Practical use case of natural language processing for observational clinical research data retrieval from electronic health records: AssistMED project.

INTRODUCTION: Electronic health records (EHRs) contain data valuable for clinical research. However, they are in textual format and require manual encoding to databases, which is a lengthy and costly process. Natural language processing (NLP) is a computational technique that allows for text analysis. OBJECTIVES: Our study aimed to demonstrate a practical use case of NLP for a large retrospective study cohort characterization and comparison with human retrieval. PATIENTS AND METHODS: Anonymized discharge documentation of 10 314 patients from a cardiology tertiary care department was analyzed for inclusion in the CRAFT registry (Multicenter Experience in Atrial Fibrillation Patients Treated with Oral Anticoagulants; NCT02987062). Extensive clinical characteristics regarding concomitant diseases, medications, daily drug dosages, and echocardiography were collected manually and through NLP. RESULTS: There were 3030 and 3029 patients identified by human and NLP­based approaches, respectively, reflecting 99.93% accuracy of NLP in detecting AF. Comprehensive baseline patient characteristics by NLP was faster than human analysis (3 h and 15 min vs 71 h and 12 min). The calculated CHA2DS2VASc and HAS­BLED scores based on both methods did not differ (human vs NLP; median [interquartile range], 3 [2-5] vs 3 [2-5]; P = 0.74 and 1 [1-2] vs 1 [1-2]; P = 0.63, respectively). For most data, an almost perfect agreement between NLP- and human-retrieved characteristics was found; daily dosage identification was the least accurate NLP feature. Similar conclusions on cohort characteristics would be made; however, daily dosage detection for some drug groups would require additional human validation in the NLP­based cohort. CONCLUSIONS: NLP utilization in EHRs may accelerate data acquisition and provide accurate information for retrospective studies.

A randomized crossover comparison of the bébé VieScope and direct laryngoscope for pediatric airway management by nurses in medical simulation settings.

BACKGROUND: Airway management in life-threatening emergencies is essential for children, and endotracheal intubation is the gold standard. It protects against regurgitation and enables mechanical ventilation. New types of airway management equipment are being developed and implemented to meet the needs of medical personnel. RESEARCH DESIGN AND METHODS: This prospective, randomized, cross-over simulation trial evaluated the success of endotracheal intubation in three scenarios: normal airway (scenario-A), tongue edema (scenario-B), and continuous chest compression (scenario-C), using the bébé Vie Scope™ laryngoscope (VieScope) and the Macintosh blade laryngoscope (MAC) as a comparative tool performed by nurses with limited tracheal intubation experience. RESULTS: The results of the study showed that in scenario-A, there were no significant differences in the first attempt success rate or endotracheal intubation time between VieScope and MAC. However, VieScope was associated with better visualization of the glottis. In scenarios B and C, VieScope was significantly more effective than MAC in terms of first-pass success rate, time to intubate, Cormack-Lehane grade, POGO score, and ease of endotracheal intubation. CONCLUSIONS: Bébé VieScope may be useful for endotracheal intubation in pediatric patients, particularly in cases of tongue edema and ongoing chest compression, providing a higher first-pass success rate than conventional laryngoscopes.