Performance and Integration of Smartphone Wireless ECG Monitoring into the Enterprise Electronic Health Record: First Clinical Experience.

INTRODUCTION: Patient initiated, remote cardiac monitoring has proved to be a significant advance in the diagnosis and management of arrhythmias. Further improvements in ease of use and access to results will further improve health outcomes and cost-effectiveness. Here we describe a proof-of-concept evaluation to assess the feasibility of successfully implementing a cloud-based management system using KardiaPro (KP) for remote electrocardiogram (ECG) monitoring to interface into EPIC, an enterprise electronic health record (EHR) system. METHODS: The KP management system was embedded using hypertext markup language (HTML) code directly into the EHR. Encrypted credentials and patient data were bundled with an application programming interface key allowing linkage of remote monitoring from patients' smartphones. During the time of implementation, a total of 322 patients and 32 179 ECGs were recorded. RESULTS: The KP-EHR interface provided full functionality, allowing detection, interpretation and documentation of atrial fibrillation (AF), flutter events, ventricular tachycardia, and complete heart block. Our study focused on KP's detection of AF, and 16.7% of tracings were classified as probable AF with only 2.3% of tracings not analyzed by the KP algorithm because of tracings that were too noisy or truncated. Enhanced management was facilitated with clinical information immediately accessible. Blinded physician ECG review validated the KP proprietary algorithm interpretation and ECGs. CONCLUSIONS: Direct integration of KP into EHR was successful and practical. It allows for historical, point of care and immediate retrieval of remote ambulatory monitoring data and documentation into the electronic health record. KP EHR integration warrants further study as it has the potential to improve cost-effectiveness and clinical diagnostic value, leading to improvements in delivery of patient care.

Will Apple devices' passive atrial fibrillation detection prevent strokes? Estimating the proportion of high-risk actionable patients with real-world user data.

OBJECTIVE: Utilizing integrated electronic health record (EHR) and consumer-grade wearable device data, we sought to provide real-world estimates for the proportion of wearers that would likely benefit from anticoagulation if an atrial fibrillation (AFib) diagnosis was made based on wearable device data. MATERIALS AND METHODS: This study utilized EHR and Apple Watch data from an observational cohort of 1802 patients at Cedars-Sinai Medical Center who linked devices to the EHR between April 25, 2015 and November 16, 2018. Using these data, we estimated the number of high-risk patients who would be actionable for anticoagulation based on (1) medical history, (2) Apple Watch wear patterns, and (3) AFib risk, as determined by an existing validated model. RESULTS: Based on the characteristics of this cohort, a mean of 0.25% (n = 4.58, 95% CI, 2.0-8.0) of patients would be candidates for new anticoagulation based on AFib identified by their Apple Watch. Using EHR data alone, we find that only approximately 36% of the 1802 patients (n = 665.93, 95% CI, 626.0-706.0) would have anticoagulation recommended even after a new AFib diagnosis. DISCUSSION AND CONCLUSION: These data suggest that there is limited benefit to detect and treat AFib with anticoagulation among this cohort, but that accessing clinical and demographic data from the EHR could help target devices to the patients with the highest potential for benefit. Future research may analyze this relationship at other sites and among other wearable users, including among those who have not linked devices to their EHR.

Incidence of interruptive penicillin allergy alerts in patients with previously documented beta-lactam exposure: Potential for leveraging the electronic health record to identify erroneous allergies.

BACKGROUND: Approximately 10% of patients report allergies to penicillin, yet >90% of these allergies are not clinically significant. Patients reporting penicillin allergies are often treated with second-line, non-ß-lactam antibiotics that are typically broader spectrum and more toxic. Orders for ß-lactam antibiotics for these patients trigger interruptive alerts, even when there is electronic health record (EHR) data indicating prior ß-lactam exposure. OBJECTIVE: To describe the rate that interruptive penicillin allergy alerts display for patients who have previously had a ß-lactam exposure. DESIGN: Retrospective EHR review from January 2013 through June 2018. SETTING: A nonprofit health system including 1 large tertiary-care medical center, a smaller associated hospital, 2 emergency departments, and ˜250 outpatient clinics. PARTICIPANTS: All patients with EHR-documented of penicillin allergies. METHODS: We examined interruptive penicillin allergy alerts and identified the number and percentage of alerts that display for patients with a prior administration of a penicillin class or other ß-lactam antibiotic. RESULTS: Of 115,081 allergy alerts that displayed during the study period, 8% were displayed for patients who had an inpatient administration of a penicillin antibiotic after the allergy was noted, and 49% were displayed for patients with a prior inpatient administration of any ß-lactam. CONCLUSIONS: Many interruptive penicillin allergy alerts display for patients who would likely tolerate a penicillin, and half of all alerts display for patients who would likely tolerate another ß-lactam.

Patient-Initiated Data: Our Experience with Enabling Patients to Initiate Incorporation of Heart Rate Data into the Electronic Health Record.

BACKGROUND: Provider organizations increasingly allow incorporation of patient-generated data into electronic health records (EHRs). In 2015, we began allowing patients to upload data to our EHR without physician orders, which we henceforth call patient-initiated data (PAIDA). Syncing wearable heart rate monitors to our EHR allows for uploading of thousands of heart rates per patient per week, including many abnormally low and high rates. Physician informaticists expressed concern that physicians and their patients might be unaware of abnormal heart rates, including those caused by treatable pathology. OBJECTIVE: This study aimed to develop a protocol to address millions of unreviewed heart rates. METHODS: As a quality improvement initiative, we assembled a physician informaticist team to meet monthly for review of abnormally low and high heart rates. By incorporating other data already present in the EHR, lessons learned from reviewing records over time, and from contacting physicians, we iteratively refined our protocol. RESULTS: We developed (1) a heart rate visualization dashboard to identify concerning heart rates; (2) experience regarding which combinations of heart rates and EHR data were most clinically worrisome, as opposed to representing artifact; (3) a protocol whereby only concerning heart rates would trigger a cardiologist review revealing protected health information; and (4) a generalizable framework for addressing other PAIDA. CONCLUSION: We expect most PAIDA to eventually require systematic integration and oversight. Our governance framework can help guide future efforts, especially for cases with large amounts of data and where abnormal values may represent concerning but treatable pathology.

Clinical Decision Support for Hyperbilirubinemia Risk Assessment in the Electronic Health Record.

BACKGROUND: Physiologic neonatal hyperbilirubinemia (jaundice) is common and affects most newborn infants. However, there is a risk for permanent neurological damage if the bilirubin levels rise above a certain threshold. The management of neonatal jaundice includes the assessment of bilirubin laboratory values, consideration of patient-specific risk factors, and plotting on a bilirubin nomogram reference to determine risk and guide therapy. When performed manually, the process can be time consuming and error-prone. Therefore, web-based calculators such as BiliTool have been developed to assist in risk assessment. METHODS: To streamline the risk assessment calculation process further within our electronic health record (EHR), we created a "BiliReport" to display patient bilirubin-related data and automate transmission of deidentified patient data to the BiliTool website (https://bilitool.org). After implementation, we evaluated usage data, provider satisfaction, and accuracy of documentation. RESULTS: We demonstrated high provider use of the BiliReport and satisfaction with the workflow. We found a significant improvement in the accuracy of bilirubin risk level documentation, with a reduction in erroneous risk stratification from 4% (15/232) to 0.4% (1/243), P < 0.001. We did not find significant a difference in erroneous documentation of the bilirubin lab value (P = 0.07). CONCLUSIONS: Integrating the neonatal hyperbilirubinemia risk assessment process into the EHR may reduce errors and improve provider documentation and adherence to recommended guidelines.

A Large-Scale Initiative Inviting Patients to Share Personal Fitness Tracker Data with Their Providers: Initial Results.

BACKGROUND: Personal fitness trackers (PFT) have substantial potential to improve healthcare. OBJECTIVE: To quantify and characterize early adopters who shared their PFT data with providers. METHODS: We used bivariate statistics and logistic regression to compare patients who shared any PFT data vs. patients who did not. RESULTS: A patient portal was used to invite 79,953 registered portal users to share their data. Of 66,105 users included in our analysis, 499 (0.8%) uploaded data during an initial 37-day study period. Bivariate and regression analysis showed that early adopters were more likely than non-adopters to be younger, male, white, health system employees, and to have higher BMIs. Neither comorbidities nor utilization predicted adoption. CONCLUSION: Our results demonstrate that patients had little intrinsic desire to share PFT data with their providers, and suggest that patients most at risk for poor health outcomes are least likely to share PFT data. Marketing, incentives, and/or cultural change may be needed to induce such data-sharing.