Rosalyn E. Maben-Feaster
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rosalyn E. Maben-Feaster has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Maya Md Hammoud
Department of Obstetrics and Gynecology, University of Michigan Medical School , Ann Arbor, MI
3 shared publications - AnneMarie Opipari
University of Michigan Medical School Ann Arbor, MI United States
2 shared publications - Judee Richardson
Judee Richardson, PhD, is Director of Medical Education Research and Program Evaluation, American Medical Association, and an Adjunct Lecturer, Department of Medical Education, College of Medicine, University of Illinois at Chicago, Chicago, Illinois, USA
2 shared publications - Jung G. Kim
Ronald O Perelman Department of Emergency Medicine, New York University Grossman School of Medicine, New York, USA
2 shared publications - Luan Lawson
Department of Emergency Medicine and Office of Medical Education, Virginia Commonwealth University School of Medicine , Richmond, VA
2 shared publications - Maya M. Hammoud
Maya M. Hammoud, MD, MBA, is a Professor of Obstetrics and Gynecology and Learning Health Sciences, University of Michigan, Ann Arbor, Michigan, USA
2 shared publications
Latest Publications
- 24 October 2026
- Published by Oxford University Press (OUP) in Academic Medicine
Bibliometric and network analysis of the dissemination of health systems science in medical education
Purpose: Societal concerns regarding the outcomes of the US healthcare system served as an impetus to incorporate a third pillar, health systems science (HSS), into medical education, complementing the basic and clinical sciences. Similar to the creation of the basic sciences as a unified construct, multiple fields were brought together under the HSS framework. The extent of adoption and dissemination of this construct is unknown. This study sought to determine the dissemination, adoption, and connections of HSS through bibliographic and social network analysis. Method: Starting with 5 foundational HSS articles, the authors conducted bibliometric and social network analysis of HSS-related publications using data from Web of Science, excluding books, book chapters, and conference abstracts. Bibliometric performance and science mapping metrics for 269 papers published January 2017-November 2025 were analyzed including publication productivity, citation impact, and author/institution contributions. Social network analysis was used to assess the structure, growth, and interconnectedness of the HSS scholarly network for 235 papers published from 2017 to October 2024. Results: Bibliometric analysis found 100 journals representing over 1087 authors at 296 institutions. The network showed consistent annual growth with increasing interconnectivity and decreasing network density, suggesting diffusion beyond early adopters. Academic Medicine was the most frequent publication outlet (59/269, 22%). Seven of the top 10 contributing institutions were part of the original AMA Accelerating Change in Medical Education Consortium. PageRank and citation analysis revealed high-impact articles were closely linked to early HSS curricular work. Social network metrics demonstrated a maturing scholarly community around HSS. Conclusions: This bibliometric analysis starting with 5 foundational articles found dissemination through an expanding network of scholarship, sustained citation of foundational papers, and broad engagement across a diverse group of authors and institutions. As HSS becomes embedded in medical education, future research should explore how its evolution meets emerging health system challenges.
- 24 October 2026
- Published by Oxford University Press (OUP) in Academic Medicine
Bibliometric and network analysis of the dissemination of health systems science in medical education
Purpose: Societal concerns regarding the outcomes of the US healthcare system served as an impetus to incorporate a third pillar, health systems science (HSS), into medical education, complementing the basic and clinical sciences. Similar to the creation of the basic sciences as a unified construct, multiple fields were brought together under the HSS framework. The extent of adoption and dissemination of this construct is unknown. This study sought to determine the dissemination, adoption, and connections of HSS through bibliographic and social network analysis. Method: Starting with 5 foundational HSS articles, the authors conducted bibliometric and social network analysis of HSS-related publications using data from Web of Science, excluding books, book chapters, and conference abstracts. Bibliometric performance and science mapping metrics for 269 papers published January 2017-November 2025 were analyzed including publication productivity, citation impact, and author/institution contributions. Social network analysis was used to assess the structure, growth, and interconnectedness of the HSS scholarly network for 235 papers published from 2017 to October 2024. Results: Bibliometric analysis found 100 journals representing over 1087 authors at 296 institutions. The network showed consistent annual growth with increasing interconnectivity and decreasing network density, suggesting diffusion beyond early adopters. Academic Medicine was the most frequent publication outlet (59/269, 22%). Seven of the top 10 contributing institutions were part of the original AMA Accelerating Change in Medical Education Consortium. PageRank and citation analysis revealed high-impact articles were closely linked to early HSS curricular work. Social network metrics demonstrated a maturing scholarly community around HSS. Conclusions: This bibliometric analysis starting with 5 foundational articles found dissemination through an expanding network of scholarship, sustained citation of foundational papers, and broad engagement across a diverse group of authors and institutions. As HSS becomes embedded in medical education, future research should explore how its evolution meets emerging health system challenges.
- Open Access
- 7 August 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e84454
Machine Learning to Identify Point-of-Care Ultrasound and Evaluate Standardized Documentation: Retrospective Operational Cohort Study
Background: Point-of-care ultrasound (POCUS) is integral to obstetrics and gynecology (OBGYN), offering bedside diagnostic and therapeutic advantages. Despite its widespread adoption, accurate documentation and billing remain challenging due to inconsistent workflows, variable free-text note quality, and inefficiencies within electronic health record (EHR) systems. These barriers often result in missed procedural charges and hinder operational, educational, and reimbursement efforts. Objective: This study leveraged machine learning (ML) to automatically identify POCUS procedures within clinical notes and assessed the effect of implementing standardized procedure documentation (ProcDoc) templates on billing capture accuracy and efficiency. Methods: We conducted a multipart retrospective cohort study at a large academic medical center using EHRs from January 2018 to August 2024 across 11 OBGYN clinic sites. ML models (LightGBM [light gradient boosting machine] and BioClinBERT [biomedical and clinical bidirectional encoder representations from transformers]) were trained on clinical encounter notes to classify POCUS procedures and validated against Current Procedural Terminology (CPT) manual code assignments. In February 2023, a standardized ProcDoc smart form was introduced to streamline POCUS documentation and automatically trigger CPT billing codes. Preintervention and postintervention periods were compared using ML metrics and manual billing audits. Outcomes included model accuracy, recall, precision, adoption rates, improvement in billing recapture, and usage of ProcDoc templates. Results: A total of 559,029 encounters from 109,776 unique patients were analyzed. The BioClinBERT model (accuracy 0.97; F 1 -score 0.55-0.63) demonstrated a robust ability to identify documented and missed procedures in free-text clinical notes. ProcDoc adoption reached 75.1% within 12 months, supported by comprehensive staff education. Billing recapture—the proportion of charges missed by providers but later identified—dropped from 10.0% preintervention to 2.4% postintervention, primarily arising from the shift toward auto-capturing documentation (odds ratio 0.22, 95% CI 0.17‐0.30; P <.001), with overall POCUS billing slightly increased (+0.6%). Most postintervention CPT codes (1812/2404, 75.4%) originated from ProcDoc templates, confirming improved workflow efficiency and reduced manual audit burden. Model analysis and billing metrics demonstrated that improvements were associated with workflow changes and not an increase in procedure frequency. Conclusions: ML modeling proved effective for extracting POCUS procedures from clinical documentation and serving as an evaluation tool for workflow interventions. Standardized documentation with ProcDoc significantly enhanced charge capture accuracy and reduced dependence on manual chart reviews and billing reconciliation. This approach highlights the use of ML as a retrospective auditing and evaluation tool for assessing clinical workflow interventions. Broader application of similar strategies could address documentation inefficiencies and promote sustainability across health care settings.
- 7 August 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e84454
Open AccessMachine Learning to Identify Point-of-Care Ultrasound and Evaluate Standardized Documentation: Retrospective Operational Cohort Study
Background: Point-of-care ultrasound (POCUS) is integral to obstetrics and gynecology (OBGYN), offering bedside diagnostic and therapeutic advantages. Despite its widespread adoption, accurate documentation and billing remain challenging due to inconsistent workflows, variable free-text note quality, and inefficiencies within electronic health record (EHR) systems. These barriers often result in missed procedural charges and hinder operational, educational, and reimbursement efforts. Objective: This study leveraged machine learning (ML) to automatically identify POCUS procedures within clinical notes and assessed the effect of implementing standardized procedure documentation (ProcDoc) templates on billing capture accuracy and efficiency. Methods: We conducted a multipart retrospective cohort study at a large academic medical center using EHRs from January 2018 to August 2024 across 11 OBGYN clinic sites. ML models (LightGBM [light gradient boosting machine] and BioClinBERT [biomedical and clinical bidirectional encoder representations from transformers]) were trained on clinical encounter notes to classify POCUS procedures and validated against Current Procedural Terminology (CPT) manual code assignments. In February 2023, a standardized ProcDoc smart form was introduced to streamline POCUS documentation and automatically trigger CPT billing codes. Preintervention and postintervention periods were compared using ML metrics and manual billing audits. Outcomes included model accuracy, recall, precision, adoption rates, improvement in billing recapture, and usage of ProcDoc templates. Results: A total of 559,029 encounters from 109,776 unique patients were analyzed. The BioClinBERT model (accuracy 0.97; F 1 -score 0.55-0.63) demonstrated a robust ability to identify documented and missed procedures in free-text clinical notes. ProcDoc adoption reached 75.1% within 12 months, supported by comprehensive staff education. Billing recapture—the proportion of charges missed by providers but later identified—dropped from 10.0% preintervention to 2.4% postintervention, primarily arising from the shift toward auto-capturing documentation (odds ratio 0.22, 95% CI 0.17‐0.30; P <.001), with overall POCUS billing slightly increased (+0.6%). Most postintervention CPT codes (1812/2404, 75.4%) originated from ProcDoc templates, confirming improved workflow efficiency and reduced manual audit burden. Model analysis and billing metrics demonstrated that improvements were associated with workflow changes and not an increase in procedure frequency. Conclusions: ML modeling proved effective for extracting POCUS procedures from clinical documentation and serving as an evaluation tool for workflow interventions. Standardized documentation with ProcDoc significantly enhanced charge capture accuracy and reduced dependence on manual chart reviews and billing reconciliation. This approach highlights the use of ML as a retrospective auditing and evaluation tool for assessing clinical workflow interventions. Broader application of similar strategies could address documentation inefficiencies and promote sustainability across health care settings.
- Open Access
- 13 July 2026
- Published by Springer Nature in Medical Science Educator
- Vol. 36 (5) , 2439-2446
Health Systems Science Scholars Program: National Faculty Development Program
Introduction: Training in health systems is important for patient care, but often faculty development is lacking. The purpose of the Health Systems Science Scholars Program (HSS-SP) was to teach faculty how to educate learners in Health Systems Science to improve healthcare delivery practices. The objective of this report was to describe program development and evaluate the HSS-SP program in meeting this goal. Methods: The 12-month HSS-SP focused on curriculum development, assessment design, program evaluation, leadership skills, and scholarship. Training formats included in-person workshops, interactive webinars, community of practice, mentoring, and completion of HSS final projects. This evaluation focused on program completion, satisfaction, learning, and HSS integration in final projects. Results: One hundred and eight scholars participated across three cohorts. Leaders from 72/155 US medical schools nominated a scholar, indicating support of the program. The retrospective pre-post survey demonstrated significant improvement across all outcome measures including perceived confidence in ability to apply systems thinking, leading change, implementing best practices, commitment to educate others in HSS, improve healthcare delivery, and practice innovative and interactive teaching. Fifty-six final projects focused on broad implementation of HSS at individual institutions, including 75 specific HSS domains (e.g., social determinants of health and patient safety/quality improvement). Medical school curricula projects arose more often than residency projects (86 versus 22), and most utilized innovative and interactive teaching methods. Conclusion: The HSS-SP enhanced confidence in and commitment to HSS. Participants’ projects implemented HSS curricular components, furthering dissemination of HSS into the medical education system.
- 13 July 2026
- Published by Springer Nature in Medical Science Educator
- Vol. 36 (5) , 2439-2446
Open AccessHealth Systems Science Scholars Program: National Faculty Development Program
Introduction: Training in health systems is important for patient care, but often faculty development is lacking. The purpose of the Health Systems Science Scholars Program (HSS-SP) was to teach faculty how to educate learners in Health Systems Science to improve healthcare delivery practices. The objective of this report was to describe program development and evaluate the HSS-SP program in meeting this goal. Methods: The 12-month HSS-SP focused on curriculum development, assessment design, program evaluation, leadership skills, and scholarship. Training formats included in-person workshops, interactive webinars, community of practice, mentoring, and completion of HSS final projects. This evaluation focused on program completion, satisfaction, learning, and HSS integration in final projects. Results: One hundred and eight scholars participated across three cohorts. Leaders from 72/155 US medical schools nominated a scholar, indicating support of the program. The retrospective pre-post survey demonstrated significant improvement across all outcome measures including perceived confidence in ability to apply systems thinking, leading change, implementing best practices, commitment to educate others in HSS, improve healthcare delivery, and practice innovative and interactive teaching. Fifty-six final projects focused on broad implementation of HSS at individual institutions, including 75 specific HSS domains (e.g., social determinants of health and patient safety/quality improvement). Medical school curricula projects arose more often than residency projects (86 versus 22), and most utilized innovative and interactive teaching methods. Conclusion: The HSS-SP enhanced confidence in and commitment to HSS. Participants’ projects implemented HSS curricular components, furthering dissemination of HSS into the medical education system.
- Open Access
- 12 March 2018
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 20 (3) , e78
Evaluating Patient Perspectives of Provider Professionalism on Twitter in an Academic Obstetrics and Gynecology Clinic: Patient Survey
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet
- 12 March 2018
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 20 (3) , e78
Open AccessEvaluating Patient Perspectives of Provider Professionalism on Twitter in an Academic Obstetrics and Gynecology Clinic: Patient Survey
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet
- Open Access
- 19 May 2017
- Published by JMIR Publications Inc. in JMIR Preprints
Evaluating Patient Perspectives of Provider Professionalism on Twitter in an Academic Obstetrics and Gynecology Clinic: Patient Survey
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: One-third of Americans use social media websites as a source of health care information. Twitter, a microblogging site that allows users to place 280-character posts—or tweets—on the Web, is emerging as an important social media platform for health care. However, most guidelines on medical professionalism on social media are based on expert opinion. Objective: This study sought to examine if provider Twitter profiles with educational tweets were viewed as more professional than profiles with personal tweets or a mixture of the two, and to determine the impact of provider gender on perceptions of professionalism in an academic obstetrics and gynecology clinic. Methods: This study randomized obstetrics and gynecology patients at the University of Michigan Von Voigtlander Clinic to view one of six medical provider Twitter profiles, which differed in provider gender and the nature of tweets. Each participant answered 10 questions about their perception of the provider’s professionalism based on the Twitter profile content. Results: The provider profiles with educational tweets alone received higher mean professionalism scores than profiles with personal tweets. Specifically, the female and male provider profiles with exclusively educational tweets had the highest and second highest overall mean professionalism ratings at 4.24 and 3.85, respectively. In addition, the female provider profiles received higher mean professionalism ratings than male provider profiles with the same content. The female profile with mixed content received a mean professionalism rating of 3.38 compared to 3.24 for the male mixed-content profile, and the female profile with only personal content received a mean professionalism rating of 3.68 compared to 2.68 for the exclusively personal male provider profile. Conclusions: This study showed that in our obstetrics and gynecology clinic, patients perceived providers with educational profiles as more professional than those with a mixture of educational and personal tweets or only personal tweets. It also showed that our patient population perceived the female provider with educational tweets to be the most professional. This study will help inform the development of evidence-based guidelines for social media use in medicine as it adds to the growing body of literature examining professionalism and social media.
- 19 May 2017
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessEvaluating Patient Perspectives of Provider Professionalism on Twitter in an Academic Obstetrics and Gynecology Clinic: Patient Survey
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: One-third of Americans use social media websites as a source of health care information. Twitter, a microblogging site that allows users to place 280-character posts—or tweets—on the Web, is emerging as an important social media platform for health care. However, most guidelines on medical professionalism on social media are based on expert opinion. Objective: This study sought to examine if provider Twitter profiles with educational tweets were viewed as more professional than profiles with personal tweets or a mixture of the two, and to determine the impact of provider gender on perceptions of professionalism in an academic obstetrics and gynecology clinic. Methods: This study randomized obstetrics and gynecology patients at the University of Michigan Von Voigtlander Clinic to view one of six medical provider Twitter profiles, which differed in provider gender and the nature of tweets. Each participant answered 10 questions about their perception of the provider’s professionalism based on the Twitter profile content. Results: The provider profiles with educational tweets alone received higher mean professionalism scores than profiles with personal tweets. Specifically, the female and male provider profiles with exclusively educational tweets had the highest and second highest overall mean professionalism ratings at 4.24 and 3.85, respectively. In addition, the female provider profiles received higher mean professionalism ratings than male provider profiles with the same content. The female profile with mixed content received a mean professionalism rating of 3.38 compared to 3.24 for the male mixed-content profile, and the female profile with only personal content received a mean professionalism rating of 3.68 compared to 2.68 for the exclusively personal male provider profile. Conclusions: This study showed that in our obstetrics and gynecology clinic, patients perceived providers with educational profiles as more professional than those with a mixture of educational and personal tweets or only personal tweets. It also showed that our patient population perceived the female provider with educational tweets to be the most professional. This study will help inform the development of evidence-based guidelines for social media use in medicine as it adds to the growing body of literature examining professionalism and social media.