The Pediatric Emergency Care Applied Research Network Registry: A Multicenter Electronic Health Record Registry of Pediatric Emergency Care.

2018

366-376

2018 Apr

1869-0327

<p><strong>BACKGROUND: </strong> Electronic health record (EHR)-based registries allow for robust data to be derived directly from the patient clinical record and can provide important information about processes of care delivery and patient health outcomes.</p>

<p><strong>METHODS: </strong> A data dictionary, and subsequent data model, were developed describing EHR data sources to include all processes of care within the emergency department (ED). ED visit data were deidentified and XML files were created and submitted to a central data coordinating center for inclusion in the registry. Automated data quality control occurred prior to submission through an application created for this project. Data quality reports were created for manual data quality review.</p>

<p><strong>RESULTS: </strong> The Pediatric Emergency Care Applied Research Network (PECARN) Registry, representing four hospital systems and seven EDs, demonstrates that ED data from disparate health systems and EHR vendors can be harmonized for use in a single registry with a common data model. The current PECARN Registry represents data from 2,019,461 pediatric ED visits, 894,503 distinct patients, more than 12.5 million narrative reports, and 12,469,754 laboratory tests and continues to accrue data monthly.</p>

<p><strong>CONCLUSION: </strong> The Registry is a robust harmonized clinical registry that includes data from diverse patients, sites, and EHR vendors derived via data extraction, deidentification, and secure submission to a central data coordinating center. The data provided may be used for benchmarking, clinical quality improvement, and comparative effectiveness research.</p>

10.1055/s-0038-1651496

Appl Clin Inform

29791930

Identification of Long Bone Fractures in Radiology Reports Using Natural Language Processing to support Healthcare Quality Improvement.

2016

1051-1068

2016 Nov 09

1869-0327

<p><strong>BACKGROUND: </strong>Important information to support healthcare quality improvement is often recorded in free text documents such as radiology reports. Natural language processing (NLP) methods may help extract this information, but these methods have rarely been applied outside the research laboratories where they were developed.</p>

<p><strong>OBJECTIVE: </strong>To implement and validate NLP tools to identify long bone fractures for pediatric emergency medicine quality improvement.</p>

<p><strong>METHODS: </strong>Using freely available statistical software packages, we implemented NLP methods to identify long bone fractures from radiology reports. A sample of 1,000 radiology reports was used to construct three candidate classification models. A test set of 500 reports was used to validate the model performance. Blinded manual review of radiology reports by two independent physicians provided the reference standard. Each radiology report was segmented and word stem and bigram features were constructed. Common English "stop words" and rare features were excluded. We used 10-fold cross-validation to select optimal configuration parameters for each model. Accuracy, recall, precision and the F1 score were calculated. The final model was compared to the use of diagnosis codes for the identification of patients with long bone fractures.</p>

<p><strong>RESULTS: </strong>There were 329 unique word stems and 344 bigrams in the training documents. A support vector machine classifier with Gaussian kernel performed best on the test set with accuracy=0.958, recall=0.969, precision=0.940, and F1 score=0.954. Optimal parameters for this model were cost=4 and gamma=0.005. The three classification models that we tested all performed better than diagnosis codes in terms of accuracy, precision, and F1 score (diagnosis code accuracy=0.932, recall=0.960, precision=0.896, and F1 score=0.927).</p>

<p><strong>CONCLUSIONS: </strong>NLP methods using a corpus of 1,000 training documents accurately identified acute long bone fractures from radiology reports. Strategic use of straightforward NLP methods, implemented with freely available software, offers quality improvement teams new opportunities to extract information from narrative documents.</p>

10.4338/ACI-2016-08-RA-0129

Appl Clin Inform

27826610