Pediatr Crit Care Me
-
Pediatr Crit Care Me · Feb 2024
Comparing the Quality of Domain-Specific Versus General Language Models for Artificial Intelligence-Generated Differential Diagnoses in PICU Patients.
Generative language models (LMs) are being evaluated in a variety of tasks in healthcare, but pediatric critical care studies are scant. Our objective was to evaluate the utility of generative LMs in the pediatric critical care setting and to determine whether domain-adapted LMs can outperform much larger general-domain LMs in generating a differential diagnosis from the admission notes of PICU patients. ⋯ A smaller LM fine-tuned using notes of PICU patients outperformed much larger models trained on general-domain data. Currently, LMs remain inferior but may serve as an adjunct to human clinicians in real-world tasks using real-world data.
-
Pediatr Crit Care Me · Feb 2024
Cardiac Critical Care Fellowship Training in the United States and Canada: Pediatric Cardiac Intensive Care Society Endorsed Subcompetencies to the 2022 Entrustable Professional Activities.
We aimed to define and map subcompetencies required for pediatric cardiac critical care (PCCC) fellowship education and training under the auspices of the Pediatric Cardiac Intensive Care Society (PCICS). We used the 2022 frameworks for PCCC fellowship learning objectives by Tabbutt et al and for entrustable professional activities (EPAs) by Werho et al and integrated new subcompetencies to the EPAs. This complementary update serves to provide a foundation for standardized trainee assessment tools for PCCC. ⋯ This represents the 2023 update to the PCCC fellowship education and training EPAs with the defining and mapping of 110 subcompetencies to the nine established 2022 EPAs. This goal of this update is to serve as the next step in the integration of EPAs into a standardized competency-based assessment framework for trainees in PCCC.
-
Pediatr Crit Care Me · Feb 2024
Post-Intensive Care Sequelae in Pediatrics-Results of an Early Rehabilitation Implementation Study.
To compare post-PICU discharge functioning, health-related quality of life (HRQL), and parental stress before and after the implementation of an early rehabilitation bundle. ⋯ We were unable to adequately determine the efficacy of a rehabilitation bundle on patient-centered outcomes as this substudy was not powered for these outcomes. Our results did reveal that persistent low functioning is common in PICU survivors, more common than low HRQL, while experiencing both functional decline and low HRQL was uncommon.
-
Pediatr Crit Care Me · Feb 2024
Utility of Hospital Failure to Rescue for Analyzing Variation in Pediatric Postoperative Mortality.
To evaluate the association between pediatric hospital performances in terms of failure to rescue (FTR), defined as postoperative mortality after a surgical complication, and mortality among patients without a surgical complication. ⋯ FTR may be a useful and valid surgical quality measure for pediatric surgery, even when considering patients without a postoperative complication. These findings suggest practices and processes for preventing FTR at high performing pediatric hospitals might help mitigate the risk of postoperative mortality even in the absence of a postoperative complication.
-
Pediatr Crit Care Me · Feb 2024
Tracheal Intubation by Advanced Practice Registered Nurses in Pediatric Critical Care: Retrospective Study From the National Emergency Airway for Children Registry (2015-2019).
To describe tracheal intubation (TI) practice by Advanced Practice Registered Nurses (APRNs) in North American PICUs, including rates of TI-associated events (TIAEs) from 2015 to 2019. ⋯ TI performed by APRNs was associated with lower odds of first attempt success when compared with other ICU clinicians although there was no appreciable difference in procedural adverse events. There appears to be a positive relationship between experience and success rates. These data suggest there is an ongoing need for opportunities to build on TI competency with APRNs.