Physician Documentation Research Articles

Proton pump inhibitors in inpatients: Are we getting it right? A retrospective analysis

Background: Proton pump inhibitors (PPIs) are commonly prescribed to hospitalized patients, but many of these prescriptions may not be based on evidence-based indications. It’s important to understand that inappropriate prescribing of PPIs can lead to unnecessary medications and financial burdens. Unfortunately, there are not many recent studies exploring how often PPIs are prescribed and if they are being prescribed appropriately. Objective: The study aimed to assess the appropriateness of PPIs use among hospitalized patients. It evaluated the indications for PPIs use and determined whether the use of PPIs in hospitalized patients is justified or not. Setting: The study was conducted at Hamad General Hospital, a tertiary academic healthcare center in the state of Qatar. Methods: A retrospective observational study with 201 subjects, was conducted in general internal medicine wards at a tertiary hospital. Physician documentation and inpatient and outpatient medication prescriptions were analyzed for PPIs exposure. Main outcome measures: The appropriateness of exposure to PPIs is determined based on international recommendations. Results: Of 533 hospitalized patients who were not critically ill, 201 (37.7%) were prescribed PPIs. The study found that 65.2% of the patients had no valid indication for PPIs exposure. Furthermore, 18% of patients were inappropriately prescribed stress ulcer prophylaxis with PPIs even though they had a low risk for the development of ulcer disease. After discharge, 82.6% of patients were prescribed PPIs, with the most common indication (43%) being gastrointestinal ulcer prophylaxis. Conclusion: This study sheds light on the issue of overutilization of PPIs, specifically in non-critically ill hospitalized patients. It highlights the unnecessary continuation of PPI prescriptions at discharge and emphasizes the importance of physicians reevaluating PPI prescriptions periodically to ensure they are still necessary and discontinuing them when possible to avoid unwanted consequences.

Occurrence of Stigmatizing Documentation Among Hospital Medicine Encounters With Opioid-Related Diagnosis Codes: Cohort Study.

Physician use of stigmatizing language in the clinical documentation of hospitalized adults with opioid use is common. However, patient factors associated with stigmatizing language in this setting remain poorly characterized. This study aimed to determine whether specific demographic factors and clinical outcomes are associated with the presence of stigmatizing language by physicians in the clinical documentation of encounters with opioid-related ICD-10 (International Statistical Classification of Diseases, Tenth Revision) codes. Hospital encounters with one or more associated opioid-related ICD-10 admission diagnoses on the hospital medicine service during the 2020 calendar year were analyzed for the presence of stigmatizing language in history and physical and discharge summaries. Multivariable adjusted logistic regression models were used to determine associations of age, race, gender, medication for addiction treatment use, against medical advice discharge, homelessness, comorbid polysubstance use, comorbid psychiatric disorder, comorbid chronic pain, cost, and 30-day readmission with the presence of stigmatizing language. A total of 221 encounters were identified, of which 64 (29%) encounters had stigmatizing language present in physician documentation. Most stigmatizing language was due to use of "substance abuse" rather than the preferred term "substance use" (63/66 instances). Polysubstance use and homelessness were independently associated with the presence of stigmatizing language (adjusted odds ratio [aOR] 7.83; 95% CI 3.42-19.24 and aOR 2.44; 95% CI 1.03-5.90) when controlling for chronic pain and other covariates. Among hospital medicine encounters with an opioid-related diagnosis, stigmatizing language by physicians in clinical documentation was common and independently associated with comorbid polysubstance use and homelessness.

34 Improving language concordant care in the paediatric emergency department

Abstract Background Paediatric patients and families with limited English proficiency (LEP) experience worse health outcomes. Use of professional medical interpreter services (IS) helps ensure that all patients receive high quality care, regardless of their preferred language of communication. Objectives The aim of this quality improvement (QI) study was to improve language concordant care within a paediatric emergency department (ED) in downtown Toronto by increasing the rate of over-the-phone interpreter use by 50% by July 2024 and to understand common reasons for interpreter non-use. Design/Methods Using the model for improvement, we assembled an interdisciplinary team that included physicians, ED registration clerks, triage nurses, and language services staff to understand current workflow and develop targeted interventions aimed at addressing key drivers through multiple plan-do-study-act (PDSA) cycles. Interventions included introduction of a standardized script to capture language preference at ED registration, EMR-integrated preferred language notification and smart text template in provider notes for standardized IS use or non-use documentation, and departmental education. Our primary outcome measure was rate of over-the-phone IS use for all ED visits. Process measures were rate of EMR documentation of patients and caregivers with non-English language preference (NELP) and rate of provider documentation of IS use or non-use. Balancing measures included time to provider initial assessment (PIA) and ED length of stay. Results The baseline period (November 2022-April 2023) revealed an over-the-phone IS rate of 5.2% for all ED visits. The initial results from the first 6 months of the intervention period demonstrated an increase in physician documentation of IS use or non-use in patients with NELP, from 10% to 76%. Additionally, 18.6% of patients or caregivers with NELP had IS use per provider notes. Over the next 9 months of the intervention period, special cause variation is anticipated in the rate of IS use and rate of EMR documentation of NELP. The most common reasons for IS non-use were: ‘deemed unnecessary by provider’, ‘declined by family’ and ‘use of family member/friend as interpreter’. There was no change in PIA or ED length of stay for patients with NELP. Conclusion This QI initiative increased consistent provider documentation of IS use in ED patient records in one of the most linguistically diverse cities in the world. Future efforts will focus on exploring additional ways to capture language preference beyond registration, facilitating IS use in the ED, and addressing top reasons for non-use of IS in patients and caregivers with NELP.

Beyond Tobacco: Bridging Gaps in Social History Records for Tobacco‐Free Nicotine Pouch Consumers

AbstractObjectiveNicotine‐containing products have historically been tobacco derivatives like cigarettes, cigars, and dip. Recently, tobacco‐free nicotine (TFN) products have been marketed as a healthy alternative. TFN pouches are small, discreet, flavored pouches containing nicotine designed to be placed between the gum and lip. This product does not fit a conventional tobacco category, leading to inaccurate reporting. This study aims to investigate discrepancies in physician documentation of TFN pouches.MethodsA retrospective chart review was conducted on TFN users.SettingSingle Health Care System.MethodsStatistical analyses assessed TFN documentation concordance between social history templates and physician notes.ResultsThere were 150 patients who used TFN and 841 patients who vaped. Concordance was higher for vape documentation than TFN pouch documentation (55.9%, 470/841 vs 25.3%, 38/150; P < .001). Of those who used TFN, 60% (90/150) were classified as “Smokeless Tobacco Users” in the social history; however, 35 were inaccurately classified as chew, and 17 did not specify TFN use. Only 38 specified TFN use; only 25% (38/150) of records demonstrated concordance.ConclusionOnly 25% of records were concordant with physician notes, highlighting the need for a designated place for TFN use within social history templates. Nicotine use history is crucial in the setting of microvascular reconstruction and cosmetic surgeries. Thus, accurate reporting is crucial for future research on the long‐term effects of TFN. This study's findings underscore a deficit in current social history templates and the need to recognize TFN pouches as distinct entities.

Didactic Instruction's Impact on Medicolegal Quality of Radiation Oncology Resident Physician Documentation.

Effective documentation serves as a cornerstone for communication and patient care, especially in radiation oncology (RO). Studies have shown room for improvement in documentation practices, and although documentation guidelines exist, it is uncertain if RO physicians are aware of or adhere to them. We aimed to assess RO resident physicians' medicolegal knowledge and the impact of an educational intervention on documentation practices. Grading rubrics for consultation and progress notes were created using guidelines, comprising of a fundamental score and total score. Residents from two institutions attended a didactic seminar on medicolegal documentation. Pre- and post-seminar, an electronic anonymous survey was used to assess resident knowledge and perspectives and random resident consultation and progress notes were scored. Mean documentation and survey item scores from pre- and post-seminar were compared. Fourteen resident physicians participated and completed surveys, and 48 consultation notes and 40 progress notes were analyzed. No participant had prior education specific to RO documentation, nor were any aware of available resources. Post-seminar, participants' medicolegal documentation knowledge significantly increased (86.61% vs. 95.54%, p = 0.001), as did the fundamental score (83.64% vs 89.29%, p = 0.041) and total scores of consultation notes (69.82% vs. 78.98%, p = 0.001) and total score of progress notes (55% vs. 75.19%, p < 0.001). Our seminar significantly enhanced residents' medicolegal knowledge and quality of documentation, and surveys revealed a lack of speciality specific documentation education. This combined with findings from other studies and participant opinions suggest that resident physicians would benefit from such training during residency.

145 Didactic Instruction’s Impact Upon Medicolegal Quality of Radiation Oncology Resident Physician Documentation

145 Didactic Instruction’s Impact Upon Medicolegal Quality of Radiation Oncology Resident Physician Documentation

Physician EHR Time and Visit Volume Following Adoption of Team-Based Documentation Support

Physicians spend the plurality of active electronic health record (EHR) time on documentation. Excessive documentation limits time spent with patients and is associated with burnout. Organizations need effective strategies to reduce physician documentation burden; however, evidence on team-based documentation (eg, medical scribes) has been limited to small, single-institution studies lacking rigorous estimates of how documentation support changes EHR time and visit volume. To analyze how EHR documentation time and visit volume change following the adoption of team-based documentation approaches. This national longitudinal cohort study analyzed physician-week EHR metadata from September 2020 through April 2021. A 2-way fixed-effects difference-in-differences regression approach was used to analyze changes in the main outcomes after team-based documentation support adoption. Event study regression models were used to examine variation in changes over time and stratified models to analyze the moderating role of support intensity. The sample included US ambulatory physicians using the EHR. Data were analyzed between October 2022 and September 2023. Team-based documentation support, defined as new onset and consistent use of coauthored documentation with another clinical team member. The main outcomes included weekly visit volume, EHR documentation time, total EHR time, and EHR time outside clinic hours. Of 18 265 physicians, 1024 physicians adopted team-based documentation support, with 17 241 comparison physicians who did not adopt such support. The sample included 57.2% primary care physicians, 31.6% medical specialists, and 11.2% surgical specialists; 40.0% practiced in academic settings and 18.4% in outpatient safety-net settings. For adopter physicians, visit volume increased by 6.0% (2.5 visits/wk [95% CI, 1.9-3.0]; P < .001), and documentation time decreased by 9.1% (23.3 min/wk [95% CI, -30.3 to -16.2]; P < .001). Following a 20-week postadoption learning period, visits per week increased by 10.8% and documentation time decreased by 16.2%. Only high-intensity adopters (>40% of note text authored by others) realized reductions in documentation time, both for the full postadoption period (-53.9 min/wk [95% CI, -65.3 to -42.4]; 21.0% decrease; P < .001) and following the learning period (-72.2 min/wk; 28.1% decrease). Low adopters saw no meaningful change in EHR time but realized a similar increase in visit volume. In this national longitudinal cohort study, physicians who adopted team-based documentation experienced increased visit volume and reduced documentation and EHR time, especially after a learning period.

Accuracy, thoroughness, and quality of outpatient primary care documentation in the U.S. Department of Veterans Affairs

BackgroundElectronic health records (EHRs) can accelerate documentation and may enhance details of notes, or complicate documentation and introduce errors. Comprehensive assessment of documentation quality requires comparing documentation to what transpires during the clinical encounter itself. We assessed outpatient primary care notes and corresponding recorded encounters to determine accuracy, thoroughness, and several additional key measures of documentation quality.MethodsPatients and primary care clinicians across five midwestern primary care clinics of the US Department of Veterans Affairs were recruited into a prospective observational study. Clinical encounters were video-recorded and transcribed verbatim. Using the Physician Documentation Quality Instrument (PDQI-9) added to other measures, reviewers scored quality of the documentation by comparing transcripts to corresponding encounter notes. PDQI-9 items were scored from 1 to 5, with higher scores indicating higher quality.ResultsEncounters (N = 49) among 11 clinicians were analyzed. Most issues that patients initiated in discussion were omitted from notes, and nearly half of notes referred to information or observations that could not be verified. Four notes lacked concluding assessments and plans; nine lacked information about when patients should return. Except for thoroughness, PDQI-9 items that were assessed achieved quality scores exceeding 4 of 5 points.ConclusionsAmong outpatient primary care electronic records examined, most issues that patients initiated in discussion were absent from notes, and nearly half of notes referred to information or observations absent from transcripts. EHRs may contribute to certain kinds of errors. Approaches to improving documentation should consider the roles of the EHR, patient, and clinician together.

Implementation of standardized electronic documentation of goals of care discussions to improve cancer care.

11127 Background: Early documentation of physician-led goals of care (GOC) discussions is important to providing comprehensive and individualized quality care to cancer patients as it can provide all members of the patient care team with a context for the type of care each patient wishes to receive prior to and at end of life. The electronic medical record (EMR) should provide easy access to these conversations to seamlessly integrate outpatient, emergency room and inpatient care of cancer patients. Methods: The institution-wide initiative was introduced via presentations and emails between 8/2021 and 11/2021 to all Moores Cancer Center faculty at UC San Diego Health. A SmartPhrase was created in our EMR Epic as the intervention, including critical components of a GOC discussion: people present during discussion, goal of cancer-directed treatment, anticipated cancer trajectory shared with the patient, and patient’s health care agent. The SmartPhrase was radiolabeled to be easily searchable for any clinician accessing the patient’s chart. Physician documentation was tracked for the purposes of achieving a group goal with a target of greater than 50% documentation of GOC discussions within 30 days of the first day of the first cycle of chemotherapy. Prior to physician education, 4% of patients had a GOC note using a searchable SmartPhrase. In 12/2021, we began sending individual emails to physicians to remind them of eligible patients. Results: By 1/2022, after education, 50% of physicians ordering chemotherapy had used the GOC SmartPhrase and 29% of patients initiating chemotherapy had a GOC note using the SmartPhrase. After initiation of monthly reminder emails, documentation increased to 51% by 10/2022. An increased use of Advanced Care Planning billing codes was also noted. Conclusions: Implementation of an initiative to standardize electronic documentation of GOC conversations improved early documentation of these vital conversations. Radiolabeling of the SmartPhrase made it easily accessible to all members of a patient’s care team.

Large language models to evaluate racial discrepancies in performance status assignment.

1561 Background: Oncologic treatment eligibility relies heavily on “Performance Status” (PS), a subjective gauge of a patient's overall health. Despite frameworks aimed at quantifying PS, these assessments remain prone to potential bias. A systematic evaluation of discrepancies in language between ECOG PS and race has yet to be conducted. Large language models (LLMs) have the ability to synthesize text and may enable an assessment of the relationship between race, note text, and physician-documented PS. We hypothesize that LLMs can quantify these relationships to understand potential inconsistencies in ECOG PS. Methods: In our single-institution cohort study, we examined patients from medical or radiation oncology clinics between January 2012 to December 2023 with documented ECOG PS. PS was extracted from clinical notes and redacted from downstream analyses. Notes were categorized by patient-reported race (Asian, Black, White, Other). 1,500 matched subjective assessments (from oncologist clinical notes) and PS were randomly sampled for each race, except for Black patients, where only 640 entries were available. We divided training and test sets using an 80-20 ratio across each race. Using the training cohort, we trained race-specific models to assign ECOG PS based on subjective assessment, using two LLMs: UCSFBERT (BERT pretrained on UCSF data) and RoBERTa. In the hold-out test sets, we applied each model across all races to assign ECOG PS based on subjective assessments. These were evaluated by micro-F1 (model accuracy) and Multiway ANOVA to compute model-specific p-values. Results: 13.6% of patients had a documented ECOG 2+, with variation across races (Asian: 16.1%, Black: 17.7%, White: 7.7%, Other: 15.3%). Models tended to assign Black patients with ECOG 0-1 with worse performance status (ECOG 2+). Other than RoBERTa models trained on Asian and White cohorts, all models trained on a specific race showed disparate classification results when applied to other races (out-of-domain), highlighting potential biases in LLM models trained where a specific race predominates (Table; ANOVA). Conclusions: This study demonstrates a novel way to use LLM to assess discordance within physician documentation and performance status assignment. It underscores the need for incorporating diverse demographic data when using LLM in medical contexts. This research has potential to dissect how bias may be propagated within physician practice and provide insight into known disparities in clinical trial enrollment and standard of care implementation.[Table: see text]

The Impact of Real-Time Documentation of In-Hospital Medication Changes on Preventing Undocumented Discrepancies at Discharge and Improving Physician-Pharmacist Communication: A Retrospective Cohort Study and Survey.

Transitional medication safety is crucial, as miscommunication about medication changes can lead to significant risks. Unclear or incomplete documentation during care transitions can result in outdated or incorrect medication lists at discharge, potentially causing medication errors, adverse drug events, and inadequate patient education. These issues are exacerbated by extended hospital stays and multiple care events, making accurate medication recall challenging at discharge. Thus, we aimed to investigate how real-time documentation of in-hospital medication changes prevents undocumented medication changes at discharge and improves physician-pharmacist communication. We conducted a retrospective cohort study in a tertiary hospital. Two pharmacists reviewed medical records of patients admitted to the acute medical unit from April to June 2020. In-hospital medication discrepancies were determined by comparing preadmission and hospitalization medication lists and it was verified whether the physician's intent of medication changes was clarified by documentation. By a documentation rate of medication changes of 100% and <100%, respectively, fully documented (FD) and partially documented (PD) groups were defined. Any undocumented medication changes at discharge were considered a "documentation error at discharge". Pharmacists' survey was conducted to assess the impact of appropriate documentation on the pharmacists. After reviewing 400 medication records, patients were categorized into FD (61.3%) and PD (38.8%) groups. Documentation errors at discharge were significantly higher in the PD than in the FD group. Factors associated with documentation errors at discharge included belonging to the PD group, discharge from a non-hospitalist-managed ward, and having three or more intentional discrepancies. Pharmacists showed favorable attitudes towards physician's documentation. Appropriate documentation of in-hospital medication changes, facilitated by free-text communication, significantly decreased documentation errors at discharge. This analysis underlines the importance of communication between pharmacists and hospitalists in improving patient safety during transitions of care.

A web-based, LLM-powered AI symptom summarization tool (ASST) for monitoring of breast cancer treatment toxicity.

e13622 Background: Traditional methods for capturing patient-reported outcomes (PROs) are often time-consuming and may lead to underreporting of symptoms by physicians. With advancements in artificial intelligence (AI), particularly large language models (LLMs) like GPT-4, there is potential to revolutionize this aspect of patient care. Methods: This study developed and tested a GPT-4-based web application for monitoring cancer treatment toxicity in breast cancer patients. The application utilized 35 items from the PRO-CTCAE scale to create an interactive form for patients to report treatment-related symptoms. Upon form completion, a natural language summary of the patient’s responses was generated using the GPT-4 API for physician review. Nine radiation oncologists (5 attendings, 4 residents) evaluated the summaries of virtual patients using the adapted Physician Documentation Quality Index (PDQI-9). PDQI-9 consists of 9 items scored using a 5-point Likert scale (1 -not at all- to 5. -extremely-). IRB approval was not required because this study did not use real patient data, in accordance with the 2018 Revised Common Rule Requirements of the NIH. All data used were researcher-generated and non-identifiable. Results: The mean time for textual summary generation was 7 (5.7-9.2) seconds. The AI-Symptom Summarization Tool (ASST) mean scores were 4.25 for accuracy and 4 for thoroughness. Usefulness, organization, comprehensibility, concision, synthesis quality and consistency were all rated between 3 and 4. Overall score was 42/50. No hallucinations (false information made up by the LLM) were found. Conclusions: The GPT-4-based application for cancer treatment toxicity monitoring demonstrates significant promise in enhancing the quality and efficiency of patient care. By automating the documentation of patient-reported symptoms, this tool could allow physicians to focus more time on patient interaction and individualized care. As AI technologies continue to evolve, their integration into clinical practice must be approached with caution, emphasizing augmentation over replacement and the importance of verification to maintain trust in these new tools.

Outcomes of rituximab as treatment for immune thrombocytopenic purpura in patients who have failed steroids or IVIG: A retrospective study in a community practice.

e23256 Background: Immune thrombocytopenic purpura (ITP) is a challenging disorder with multiple treatment options. The 2019 American Society of Hematology guidelines outline treatment recommendations for ITP which include intravenous immunoglobulin (IVIG) and steroids as first-line, with Thrombopoietin receptor agonists (TPO-RAs) and Rituximab as second-line agents. They favor TPO-RAs over Rituximab but suggest that the choice should be individualized. In this study, we explore the rate and duration of response to Rituximab as a second-line agent for ITP. We also analyze relapse rates and response to sequential TPO-RAs. Methods: A retrospective study of patients with ITP managed in a community practice from 2018 to 2022. The practice’s electronic medical records were searched for the keywords “ITP” and “Rituximab”. 87 patients fit the search terms. We included patients above age 18 treated with Rituximab for ITP after failing steroids or IVIG. We excluded duplicates, incomplete medical records, patients given Rituximab for reasons other than ITP, patients treated with medications other than steroids or IVIG prior to Rituximab, and patients given less than 4 doses of Rituximab. 60 out of 87 patients were eligible. The primary outcome was response to Rituximab defined as platelets above 30,000 per microliter of blood after 12 weeks of its initiation. Secondary outcomes include relapse rate, duration of response, and subsequent response to TPO-RAs. Secondary outcomes were determined by chart-reviewing physician documentation. Results: SAS 9.4 (SAS/STAT Inst., Carry NC) was used for all data. Categorical variables were quoted as absolute numbers and relative frequencies. A test result was considered statistically significant if p &lt; 0.05. For categorical variables, likelihood ratio chi-square, and Fisher’s exact tests were conducted for 2*2 and r*c contingency tables to test associations. 96.7% of eligible patients responded to Rituximab (P &lt; 0.0001), however 46.7% relapsed. 42.9% of relapses happened in less than 1 year, 14.3% in 1 year, 21.4% in 2 years, 7.1% in 3 years, 10.7% in 4 years, and 3.6% in 5 or more years (P = 0.0043). The response rate to TPO-RAs after Rituximab failure was 88%. No significant toxicity from Rituximab was noted beyond previously reported minor side effects, and there was no treatment-related death. Conclusions: The response rate to Rituximab was 96.7% (P &lt; 0.0001) which was sustained in 53.3% of patients. Most relapsed patients responded well to TPO-RAs. These numbers are very comparable to previously reported response to Rituximab. Therefore, we believe that the strategy of using Rituximab as second-line and reserving TPO-RAs for non-responders is clinically-effective and certainly cost-effective given the fact that Rituximab is administered over four weeks as compared to the often lifetime treatment with TPO-RAs.

Enhancing Procedure Documentation in Neonatal Intensive Care Unit (NICU): A Quality Improvement Initiative at a Tertiary Neonatal Hospital.

Background Accurate and comprehensive procedure documentation in Electronic Medical Records (EMR) is crucial for high-quality patient care, especially in high-acuity settings like Neonatal Intensive Care Units (NICU). Gaps in documentation at Corniche Hospital's NICU that were affecting patient safety and continuity of care were identified and addressed by following a pre and post-intervention design in the research. The process involved the initial audit, educational sessions with healthcare providers, and follow-up audits to measure improvements.Results post-intervention showed a significant increase in compliance with documentation standards, pointing out the effectiveness of educational interventions in improving EMR documentation practices. The local problem is demonstrated through the observation ofincomplete and inconsistent procedure documentation in the NICU,hindering effective patient management and multi-disciplinary team communication. Methods A Quality Improvement Project (QIP) was implemented, including a baseline audit, educational interventions targeting healthcare providers, and subsequent re-audits to assess improvement. The project involved tailored educational sessions focused on correct EMR usage, adherence to documentation standards, and practical aspects of documenting procedures. Results Post-intervention, there was a significant increase in documentation compliance. The percentage of compliance in procedure encounter placement in EMR increased from 81% to 100%, and nursing documentation compliance improved from 11 (52.4%) to 18 (85.7%). However, a slight decrease in the completeness of physician documentation was noted. Conclusions The QIP effectively improved procedure documentation in the NICU. Continuous education and periodic review are essential for maintaining and further enhancing documentation standards. This initiative underscores the importance of targeted training and consistent audits in improving clinical documentation in healthcare settings.

Pharmacologic Anticoagulation Is Associated With a Lower Risk of Recurrent Venous Thromboembolic Events During Janus Kinase Inhibitor Use for Patients With a Prior Thrombosis.

Janus kinase (JAK) inhibitors tofacitinib and upadacitinib are effective therapies for inflammatory bowel disease and rheumatologic disorders but currently possess a warning for increased venous thromboembolism (VTE) risk. Some patients with a history of VTE may benefit from a JAK inhibitor, but the risk of recurrent VTE with JAK inhibitor use is unclear. Our goal was to observe rates of new VTE events after starting JAK inhibitor therapy in patients with a prior VTE, and observe whether concurrent anticoagulation (AC) reduces this risk. We conducted a review of adults prescribed tofacitinib or upadacitinib between January 1, 2000, and June 30, 2023, with a prior history of VTE. Patient charts were reviewed for demographic data, disease type, and VTE date(s), and to verify duration of JAK inhibitor use along with any concurrent AC. VTEs following JAK inhibitor initiation were identified by International Classification of Diseases-Tenth Revision code and verified by physician documentation and imaging. We identified 79 patients with a documented VTE history before initiating JAK inhibitors, 47 of whom began a JAK inhibitor with concurrent AC. Of these, 15 patients discontinued AC while receiving JAK inhibitors. In total, 5 new VTE events were observed during 55.42 patient-years of JAK inhibitor treatment without concurrent AC (9.0 events per 100 patient-years), while no new VTE events occurred during 65.2 patient-years of JAK inhibitor treatment with concurrent AC, demonstrating a lower risk of recurrent VTE (P = .020). These results suggest that for patients with a prior VTE history there is a high risk for recurrent VTE while receiving JAK inhibitors. Concurrent use of AC with JAK inhibitors appears to be protective against recurrent VTEs in this population.

Abstract PO4-02-11: Optimizing Taxane-based Chemotherapy in Breast Cancer: Retrospective study comparing 4 cycles of TC to 6 cycles of TC

Abstract Breast cancer remains one of the most prevalent cancers among women worldwide. First-line chemotherapy options include anthracycline (AC-T) and Taxane (TC) based regimens. While anthracycline-based chemotherapy is most commonly used, the use of anthracycline-sparing regimens is also approved. The US Oncology 9735 trial conducted in the mid 2000s showed that four cycles of docetaxel and cyclophosphamide (TC4) were superior to four cycles of Doxorubicin and cyclophosphamide (AC). The follow-up ABC trials compared six cycles of TC(TC6) to AC-T. This trial showed that while AC-T was superior to TC, the difference was modest. AC-T has remained the standard of care, but TC is an acceptable option. One retrospective analysis involving 143 patients showed TC4 was non-inferior to TC6, and suggested that TC4 had fewer adverse events; however, statistical significance was not reached. The question remains whether six cycles of TC is required, or if four cycles is adequate. Methods: Patient information was retrieved from the EMR of a large private oncology group. The EMR was screened for all breast cancer patients who began treatment with TC between 1/1/2011 and 12/31/2021. Patients were required to have continuous follow-up, documented up to at least 6/30/2022. Only patients receiving TC as the first-line setting were included, while patients with metastatic disease were excluded. Adjusted Kaplan Meier curves for overall survival (OS) and disease-free survival (DFS) were generated. A log-rank test was used to determine the statistical difference between the two curves. OS was defined from the date of the last chemotherapy given to death. DFS is defined from the date of the last chemotherapy given to disease recurrence. The Chi-square analysis test of homogeneity was conducted to evaluate the differences in reported symptoms. Statistical analysis was completed with IBM SPSS version 29. Ethical approval was obtained from The Brooklyn Hospital Center Institutional Review Board. Results: A total of 376 charts were reviewed, out of which 224 met the criteria for inclusion. Of these 191 patients received TC4 and 33 received TC6. TC4 patients were noted to be older than TC6 patients. There were a higher percentage of hormone-positive cancers in the TC4 group while the TC6 group had a larger proportion of triple-negative breast cancers. There was a larger proportion of stage III patients that received TC6 than in TC4. TC6 patients were also noted to receive neo-adjuvant chemotherapy at a substantially higher rate. A greater proportion of patients in the TC4 group received breast-conserving surgery, with radiation than the TC6 group. TC6 had a completion rate of 76 % (Table 1). There was a significant difference in DFS noted between TC4 and TC6 (p = 0.016) with TC6 patients having a higher rate of relapse. No difference was noted in the overall survival. No differences were seen in side effects between TC4 and TC6, however, there was a trend toward high rates of neutropenia, anemia, and neuropathy seen in the TC6 group (Table 2). Conclusions: This real-world retrospective study reviewed patients who received TC in a large community oncology practice. The study reaffirms conclusions seen in previous retrospective studies conducted in the academic setting that there is no difference in overall survival when using six cycles of TC compared to four cycles of TC. Slight detriment was seen in the DFS setting when using TC6 however the small sample size along with the larger proportion of patients with stage III disease make it challenging to interpret this finding. There was a trend towards higher toxicities with TC6 that did not reach significance. Until a prospective randomized study comparing four vs six cycles of TC is conducted no definitive conclusions can be drawn, however, this study contributes to the current body of evidence that four cycles of TC is adequate and could potentially improve the quality of life of patients with early breast cancer. Table. Patient characteristics Patient characteristics including age, hormone status, stage, type of surgery, radiation, and treatment setting. Table. Adverse effects Adverse effect information obtained from physician documentation, and CBC reports documented at time of treatment with TC. Citation Format: Amith Ahluwalia, Michelle Koifman, Jaspreet Nannar, Bhavya Vachhani, Kanwal Ashraf, Maxim Shulimovich. Optimizing Taxane-based Chemotherapy in Breast Cancer: Retrospective study comparing 4 cycles of TC to 6 cycles of TC [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO4-02-11.

The Utility of Dot Phrases and SmartPhrases in Improving Physician Documentation of Interpreter Use.

Patients with limited English proficiency (LEP) experience significant healthcare disparities. Clinicians are responsible for using and documenting their use of certified interpreters for patient encounters when appropriate. However, the data on interpreter use documentation in the emergency department (ED) is limited and variable. We sought to assess the effects of dot phrase and SmartPhrase implementation in an adult ED on the rates of documentation of interpreter use. We conducted an anonymous survey asking emergency clinicians to self-report documentation of interpreter use. We also retrospectively reviewed documentation of interpreter- services use in ED charts at three time points: 1)pre-intervention baseline; 2)post-implementation of a clinician-driven dot phrase shortcut; and 3)post-implementation of a SmartPhrase. Most emergency clinicians reported using an interpreter "almost always" or "often." Our manual audit revealed that at baseline, interpreter use was documented in 35% of the initial clinician note, 4% of reassessments, and 0% of procedure notes; 52% of discharge instructions were written in the patients' preferred languages. After implementation of the dot phrase and SmartPhrase, respectively, rates of interpreter-use documentation improved to 43% and 97% of initial clinician notes, 9% and 6% of reassessments, and 5% and 35% of procedure notes, with 62% and 64% of discharge instructions written in the patients' preferred languages. There was a discrepancy between reported rates of interpreter use and interpreter-use documentation rates. The latter increased with the implementation of a clinician-driven dot phrase and then a SmartPhrase built into the notes. Ensuring accurate documentation of interpreter use is an impactful step in language equity for LEP patients.

Using ChatGPT-4 to Create Structured Medical Notes From Audio Recordings of Physician-Patient Encounters: Comparative Study.

Medical documentation plays a crucial role in clinical practice, facilitating accurate patient management and communication among health care professionals. However, inaccuracies in medical notes can lead to miscommunication and diagnostic errors. Additionally, the demands of documentation contribute to physician burnout. Although intermediaries like medical scribes and speech recognition software have been used to ease this burden, they have limitations in terms of accuracy and addressing provider-specific metrics. The integration of ambient artificial intelligence (AI)-powered solutions offers a promising way to improve documentation while fitting seamlessly into existing workflows. This study aims to assess the accuracy and quality of Subjective, Objective, Assessment, and Plan (SOAP) notes generated by ChatGPT-4, an AI model, using established transcripts of History and Physical Examination as the gold standard. We seek to identify potential errors and evaluate the model's performance across different categories. We conducted simulated patient-provider encounters representing various ambulatory specialties and transcribed the audio files. Key reportable elements were identified, and ChatGPT-4 was used to generate SOAP notes based on these transcripts. Three versions of each note were created and compared to the gold standard via chart review; errors generated from the comparison were categorized as omissions, incorrect information, or additions. We compared the accuracy of data elements across versions, transcript length, and data categories. Additionally, we assessed note quality using the Physician Documentation Quality Instrument (PDQI) scoring system. Although ChatGPT-4 consistently generated SOAP-style notes, there were, on average, 23.6 errors per clinical case, with errors of omission (86%) being the most common, followed by addition errors (10.5%) and inclusion of incorrect facts (3.2%). There was significant variance between replicates of the same case, with only 52.9% of data elements reported correctly across all 3 replicates. The accuracy of data elements varied across cases, with the highest accuracy observed in the "Objective" section. Consequently, the measure of note quality, assessed by PDQI, demonstrated intra- and intercase variance. Finally, the accuracy of ChatGPT-4 was inversely correlated to both the transcript length (P=.05) and the number of scorable data elements (P=.05). Our study reveals substantial variability in errors, accuracy, and note quality generated by ChatGPT-4. Errors were not limited to specific sections, and the inconsistency in error types across replicates complicated predictability. Transcript length and data complexity were inversely correlated with note accuracy, raising concerns about the model's effectiveness in handling complex medical cases. The quality and reliability of clinical notes produced by ChatGPT-4 do not meet the standards required for clinical use. Although AI holds promise in health care, caution should be exercised before widespread adoption. Further research is needed to address accuracy, variability, and potential errors. ChatGPT-4, while valuable in various applications, should not be considered a safe alternative to human-generated clinical documentation at this time.

Should Artificial Intelligence Be Used for Physician Documentation to Reduce Burnout?

Should Artificial Intelligence Be Used for Physician Documentation to Reduce Burnout?

Resident Physician Documentation Practice Changes as a Result of Focused Training on the 2023 Evaluation and Management Coding Guidelines

Resident Physician Documentation Practice Changes as a Result of Focused Training on the 2023 Evaluation and Management Coding Guidelines