Real-Time Electronic Patient Portal Use Among Emergency Department Patients.

Importance: Patients with inequitable access to patient portals frequently present to emergency departments (EDs) for care. Little is known about portal use patterns among ED patients. Objectives: To describe real-time patient portal usage trends among ED patients and compare demographic and clinical characteristics between portal users and nonusers. Design, Setting, and Participants: In this cross-sectional study of 12 teaching and 24 academic-affiliated EDs from 8 health systems in California, Connecticut, Massachusetts, Ohio, Tennessee, Texas, and Washington, patient portal access and usage data were evaluated for all ED patients 18 years or older between April 5, 2021, and April 4, 2022. Exposure: Use of the patient portal during ED visit. Main Outcomes and Measures: The primary outcomes were the weekly proportions of ED patients who logged into the portal, viewed test results, and viewed clinical notes in real time. Pooled random-effects models were used to evaluate temporal trends and demographic and clinical characteristics associated with real-time portal use. Results: The study included 1 280 924 unique patient encounters (53.5% female; 0.6% American Indian or Alaska Native, 3.7% Asian, 18.0% Black, 10.7% Hispanic, 0.4% Native Hawaiian or Pacific Islander, 66.5% White, 10.0% other race, and 4.0% with missing race or ethnicity; 91.2% English-speaking patients; mean [SD] age, 51.9 [19.2] years). During the study, 17.4% of patients logged into the portal while in the ED, whereas 14.1% viewed test results and 2.5% viewed clinical notes. The odds of accessing the portal (odds ratio [OR], 1.36; 95% CI, 1.19-1.56), viewing test results (OR, 1.63; 95% CI, 1.30-2.04), and viewing clinical notes (OR, 1.60; 95% CI, 1.19-2.15) were higher at the end of the study vs the beginning. Patients with active portal accounts at ED arrival had a higher odds of logging into the portal (OR, 17.73; 95% CI, 9.37-33.56), viewing test results (OR, 18.50; 95% CI, 9.62-35.57), and viewing clinical notes (OR, 18.40; 95% CI, 10.31-32.86). Patients who were male, Black, or without commercial insurance had lower odds of logging into the portal, viewing results, and viewing clinical notes. Conclusions and Relevance: These findings suggest that real-time patient portal use during ED encounters has increased over time, but disparities exist in portal access that mirror trends in portal usage more generally. Given emergency medicine's role in caring for medically underserved patients, there are opportunities for EDs to enroll and train patients in using patient portals to promote engagement during and after their visits.

Implementable Prediction of Pressure Injuries in Hospitalized Adults: Model Development and Validation.

Background: Numerous pressure injury prediction models have been developed using electronic health record data, yet hospital-acquired pressure injuries (HAPIs) are increasing, which demonstrates the critical challenge of implementing these models in routine care. Objective: To help bridge the gap between development and implementation, we sought to create a model that was feasible, broadly applicable, dynamic, actionable, and rigorously validated and then compare its performance to usual care (ie, the Braden scale). Methods: We extracted electronic health record data from 197,991 adult hospital admissions with 51 candidate features. For risk prediction and feature selection, we used logistic regression with a least absolute shrinkage and selection operator (LASSO) approach. To compare the model with usual care, we used the area under the receiver operating curve (AUC), Brier score, slope, intercept, and integrated calibration index. The model was validated using a temporally staggered cohort. Results: A total of 5458 HAPIs were identified between January 2018 and July 2022. We determined 22 features were necessary to achieve a parsimonious and highly accurate model. The top 5 features included tracheostomy, edema, central line, first albumin measure, and age. Our model achieved higher discrimination than the Braden scale (AUC 0.897, 95% CI 0.893-0.901 vs AUC 0.798, 95% CI 0.791-0.803). Conclusions: We developed and validated an accurate prediction model for HAPIs that surpassed the standard-of-care risk assessment and fulfilled necessary elements for implementation. Future work includes a pragmatic randomized trial to assess whether our model improves patient outcomes.

Leveraging large language models for generating responses to patient messages-a subjective analysis.

OBJECTIVE: This study aimed to develop and assess the performance of fine-tuned large language models for generating responses to patient messages sent via an electronic health record patient portal. MATERIALS AND METHODS: Utilizing a dataset of messages and responses extracted from the patient portal at a large academic medical center, we developed a model (CLAIR-Short) based on a pre-trained large language model (LLaMA-65B). In addition, we used the OpenAI API to update physician responses from an open-source dataset into a format with informative paragraphs that offered patient education while emphasizing empathy and professionalism. By combining with this dataset, we further fine-tuned our model (CLAIR-Long). To evaluate fine-tuned models, we used 10 representative patient portal questions in primary care to generate responses. We asked primary care physicians to review generated responses from our models and ChatGPT and rated them for empathy, responsiveness, accuracy, and usefulness. RESULTS: The dataset consisted of 499 794 pairs of patient messages and corresponding responses from the patient portal, with 5000 patient messages and ChatGPT-updated responses from an online platform. Four primary care physicians participated in the survey. CLAIR-Short exhibited the ability to generate concise responses similar to provider's responses. CLAIR-Long responses provided increased patient educational content compared to CLAIR-Short and were rated similarly to ChatGPT's responses, receiving positive evaluations for responsiveness, empathy, and accuracy, while receiving a neutral rating for usefulness. CONCLUSION: This subjective analysis suggests that leveraging large language models to generate responses to patient messages demonstrates significant potential in facilitating communication between patients and healthcare providers.

Development and Validation of a Machine Learning Algorithm Using Clinical Pages to Predict Imminent Clinical Deterioration.

BACKGROUND: Early detection of clinical deterioration among hospitalized patients is a clinical priority for patient safety and quality of care. Current automated approaches for identifying these patients perform poorly at identifying imminent events. OBJECTIVE: Develop a machine learning algorithm using pager messages sent between clinical team members to predict imminent clinical deterioration. DESIGN: We conducted a large observational study using long short-term memory machine learning models on the content and frequency of clinical pages. PARTICIPANTS: We included all hospitalizations between January 1, 2018 and December 31, 2020 at Vanderbilt University Medical Center that included at least one page message to physicians. Exclusion criteria included patients receiving palliative care, hospitalizations with a planned intensive care stay, and hospitalizations in the top 2% longest length of stay. MAIN MEASURES: Model classification performance to identify in-hospital cardiac arrest, transfer to intensive care, or Rapid Response activation in the next 3-, 6-, and 12-hours. We compared model performance against three common early warning scores: Modified Early Warning Score, National Early Warning Score, and the Epic Deterioration Index. KEY RESULTS: There were 87,783 patients (mean [SD] age 54.0 [18.8] years; 45,835 [52.2%] women) who experienced 136,778 hospitalizations. 6214 hospitalized patients experienced a deterioration event. The machine learning model accurately identified 62% of deterioration events within 3-hours prior to the event and 47% of events within 12-hours. Across each time horizon, the model surpassed performance of the best early warning score including area under the receiver operating characteristic curve at 6-hours (0.856 vs. 0.781), sensitivity at 6-hours (0.590 vs. 0.505), specificity at 6-hours (0.900 vs. 0.878), and F-score at 6-hours (0.291 vs. 0.220). CONCLUSIONS: Machine learning applied to the content and frequency of clinical pages improves prediction of imminent deterioration. Using clinical pages to monitor patient acuity supports improved detection of imminent deterioration without requiring changes to clinical workflow or nursing documentation.

The State-of-the-Art of Patient Portals: Adapting to External Factors, Addressing Barriers, and Innovating.

BACKGROUND AND OBJECTIVE: Recent external factors-the 21st Century Cures Act and the coronavirus disease 2019 (COVID-19) pandemic-have stimulated major changes in the patient portal landscape. The objective of this state-of-the-art review is to describe recent developments in the patient portal literature and to identify recommendations and future directions for the design, implementation, and evaluation of portals. METHODS: To focus this review on salient contemporary issues, we elected to center it on four topics: (1) 21st Century Cures Act's impact on patient portals (e.g., Open Notes); (2) COVID-19's pandemic impact on portals; (3) proxy access to portals; and (4) disparities in portal adoption and use. We conducted targeted PubMed searches to identify recent empirical studies addressing these topics, used a two-part screening process to determine relevance, and conducted thematic analyses. RESULTS: Our search identified 174 unique papers, 74 were relevant empirical studies and included in this review. Among these papers, we identified 10 themes within our four a priori topics, including preparing for and understanding the consequences of increased patient access to their electronic health information (Cures Act); developing, deploying, and evaluating new virtual care processes (COVID-19); understanding current barriers to formal proxy use (proxy access); and addressing disparities in portal adoption and use (disparities). CONCLUSION: Our results suggest that the recent trends toward understanding the implications of immediate access to most test results, exploring ways to close gaps in portal adoption and use among different sub-populations, and finding ways to leverage portals to improve health and health care are the next steps in the maturation of patient portals and are key areas that require more research. It is important that health care organizations share their innovative portal efforts, so that successful measures can be tested in other contexts, and progress can continue.

POINT: Pipeline for Offline Conversion and Integration of Geocodes and Neighborhood Data.

OBJECTIVES: Geocoding, the process of converting addresses into precise geographic coordinates, allows researchers and health systems to obtain neighborhood-level estimates of social determinants of health. This information supports opportunities to personalize care and interventions for individual patients based on the environments where they live. We developed an integrated offline geocoding pipeline to streamline the process of obtaining address-based variables, which can be integrated into existing data processing pipelines. METHODS: POINT is a web-based, containerized, application for geocoding addresses that can be deployed offline and made available to multiple users across an organization. Our application supports use through both a graphical user interface and application programming interface to query geographic variables, by census tract, without exposing sensitive patient data. We evaluated our application's performance using two datasets: one consisting of 1 million nationally representative addresses sampled from Open Addresses, and the other consisting of 3,096 previously geocoded patient addresses. RESULTS: A total of 99.4 and 99.8% of addresses in the Open Addresses and patient addresses datasets, respectively, were geocoded successfully. Census tract assignment was concordant with reference in greater than 90% of addresses for both datasets. Among successful geocodes, median (interquartile range) distances from reference coordinates were 52.5 (26.5-119.4) and 14.5 (10.9-24.6) m for the two datasets. CONCLUSION: POINT successfully geocodes more addresses and yields similar accuracy to existing solutions, including the U.S. Census Bureau's official geocoder. Addresses are considered protected health information and cannot be shared with common online geocoding services. POINT is an offline solution that enables scalability to multiple users and integrates downstream mapping to neighborhood-level variables with a pipeline that allows users to incorporate additional datasets as they become available. As health systems and researchers continue to explore and improve health equity, it is essential to quickly and accurately obtain neighborhood variables in a Health Insurance Portability and Accountability Act (HIPAA)-compliant way.

Impact of notification policy on patient-before-clinician review of immediately released test results.

The 21st Century Cures Act mandates immediate availability of test results upon request. The Cures Act does not require that patients be informed of results, but many organizations send notifications when results become available. Our medical center implemented 2 sequential policies: immediate notifications for all results, and notifications only to patients who opt in. We used over 2 years of data from Vanderbilt University Medical Center to measure the effect of these policies on rates of patient-before-clinician result review and patient-initiated messaging using interrupted time series analysis. When releasing test results with immediate notification, the proportion of patient-before-clinician review increased 4-fold and the proportion of patients who sent messages rose 3%. After transition to opt-in notifications, patient-before-clinician review decreased 2.4% and patient-initiated messaging decreased 0.4%. Replacing automated notifications with an opt-in policy provides patients flexibility to indicate their preferences but may not substantially alleviate clinicians' messaging workload.

Leveraging natural language processing to identify eligible lung cancer screening patients with the electronic health record.

OBJECTIVE: To develop and validate an approach that identifies patients eligible for lung cancer screening (LCS) by combining structured and unstructured smoking data from the electronic health record (EHR). METHODS: We identified patients aged 50-80 years who had at least one encounter in a primary care clinic at Vanderbilt University Medical Center (VUMC) between 2019 and 2022. We fine-tuned an existing natural language processing (NLP) tool to extract quantitative smoking information using clinical notes collected from VUMC. Then, we developed an approach to identify patients who are eligible for LCS by combining smoking information from structured data and clinical narratives. We compared this method with two approaches to identify LCS eligibility only using smoking information from structured EHR. We used 50 patients with a documented history of tobacco use for comparison and validation. RESULTS: 102,475 patients were included. The NLP-based approach achieved an F1-score of 0.909, and accuracy of 0.96. The baseline approach could identify 5,887 patients. Compared to the baseline approach, the number of identified patients using all structured data and the NLP-based algorithm was 7,194 (22.2 %) and 10,231 (73.8 %), respectively. The NLP-based approach identified 589 Black/African Americans, a significant increase of 119 %. CONCLUSION: We present a feasible NLP-based approach to identify LCS eligible patients. It provides a technical basis for the development of clinical decision support tools to potentially improve the utilization of LCS and diminish healthcare disparities.

Leveraging Large Language Models for Generating Responses to Patient Messages.

Objective: This study aimed to develop and assess the performance of fine-tuned large language models for generating responses to patient messages sent via an electronic health record patient portal. Methods: Utilizing a dataset of messages and responses extracted from the patient portal at a large academic medical center, we developed a model (CLAIR-Short) based on a pre-trained large language model (LLaMA-65B). In addition, we used the OpenAI API to update physician responses from an open-source dataset into a format with informative paragraphs that offered patient education while emphasizing empathy and professionalism. By combining with this dataset, we further fine-tuned our model (CLAIR-Long). To evaluate the fine-tuned models, we used ten representative patient portal questions in primary care to generate responses. We asked primary care physicians to review generated responses from our models and ChatGPT and rated them for empathy, responsiveness, accuracy, and usefulness. Results: The dataset consisted of a total of 499,794 pairs of patient messages and corresponding responses from the patient portal, with 5,000 patient messages and ChatGPT-updated responses from an online platform. Four primary care physicians participated in the survey. CLAIR-Short exhibited the ability to generate concise responses similar to provider's responses. CLAIR-Long responses provided increased patient educational content compared to CLAIR-Short and were rated similarly to ChatGPT's responses, receiving positive evaluations for responsiveness, empathy, and accuracy, while receiving a neutral rating for usefulness. Conclusion: Leveraging large language models to generate responses to patient messages demonstrates significant potential in facilitating communication between patients and primary care providers.

Perspectives of Patients About Immediate Access to Test Results Through an Online Patient Portal.

Importance: The 21st Century Cures Act Final Rule mandates the immediate electronic availability of test results to patients, likely empowering them to better manage their health. Concerns remain about unintended effects of releasing abnormal test results to patients. Objective: To assess patient and caregiver attitudes and preferences related to receiving immediately released test results through an online patient portal. Design, Setting, and Participants: This large, multisite survey study was conducted at 4 geographically distributed academic medical centers in the US using an instrument adapted from validated surveys. The survey was delivered in May 2022 to adult patients and care partners who had accessed test results via an online patient portal account between April 5, 2021, and April 4, 2022. Exposures: Access to test results via a patient portal between April 5, 2021, and April 4, 2022. Main Outcomes and Measures: Responses to questions related to demographics, test type and result, reaction to result, notification experience and future preferences, and effect on health and well-being were aggregated. To evaluate characteristics associated with patient worry, logistic regression and pooled random-effects models were used to assess level of worry as a function of whether test results were perceived by patients as normal or not normal and whether patients were precounseled. Results: Of 43 380 surveys delivered, there were 8139 respondents (18.8%). Most respondents were female (5129 [63.0%]) and spoke English as their primary language (7690 [94.5%]). The median age was 64 years (IQR, 50-72 years). Most respondents (7520 of 7859 [95.7%]), including 2337 of 2453 individuals (95.3%) who received nonnormal results, preferred to immediately receive test results through the portal. Few respondents (411 of 5473 [7.5%]) reported that reviewing results before they were contacted by a health care practitioner increased worry, though increased worry was more common among respondents who received abnormal results (403 of 2442 [16.5%]) than those whose results were normal (294 of 5918 [5.0%]). The result of the pooled model for worry as a function of test result normality was statistically significant (odds ratio [OR], 2.71; 99% CI, 1.96-3.74), suggesting an association between worry and nonnormal results. The result of the pooled model evaluating the association between worry and precounseling was not significant (OR, 0.70; 99% CI, 0.31-1.59). Conclusions and Relevance: In this multisite survey study of patient attitudes and preferences toward receiving immediately released test results via a patient portal, most respondents preferred to receive test results via the patient portal despite viewing results prior to discussion with a health care professional. This preference persisted among patients with nonnormal results.

Association of Educational Intervention With Knowledge of Airway Injury After Endotracheal Intubation and Tube Size Selection.

In this nonrandomized controlled trial, an educational intervention for emergency medicine residents was developed to increase knowledge of airway injury following prolonged intubation and reduce the proportion of large-for-height endotracheal tubes placed in the emergency department.

New onset delirium prediction using machine learning and long short-term memory (LSTM) in electronic health record.

OBJECTIVE: To develop and test an accurate deep learning model for predicting new onset delirium in hospitalized adult patients. METHODS: Using electronic health record (EHR) data extracted from a large academic medical center, we developed a model combining long short-term memory (LSTM) and machine learning to predict new onset delirium and compared its performance with machine-learning-only models (logistic regression, random forest, support vector machine, neural network, and LightGBM). The labels of models were confusion assessment method (CAM) assessments. We evaluated models on a hold-out dataset. We calculated Shapley additive explanations (SHAP) measures to gauge the feature impact on the model. RESULTS: A total of 331 489 CAM assessments with 896 features from 34 035 patients were included. The LightGBM model achieved the best performance (AUC 0.927 [0.924, 0.929] and F1 0.626 [0.618, 0.634]) among the machine learning models. When combined with the LSTM model, the final model's performance improved significantly (P = .001) with AUC 0.952 [0.950, 0.955] and F1 0.759 [0.755, 0.765]. The precision value of the combined model improved from 0.497 to 0.751 with a fixed recall of 0.8. Using the mean absolute SHAP values, we identified the top 20 features, including age, heart rate, Richmond Agitation-Sedation Scale score, Morse fall risk score, pulse, respiratory rate, and level of care. CONCLUSION: Leveraging LSTM to capture temporal trends and combining it with the LightGBM model can significantly improve the prediction of new onset delirium, providing an algorithmic basis for the subsequent development of clinical decision support tools for proactive delirium interventions.

Endotracheal Tube Size in Critically Ill Patients.

Importance: Many patients who survive critical illness are left with laryngeal functional impairment from endotracheal intubation that permanently limits their recovery and quality of life. Although the risk for laryngeal injury increases with larger endotracheal tube sizes, there are no data delineating the association of smaller endotracheal tube sizes with survival or acute recovery from critical illness. Objective: To determine if smaller endotracheal tubes are noninferior to larger endotracheal tubes with respect to critical illness outcomes. Design, Setting, and Participants: This propensity score-matched retrospective cohort study included all adult patients who underwent endotracheal intubation in the emergency department or intensive care unit and received mechanical ventilation for at least 12 hours from June 2020 to November 2020 at a single tertiary referral academic medical center. Exposures: Endotracheal intubation. Main Outcomes and Measures: Propensity score-matched analyses were performed with respect to the primary end point of 30-day all-cause in-hospital survival as well as the secondary end points of duration of invasive mechanical ventilation, length of hospital stay, mean peak inspiratory pressure, 30-day readmission, need for reintubation, and need for tracheostomy or gastrostomy tube placement. Results: Overall, 523 participants (64%) were men and 291 (36%) were women. Of these, 814 patients were categorized into 3 endotracheal tube groups: small for height (n = 182), appropriate for height (n = 408), and large for height (n = 224). There was not a significant difference in 30-day all-cause in-hospital survival between groups ([HR, 1.1; 95% CI, 0.7-1.7] for small vs appropriate; [HR, 1.1; 95% CI, 0.7-1.6] for large vs appropriate). Patients with small-for-height endotracheal tubes had longer intubation durations (mean difference, 32.5 hrs [95% CI, 6.4-58.6 hrs]) compared with patients with appropriate-for-height tubes. Conclusions and Relevance: Despite differences in intubation duration, the results of this cohort study suggest that smaller endotracheal tube sizes are not associated with impaired survival or recovery from critical illness. They support future prospective exploration of the association of smaller endotracheal tube sizes with recovery from critical illness.

Conceptualizing clinical decision support as complex interventions: a meta-analysis of comparative effectiveness trials.

OBJECTIVES: Complex interventions with multiple components and behavior change strategies are increasingly implemented as a form of clinical decision support (CDS) using native electronic health record functionality. Objectives of this study were, therefore, to (1) identify the proportion of randomized controlled trials with CDS interventions that were complex, (2) describe common gaps in the reporting of complexity in CDS research, and (3) determine the impact of increased complexity on CDS effectiveness. MATERIALS AND METHODS: To assess CDS complexity and identify reporting gaps for characterizing CDS interventions, we used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses reporting tool for complex interventions. We evaluated the effect of increased complexity using random-effects meta-analysis. RESULTS: Most included studies evaluated a complex CDS intervention (76%). No studies described use of analytical frameworks or causal pathways. Two studies discussed use of theory but only one fully described the rationale and put it in context of a behavior change. A small but positive effect (standardized mean difference, 0.147; 95% CI, 0.039-0.255; P < .01) in favor of increasing intervention complexity was observed. DISCUSSION: While most CDS studies should classify interventions as complex, opportunities persist for documenting and providing resources in a manner that would enable CDS interventions to be replicated and adapted. Unless reporting of the design, implementation, and evaluation of CDS interventions improves, only slight benefits can be expected. CONCLUSION: Conceptualizing CDS as complex interventions may help convey the careful attention that is needed to ensure these interventions are contextually and theoretically informed.

Non-Interruptive Clinical Decision Support to Improve Perioperative Electronic Positive Patient Identification.

Positive patient identification (PPID) is an integral step to ensure the correct patient identity prior to a healthcare delivery event. Following implementation of a new EHR in November 2017, Vanderbilt University Medical Center (VUMC) experienced frequent and inconsistent failure of barcode scanners which impacted the electronic PPID (ePPID) and blood verification processes. Following multiple iterations of troubleshooting, vendor engagement, and device upgrades, we developed a clinical decision support (CDS) tool as a visual reminder to perform ePPID. If ePPID was initially bypassed, the clinician received a passive alert which remained visible throughout the procedure or until ePPID was completed successfully. We conducted a retrospective observational study using an interrupted time series analysis and analysis of variance pre- and post- CDS intervention. Following CDS intervention, we observed an immediate 20.8% increase in successful ePPID (p < 0.001). The mean success rate of ePPID attempts increased from 62.0% pre-intervention to 94.4% post-intervention (p < 0.001). There were 108 providers who had less than 80.0% success in the six-months prior to CDS intervention, of whom all improved to an average of 95.9% success. Our CDS approach highlights the utility of non-interruptive but continually visible alerts to improve patient safety workflows. By making errors clearly visible to users and their peers, performance improved to only 5.6% of alerts bypassed.

An Analysis of Electronic Health Record Work to Manage Asynchronous Clinical Messages among Breast Cancer Care Teams.

OBJECTIVE: Asynchronous messaging is an integral aspect of communication in clinical settings, but imposes additional work and potentially leads to inefficiency. The goal of this study was to describe the time spent using the electronic health record (EHR) to manage asynchronous communication to support breast cancer care coordination. METHODS: We analyzed 3 years of audit logs and secure messaging logs from the EHR for care team members involved in breast cancer care at Vanderbilt University Medical Center. To evaluate trends in EHR use, we combined log data into sequences of events that occurred within 15 minutes of any other event by the same employee about the same patient. RESULTS: Our cohort of 9,761 patients were the subject of 430,857 message threads by 7,194 employees over a 3-year period. Breast cancer care team members performed messaging actions in 37.5% of all EHR sessions, averaging 29.8 (standard deviation [SD] = 23.5) messaging sessions per day. Messaging sessions lasted an average of 1.1 (95% confidence interval: 0.99-1.24) minutes longer than nonmessaging sessions. On days when the cancer providers did not otherwise have clinical responsibilities, they still performed messaging actions in an average of 15 (SD = 11.9) sessions per day. CONCLUSION: At our institution, clinical messaging occurred in 35% of all EHR sessions. Clinical messaging, sometimes viewed as a supporting task of clinical work, is important to delivering and coordinating care across roles. Measuring the electronic work of asynchronous communication among care team members affords the opportunity to systematically identify opportunities to improve employee workload.

Classification and analysis of asynchronous communication content between care team members involved in breast cancer treatment.

OBJECTIVE: A growing research literature has highlighted the work of managing and triaging clinical messages as a major contributor to professional exhaustion and burnout. The goal of this study was to discover and quantify the distribution of message content sent among care team members treating patients with breast cancer. MATERIALS AND METHODS: We analyzed nearly two years of communication data from the electronic health record (EHR) between care team members at Vanderbilt University Medical Center. We applied natural language processing to perform sentence-level annotation into one of five information types: clinical, medical logistics, nonmedical logistics, social, and other. We combined sentence-level annotations for each respective message. We evaluated message content by team member role and clinic activity. RESULTS: Our dataset included 81 857 messages containing 613 877 sentences. Across all roles, 63.4% and 21.8% of messages contained logistical information and clinical information, respectively. Individuals in administrative or clinical staff roles sent 81% of all messages containing logistical information. There were 33.2% of messages sent by physicians containing clinical information-the most of any role. DISCUSSION AND CONCLUSION: Our results demonstrate that EHR-based asynchronous communication is integral to coordinate care for patients with breast cancer. By understanding the content of messages sent by care team members, we can devise informatics initiatives to improve physicians' clerical burden and reduce unnecessary interruptions.

Analysis of Employee Patient Portal Use and Electronic Health Record Access at an Academic Medical Center.

BACKGROUND: Patient portals provide patients and their caregivers online access to limited health results. Health care employees with electronic health record (EHR) access may be able to view their health information not available in the patient portal by looking in the EHR. OBJECTIVE: In this study, we examine how employees use the patient portal when they also have access to the tethered EHR. METHODS: We obtained patient portal and EHR usage logs corresponding to all employees who viewed their health data at our institution between January 1, 2013 and November 1, 2017. We formed three cohorts based on the systems that employees used to view their health data: employees who used the patient portal only, employees who viewed health data in the EHR only, and employees who used both systems. We compared system accesses and usage patterns for each employee cohort. RESULTS: During the study period, 35,172 employees accessed the EHR as part of patients' treatment and 28,631 employees accessed their health data: 25,193 of them used the patient portal and 13,318 accessed their clinical data in EHR. All employees who accessed their records in the EHR viewed their clinical notes at least once. Among EHR accesses, clinical note accesses comprised more than 42% of all EHR accesses. Provider messaging and appointment scheduling were the most commonly used functions in the patient portal. Employees who had access to their health data in both systems were more likely to engage with providers through portal messages. CONCLUSION: Employees at a large medical center accessed clinical notes in the EHR to obtain information about their health. Employees also viewed other health data not readily available in the patient portal.

Characterizing communication patterns among members of the clinical care team to deliver breast cancer treatment.

OBJECTIVE: Research to date focused on quantifying team collaboration has relied on identifying shared patients but does not incorporate the major role of communication patterns. The goal of this study was to describe the patterns and volume of communication among care team members involved in treating breast cancer patients. MATERIALS AND METHODS: We analyzed 4 years of communications data from the electronic health record between care team members at Vanderbilt University Medical Center (VUMC). Our cohort of patients diagnosed with breast cancer was identified using the VUMC tumor registry. We classified each care team member participating in electronic messaging by their institutional role and classified physicians by specialty. To identify collaborative patterns, we modeled the data as a social network. RESULTS: Our cohort of 1181 patients was the subject of 322 424 messages sent in 104 210 unique communication threads by 5620 employees. On average, each patient was the subject of 88.2 message threads involving 106.4 employees. Each employee, on average, sent 72.9 messages and was connected to 24.6 collaborators. Nurses and physicians were involved in 98% and 44% of all message threads, respectively. DISCUSSION AND CONCLUSION: Our results suggest that many providers in our study may experience a high volume of messaging work. By using data routinely generated through interaction with the electronic health record, we can begin to evaluate how to iteratively implement and assess initiatives to improve the efficiency of care coordination and reduce unnecessary messaging work across all care team roles.