Electronic Health Record Note Research Articles

Virtual Scribes and Physician Time Spent on Electronic Health Records

Time on the electronic health record (EHR) is associated with burnout among physicians. Newer virtual scribe models, which enable support from either a real-time or asynchronous scribe, have the potential to reduce the burden of the EHR and EHR-related documentation. To characterize the association of use of virtual scribes with changes in physicians' EHR time and note and order composition and to identify the physician, scribe, and scribe response factors associated with changes in EHR time upon virtual scribe use. Retrospective, pre-post quality improvement study of 144 physicians across specialties who had used a scribe for at least 3 months from January 2020 to September 2022, were affiliated with Brigham and Women's Hospital and Massachusetts General Hospital, and cared for patients in the outpatient setting. Data were analyzed from November 2022 to January 2024. Use of either a real-time or asynchronous virtual scribe. Total EHR time, time on notes, and pajama time (5:30 pm to 7:00 am on weekdays and nonscheduled weekends and holidays), all per appointment; proportion of the note written by the physician and team contribution to orders. The main study sample included 144 unique physicians who had used a virtual scribe for at least 3 months in 152 unique scribe participation episodes (134 [88.2%] had used an asynchronous scribe service). Nearly two-thirds of the physicians (91 physicians [63.2%]) were female and more than half (86 physicians [59.7%]) were in primary care specialties. Use of a virtual scribe was associated with significant decreases in total EHR time per appointment (mean [SD] of 5.6 [16.4] minutes; P < .001) in the 3 months after vs the 3 months prior to scribe use. Scribe use was also associated with significant decreases in note time per appointment and pajama time per appointment (mean [SD] of 1.3 [3.3] minutes; P < .001 and 1.1 [4.0] minutes; P = .004). In a multivariable linear regression model, the following factors were associated with significant decreases in total EHR time per appointment with a scribe use at 3 months: practicing in a medical specialty (-7.8; 95% CI, -13.4 to -2.2 minutes), greater baseline EHR time per appointment (-0.3; 95% CI, -0.4 to -0.2 minutes per additional minute of baseline EHR time), and decrease in the percentage of the note contributed by the physician (-9.1; 95% CI, -17.3 to -0.8 minutes for every percentage point decrease). In 2 academic medical centers, use of virtual scribes was associated with significant decreases in total EHR time, time spent on notes, and pajama time, all per appointment. Virtual scribes may be particularly effective among medical specialists and those physicians with greater baseline EHR time.

1873. The role of electronic health record note templates to improve screening for tuberculosis risk factors in children

Abstract Background Children should be evaluated annually for tuberculosis (TB) risk factors to detect and treat latent TB infection (LTBI), but there are gaps in screening and documentation. Embedding TB questions in an electronic health record (EHR) note template may increase screening. Methods TB risk assessment questions were added to the well-child and -adolescent note templates at a Federally Qualified Health Center in Oakland, California in 2014. We extracted EHR data from all well patient visits from individuals 1-19 years old without a past medical history of latent or active TB over a 7-year period. We compared the proportion of visits that documented TB risk factor screening, before and after introduction of the note template and annually. Results We examined 18,681 visits from 2014-2020, of which 7,071 (38%) were for children 1-4 years old, and 3,556 (19%) preferred a language other than English. One year after embedding TB risk factor questions in the note template, TB risk assessment increased from 76% to 92% (p = 0.02). In the subsequent six years, TB risk factor screening remained high ( &amp;gt;90%) and sustained (Figure 1). This trend was also seen among visits for those whose primary language spoken was not English. Screening for adolescents ≥12 years old improved over time (63% to 86%) but had lower overall screening than children 1-4 years old (≥90%) (Figure 1, p &amp;lt; 0.01). The lines represent the proportion of well-child or -adolescent visits that have documentation of a TB risk assessment, overall and for children who prefer a language other than English, as well as for children aged 1-4 years old and those older than 12. The red horizontal line indicates that assessments for TB risk factors were completed in 90% of visits during the given year. Conclusion A simple EHR-based intervention can significantly improve screening and documentation for TB risk factors in the primary care setting and suggests that additional EHR solutions may address other gaps in the LTBI care cascade. Disclosures All Authors: No reported disclosures

Quantifying EHR and Policy Factors Associated with the Gender Productivity Gap in Ambulatory, General Internal Medicine

BackgroundThe gender gap in physician compensation has persisted for decades. Little is known about how differences in use of the electronic health record (EHR) may contribute.ObjectiveTo characterize how time on clinical activities, time on the EHR, and clinical productivity vary by physician gender and to identify factors associated with physician productivity.Design, Setting, and ParticipantsThis longitudinal study included general internal medicine physicians employed by a large ambulatory practice network in the Northeastern United States from August 2018 to June 2021.Main MeasuresMonthly data on physician work relative value units (wRVUs), physician and practice characteristics, metrics of EHR use and note content, and temporal trend variables.Key ResultsThe analysis included 3227 physician-months of data for 108 physicians (44% women). Compared with men physicians, women physicians generated 23.8% fewer wRVUs per month, completed 22.1% fewer visits per month, spent 4.0 more minutes/visit and 8.72 more minutes on the EHR per hour worked (all p < 0.001), and typed or dictated 36.4% more note characters per note (p = 0.006). With multivariable adjustment for physician age, practice characteristics, EHR use, and temporal trends, physician gender was no longer associated with productivity (men 4.20 vs. women 3.88 wRVUs/hour, p = 0.31). Typing/dictating fewer characters per note, relying on greater teamwork to manage orders, and spending less time on documentation were associated with higher wRVUs/hour. The 2021 E/M code change was associated with higher wRVUs/hour for all physicians: 10% higher for men physicians and 18% higher for women physicians (p < 0.001 and p = 0.009, respectively).ConclusionsIncreased team support, briefer documentation, and the 2021 E/M code change were associated with higher physician productivity. The E/M code change may have preferentially benefited women physicians by incentivizing time-intensive activities such as medical decision-making, preventive care discussion, and patient counseling that women physicians have historically spent more time performing.

Social Determinants of Health Documentation Among Individuals With Rheumatic and Musculoskeletal Conditions in an Integrated Care Management Program.

Social determinants of health (SDoH), such as poverty, are associated with increased burden and severity of rheumatic and musculoskeletal diseases. This study was undertaken to study the prevalence and documentation of SDoH-related needs in electronic health records (EHRs) of individuals with these conditions. We randomly selected individuals with ≥1 International Classification of Diseases, Ninth/Tenth Revision (ICD-9/10) code for a rheumatic/musculoskeletal condition enrolled in a multihospital integrated care management program that coordinates care for medically and/or psychosocially complex individuals. We assessed SDoH documentation using terms for financial needs, food insecurity, housing instability, transportation, and medication access according to EHR note review and ICD-10 SDoH billing codes (Z codes). We used multivariable logistic regression to examine associations between demographic factors (age, gender, race, ethnicity, insurance) and ≥1 (versus 0) SDoH need as the odds ratio (OR) with 95% confidence interval (95% CI). Among 558 individuals with rheumatic/musculoskeletal conditions, 249 (45%) had ≥1 SDoH need documented in EHR notes by social workers, care coordinators, nurses, and physicians. A total of 171 individuals (31%) had financial insecurity, 105 (19%) had transportation needs, 94 (17%) had food insecurity; 5% had ≥1 related Z code. In the multivariable model, the odds of having ≥1 SDoH need was 2.45 times higher (95% CI 1.17-5.11) for Black versus White individuals and significantly higher for Medicaid or Medicare beneficiaries versus commercially insured individuals. Nearly half of this sample of complex care management patients with rheumatic/musculoskeletal conditions had SDoH documented within EHR notes; financial insecurity was the most prevalent. Only 5% of patients had representative billing codes suggesting that systematic strategies to extract SDoH from notes are needed.

Changes in Primary Care Quality Associated With Implementation of the Veterans Health Administration Preventive Health Inventory

The COVID-19 pandemic caused significant disruptions in primary care delivery. The Veterans Health Administration (VHA) launched the Preventive Health Inventory (PHI) program-a multicomponent care management intervention, including a clinical dashboard and templated electronic health record note-to support primary care in delivering chronic disease care and preventive care that had been delayed by the pandemic. To describe patient, clinician, and clinic correlates of PHI use in primary care clinics and to examine associations between PHI adoption and clinical quality measures. This quality improvement study used VHA administrative data from February 1, 2021, through February 28, 2022, from a national cohort of 216 VHA primary care clinics that have implemented the PHI. Participants comprised 829 527 veterans enrolled in primary care in clinics with the highest and lowest decile of PHI use as of February 2021. Templated electronic health record note documenting use of the PHI. Diabetes and blood pressure clinical quality measures were the primary outcomes. Interrupted time series models were applied to estimate changes in diabetes and hypertension quality measures associated with PHI implementation. Low vs high PHI use was stratified at the facility level to measure whether systematic differences in uptake were associated with quality. A total of 216 primary clinics caring for 829 527 unique veterans (mean [SD] age, 64.1 [16.9] years; 755 158 of 829 527 [91%] were men) formed the study cohort. Use of the PHI varied considerably across clinics. The clinics in the highest decile of PHI use completed a mean (SD) of 32 997.4 (14 019.3) notes in the electronic health record per 100 000 veterans compared with 56.5 (35.3) notes per 100 000 veterans at the clinics in the lowest decile of use (P < .001). Compared with the clinics with the lowest use of the PHI, clinics with the highest use had a larger mean (SD) clinic size (12 072 [7895] patients vs 5713 [5825] patients; P < .001), were more likely to be urban (91% vs 57%; P < .001), and served more non-Hispanic Black veterans (16% vs 5%; P < .001) and Hispanic veterans (14% vs 4%; P < .001). Staffing did not differ meaningfully between high- and low-use clinics (mean [SD] ratio of full-time equivalent staff to clinician, 3.4 [1.2] vs 3.4 [0.8], respectively; P < .001). After PHI implementation, compared with the clinics with the lowest use, those with the highest use had fewer veterans with a hemoglobin A1c greater than 9% or missing (mean [SD], 6577 [3216] per 100 000 veterans at low-use clinics; 9928 [4236] per 100 000 veterans at high-use clinics), more veterans with an annual hemoglobin A1c measurement (mean [SD], 13 181 [5625] per 100 000 veterans at high-use clinics; 8307 [3539] per 100 000 veterans at low-use clinics), and more veterans with adequate blood pressure control (mean [SD], 20 582 [12 201] per 100 000 veterans at high-use clinics; 12 276 [6850] per 100 000 veterans at low-use clinics). This quality improvement study of the implementation of the VHA PHI suggests that higher use of a multicomponent care management intervention was associated with improved quality-of-care metrics. The study also found significant variation in PHI uptake, with higher uptake associated with clinics with more racial and ethnic diversity and larger, urban clinic sites.

Optimizing Endoscopy Procedure Documentation Improves Guideline-Adherent Care in Upper Gastrointestinal Bleeding

Background and AimsUpper GI bleeding (UGIB) is a common indication for inpatient esophagogastroduodenoscopy (EGD). Guideline adherence improves post-EGD care, including appropriate medication dosing/duration and follow-up procedures that reduce UGIB-related morbidity. We aimed to optimize and standardize post-EGD documentation to improve process and clinical outcomes in UGIB-related care.MethodsWe performed a prospective quality improvement study of inpatient UGIB endoscopies at an academic tertiary referral center during 6/2019–7/2021. Guidelines were used to develop etiology/severity-specific electronic health record note templates. Participants (39 faculty/15 trainees) completed 10-min training in template content/use. We collected pre/post-intervention process data on “Minimal Standard Report” (MSR) documentation including patient disposition, diet, and medications. We also recorded documentation of re-bleed precautions and follow-up procedures. Study outcomes included guideline-based medication prescriptions, ordering of follow-up EGD, and post-discharge re-bleeding. Pre/post-intervention analysis was performed using chi-square tests.ResultsFrom a pre-intervention baseline of 199 patients to 459 patients post-intervention, compliance improved with inpatient PPI (53.4–77.9%, p < 0.001) and discharge PPI (31.3–61.0%, p < 0.001) prescriptions. There was improvement in MSR completion (28.6–42.5%, p < 0.001). Compliance improved with octreotide prescriptions (75.0–93.6%, p = 0.002) and follow-up EGD order (61.3–87.1%, p < 0.001). There was no change in post-discharge re-bleeding. 82.6% of cases used templates.ConclusionsOur project leveraged endoscopy software to standardize documentation, resulting in improved clinical care behavior and efficiency. Our intervention required low burden of maintenance, and sustainability with high utilization over 9 months. Similar endoscopy templates can be applied to other health systems and procedures to improve care.

Physician Note Composition Patterns and Time on the EHR Across Specialty Types: a National, Cross-sectional Study.

The burden of clinical documentation in electronic health records (EHRs) has been associated with physician burnout. Numerous tools (e.g., note templates and dictation services) exist to ease documentation burden, but little evidence exists regarding how physicians use these tools in combination and the degree to which these strategies correlate with reduced time spent on documentation. To characterize EHR note composition strategies, how these strategies differ in time spent on notes and the EHR, and their distribution across specialty types. Secondary analysis of physician-level measures of note composition and EHR use derived from Epic Systems' Signal data warehouse. We used k-means clustering to identify documentation strategies, and ordinary least squares regression to analyze the relationship between documentation strategies and physician time spent in the EHR, on notes, and outside scheduled hours. A total of 215,207 US-based ambulatory physicians using the Epic EHR between September 2020 and May 2021. Percent of note text derived from each of five documentation tools: SmartTools, copy/paste, manual text, NoteWriter, and voice recognition and transcription; average total and after-hours EHR time per visit; average time on notes per visit. Six distinct note composition strategies emerged in cluster analyses. The most common strategy was predominant SmartTools use (n=89,718). In adjusted analyses, physicians using primarily transcription and dictation (n=15,928) spent less time on notes than physicians with predominant Smart Tool use. (b=-1.30, 95% CI=-1.62, -0.99, p<0.001; average 4.8 min per visit), while those using mostly copy/paste (n=23,426) spent more time on notes (b=2.38, 95% CI=1.92, 2.84, p<0.001; average 13.1 min per visit). Physicians' note composition strategies have implications for both time in notes and after-hours EHR use, suggesting that how physicians use EHR-based documentation tools can be a key lever for institutions investing in EHR tools and training to reduce documentation time and alleviate EHR-associated burden.

Applying the Tailored Implementation in Chronic Diseases framework to inform implementation of the Preferences Elicited and Respected for Seriously Ill Veterans through enhanced decision-making program in the United States Veterans Health Administration.

In 2017, the National Center for Ethics in Health Care for the United States Department of Veterans Affairs (VA) commenced national roll-out of the Life-Sustaining Treatment Decisions Initiative. This national VA initiative aimed to promote personalized, proactive, patient-driven care for seriously ill Veterans by documenting Veterans' goals and preferences for life-sustaining treatments in a durable electronic health record note template known as the life-sustaining treatment template. The Preferences Elicited and Respected for Seriously Ill Veterans through Enhanced Decision-Making (PERSIVED) quality improvement program was created to address the high variation in life-sustaining treatment template completion in VA Home Based Primary Care (HBPC) and Community Nursing Home programs. This manuscript describes the program that focuses on improving life sustaining treatment template completion rates amongst HBPC programs. To increase life-sustaining treatment template completion for Veterans receiving care from HBPC programs, the PERSIVED team applies two implementation strategies: audit with feedback and implementation facilitation. The PERSIVED team conducts semi-structured interviews, needs assessments, and process mapping with HBPC programs in order to identify barriers and facilitators to life-sustaining treatment template completion to inform tailored facilitation. Our interview data is analyzed using the Tailored Implementation in Chronic Diseases (TICD) framework, which identifies 57 determinants that might influence practice or implementation of interventions. To quickly synthesize and use baseline data to inform the tailored implementation plan, we adapted a rapid analysis process for our purposes. This paper describes a six-step process for conducting and analyzing baseline interviews through applying the TICD that can be applied and adapted by implementation scientists to rapidly inform tailoring of implementation facilitation.

"Advancing" Advance Care Planning to Veterans in the Veterans Health Administration.

The completion rate of Advance Directive (ADs) in the Veterans Health Administration (VHA) is unknown. There is substantial literature on the need for effective Advance Care Planning (ACP) that leads to an AD to ensure that health care preferences for patients are known. Advance Directive are essential to consider since ACP, which explains and plans Advance Directive, does not reach all individuals. Health inequities, such as those experienced in rural areas, continue to exist. While ACP may disproportionately affect rural-residing veterans and their providers, a VHA program was specifically designed to increase ACP engagement with rural veterans and to address several systemic barriers to ACP. This descriptive analysis seeks to identify patient, provider, and geographic characteristics associated with higher rates of ACP participation in VHA. An observational examination of the profile of veterans and the types of ACP (e.g., individual or in groups) using administrative data for all beneficiaries receiving VHA health care services in federal fiscal year (FY) 2020 was conducted as part of a national program evaluation. The measures include patient-level data on demographics (e.g., race, ethnicity, gender), unique patient identifiers (e.g., name, social security number), geographic characteristics of patient's location (e.g., rurality defined as Rural-Urban Commuting Areas [RUCA]), VHA priority group; provider-level data (e.g., type of document definition, clinic stop codes, visit date used to verify Advance Care Planning via Group Visits [ACP-GV] attendance; data not shown), and electronic health record note titles that indicated the presence of ACP in VHA (e.g., "Advance Directive [AD] Discussion" note title, "ACP-GV CHAR 4 code"). Pearson's chi-square statistics were used for between-group comparisons based on a two-sided test with a significance level of 0.05. The overall rate of AD discussions among unique VHA users in FY2020 was 5.2% (95% CI: 5.2%-5.2%) and for Advance Care Planning via Group Visits, which targets rural veterans using groups, it was 1.8% (95% CI: 1.8%-1.9%). Advance Directive discussions in VHA are more successful at reaching middle age (M = 64; SD = 16), African Americans, males, veterans living in urban areas, and veterans with a VA disability (Priority Group 1-4). Advance Care Planning delivered in groups is reaching slightly younger veterans under the age of 75 years (M = 62; SD = 15), African Americans, females, disabled veterans (e.g., Priority Group 1-4), and more veterans residing in rural communities compared to the national population of VHA users. Advance Directive discussion rates are low across VHA, yet intentional efforts with ACP via group visits are reaching veterans who are considered underserved owing to residing in rural areas. Advance Care Planning needs to be a well-informed clinical priority for VHA to engage with the entire veteran population and to support the completion of ADs.

A Quality Improvement Initiative Addressing Provider Prescription of Weight Management Follow-up in Primary Care.

Introduction:Few providers routinely comply with the American Academy of Pediatrics recommendations to prescribe weight management follow-up in-between well-child checks for children with obesity/overweight. This quality improvement (QI) project aimed to increase the percentage of patients prescribed weight management follow-up within three months of their well-child check.Methods:The project took place in 1 outpatient primary care clinic at a large, free-standing children’s hospital from May 2018 to April 2019. We grouped interventions in 4 Plan-Do-Study-Act ramps with the following themes: (1) provider education; (2) electronic health record note changes; (3) discharge order modifications; and (4) provider feedback. The primary outcome was the percent of patients ages 2–18 years with body mass index ≥ 85% that had an order placed to schedule a follow-up weight management appointment in primary care. We monitored attendance rates for scheduled follow-up visits as a balancing measure.Results:Mean prescription rates increased from 32% at baseline to 58%, with special cause analysis demonstrating improvement. Of patients prescribed follow-up, 40% returned for a weight management visit, compared to 13% before the QI initiative. The no-show rate was 35%.Conclusions:The utilization of QI methodology led to an increase in the percentage of patients appropriately prescribed weight management follow-up and a resultant increase in the number of patients seen for follow-up. The next steps include a re-examination of process failures to improve patient buy-in in follow-up prescriptions.

Electronic health record note review in an outpatient specialty clinic: who is looking?

Note entry and review in electronic health records (EHRs) are time-consuming. While some clinics have adopted team-based models of note entry, how these models have impacted note review is unknown in outpatient specialty clinics such as ophthalmology. We hypothesized that ophthalmologists and ancillary staff review very few notes. Using audit log data from 9775 follow-up office visits in an academic ophthalmology clinic, we found ophthalmologists reviewed a median of 1 note per visit (2.6 ± 5.3% of available notes), while ancillary staff reviewed a median of 2 notes per visit (4.1 ± 6.2% of available notes). While prior ophthalmic office visit notes were the most frequently reviewed note type, ophthalmologists and staff reviewed no such notes in 51% and 31% of visits, respectively. These results highlight the collaborative nature of note review and raise concerns about how cumbersome EHR designs affect efficient note review and the utility of prior notes in ophthalmic clinical care.

Impact of a medical scribe on clinical efficiency and quality in an academic general internal medicine practice

BackgroundScribes have been proposed as an intervention to decrease physician electronic health record (EHR) workload and improve clinical quality. We aimed to assess the impact of a scribe on clinical efficiency and quality in an academic internal medicine practice.MethodsSix faculty physicians worked with one scribe at an urban academic general internal medicine clinic April through June 2017. Patient visits during the 3 months prior to intervention (baseline, n = 789), unscribed visits during the intervention (concurrent control, n = 605), and scribed visits (n = 579) were included in the study. Clinical efficiency outcomes included time to close encounter, patient time in clinic, and number of visits per clinic session. Quality outcomes included EHR note quality, rates of medication and immunization review, population of patient instructions, reconciliation of outside information, and completion of preventative health recommendations.ResultsMedian time to close encounter (IQR) was lower for scribed visits [0.4 (4.8) days] compared to baseline and unscribed visits [1.2 (5.9) and 2.9 (5.4) days, both p < 0.001]. Scribed notes were more likely to have a clear history of present illness (HPI) [OR = 7.30 (2.35–22.7), p = 0.001] and sufficient HPI information [OR = 2.21 (1.13–4.35), p = 0.02] compared to unscribed notes. Physicians were more likely to review the medication list during scribed vs. baseline visits [OR = 1.70 (1.22–2.35), p = 0.002]. No differences were found in the number of visits per clinic session, patient time in clinic, completion of preventative health recommendations, or other outcomes.ConclusionsWorking with a scribe in an academic internal medicine practice was associated with more timely documentation.

Evaluating the Effectiveness of NoteAid in a Community Hospital Setting: Randomized Trial of Electronic Health Record Note Comprehension Interventions With Patients.

BackgroundInterventions to define medical jargon have been shown to improve electronic health record (EHR) note comprehension among crowdsourced participants on Amazon Mechanical Turk (AMT). However, AMT participants may not be representative of the general population or patients who are most at-risk for low health literacy.ObjectiveIn this work, we assessed the efficacy of an intervention (NoteAid) for EHR note comprehension among participants in a community hospital setting.MethodsParticipants were recruited from Lowell General Hospital (LGH), a community hospital in Massachusetts, to take the ComprehENotes test, a web-based test of EHR note comprehension. Participants were randomly assigned to control (n=85) or intervention (n=89) groups to take the test without or with NoteAid, respectively. For comparison, we used a sample of 200 participants recruited from AMT to take the ComprehENotes test (100 in the control group and 100 in the intervention group).ResultsA total of 174 participants were recruited from LGH, and 200 participants were recruited from AMT. Participants in both intervention groups (community hospital and AMT) scored significantly higher than participants in the control groups (P<.001). The average score for the community hospital participants was significantly lower than the average score for the AMT participants (P<.001), consistent with the lower education levels in the community hospital sample. Education level had a significant effect on scores for the community hospital participants (P<.001).ConclusionsUse of NoteAid was associated with significantly improved EHR note comprehension in both community hospital and AMT samples. Our results demonstrate the generalizability of ComprehENotes as a test of EHR note comprehension and the effectiveness of NoteAid for improving EHR note comprehension.

Creation and implementation of an electronic health record note for quality improvement in pediatric epilepsy: Practical considerations and lessons learned.

ObjectiveTo describe the development of the Pediatric Epilepsy Outcome‐Informatics Project (PEOIP) at Alberta Children's Hospital (ACH), which was created to provide standardized, point‐of‐care data entry; near‐time data analysis; and availability of outcome dashboards as a baseline on which to pursue quality improvement.MethodsStakeholders involved in the PEOIP met weekly to determine the most important outcomes for patients diagnosed with epilepsy, create a standardized electronic note with defined fields (patient demographics, seizure and syndrome type and frequency and specific outcomes‐ seizure type and frequency, adverse effects, emergency department visits, hospitalization, and care pathways for clinical decision support. These were embedded in the electronic health record from which the fields were extracted into a data display platform that provided patient‐ and population‐level dashboards updated every 36 hours. Provider satisfaction and family experience surveys were performed to assess the impact of the standardized electronic note.ResultsIn the last 5 years, 3,245 unique patients involving 13, 831 encounters had prospective, longitudinal, standardized epilepsy data accrued via point‐of‐care data entry into an electronic note as part of routine clinical care. A provider satisfaction survey of the small number of users involved indicated that the vast majority believed that the note makes documentation more efficient. A family experience survey indicated that being provided with the note was considered “valuable” or “really valuable” by 86% of respondents and facilitated communication with family members, school, and advocacy organizations.SignificanceThe PEOIP serves as a proof of principle that information obtained as part of routine clinical care can be collected in a prospective, standardized, efficient manner and be used to construct filterable process/outcome dashboards, updated in near time (36 hours). This information will provide the necessary baseline data on which multiple of QI projects to improve meaningful outcomes for children with epilepsy will be based.

Postpartum Note Template Implementation Demonstrates Adherence to Recommended Counseling Guidelines.

Postpartum visits may provide patients with an inadequate amount of counseling on postpartum depression, birth spacing, healthy eating, exercise, or changes in sexual response and emotions. We created a template in our electronic health record (EHR) with the aid of our clinical informatics department to increased adherence with recommended counseling guidelines. We retrospectively reviewed the postpartum visits of 200 patients who had a delivery and received postpartum care. Patients were seen in a resident-run clinic: 100 visits occurred prior to implementation of the template, while 100 visits occurred post-implementation with use of the template. We observed for documentation of counseling on Pap smear, birth spacing, breastfeeding, contraception, depression, gestational diabetes mellitus, pre-eclampsia, and sleep/fatigue. Descriptive statistics of mean and standard deviation were used to describe the continuous variables. Frequency and percentage were used to describe the continuous variables. Analysis of variance compared the continuous variables. The Pearson chi-square test compared the categorical variables. In visits that occurred without use of the template, counseling was charted as low as 1.0% for birth spacing to as high as 86.0% for contraception. With use of the template, counseling was charted as 100% in all visits for each of the recommended counseling guidelines (all p < 0.001). In conclusion, an EHR template for documentation of postpartum visits is associated with resident adherence with recommended postpartum counseling guidelines. Managers in hospitals and clinical practices should consider incorporating OBGYN-specific EHR note templates to improve quality and increase adherence with recommended guidelines during postpartum visits.

Bone conduction hearing device adherence in relationship to age in pediatric unilateral congenital aural atresia

ObjectiveTo characterize the adherence of bone conduction hearing devices (BCHDs) for hearing management in children with unilateral congenital aural atresia (UCAA) in relation to the age of offer and fitting. BCHD Soft Bands help predict amplification benefits before surgery can be performed beginning around five years when both hearing and parental compliance reach stability. We hypothesized device compliance might decrease with age of fitting from lack of early acclimatization. MethodsRetrospective case series of patients less than five years old at a tertiary pediatric center's microtia clinic database, born between 2014 and 2018 with UCAA. Adherence was assessed through electronic health record note documentation at less than 1 year, 1–2 years, and greater than 2 years from fitting. The ages at offer and fitting, along with the time from offer to fitting, were recorded. ResultsOne hundred and eight patients with UCAA were identified, including 46 patients fit with a BCHD used for further analysis. Adherence rates at 1 year, 1–2 years, and greater than 2 years were 47.8%, 30%, and 43.5%, respectively. However, there was no significant association between age offered, age fit, or time from offer to fit and adherence at all time points. Also, there was no significant difference between ages at the time of BCHD offer for those who chose not to proceed with fitting (20.9 months) compared to the age of offer in patients that were subsequently fit (13.9 months). ConclusionBCHD adherence in patients less than five years old may not be affected by the age offered or fit. The time between offer and fitting was also not associated with usage. BCHDs should be offered to UCAA patients regardless of age. Further investigation in this younger age group would help expand these findings.

Identifying Symptom Information in Clinical Notes Using Natural Language Processing.

Symptoms are a core concept of nursing interest. Large-scale secondary data reuse of notes in electronic health records (EHRs) has the potential to increase the quantity and quality of symptom research. However, the symptom language used in clinical notes is complex. A need exists for methods designed specifically to identify and study symptom information from EHR notes. We aim to describe a method that combines standardized vocabularies, clinical expertise, and natural language processing to generate comprehensive symptom vocabularies and identify symptom information in EHR notes. We piloted this method with five diverse symptom concepts: constipation, depressed mood, disturbed sleep, fatigue, and palpitations. First, we obtained synonym lists for each pilot symptom concept from the Unified Medical Language System. Then, we used two large bodies of text (clinical notes from Columbia University Irving Medical Center and PubMed abstracts containing Medical Subject Headings or key words related to the pilot symptoms) to further expand our initial vocabulary of synonyms for each pilot symptom concept. We used NimbleMiner, an open-source natural language processing tool, to accomplish these tasks and evaluated NimbleMiner symptom identification performance by comparison to a manually annotated set of nurse- and physician-authored common EHR note types. Compared to the baseline Unified Medical Language System synonym lists, we identified up to 11 times more additional synonym words or expressions, including abbreviations, misspellings, and unique multiword combinations, for each symptom concept. Natural language processing system symptom identification performance was excellent. Using our comprehensive symptom vocabularies and NimbleMiner to label symptoms in clinical notes produced excellent performance metrics. The ability to extract symptom information from EHR notes in an accurate and scalable manner has the potential to greatly facilitate symptom science research.

Leveraging an electronic health record note template to standardize screening and testing for COVID-19

The coronavirus disease 2019 (COVID-19) pandemic challenged health care organizations to develop ways to provide patient care with rapidly changing guidelines and scarce resources. Clinical leaders and informatics specialists partnered to rapidly develop an electronic health record (EHR) template for primary care staff to screen Veterans at Veterans Affairs (VA) Puget Sound. The template prompts categorization of patients by stability and suspicion for COVID-19, and provides just-in-time triaging advice for clinic staff. Each category is a discrete data element and this information was used by leadership to track screening and testing volumes. We found that a brief, practical EHR note template can be quickly adopted to inform guideline-based screening, direct patient care, and conserve resources.

Generating Medical Assessments Using a Neural Network Model: Algorithm Development and Validation

BackgroundSince its inception, artificial intelligence has aimed to use computers to help make clinical diagnoses. Evidence-based medical reasoning is important for patient care. Inferring clinical diagnoses is a crucial step during the patient encounter. Previous works mainly used expert systems or machine learning–based methods to predict the International Classification of Diseases - Clinical Modification codes based on electronic health records. We report an alternative approach: inference of clinical diagnoses from patients’ reported symptoms and physicians’ clinical observations.ObjectiveWe aimed to report a natural language processing system for generating medical assessments based on patient information described in the electronic health record (EHR) notes.MethodsWe processed EHR notes into the Subjective, Objective, Assessment, and Plan sections. We trained a neural network model for medical assessment generation (N2MAG). Our N2MAG is an innovative deep neural model that uses the Subjective and Objective sections of an EHR note to automatically generate an “expert-like” assessment of the patient. N2MAG can be trained in an end-to-end fashion and does not require feature engineering and external knowledge resources.ResultsWe evaluated N2MAG and the baseline models both quantitatively and qualitatively. Evaluated by both the Recall-Oriented Understudy for Gisting Evaluation metrics and domain experts, our results show that N2MAG outperformed the existing state-of-the-art baseline models.ConclusionsN2MAG could generate a medical assessment from the Subject and Objective section descriptions in EHR notes. Future work will assess its potential for providing clinical decision support.

Automatic Detection of Hypoglycemic Events From the Electronic Health Record Notes of Diabetes Patients: Empirical Study.

BackgroundHypoglycemic events are common and potentially dangerous conditions among patients being treated for diabetes. Automatic detection of such events could improve patient care and is valuable in population studies. Electronic health records (EHRs) are valuable resources for the detection of such events.ObjectiveIn this study, we aim to develop a deep-learning–based natural language processing (NLP) system to automatically detect hypoglycemic events from EHR notes. Our model is called the High-Performing System for Automatically Detecting Hypoglycemic Events (HYPE).MethodsDomain experts reviewed 500 EHR notes of diabetes patients to determine whether each sentence contained a hypoglycemic event or not. We used this annotated corpus to train and evaluate HYPE, the high-performance NLP system for hypoglycemia detection. We built and evaluated both a classical machine learning model (ie, support vector machines [SVMs]) and state-of-the-art neural network models.ResultsWe found that neural network models outperformed the SVM model. The convolutional neural network (CNN) model yielded the highest performance in a 10-fold cross-validation setting: mean precision=0.96 (SD 0.03), mean recall=0.86 (SD 0.03), and mean F1=0.91 (SD 0.03).ConclusionsDespite the challenges posed by small and highly imbalanced data, our CNN-based HYPE system still achieved a high performance for hypoglycemia detection. HYPE can be used for EHR-based hypoglycemia surveillance and population studies in diabetes patients.