Jasmine James
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Jasmine James has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Rachel Umoren
Associate Professor, Division of Neonatology, Department of Pediatrics, School of Medicine, University of Washington, Seattle, WA
4 shared publications - Austin Baird
University of Washington Department of Surgery, Division of Healthcare Simulation Sciences, Seattle, Washington, United States of America
2 shared publications - Jeanne Alexandra Krick
Department of Pediatrics, Brooke Army Medical Center, San Antonio, USA
2 shared publications - Megan Mariner Gray
Department of Pediatrics, University of Washington School of Medicine, Seattle, USA
2 shared publications - Michelle Bartlett
Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States
2 shared publications - Taylor Sawyer
Department of Pediatrics, Division of Neonatology, University of Washington School of Medicine, Seattle, USA
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 1 February 2024
- Published by JMIR Publications Inc. in JMIR Medical Education
- Vol. 10, e50705
Increasing Realism and Variety of Virtual Patient Dialogues for Prenatal Counseling Education Through a Novel Application of ChatGPT: Exploratory Observational Study
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.
- 1 February 2024
- Published by JMIR Publications Inc. in JMIR Medical Education
- Vol. 10, e50705
Top Cited PapersOpen AccessIncreasing Realism and Variety of Virtual Patient Dialogues for Prenatal Counseling Education Through a Novel Application of ChatGPT: Exploratory Observational Study
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.
- 4 December 2023
- Published by Elsevier in International Journal of Industrial Ergonomics
- Vol. 99
Disparities in access to healthcare services in a regional neonatal transport network
- 4 December 2023
- Published by Elsevier in International Journal of Industrial Ergonomics
- Vol. 99
Disparities in access to healthcare services in a regional neonatal transport network
- Open Access
- 17 July 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Increasing Realism and Variety of Virtual Patient Dialogues for Prenatal Counseling Education Through a Novel Application of ChatGPT: Exploratory Observational Study (Preprint)
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.
- 17 July 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessIncreasing Realism and Variety of Virtual Patient Dialogues for Prenatal Counseling Education Through a Novel Application of ChatGPT: Exploratory Observational Study (Preprint)
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.
- 22 June 2023
- Published by Georg Thieme Verlag KG in American Journal of Perinatology
- Vol. 41 (S 01) , e2436-e2443
Quality Indices and Outcomes of a Neonatology Telerounding Program in a Level II Neonatal Intensive Care Unit: Single-Center Experience during the COVID-19 Pandemic
Objective The objective of this program evaluation was to describe the outcomes of daily neonatologist telerounding with the onsite advanced practice provider (APP) in a Level II neonatal intensive care unit (NICU), before and during the coronavirus disease 2019 (COVID-19) pandemic. Study Design Bedside telerounding occurred with an onsite APP using a telehealth cart and paired Bluetooth stethoscope. Data collected by longitudinal and cross-sectional surveys and chart review before (May 2019–February 2020) and during (March 2020–February 2021) the COVID-19 pandemic were analyzed using descriptive statistics and thematic analysis. Results A total of 258 patients were admitted to the Level II NICU before (May 2019–February 2020) and during (March 2020–February 2021) the COVID-19 pandemic. Demographic characteristics and outcomes, including breastfeeding at discharge and length of stay were similar pre- and postonset of the COVID-19 pandemic. Postrounding surveys by 10 (response rate 83%) neonatologists indicated parents were present in 80 (77%) of rounds and video was at least somewhat helpful in 94% of cases. Cross-sectional survey responses of 23 neonatologists and APPs (response rate 62%) indicated satisfaction with the program. Common themes on qualitative analysis of open-ended survey responses were “need for goodness of fit” and “another set of eyes” and “opportunities for use.” Conclusion Daily telerounding with neonatologists and APPs in a Level II NICU supported neonatal care. Quality metrics and clinical outcomes are described with no differences seen before and during the COVID-19 pandemic. Key Points
- 22 June 2023
- Published by Georg Thieme Verlag KG in American Journal of Perinatology
- Vol. 41 (S 01) , e2436-e2443
Quality Indices and Outcomes of a Neonatology Telerounding Program in a Level II Neonatal Intensive Care Unit: Single-Center Experience during the COVID-19 Pandemic
Objective The objective of this program evaluation was to describe the outcomes of daily neonatologist telerounding with the onsite advanced practice provider (APP) in a Level II neonatal intensive care unit (NICU), before and during the coronavirus disease 2019 (COVID-19) pandemic. Study Design Bedside telerounding occurred with an onsite APP using a telehealth cart and paired Bluetooth stethoscope. Data collected by longitudinal and cross-sectional surveys and chart review before (May 2019–February 2020) and during (March 2020–February 2021) the COVID-19 pandemic were analyzed using descriptive statistics and thematic analysis. Results A total of 258 patients were admitted to the Level II NICU before (May 2019–February 2020) and during (March 2020–February 2021) the COVID-19 pandemic. Demographic characteristics and outcomes, including breastfeeding at discharge and length of stay were similar pre- and postonset of the COVID-19 pandemic. Postrounding surveys by 10 (response rate 83%) neonatologists indicated parents were present in 80 (77%) of rounds and video was at least somewhat helpful in 94% of cases. Cross-sectional survey responses of 23 neonatologists and APPs (response rate 62%) indicated satisfaction with the program. Common themes on qualitative analysis of open-ended survey responses were “need for goodness of fit” and “another set of eyes” and “opportunities for use.” Conclusion Daily telerounding with neonatologists and APPs in a Level II NICU supported neonatal care. Quality metrics and clinical outcomes are described with no differences seen before and during the COVID-19 pandemic. Key Points