Scholarlink

<p>Prolonged invasive mechanical ventilation and extubation failure are common and are associated with increased mortality, length of stay, and costs. Current studies involving airway events usually rely on manual chart review or are dependent on a single data source and typically work because the study populations are limited to homogeneous cohorts with consistent documentation workflow. To support quality improvement and research efforts addressing airway-related outcomes, ways to accurately and reliably identify airway events in electronic health records (EHR) are critical. We developed and validated an automated SQL-based algorithm to obtain high-quality airway event data that performs across diverse clinical settings within a single health system. Using data from all adult and pediatric patients at two large quaternary care hospitals from 2013 to 2025, the algorithm integrated multiple data sources to identify airway events, including ventilator flowsheets, tracheostomy procedures, anesthesia records, admission tables, and lines/drains/airway tables. Data quality was graded using a grading scale that incorporated both the number of data sources and temporal concordance between sources, with higher source count and closer temporal agreement indicating higher data quality (range 1&#xa0;A [highest] to 3&#xa0;C [lowest]). Qualitative validation was performed through manual review of 400 records. During the 12-year period, 285,157 unique airway events were identified. Of these, 11.8% were neonatal or pediatric, and 17.5% occurred in critical care or emergency settings. Over 95% of events were graded as high-quality, and this data quality was maintained across diverse intensive care units, perioperative, emergency, and other settings. While external validation is needed, the framework is designed to be adaptable with site-specific validation, and the full codebase is provided to support replication. This automated airway event algorithm generated high-quality airway event data for diverse hospital settings and age-groups within a single health system, and provides a practical framework to improve data quality for airway-related research and quality improvement.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated Detection of Airway Events in Diverse Hospital Settings: Development and Validation of a Scalable System

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月9日

查看全文
  • Kelly Feldman,
  • Sarah Hamza,
  • Jacqueline C. Stocking,
  • Stephen Murray,
  • Tristan Grogan,
  • Colin J. Sallee,
  • Eilon Gabel,
  • Theodora Wingert

摘要

Prolonged invasive mechanical ventilation and extubation failure are common and are associated with increased mortality, length of stay, and costs. Current studies involving airway events usually rely on manual chart review or are dependent on a single data source and typically work because the study populations are limited to homogeneous cohorts with consistent documentation workflow. To support quality improvement and research efforts addressing airway-related outcomes, ways to accurately and reliably identify airway events in electronic health records (EHR) are critical. We developed and validated an automated SQL-based algorithm to obtain high-quality airway event data that performs across diverse clinical settings within a single health system. Using data from all adult and pediatric patients at two large quaternary care hospitals from 2013 to 2025, the algorithm integrated multiple data sources to identify airway events, including ventilator flowsheets, tracheostomy procedures, anesthesia records, admission tables, and lines/drains/airway tables. Data quality was graded using a grading scale that incorporated both the number of data sources and temporal concordance between sources, with higher source count and closer temporal agreement indicating higher data quality (range 1 A [highest] to 3 C [lowest]). Qualitative validation was performed through manual review of 400 records. During the 12-year period, 285,157 unique airway events were identified. Of these, 11.8% were neonatal or pediatric, and 17.5% occurred in critical care or emergency settings. Over 95% of events were graded as high-quality, and this data quality was maintained across diverse intensive care units, perioperative, emergency, and other settings. While external validation is needed, the framework is designed to be adaptable with site-specific validation, and the full codebase is provided to support replication. This automated airway event algorithm generated high-quality airway event data for diverse hospital settings and age-groups within a single health system, and provides a practical framework to improve data quality for airway-related research and quality improvement.