scholarly journals Best Paper Selection

2021 ◽  
Vol 30 (01) ◽  
pp. 237-238
Keyword(s):  
Electronic Health Record ◽  
High Throughput ◽  
Adverse Drug Event ◽  
Real World ◽  
Drug Event ◽  
Health Record ◽  
Real World Data ◽  
Patient Reported ◽  
High Throughput Phenotyping ◽  
Temporal Sequences

Bell SK, Delbanco T, Elmore JG, Fitzgerald PS, Fossa A, Harcourt K, Leveille SG, Payne TH, Stametz RA, Walker J, DesRoches CM. Frequency and types of patient-reported errors in electronic health record ambulatory care notes. https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2766834 Estiri H, Strasser ZH, Murphy SN. High-throughput phenotyping with temporal sequences. https://academic.oup.com/jamia/article-lookup/doi/10.1093/jamia/ocaa288 Geva A, Stedman JP, Manzi SF, Lin C, Savova GK, Avillach P, Mandl KD. Adverse drug event presentation and tracking (ADEPT): semiautomated, high throughput pharmacovigilance using real-world data. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7660953/ Zhang Z, Yan C, Mesa DA, Sun J, Malin BA. Ensuring electronic medical record simulation through better training, modeling, and evaluation. https://academic.oup.com/jamia/article/27/1/99/5583723

scholarly journals Adverse drug event presentation and tracking (ADEPT): semiautomated, high throughput pharmacovigilance using real-world data

JAMIA Open ◽  
2020 ◽  
Vol 3 (3) ◽  
pp. 413-421
Author(s):  
Alon Geva ◽  
Jason P Stedman ◽  
Shannon F Manzi ◽  
Chen Lin ◽  
Guergana K Savova ◽  
...  
Keyword(s):  
Language Processing ◽  
High Throughput ◽  
Adverse Drug Event ◽  
Real World ◽  
High Efficiency ◽  
Signs And Symptoms ◽  
Drug Event ◽  
Computer Assisted ◽  
Real World Data ◽  
World Data

Abstract Objective To advance use of real-world data (RWD) for pharmacovigilance, we sought to integrate a high-sensitivity natural language processing (NLP) pipeline for detecting potential adverse drug events (ADEs) with easily interpretable output for high-efficiency human review and adjudication of true ADEs. Materials and methods The adverse drug event presentation and tracking (ADEPT) system employs an open source NLP pipeline to identify in clinical notes mentions of medications and signs and symptoms potentially indicative of ADEs. ADEPT presents the output to human reviewers by highlighting these drug-event pairs within the context of the clinical note. To measure incidence of seizures associated with sildenafil, we applied ADEPT to 149 029 notes for 982 patients with pediatric pulmonary hypertension. Results Of 416 patients identified as taking sildenafil, NLP found 72 [17%, 95% confidence interval (CI) 14–21] with seizures as a potential ADE. Upon human review and adjudication, only 4 (0.96%, 95% CI 0.37–2.4) patients with seizures were determined to have true ADEs. Reviewers using ADEPT required a median of 89 s (interquartile range 57–142 s) per patient to review potential ADEs. Discussion ADEPT combines high throughput NLP to increase sensitivity of ADE detection and human review, to increase specificity by differentiating true ADEs from signs and symptoms related to comorbidities, effects of other medications, or other confounders. Conclusion ADEPT is a promising tool for creating gold standard, patient-level labels for advancing NLP-based pharmacovigilance. ADEPT is a potentially time savings platform for computer-assisted pharmacovigilance based on RWD.

Secondary use of electronic health record data: spontaneous triggered adverse drug event reporting

2010 ◽  
Vol 19 (12) ◽  
pp. 1211-1215 ◽  
Author(s):  
Jeffrey A. Linder ◽  
Jennifer S. Haas ◽  
Aarthi Iyer ◽  
Michael A. Labuzetta ◽  
Michael Ibara ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Adverse Drug Event ◽  
Drug Event ◽  
Health Record ◽  
Electronic Health Record Data ◽  
Event Reporting ◽  
Secondary Use ◽  
Record Data ◽  
Electronic Health

Assessing Quality of Surgical Real-World Data from an Automated Electronic Health Record Pipeline

2020 ◽  
Vol 230 (3) ◽  
pp. 295-305.e12 ◽  
Author(s):  
Kristin M. Corey ◽  
Joshua Helmkamp ◽  
Morgan Simons ◽  
Lesley Curtis ◽  
Keith Marsolo ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Real World ◽  
Health Record ◽  
Real World Data ◽  
World Data ◽  
Electronic Health

scholarly journals Generalized Mixed Modeling in Massive Electronic Health Record Databases: What is a Healthy Serum Potassium?

2021 ◽  
Author(s):  
Cristian G. Bologa ◽  
Vernon Shane Pankratz ◽  
Mark L Unruh ◽  
Maria Eleni Roumelioti ◽  
Vallabh Shah ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Real World ◽  
Serum Potassium ◽  
Repeated Measures ◽  
Linear Models ◽  
Care Facility ◽  
Health Care Facility ◽  
Health Record ◽  
Real World Data ◽  
Electronic Health

Abstract Background: Converting electronic health record (EHR) entries to useful clinical inferences requires one to address the poor scalability of existing implementations of Generalized Linear Mixed Models (GLMM) for repeated measures. The major computational bottleneck concerns the numerical evaluation of multivariable integrals, which even for the simplest EHR analyses may involve millions of dimensions (one for each patient). The hierarchical likelihood (h-lik) approach to GLMMs is a methodologically rigorous framework for the estimation of GLMMs that is based on the Laplace Approximation (LA), which replaces integration with numerical optimization, and thus scales very well with dimensionality. Methods: We present a high-performance implementation of the h-lik for GLMMs in the R package TMB. Using this approach, we examined the relation of repeated serum potassium measurements and survival in the Cerner Real World Data (CRWD) EHR database. Analyzing this data requires the evaluation of an integral in over 3 million dimensions, putting this problem beyond the reach of conventional approaches. We also assessed the scalability and accuracy of LA in smaller samples of 1 and 10% size of the full dataset that were analyzed via the a) original, interconnected Generalized Linear Models (iGLM), approach to h-lik, b) Adaptive Gaussian Hermite (AGH) and c) the gold standard of Markov Chain Monte Carlo (MCMC) for multivariate integration. Results: Random effects estimates generated by the LA were within 10% of the values obtained by the iGLMs, AGH and MCMC techniques. The H-lik approach was 4-30 times faster than AGH and nearly 800 times faster than MCMC. The major clinical inferences in this problem are the establishment of the non-linear relationship between the potassium level and the risk of mortality, as well as estimates of the individual and health care facility sources of variations for mortality risk in CRWD. Conclusions: We found that the combination of the LA and AD offers a computationally efficient, numerically accurate approach for the analysis of extremely large, real world repeated measures data via the h-lik approach to GLMMs. The clinical inference from our analysis may guide choices of threatment thresholds for treating potassium disorders in the clinic.

Real-world incidence, duration, and severity of treatment-emergent (TE) neutropenia among patients (pts) with metastatic breast cancer (MBC) treated with ribociclib (RIB) or palbociclib (PAL).

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e13048-e13048
Author(s):  
Lee S. Schwartzberg ◽  
Juan Pablo Zarate ◽  
David Chandiwana ◽  
Chu-Ling Yu ◽  
Sanjeev Balu ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Real World ◽  
Rate Ratio ◽  
Small Sample ◽  
Administrative Claims ◽  
Health Record ◽  
Real World Data ◽  
World Data ◽  
Electronic Health ◽  
Grade 3

e13048 Background: Neutropenia is the most common adverse event following administration of CDK4/6 inhibitors RIB and PAL for hormone receptor–positive (HR+) MBC. There are limited comparative real-world data on TE neutropenia in pts receiving these agents. Here we report incidence, duration, and severity data on TE neutropenia in such pts from an electronic health record dataset and administrative claims. Methods: This retrospective study comprised 2 mutually exclusive cohorts of pts with MBC receiving RIB or PAL. Pts were matched 1:1 based on age and year of treatment start. Prior baseline activity of ≥6 mo was required. The MarketScan claims databases was used to evaluate incidence rates of TE neutropenia from Jan 1, 2015, to Dec 31, 2018, in pts receiving RIB or PAL. Rate ratio was calculated using a Poisson model. Data on neutropenia severity and duration were obtained from Optum de-identified Electronic Health Record dataset. Neutropenia severity was defined by neutrophil counts from lab tests (grade 1/2, 1000- < 1500/μL; grade 3, 500- < 1000/μL; grade 4 < 500/μL) within the first 180 days of treatment. Neutropenia duration was estimated using Kaplan-Meier analysis and defined as the time between first abnormal neutrophil result and a lab result demonstrating neutropenia resolution. Results: After 1:1 matching, 152 pts from the MarketScan database were included in both the PAL and RIB cohorts; 168 matched pts were included from the Optum dataset. Neutropenia was reported in 38 pts (25%) in the PAL group and 25 pts (17%) in the RIB group. The rate of neutropenia per person–treatment year was 0.5 (95% CI, 0.4-0.7) in PAL pts vs 0.4 (95% CI, 0.3-0.6) in RIB pts. The rate ratio of neutropenia between treatments (PAL vs RIB) was 1.4 (95% CI, 0.8-2.3), which was not statistically significant, likely due to small sample size. Rates of neutropenia by severity with PAL vs RIB were 32% vs 32% for grade 1/2, 35% vs 26% for grade 3, and 4% vs 4% for grade 4, respectively. The rate ratio for grade 3 or grade 4 neutropenia (PAL vs RIB) was 1.3 (95% CI, 0.9-1.8). Median neutropenia duration was 29 vs 20 days ( P< .01) with PAL vs RIB. Conclusions: Treatment of HR+ MBC with RIB and PAL requires optimal management of TE neutropenia. Real-world data showed that pts with MBC receiving PAL had a numerically higher rate of neutropenia than pts receiving RIB. Rates of grade 3 neutropenia were higher with PAL vs RIB, and duration of neutropenia was longer with PAL vs RIB. Economic burden analyses of neutropenia will be presented.

scholarly journals Pilot-testing an adverse drug event reporting form prior to its implementation in an electronic health record

SpringerPlus ◽  
2016 ◽  
Vol 5 (1) ◽  
Author(s):  
Adam Chruscicki ◽  
Katherin Badke ◽  
David Peddie ◽  
Serena Small ◽  
Ellen Balka ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Adverse Drug Event ◽  
Drug Event ◽  
Health Record ◽  
Event Reporting ◽  
Pilot Testing ◽  
Electronic Health
Sign in / Sign up

Export Citation Format

Share Document