Brief communication: Louisiana Clinical Data Research Network: establishing an infrastructure for efficient conduct of clinical research

The state of Louisiana, like the nation as a whole, is facing the salient challenge of improving population health and efficiency of healthcare delivery. Research to inform innovations in healthcare will best enhance this effort if it is timely, efficient, and patient-centered. The Louisiana Clinical Data Research Network (LACDRN) will increase the capacity to conduct robust comparative effectiveness research by building a health information technology infrastructure that provides access to comprehensive clinical data for more than 1 million patients statewide. To ensure that network-based research best serves its end-users, the project will actively engage patients and providers as key informants and decision-makers in the implementation of LACDRN. The network''s patient-centered research agenda will prioritize patients’ and clinicians’ needs and aim to support evidence-based decisions on the healthcare they receive and provide, to optimize patient outcomes and quality of life.     

Research and applications: Phenotyping for patient safety: algorithm development for electronic health record based automated adverse event and medical error detection in neonatal intensive care

Background

Although electronic health records (EHRs) have the potential to provide a foundation for quality and safety algorithms, few studies have measured their impact on automated adverse event (AE) and medical error (ME) detection within the neonatal intensive care unit (NICU) environment.

Objective

This paper presents two phenotyping AE and ME detection algorithms (ie, IV infiltrations, narcotic medication oversedation and dosing errors) and describes manual annotation of airway management and medication/fluid AEs from NICU EHRs.

Methods

From 753 NICU patient EHRs from 2011, we developed two automatic AE/ME detection algorithms, and manually annotated 11 classes of AEs in 3263 clinical notes. Performance of the automatic AE/ME detection algorithms was compared to trigger tool and voluntary incident reporting results. AEs in clinical notes were double annotated and consensus achieved under neonatologist supervision. Sensitivity, positive predictive value (PPV), and specificity are reported.

Results

Twelve severe IV infiltrates were detected. The algorithm identified one more infiltrate than the trigger tool and eight more than incident reporting. One narcotic oversedation was detected demonstrating 100% agreement with the trigger tool. Additionally, 17 narcotic medication MEs were detected, an increase of 16 cases over voluntary incident reporting.

Conclusions

Automated AE/ME detection algorithms provide higher sensitivity and PPV than currently used trigger tools or voluntary incident-reporting systems, including identification of potential dosing and frequency errors that current methods are unequipped to detect.