Enhanced phenotypes for identifying opioid overdose in emergency department visit electronic health record data.

Background: Accurate identification of opioid overdose (OOD) cases in electronic healthcare record (EHR) data is an important element in surveillance, empirical research, and clinical intervention. We sought to improve existing OOD electronic phenotypes by incorporating new data types beyond diagnostic codes and by applying several statistical and machine learning methods. Materials and Methods: We developed an EHR dataset of emergency department visits involving OOD cases or patients considered at risk for an OOD and ascertained true OOD status through manual chart reviews. We developed and validated prediction models using Random Forest, Extreme Gradient Boost, and Elastic Net models that incorporated 717 features involving primary and second diagnoses, chief complaints, medications prescribed, vital signs, laboratory results, and procedural codes. We also developed models limited to single data types. Results: A total of 1718 records involving 1485 patients were manually reviewed; 541 (36.4%) patients had one or more OOD. Prediction performance was similar for all models; sensitivity varied from 94% to 97%; and area under the receiver operating characteristic curve (AUC) was 98% for all methods. The primary diagnosis and chief complaint were the most important contributors to AUC performance; primary diagnoses and medication class contributed most to sensitivity; chief complaint, primary diagnosis, and vital signs were most important for specificity. Models limited to decision support data types available in real time demonstrated robust prediction performance. Conclusions: Substantial prediction performance improvements were demonstrated for identifying OODs in EHR data. Our e-phenotypes could be applied in surveillance, retrospective empirical applications, or clinical decision support systems.

The use of a traditional nonlooping event monitor versus a loan-based program with a smartphone ECG device in the pediatric cardiology clinic.

Background: A smartphone-enabled device has been developed that provides a single-lead electrocardiogram using a portable monitor. The increase in direct-to-consumer medical devices may lead to health disparities affecting members of socially disadvantaged populations. Objective: Here we provide a single center's experience in the use of this device in a pediatric cardiology clinic using a loan-based program. We also compare it to retrospective data from patients who received a traditional nonlooping event monitor. Methods: Forty AliveCor Kardia monitor devices were purchased with grant support from the South Carolina TeleHealth Alliance. The devices were provided between June 2018 and August 2019 to patients presenting to the pediatric cardiology clinic who would have otherwise received a nonlooping event monitor. A retrospective chart review was performed for all patients who were given a MicroER nonlooping event monitor between May and December of 2017. Results: Over a 15-month period, 65 patients were given the smartphone device. A total of 692 tracings were recorded by patients with 9 abnormal recordings. Of the devices expected to be returned, 35 devices have been returned to clinic (54%). Over an 8-month period, 61 patients received the traditional event monitors, accounting for a total of 142 transmissions with 3 abnormal transmissions. Conclusion: Our results reveal adequate use of the device with reliable tracings and show more frequent utilization of the smartphone-enabled device. Utilization of these devices in a loan-based program may improve access to care with improved methods to ensure return of the devices.

Melody pulmonary valve bacterial endocarditis: experience in four pediatric patients and a review of the literature.

OBJECTIVES: The objectives of this manuscript are two-fold: (a) to describe the clinical characteristics and management of four pediatric patients with bacterial endocarditis (BE) after Melody pulmonary valve implantation (MPVI); and (b) to review the literature regarding Melody pulmonary valve endocarditis. BACKGROUND: There are several reports of BE following MPVI. The clinical course, BE management and outcome remain poorly defined. METHODS: This is a multi-center report of four pediatric patients with repaired tetralogy of Fallot (TOF) and BE after MPVI. Clinical presentation, echocardiogram findings, infecting organism, BE management, and follow-up assessment are described. We review available literature on Melody pulmonary valve endocarditis and discuss the prognosis and challenges in the management of these patients. RESULTS: Of our four BE patients, two had documented vegetations and three showed worsening pulmonary stenosis. All patients remain asymptomatic after medical treatment (4) and surgical prosthesis replacement (3) at follow-up of 17 to 40 months. Analysis of published data shows that over half of patients undergo bioprosthesis explantation and that there is a 13% overall mortality. The most common BE pathogens are the Staphylococcus and Streptococcus species. CONCLUSIONS: Our case series of four pediatric patients with repaired TOF confirms a risk for BE after MPVI. A high index of suspicion for BE should be observed after MPVI. All patients should be advised to follow lifelong BE prophylaxis after MPVI. In case of BE, surgery should be considered for valve dysfunction or no clinical improvement in spite of medical treatment.