabetes mellitus (T2DM), and cardiovascular disease (CVD) and the joint associations of overweight/obesity (BMI ≥25 kg/m2) and each cardiometabolic condition with obesity‐related cancer risk Methods: We conducted a population‐based cohort (n = 1,774,904 individuals aged ≥40 years and free of cancer and cardiometabolic conditions at baseline) study between 2010 and 2018 with electronic health records from Spain. Our main outcome measures were hazard ratios (HRs) for incident obesity‐related cancers and relative excess risk due to interaction (RERI). Results: A total of 38,082 individuals developed obesity‐related cancers after a median of 8 years of follow‐up. The positive association between BMI and obesity‐related cancer risk was similar among individuals free of cardiometabolic conditions (hazard ratio, HR per 5 kg/m2: 1.08, 95% confidence interval, CI: 1.06–1.10) and with incident HTN (1.05, 1.01–1.08). The association among those with incident T2DM was null (0.98, 0.93–1.03). There was a positive additive interaction between overweight/obesity and CVD (relative excess risk due to interaction [RERI]: 0.19 [0.09, 0.30]), meaning that the combined association was 0.19 more than the sum of the individual associations. In contrast, a RERI of −0.24 (−0.28, −0.20) was observed for the combined association between overweight/obesity and T2DM. Conclusions: Public health strategies to reduce overweight can help prevent cancer cases among the general population and individuals with incident HTN/CVD. Further, weight‐loss interventions seem to lead to a greater cancer risk reduction among individuals with CVD. [ABSTRACT FROM AUTHOR]

Background and Objective: Electronic medical record (EMR) databases can facilitate epidemiology research in various diseases including bronchiectasis. Given the diagnostic challenges of bronchiectasis, the validity of the coding in EMR requires clarification. We aimed to assess the validity of International Classification of Diseases, 9th Revision (ICD‐9) code algorithms for identifying bronchiectasis in the territory‐wide electronic medical health record system of Clinical Data Analysis and Reporting System (CDARS) in Hong Kong. Materials and Methods: Adult patients who had the diagnosis of bronchiectasis input from Queen Mary Hospital in 2011–2020 were identified using the ICD‐9 code of 494 by CDARS. All patients who had high resolution computed tomography (HRCT) were reviewed by respiratory specialists to confirm the presence of bronchiectasis on HRCT. Results: A total of 19 617 patients who had the diagnostic code of bronchiectasis among all public hospitals in Hong Kong and 1866 in Queen Mary Hospital in the same period. Six hundred and forty‐eight cases were randomly selected and validated using medical record and HRCT review by a respiratory specialist. The overall positive predictive value (PPV) was 92.7% (95% CI 90.7–94.7). Conclusions: This was the first ICD‐9 coding validation for bronchiectasis in Hong Kong CDARS. Our study demonstrated that using ICD‐9 code of 494 was reliable to support utility of CDARS database for further clinical research on bronchiectasis. [ABSTRACT FROM AUTHOR]

Introduction: With the increasing complexity of haemophilia care and the advent of numerous therapeutic innovations, there is an unmet need for documentation and data collection tools tailored to people with haemophilia (PwH). To date, no fully integrated haemophilia‐specific electronic health record (EHR) has been described in the literature. Aim: To evaluate the feasibility of integrating a haemophilia‐specific navigator into the Epic EHR. Methods: Based on clinical experience and registry datasets, we identified key variables describing both PwH and carriers of haemophilia. These were then incorporated into a REDCap database, which served as a starting point for the development of a comprehensive haemophilia flowsheet. We built a dedicated haemophilia navigator within Epic that includes a flowsheet featuring up to 212 variables, as well as customised note templates and patient lists integrating data from the haemophilia flowsheet. Results: It was feasible to develop a haemophilia navigator within Epic over the course of 12 months. The navigator's flowsheet enables systematic and comprehensive clinical assessment of PwH and carriers, while customised patient lists provide a quick summary of each patient's profile to the haemophilia treatment centre staff and highlight issues that require an intervention. In our clinical practice, patients actively participated in the new documentation process and responded positively to the navigator. Conclusion: Adapting EHRs to the needs of PwH and carriers promotes holistic care for this population and provides an opportunity for patient empowerment. Such haemophilia‐specific EHRs are expected to promote standardisation of care and facilitate the collection of registry data on a national and international level. [ABSTRACT FROM AUTHOR]

Objective: To determine whether an electronic health record (EHR) system can be used to identify cases of aspirin‐exacerbated respiratory disease (AERD) in an area outside of a regional referral center with low rates of aspirin desensitization therapy. Study Design: Retrospective chart review single academic tertiary care hospital. Setting: Single‐site academic tertiary care hospital. Methods: Using Epic's SlicerDicer function, an algorithm was created and applied to all patient charts from 2013 to 2021. The algorithm was as follows: "Allergy/Contraindication to NSAIDs OR aspirin" AND "Diagnosis of Nasal polyp AND "Diagnosis of Asthma." Clinical data including demographics, NSAID reaction, and specialist involvement was collected. Results: A total of 54 potential cases of AERD were identified. Thirty‐two were determined to have AERD after chart review, yet 12 of these patients (37.5%) had no mention of AERD within the chart. The 54 patients were stratified into 2 cohorts based on reaction to NSAIDs: respiratory (n = 29) or unspecified (n = 25). Of the patients in the respiratory reaction group, 26 were found to have clinical AERD, demonstrating a positive predictive values (PPV) of 89.7%. The overall PPV was 59.3%. Those with a respiratory reaction to NSAIDS listed in the EHR were more likely to have clinical AERD (odds ratio 27.44; confidence interval 6.08‐123.85; p < 0.0001). Only 2 patients (6.3%) underwent aspirin desensitization. Conclusion: AERD remains under‐diagnosed in the study population. The informatics algorithm presented here has a high positive predictive value for identifying clinical AERD patients in a geographical area with low rates of aspirin desensitization and may aid in identifying candidates for expanded treatment options. [ABSTRACT FROM AUTHOR]

The augmented randomized controlled trial (RCT) with hybrid control arm includes a randomized treatment group (RT), a smaller randomized control group (RC), and a large synthetic control (SC) group from real‐world data. This kind of trial is useful when there is logistics and ethics hurdle to conduct a fully powered RCT with equal allocation, or when it is necessary to increase the power of the RCT by incorporating real‐world data. A difficulty in the analysis of augmented RCT is that the SC and RC may be systematically different in the distribution of observed and unmeasured confounding factors, causing bias when the two control groups are analyzed together as hybrid controls. We propose to use propensity score (PS) analysis to balance the observed confounders between SC and RC. The possible bias caused by unmeasured confounders can be estimated and tested by analyzing propensity score adjusted outcomes from SC and RC. We also propose a partial bias correction (PBC) procedure to reduce bias from unmeasured confounding. Extensive simulation studies show that the proposed PS + PBC procedures can improve the efficiency and statistical power by effectively incorporating the SC into the RCT data analysis, while still control the estimation bias and Type I error inflation that might arise from unmeasured confounding. We illustrate the proposed statistical procedures with data from an augmented RCT in oncology. [ABSTRACT FROM AUTHOR]

Background: Despite the increased availability and use of novel therapies for multiple myeloma, early mortality is a pervasive challenge with a significant impact on older adults. Reported rates and predictors of early mortality have varied in the literature, with most studies seldom focusing on community‐treated patients. Methods: In this retrospective cohort analysis of a real‐world electronic health record–derived deidentified database of 7512 patients newly diagnosed with multiple myeloma between January 1, 2011, and February 2, 2021, and treated primarily in US‐based community oncology practices, factors associated with early mortality (defined as death within 6 months after the multiple myeloma diagnosis) were examined with the use of binary logistic regression. Results: The median age was 70 years overall. We found an overall early mortality rate of 8.3%, with 73% of early deaths occurring in those aged ≥70 years. Among the early deaths, only 49 patients (8.7%) had documented disease progression before death (median time to progression, 30 days [interquartile range, 7–53 days]). Baseline factors associated with higher odds of early mortality included an Eastern Cooperative Oncology Group performance status (ECOG PS) ≥ 2, Revised International Staging System (R‐ISS) stage III, an age ≥ 70 years, receipt of proteasome inhibitor–doublet therapy, a light‐chain isotype, and the presence of renal dysfunction (estimated glomerular filtration rate < 30 mL/min). Among those aged ≥70 years, ECOG PS ≥ 2 and R‐ISS stage III remained the strongest predictors of early mortality. Conclusions: Early mortality disproportionately affects older adults (aged ≥70 years) with multiple myeloma. Interventions to support this population are needed to reduce disparate survival outcomes. Plain language summary: Factors associated with an increased risk of dying within 6 months (early mortality) of a new diagnosis of multiple myeloma (MM) among 7512 mostly community‐treated patients with MM were evaluated.The early mortality rate was 8.3%; among those deaths, 49 patients (8.7%) had documented evidence of MM progression before death.The risk of early mortality was greatest for older patients (aged ≥70 years) and those with a poor performance status, poor kidney function, a higher disease stage, and light‐chain MM and those receiving two‐drug MM therapies.These findings highlight the need for supportive interventions geared toward older adults with MM. Approximately 9% of adults newly diagnosed with multiple myeloma will die within 6 months. Most early deaths occur in those aged 70 years or older and among those with advanced disease, a poor performance status, and kidney dysfunction and those who have received a proteasome inhibitor‐based doublet regimen. [ABSTRACT FROM AUTHOR]

Objective: Electronic medical records allow for retrospective clinical research with large patient cohorts. However, epilepsy outcomes are often contained in free text notes that are difficult to mine. We recently developed and validated novel natural language processing (NLP) algorithms to automatically extract key epilepsy outcome measures from clinic notes. In this study, we assessed the feasibility of extracting these measures to study the natural history of epilepsy at our center. Methods: We applied our previously validated NLP algorithms to extract seizure freedom, seizure frequency, and date of most recent seizure from outpatient visits at our epilepsy center from 2010 to 2022. We examined the dynamics of seizure outcomes over time using Markov model‐based probability and Kaplan–Meier analyses. Results: Performance of our algorithms on classifying seizure freedom was comparable to that of human reviewers (algorithm F1 =.88 vs. human annotator κ =.86). We extracted seizure outcome data from 55 630 clinic notes from 9510 unique patients written by 53 unique authors. Of these, 30% were classified as seizure‐free since the last visit, 48% of non‐seizure‐free visits contained a quantifiable seizure frequency, and 47% of all visits contained the date of most recent seizure occurrence. Among patients with at least five visits, the probabilities of seizure freedom at the next visit ranged from 12% to 80% in patients having seizures or seizure‐free at the prior three visits, respectively. Only 25% of patients who were seizure‐free for 6 months remained seizure‐free after 10 years. Significance: Our findings demonstrate that epilepsy outcome measures can be extracted accurately from unstructured clinical note text using NLP. At our tertiary center, the disease course often followed a remitting and relapsing pattern. This method represents a powerful new tool for clinical research with many potential uses and extensions to other clinical questions. [ABSTRACT FROM AUTHOR]

Background: Obtaining accurate medication histories at transitions of care is challenging, but important for patient safety. Prescription exchange services (PES) securely transfer electronic prescription and dispensing records between prescribers and pharmacies, which is potentially useful data for determining medication histories. Aim: To evaluate the accuracy of PES‐derived medication histories. Methods: Prospective observational study, at two Australian tertiary‐referral health services. A convenience sample of adult inpatients was recruited. The main outcome measure was: proportion of patients with ≥1 errors in their PES‐derived pre‐admission medication histories, compared with gold‐standard best‐possible medication histories, including prescribed and non‐prescribed medications, obtained by pharmacists using multiple sources including patient/carer interview. Results: Of 154 patients (median age 76 years; interquartile range (IQR) 64–84 years; median 10.0 pre‐admission medications; IQR 6.0–14.0), 153 (99.4%) had ≥1 errors in their PES‐derived medication history (median 6.0 errors per patient; IQR 4.0–9.0). Excluding when‐required medications, 146 (94.8%) patients had >1 errors (median 4.0 errors per patient; IQR 2.0–6.0). Omission was the most common error, affecting 549 (33.3%) of 1648 current medications (median 3.0; IQR 1.0–5.0 per patient); 396 (72.1%) omissions were over‐the‐counter medicines. Dose‐regimen errors affected 276 (25.1%) of 1099 current medications captured in PES‐derived medication histories (median 1.0 error per patient; IQR 0.0–3.0). Commission errors (medications in PES‐derived histories that were not current) affected 224 (16.9%) of 1323 medications (median 1.0 error per patient; IQR 1.0–2.0). Conclusions: Medication histories derived solely from a cloud‐based medication record repository had a high error rate compared with patients' actual medication use. Like all medication history sources, data from cloud‐based repositories need to be verified with additional sources including the patient and/or their carer. [ABSTRACT FROM AUTHOR]

Aim: The aim of this study was to describe what psychosocial factors associated with postoperative persistent pain can be found in electronic health records of patients with breast cancer, and which of these factors that may be used in the development of a decision‐support system algorithm to better support health professionals in their clinical work. Design: A qualitative descriptive study. Methods: A retrospective electronic health record review was done using manual semantic annotation. A set of 101 records of patients with breast cancer were selected by computerized random sampling. The data were analysed with deductive content analysis. Results: A total of 337 different expressions describing psychosocial factors associated with postoperative persistent pain were identified from the documentation done in the electronic health records. These regarded psychological strength and resilience, social factors, emotional factors, anxiety, sleep‐related factors and depression. No records were found dealing with pain catastrophizing. Although psychosocial factors associated with postoperative persistent pain were documented in the electronic health records, documentation about such factors was not found in all patient's records, nor was the documentation done in a systematic manner. Conclusions: The findings show that there is potential to use electronic health records as information source in the development of decision‐support system algorithms to better support nurses in the identification of patients at risk of developing postoperative persistent pain. However, the documentation quality needs to be acknowledged in the application of decision support systems, which are built on information extracted from electronic health records. Future work is needed to standardize documentation practices and assess the comprehensiveness of the documentation. [ABSTRACT FROM AUTHOR]

Research Objective: To identify patient-reported social risk, behavioral, and health factors associated with emergency department (ED) utilization in high-risk Veterans Affairs (VA) patients.Data Sources: Patient survey, VA, Medicare data.Study Design: Prospective cohort study using multivariable logistic regression to identify patient-reported factors associated with all-cause and ambulatory care sensitive condition (ACSC)-related ED visits among VA patients at high risk for hospitalization or death.Data Extraction Methods: Patient-reported measures derived from a 2018 survey sent to 10,000 VA patients; clinical and demographic characteristics derived from VA data; ED visits derived from VA and Medicare claims.Principal Findings: Among 4680 survey respondents, 52.5% and 16.3% experienced an all-cause or ACSC-related ED visit in the following year, respectively. An ED visit was more likely among individuals with functional status limitations (6.0% points (Confidence Interval [CI] 0.017-0.103)) and transportation barriers (5.2% points [CI 0.005-0.099]). An ACSC-related ED visit was more likely among individuals with functional status limitations (3.2% points [CI 0.003-0.062]) and self-rated poorer health (7.4% points (CI 0.030-0.119) poor; 6.2% points (CI 0.029-0.096) fair; 4.1% points (CI 0.009-0.073) good; compared with excellent/very good).Conclusions: Patient-reported factors not present in most electronic health records were significantly associated with future ED visits in high-risk VA patients. [ABSTRACT FROM AUTHOR]

Serrated polyps (SPs) are precursors to one‐third of colorectal cancers (CRCs), with histological subtypes: hyperplastic polyps (HPs), sessile serrated lesions (SSLs) and traditional serrated adenomas (TSAs). The incidence of early‐onset CRC before the age of 50 is increasing, with limited understanding of SPs in younger cohorts. Using a large colonoscopy‐based cohort, we characterized epidemiologic profiles of SP subtypes, compared to conventional adenomas, with secondary analysis on early‐onset polyps. Ninety‐four thousand four hundred and twenty‐seven patients underwent screening colonoscopies between 2010 and 2018. Demographic, endoscopic and histopathologic characteristics of each polyp subtype were described. High‐risk polyps included SSLs ≥10 mm/with dysplasia and conventional adenomas ≥10 mm/with tubulovillous/villous histology/high‐grade dysplasia. We examined polyp prevalence with age and compared early‐ (age < 50) and late‐onset polyps (age ≥ 50). Eighteen thousand one hundred and twenty‐five patients had SPs (4357 SSLs, 15 415 HPs, 120 TSAs) and 26 699 had conventional adenomas. High‐risk SSLs were enriched in the ascending colon (44.1% vs 2.6‐35.8% for other locations; P <.003). Early‐ and late‐onset SPs had similar subsite distribution. Early‐onset conventional adenomas were more enriched in the distal colon/rectum (51.8% vs 43.4%, P <.001). Multiple conventional adenomas were more represented in late‐onset groups (40.8% vs 33.8%, P <.001), with no difference in SSLs. The prevalence of conventional adenomas/high‐risk conventional adenomas increased continuously with age, whereas the prevalence of SSLs/high‐risk SSLs was stable from age 40 years onwards. A higher proportion of women were diagnosed with early‐onset than late‐onset SSLs (62.9% vs 57.6%, P =.03). Conventional adenomas, SSLs, early‐ and late‐onset polyps have distinct epidemiology. The findings have implications for improved colonoscopy screening and surveillance and understanding the etiologic heterogeneity of CRC. [ABSTRACT FROM AUTHOR]

Diagnosis prediction exploits electronic health records (EHRs) to predict the future diagnoses of patients, further supporting clinical decision making and personalized treatments. However, a patient's EHR is an irregular sequence of visits that contains a large number of medical concepts. The disease progression patterns are closely related to the visits, as well as the contextual knowledge of each visit. The existing diagnosis prediction methods ignore the complex relationships between the visits and the contextual knowledge, and thus cannot achieve satisfactory performance. Therefore, we develop a knowledge‐aware representation learning method to comprehensively model these complex relationships. Specifically, we first construct a medical knowledge graph to model the correlations between medical concepts in EHRs, and project the contextual knowledge into the pre‐learned vectors. We then devise an enhanced gated recurrent unit (GRU) neural network to extract the long‐term intra‐relationships between visits, and design a novel knowledge attention module to capture the complex inter‐relationships between the visits and the contextual knowledge. Armed with these, we provide a powerful and flexible framework to capture the long‐term discriminative disease progression patterns for diagnosis prediction. Intensive experiments are conducted on two real‐world EHR datasets. And the model achieves a competitive performance with Code‐level Accuracy@20 of 0.7465 and Visit‐level Precision@20 of 0.7547 on MIMIC‐III, and Code‐level Accuracy@20 of 0.9337 and Visit‐level Precision@20 of 0.9427 on MIMIC‐IV. [ABSTRACT FROM AUTHOR]

Background: The quality of care of the 6.5 million Americans living with dementia has been suboptimal, leading to worse outcomes and higher costs. Few health systems have formal systems in place to guide the care of these patients. To help improve the care of persons living with dementia, we developed and preliminarily evaluated the effectiveness of electronic health record (EHR)-generated recommendations for patients with dementia. Methods: This quality improvement study was conducted from October 2020 through June 2022 at a single academic healthcare system and included patients identified as having dementia on their problem list and their physicians. Ten (seven outpatient and three inpatient) algorithms based on clinical logic and evidence were embedded in an EHR system to generate specific recommendations based on combinations of utilization, diagnosis, and medications. The number of each type of recommendation generated, and orders for each type of recommendation were recorded, as well as physician's perceptions of this approach. Results: Three thousand six hundred and nine recommendations on 763 patients were triggered by the algorithms in the outpatient setting, and 185 referrals were placed. The most common recommendations were for ongoing care through the UCLA Alzheimer's and Dementia Care program, Palliative Care, the Extensivist Clinic, Urogynecology, and Clinical Pharmacy. The most commonly acted upon by providers were recommendations for referral to Pharmacists and the UCLA Alzheimer's and Dementia Care program. The most common reason for not responding to specific recommendations was that these were not perceived as relevant to the patient. Compared to general medicine physicians, geriatricians felt more comfortable managing dementia care without a referral to a service (23% (95% CI 15%–34%) versus 3% (95% CI 0%–17%), p = 0.012) and less commonly felt the recommendation was appropriate (1% (95% CI 0%–7%) versus 13% (95% CI 4%–30%), p = 0.02). Conclusions: EHR-generated algorithms can help guide patients with dementia to appropriate clinical services. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study was to describe the extent to which nursing assessment data was present in the electronic health record and linked to NANDA‐I, NIC, and NOC. Methods: This retrospective review used a descriptive approach to examine documentation in the electronic health records (EHR) of 10 hospitalized patients requiring cardiac surgery. A team of experts applied a Delphi consensus‐building process to identify the supports and barriers for nursing documentation. Findings: Collection of the health history was organized using Gordon's Functional Health Pattern (FHP) Framework. Seventy‐five fields were noted for the entry of nursing assessment data of which 65 focused on health history data and 30 documented physical findings and observations. There were no references to the defining characteristics or etiologies with any of the diagnostic labels used. Care plans included the nursing diagnoses, goals of care, and interventions, although there was a lack of clear alignment between the assessment, NANDA‐I, NIC, and NOC and the care plan. Progress note documentation addressed significant events in the patient's clinical course; however, these were not nursing problem or diagnosis focused. Four expert reviewers arrived at consensus regarding the supports and challenges impacting nurses' ability to document data depicting nursing's contribution to care using a FHP and standardized nursing language in the EHR. Conclusions: The EHR provides an opportunity to reflect nursing clinical judgment and make nursing care visible. These findings suggest there are challenges to capturing nurse focused data elements in the EHR. Implications for nursing practice: This work has important implications for clinicians, educators, and administrators alike. EHR systems must accurately capture nurses' contribution to patient care to plan for resource allocation and quality care delivery. Ultimately, the development of standardized data sources reflecting the outcomes of nursing care will expand the opportunities to advance nursing knowledge. [ABSTRACT FROM AUTHOR]

Objectives: To develop outcomes of care quality measures derived from the dental electronic health record (EHR) to assess the occurrence and timely treatment of tooth decay. Methods: Quality measures were developed to assess whether decay was treated within 6 months and if new decay occurred in patients seen. Using EHR‐derived data of the state of each tooth surface, algorithms compared the patient's teeth at different dates to determine if decay was treated or new decay had occurred. Manual chart reviews were conducted at three sites to validate the measures. The measures were implemented and scores were calculated for three sites over four calendar years, 2016 through 2019. Results: About 954 charts were manually reviewed for the timely treatment of tooth decay measure, with measure performance of sensitivity 97%, specificity 85%, positive predictive value (PPV) 91%, negative predictive value (NPV) 95%. About 739 charts were reviewed for new decay measure, with sensitivity 94%, specificity 99%, PPV 99%, and NPV 94%. Across all sites and years, 52.8% of patients with decay were fully treated within 6 months of diagnosis (n = 247,959). A total of 23.8% of patients experienced new decay, measured at an annual exam (n = 640,004). Conclusion: Methods were developed and validated for assessing timely treatment of decay and occurrence of new decay derived from EHR data, creating effective outcome measures. These EHR‐based quality measures produce accurate and reliable results that support efforts and advancement in quality assessment, quality improvement, patient care and research. [ABSTRACT FROM AUTHOR]

Nowadays, blockchain and Internet of Things (IoT) are two emerging areas of the Information Technology (IT) sector. These two emerging areas are used in various fields, such as supply chain, logistics and automotive industry. Due to the low processing power and storage space of IoT devices, users' medical information is usually saved in a centralized third party like a clinical repository or a cloud computing environment. Thus, in many cases, users lose control of their medical information, which can result in security disclosure and a single‐point impediment. So, an advanced solution is required to improve the data sharing process, while restricting it in terms of security. Blockchain technology with IoT can significantly affect the healthcare industry by improving its efficiency, security and transparency, as well as can provide more business opportunities. The efficient sharing of Electronic Health Record (EHR) can improve the treatment process, diagnosis accuracy, security and privacy. This article proposes a blockchain‐based IoT architecture to provide enhanced security of healthcare data by using Identity‐Based Encryption (IBE) algorithm. Here, the smart contract defines all the basic operations of the healthcare system, which can be beneficial to all stakeholders. Many experiments are executed to evaluate the efficiency of the proposed scheme. The results show that the proposed scheme is better than the existing renowned schemes. [ABSTRACT FROM AUTHOR]

Background: We sought to improve the referral process to a community paramedicine (CP) program following a 9‐1‐1 encounter. Methods: An electronic health record (EHR) for CP records with the ability to link to emergency EHR was identified and implemented with a single‐click referral to the CP program. Referrals were tracked for 15 months before and after implementation. Results: Referral capacity increased from an average of 14.2 referrals per month to 44.9 referrals per month. Conclusion: The results of this study suggest an EHR is a useful investment for CP programs and may be integral to efficient program operations. [ABSTRACT FROM AUTHOR]

Purpose: Acute pancreatitis (AP) is a frequently encountered adverse drug reaction. However, the validity of diagnostic codes for AP is unknown. We aimed to determine the positive predictive value (PPV) of a diagnostic code‐based algorithm for identifying patients with AP within the US Veterans Health Administration and evaluate the value of adding readily available structured laboratory information. Methods: We identified patients with possible AP events first based on the presence of a single hospital discharge ICD‐9 or ICD‐10 diagnosis of AP (Algorithm 1). We then expanded Algorithm 1 by including relevant laboratory test results (Algorithm 2). Specifically, we considered amylase or lipase serum values obtained between 2 days before admission and the end of the hospitalization. Medical records of a random sample of patients identified by the respective algorithms were reviewed by two separate gastroenterologists to adjudicate AP events. The PPV (95% confidence interval [CI]) for the algorithms were calculated. Results: Algorithm 2, consisting of one ICD‐9 or ICD‐10 hospital discharge diagnosis of AP and the addition of lipase serum value ≥200 U/L, had a PPV 89.1% (95% CI 83.0%–95.2%), improving from the PPV of algorithm 1 (57.9% [95% CI 46.8–69.0]). Conclusions: An algorithm consisting of an ICD‐9 or ICD‐10 diagnosis of AP with a lipase value ≥200 U/L achieved high PPV. This simple algorithm can be readily implemented in any electronic health records (EHR) systems and could be useful for future pharmacoepidemiologic studies on AP. [ABSTRACT FROM AUTHOR]

Summary: Due to the increasing number of people accessing their personal medical information online, it has raised concerns about the security of their data. Unauthorized access to patient's records can lead to disclosure of their privacy. There are various types of frauds that can affect the integrity of a patient's records such as theft of identity and tax fraud. It is therefore necessary to implement a secure data access and retrieval system in order to prevent these types of crimes. Security passwords are often the only barrier between hackers and users. Many of us often use the same ones for multiple accounts. Biometric passwords are more secure than traditional ones due to their ability to be created by observing a person's eyes. They can also be created with a secret key that's stored in an encrypted format. Proposed method combines a secure key with an optimized fuzzy extraction algorithm to provide high‐level security. The file is then encrypted using adaptive ElGamal and its digital signature is uploaded in cloud. Data recovery services are also introduced to help users keep their data secure using seed block algorithm (SBA). These services can be utilized to recover files once they get lost or get destroyed. The proposed security approach for back‐up files (SBA) can be used to minimize the time it takes for the recovery process. It also addresses the issue of unauthorized access to the data stored on remote servers. [ABSTRACT FROM AUTHOR]

Summary: In the past few years, the growing demands of cloud computing became high in the healthcare sector. The electronic health record (EHR) has turned out to be the chosen system to uphold patient's healthcare data. Due to the advancement of cloud computing, the users in the cloud are empowered to access their data with elasticity and offering huge storage capability at minimum costs. This motivates EHR maintainers to transfer their personal storage to the remote cloud servers as it significantly reduces the burden of storage and computation. Nevertheless, securing healthcare data file poses a gigantic challenge as data outsourced in the cloud are too sensitive. Several security features such as data confidentiality, data privacy, access control, data integrity, and data security necessities to be satisfied. This article proposed a secure sharing of healthcare data file by incorporating obfuscation technique and elliptic curve cryptography (ECC) algorithm to enforce better data confidentiality and integrity. Data obfuscation is a beneficial technique in preserving the data confidentiality on the cloud by minimizing the risk of data theft and data leakage. Moreover, ECC methodology aims to provide a high level of security, low communication and computation cost with smaller key size. Experimental analysis reveals better performance than other existing schemes in terms of computation time, communication time, key generation time, throughput rate, turnaround time, and uploading speed. Besides, it exposes that the proposed framework is highly secure and efficient in the field of healthcare system. [ABSTRACT FROM AUTHOR]

Aims: Individuals with supranormal left ventricular ejection fraction (snLVEF; LVEF >70%) have increased mortality. However, the genetic and phenotypic profile of snLVEF remains unknown. This study aimed to determine the relationship of both snLVEF genetic risk and phenotype with survival and underdiagnosed heart failure (HF). Methods and results: A snLVEF genetic risk score (GRS) was applied and cases of snLVEF were identified in 486 754 individuals across two population‐based cohorts (BioMe Biobank and UK Biobank). The snLVEF GRS and phenotype were evaluated for association with survival, as well as HF diagnosis, markers, symptoms, and medications. Of 486 754 participants, the median age was 58 years, 20 069 (4.1%) died, and 10 088 (2.1%) had diagnosed HF. Both snLVEF GRS (hazard ratio [HR] 1.1 for top 10% vs. bottom 10% GRS; p = 0.002) and phenotype (HR 1.4; p = 0.003) were associated with increased all‐cause mortality. Both snLVEF GRS and phenotype were associated with reduced HF diagnosis (odds ratio [OR] 0.97 and OR 0.63, respectively; both p ≤0.002). However, the snLVEF GRS and phenotype were both associated with elevated brain natriuretic peptide (BNP) levels (146 and 185 pg/ml increase, respectively; p <0.001), including 268 out of 455 (59%) individuals with snLVEF phenotype who had BNP >100 pg/ml. Among 476 666 participants without HF diagnoses, snLVEF GRS and phenotype were associated with increased HF symptoms (e.g. exertional dyspnoea OR 1.4 and OR 1.3; p <0.003) and HF medications (e.g. loop diuretic OR 1.2 and OR 1.03; p <0.02). Associations were consistent in hypertensive individuals without cardiac comorbidities. Conclusions: Genetic predisposition to and presence of snLVEF are associated with decreased survival and underdiagnosed HF. [ABSTRACT FROM AUTHOR]