Megan Mariner Gray

Megan Mariner Gray

Auto-generated profile, based on publicly available information

Megan Mariner Gray

Department of Pediatrics, University of Washington School of Medicine, Seattle, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2024 in JMIR Medical Education
Verified
Journal Article
Open access
MGMegan Gray
Megan Gray
ABAustin J Baird
Austin J Baird
TSTaylor Sawyer
Taylor Sawyer
JJJasmine James
Jasmine James
TDThea DeBroux
Thea DeBroux
RURachel A. Umoren
Rachel A. Umoren
Background: Using virtual patients, facilitated by natural language processing, provides a valuable educational experience for learners. Generating a large, varied sample of realistic and appropriate responses for virtual patients is challenging. Artificial intelligence (AI) programs can be a viable source for these responses, but their utility for this purpose has not been explored. Objective: In this study, we explored the effectiveness of generative AI (ChatGPT) in developing realistic virtual standardized patient dialogues to teach prenatal counseling skills. Methods: ChatGPT was prompted to generate a list of common areas of concern and questions that families expecting preterm delivery at 24 weeks gestation might ask during prenatal counseling. ChatGPT was then prompted to generate 2 role-plays with dialogues between a parent expecting a potential preterm delivery at 24 weeks and their counseling physician using each of the example questions. The prompt was repeated for 2 unique role-plays: one parent was characterized as anxious and the other as having low trust in the medical system. Role-play scripts were exported verbatim and independently reviewed by 2 neonatologists with experience in prenatal counseling, using a scale of 1-5 on realism, appropriateness, and utility for virtual standardized patient responses. Results: ChatGPT generated 7 areas of concern, with 35 example questions used to generate role-plays. The 35 role-play transcripts generated 176 unique parent responses (median 5, IQR 4-6, per role-play) with 268 unique sentences. Expert review identified 117 (65%) of the 176 responses as indicating an emotion, either directly or indirectly. Approximately half (98/176, 56%) of the responses had 2 or more sentences, and half (88/176, 50%) included at least 1 question. More than half (104/176, 58%) of the responses from role-played parent characters described a feeling, such as being scared, worried, or concerned. The role-plays of parents with low trust in the medical system generated many unique sentences (n=50). Most of the sentences in the responses were found to be reasonably realistic (214/268, 80%), appropriate for variable prenatal counseling conversation paths (233/268, 87%), and usable without more than a minimal modification in a virtual patient program (169/268, 63%). Conclusions: Generative AI programs, such as ChatGPT, may provide a viable source of training materials to expand virtual patient programs, with careful attention to the concerns and questions of patients and families. Given the potential for unrealistic or inappropriate statements and questions, an expert should review AI chat outputs before deploying them in an educational program.

21 February 2018 in Journal of Perinatology
Verified
Journal Article
Closed access
PDF file
JKJeanne Krick
Jeanne Krick
MGMegan Gray
Megan Gray
RURachel A. Umoren
Rachel A. Umoren
GLGina Lee
Gina Lee
TSTaylor Sawyer
Taylor Sawyer

7 August 2018 in Journal of Perinatology
Verified
Journal Article
Closed access
PDF file
HFHeather French
Heather French
MGMegan Gray
Megan Gray
MGMaria Gillam-Krakauer
Maria Gillam-Krakauer
EBElizabeth M. Bonachea
Elizabeth M. Bonachea
MCMelissa Carbajal
Melissa Carbajal
RDRita Dadiz
Rita Dadiz

25 May 2023 in Air Medical Journal
Verified
Journal Article
Closed access
MGMegan M. Gray
Megan M. Gray
TRTaylor Riley
Taylor Riley
NGNancy D. Greene
Nancy D. Greene
RMRossella Mastroianni
Rossella Mastroianni
CMCourtney McLean
Courtney McLean
ZBZeenia C. Billimoria
Zeenia C. Billimoria

15 February 2019 in Journal of Perinatology
Verified
Journal Article
Closed access
PDF file
EEElizabeth Enlow
Elizabeth Enlow
MGMegan M. Gray
Megan M. Gray
SWSara Wallace-Keeshen
Sara Wallace-Keeshen
JDJo Ann D’agostino
Jo Ann D’agostino
SASoraya Abbasi
Soraya Abbasi
SLScott A. Lorch
Scott A. Lorch

4 May 2020 in Simulation in Healthcare: The Journal of the Society for Simulation in Healthcare
Verified
Journal Article
Closed access
MGMegan M. Gray
Megan M. Gray
ATAnita Anne Thomas
Anita Anne Thomas
BBBrian Dnp Burns
Brian Dnp Burns
RURachel A. Umoren
Rachel A. Umoren
Introduction: Virtual simulation (VS) is an adaptable medium for teaching critical disaster management skills such as efficient hospital evacuation. We aimed to compare VS and prerecorded narrated multimedia lecture–based training of pediatric nurses for evacuation of a sick newborn in the neonatal intensive care unit and pediatric emergency department (ED) using live evacuation simulations. Methods: Thirty neonatal intensive care unit and 30 ED nurses enrolled with 30 randomized to multimedia lecture and 30 randomized to VS, with equal block distribution of nurses from each unit. Pretraining/posttraining surveys were administered, and live evacuation simulations were scored for time to evacuation, items collected, and communication. Results: Overall, disaster preparation and communication improved within the VS group as compared with the multimedia lecture group. Virtual simulation rated more immersive (P < 0.001), better at safety threat identification (P < 0.05), and better at evacuation preparation compared with multimedia lecture (P < 0.01). Virtual simulation participants felt more prepared in disaster response (P < 0.001) and patient evacuation (P < 0.001). Both groups packed equal essential items, but VS participants packed more equipment (mean, 19 vs. 15, P < 0.01) with no significant evacuation time difference between the VS group (145 ± 58 seconds) and multimedia lecture group (152 ± 59 seconds, P = not significant). Virtual simulation participants had better communication ratings with the charge nurse (P < 0.05) and family (P < 0.001). Conclusions: Virtual simulation was well received by nurses compared with multimedia lecture and may be an effective adjunct for training nurses on infant patient evacuation during a disaster.