Dataset Information

A Computable Phenotype Improves Cohort Ascertainment in a Pediatric Pulmonary Hypertension Registry.

ABSTRACT: OBJECTIVES:To compare registry and electronic health record (EHR) data mining approaches for cohort ascertainment in patients with pediatric pulmonary hypertension (PH) in an effort to overcome some of the limitations of registry enrollment alone in identifying patients with particular disease phenotypes. STUDY DESIGN:This study was a single-center retrospective analysis of EHR and registry data at Boston Children's Hospital. The local Informatics for Integrating Biology and the Bedside (i2b2) data warehouse was queried for billing codes, prescriptions, and narrative data related to pediatric PH. Computable phenotype algorithms were developed by fitting penalized logistic regression models to a physician-annotated training set. Algorithms were applied to a candidate patient cohort, and performance was evaluated using a separate set of 136 records and 179 registry patients. We compared clinical and demographic characteristics of patients identified by computable phenotype and the registry. RESULTS:The computable phenotype had an area under the receiver operating characteristics curve of 90% (95% CI, 85%-95%), a positive predictive value of 85% (95% CI, 77%-93%), and identified 413 patients (an additional 231%) with pediatric PH who were not enrolled in the registry. Patients identified by the computable phenotype were clinically distinct from registry patients, with a greater prevalence of diagnoses related to perinatal distress and left heart disease. CONCLUSIONS:Mining of EHRs using computable phenotypes identified a large cohort of patients not recruited using a classic registry. Fusion of EHR and registry data can improve cohort ascertainment for the study of rare diseases. TRIAL REGISTRATION:ClinicalTrials.gov: NCT02249923.

SUBMITTER: Geva A

PROVIDER: S-EPMC5572538 | biostudies-literature | 2017 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Computable Phenotype Improves Cohort Ascertainment in a Pediatric Pulmonary Hypertension Registry.

Geva Alon A Gronsbell Jessica L JL Cai Tianxi T Cai Tianrun T Murphy Shawn N SN Lyons Jessica C JC Heinz Michelle M MM Natter Marc D MD Patibandla Nandan N Bickel Jonathan J Mullen Mary P MP Mandl Kenneth D KD

The Journal of pediatrics 20170616

<h4>Objectives</h4>To compare registry and electronic health record (EHR) data mining approaches for cohort ascertainment in patients with pediatric pulmonary hypertension (PH) in an effort to overcome some of the limitations of registry enrollment alone in identifying patients with particular disease phenotypes.<h4>Study design</h4>This study was a single-center retrospective analysis of EHR and registry data at Boston Children's Hospital. The local Informatics for Integrating Biology and the B ...[more]

PMID: 28625502

Similar Datasets

Project description:IntroductionPulmonary hypertension (PH) is a devastating, progressive disease with increasingly debilitating symptoms and usually shortened overall life expectancy due to a narrowing of the pulmonary vasculature and consecutive right heart failure. Little is known about PH in Africa, but limited reports suggest that PH is more prevalent in Africa compared with developed countries due to the high prevalence of risk factors in the region.Methods and analysisA multinational multicentre registry-type cohort study was established and tailored to resource-constraint settings to describe disease presentation, disease severity and aetiologies of PH, comorbidities, diagnostic and therapeutic management, and the natural course of PH in Africa. PH will be diagnosed by specialist cardiologists using echocardiography (right ventricular systolic pressure >35 mm Hg, absence of pulmonary stenosis and acute right heart failure), usually accompanied by shortness of breath, fatigue, peripheral oedema and other cardiovascular symptoms, ECG and chest X-ray changes in keeping with PH as per guidelines (European Society of Cardiology and European Respiratory Society (ESC/ERS) guidelines). Additional investigations such as a CT scan, a ventilation/perfusion scan or right heart catheterisation will be performed at the discretion of the treating physician. Functional tests include a 6 min walk test and the Karnofsky Performance Score. The WHO classification system for PH will be applied to describe the different aetiologies of PH. Several substudies have been implemented within the registry to investigate specific types of PH and their outcome at up to 24 months. Data will be analysed by an independent institution following a data analyse plan.Ethics and disseminationAll local ethics committees of the participating centres approved the protocol. The data will be disseminated through peer-reviewed journals at national and international conferences and public events at local care providers.

Dataset Information

A Computable Phenotype Improves Cohort Ascertainment in a Pediatric Pulmonary Hypertension Registry.

Publications

A Computable Phenotype Improves Cohort Ascertainment in a Pediatric Pulmonary Hypertension Registry.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets