The use of natural language processing on pediatric diagnostic radiology reports in the electronic health record to identify deep venous thrombosis in children.

Venous thromboembolism (VTE) is a potentially life-threatening condition that includes both deep vein thrombosis (DVT) and pulmonary embolism. We sought to improve detection and reporting of children with a new diagnosis of VTE by applying natural language processing (NLP) tools to radiologists' reports. We validated an NLP tool, Reveal NLP (Health Fidelity Inc, San Mateo, CA) and inference rules engine's performance in identifying reports with deep venous thrombosis using a curated set of ultrasound reports. We then configured the NLP tool to scan all available radiology reports on a daily basis for studies that met criteria for VTE between July 1, 2015, and March 31, 2016. The NLP tool and inference rules engine correctly identified 140 out of 144 reports with positive DVT findings and 98 out of 106 negative reports in the validation set. The tool's sensitivity was 97.2% (95% CI 93-99.2%), specificity was 92.5% (95% CI 85.7-96.7%). Subsequently, the NLP tool and inference rules engine processed 6373 radiology reports from 3371 hospital encounters. The NLP tool and inference rules engine identified 178 positive reports and 3193 negative reports with a sensitivity of 82.9% (95% CI 74.8-89.2) and specificity of 97.5% (95% CI 96.9-98). The system functions well as a safety net to screen patients for HA-VTE on a daily basis and offers value as an automated, redundant system. To our knowledge, this is the first pediatric study to apply NLP technology in a prospective manner for HA-VTE identification.

Improving Cardiac Surgical Site Infection Reporting and Prevention By Using Registry Data for Case Ascertainment.

BACKGROUND: The use of administrative data for surgical site infection (SSI) surveillance leads to inaccurate reporting of SSI rates [1]. A quality improvement (QI) initiative was conducted linking clinical registry and administrative databases to improve reporting and reduce the incidence of SSI [2]. METHODS: At our institution, The Society of Thoracic Surgeons Congenital Heart Surgery Database (STS-CHSD) and infection surveillance database (ISD) were linked to the enterprise data warehouse containing electronic health record (EHR) billing data. A data visualization tool was created to (1) use the STS-CHSD for case ascertainment, (2) resolve discrepancies between the databases, and (3) assess impact of QI initiatives, including wound alert reports, bedside reviews, prevention bundles, and billing coder education. RESULTS: Over the 24-month study period, 1,715 surgical cases were ascertained according to the STS-CHSD clinical criteria, with 23 SSIs identified through the STS-CHSD, 20 SSIs identified through the ISD, and 32 SSIs identified through the billing database. The rolling 12-month STS-CHSD SSI rate decreased from 2.73% (21 of 769 as of January 2013) to 1.11% (9 of 813 as of December 2014). Thirty reporting discrepancies were reviewed to ensure accuracy. Workflow changes facilitated communication and improved adjudication of suspected SSIs. Billing coder education increased coding accuracy and narrowed variation between the 3 SSI sources. The data visualization tool demonstrated temporal relationships between QI initiatives and SSI rate reductions. CONCLUSIONS: Linkage of registry and infection control surveillance data with the EHR improves SSI surveillance. The visualization tool and workflow changes facilitated communication, SSI adjudication, and assessment of the QI initiatives. Implementation of these initiatives was associated with decreased SSI rates.