Objectives (1) To develop an automated eligibility screening (ES) approach for clinical trials in an urban tertiary care pediatric emergency department (ED); (2) to assess the effectiveness of natural language processing (NLP), information extraction (IE), and machine learning (ML) techniques on real-world clinical data and trials.Data and methods We collected eligibility criteria for 13 randomly selected, disease-specific clinical trials actively enrolling patients between January 1, 2010 and August 31, 2012. In parallel, we retrospectively selected data fields including demographics, laboratory data, and clinical notes from the electronic health record (EHR) to represent profiles of all 202795 patients visiting the ED during the same period. Leveraging NLP, IE, and ML technologies, the automated ES algorithms identified patients whose profiles matched the trial criteria to reduce the pool of candidates for staff screening. The performance was validated on both a physician-generated gold standard of trial–patient matches and a reference standard of historical trial–patient enrollment decisions, where workload, mean average precision (MAP), and recall were assessed.Results Compared with the case without automation, the workload with automated ES was reduced by 92% on the gold standard set, with a MAP of 62.9%. The automated ES achieved a 450% increase in trial screening efficiency. The findings on the gold standard set were confirmed by large-scale evaluation on the reference set of trial–patient matches.Discussion and conclusion By exploiting the text of trial criteria and the content of EHRs, we demonstrated that NLP-, IE-, and ML-based automated ES could successfully identify patients for clinical trials.

No abstract

Objectives: The objective was to assess the relationship between emergency department (ED) crowding and timeliness of antibiotic administration to neonates presenting with fever in a pediatric ED.Methods: This was a retrospective cohort study of febrile neonates (aged 0-30 days) evaluated for serious bacterial infections (SBIs) in a pediatric ED from January 2006 to January 2008. General linear models were used to evaluate the association of five measures of ED crowding with timeliness of antibiotic administration, controlling for patient characteristics. A secondary analysis was conducted to determine which part of the ED visit for this population was most affected by crowding.Results: A total of 190 patients met inclusion criteria. Mean time to first antibiotic was 181.7 minutes (range = 18-397 minutes). At the time of case presentation, the number of patients waiting in the waiting area, total number of hours spent in the ED by current ED patients, number of ED patients awaiting admission, and hourly boarding time were all positively associated with longer times to antibiotic. The time from patient arrival to room placement exhibited the strongest association with measures of crowding.Conclusions: Emergency department crowding is associated with delays in antibiotic administration to the febrile neonate despite rapid recognition of this patient population as a high-risk group. Each component of ED crowding, in terms of input, throughput, and output factors, was associated with delays. Further work is required to develop processes that foster a more rapid treatment protocol for these high-risk patients, regardless of ED crowding pressures.