Rebecca Mbadiwe Awofisayo
Research Subjects
Rebecca Mbadiwe Awofisayo has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ishaan Rischie
University of Michigan Medical School, Ann Arbor, USA
3 shared publications - Sweta Sneha
Kennesaw State University, Marietta, GA, United States
3 shared publications - Valentina Nino
Kennesaw State University
3 shared publications - Lawrence Ignatius Kumah2 shared publications
- Maria Valero
Kennesaw State University
1 shared publication - Simran Dua
Lambert High School, 805 Nichols Rd, Suwanee, GA 30024, USA
1 shared publication
Latest Publications
- Open Access
- 18 September 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Virtual Discharge in Healthcare: Enhancing Patient Safety and Efficiency with FMEAFMEA, hospital discharge, virtual nurse, patient safety (Preprint)
BACKGROUND Background: Hospital discharge is a critical yet often inefficient phase of patient care, prone to communication failures, incomplete patient education, and preventable readmissions. OBJECTIVE This study aimed to apply Failure Mode and Effects Analysis (FMEA) to compare in-person and virtual nurse discharge workflows at a 112-room county hospital that recorded 9,318 discharges in 2023 METHODS A mixed-methods approach combining structured observational analysis and focus groups with frontline nursing staff, and a comprehensive literature review. Swimlane flowcharts were used to map bedside nurse and virtual registered nurse workflows, and FMEA was applied to identify potential failure modes and assign Risk Priority Numbers based on severity, occurrence, and detectability. At the beginning of each focus group session, participants reported on the steps of the discharge process as they understood them and then provided information about failure modes that might occur at each step, consistent with established FMEA data collection methods. RESULTS Forty-five failure modes were identified across both workflows, comprising 20 in the in-person bedside nurse workflow and 25 in the virtual discharge workflow. The highest Risk Priority Number identified in the in-person workflow was 210, assigned to the failure mode of a nurse being interrupted during the After Visit Summary review. Virtual discharge workflows consistently produced lower Risk Priority Numbers: missed patient questions scored 150 in person versus 60 virtually, and failure to escalate concerns scored 120 in person versus 45 virtually. Virtual Registered Nurse workflows saved bedside nurses approximately 40 minutes per patient's discharge; target recommendations for each identified failure mode were developed. CONCLUSIONS FMEA provides an effective framework for identifying and mitigating discharge process failures. Virtual discharge workflows demonstrate superior safety profiles and efficiency compared to traditional in-person methods. Integrating Virtual Registered Nurses reduces bedside nursing workload, improves consistency in patient education, and supports workforce sustainability amid ongoing nursing shortages CLINICALTRIAL Not applicable
- 18 September 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessVirtual Discharge in Healthcare: Enhancing Patient Safety and Efficiency with FMEAFMEA, hospital discharge, virtual nurse, patient safety (Preprint)
BACKGROUND Background: Hospital discharge is a critical yet often inefficient phase of patient care, prone to communication failures, incomplete patient education, and preventable readmissions. OBJECTIVE This study aimed to apply Failure Mode and Effects Analysis (FMEA) to compare in-person and virtual nurse discharge workflows at a 112-room county hospital that recorded 9,318 discharges in 2023 METHODS A mixed-methods approach combining structured observational analysis and focus groups with frontline nursing staff, and a comprehensive literature review. Swimlane flowcharts were used to map bedside nurse and virtual registered nurse workflows, and FMEA was applied to identify potential failure modes and assign Risk Priority Numbers based on severity, occurrence, and detectability. At the beginning of each focus group session, participants reported on the steps of the discharge process as they understood them and then provided information about failure modes that might occur at each step, consistent with established FMEA data collection methods. RESULTS Forty-five failure modes were identified across both workflows, comprising 20 in the in-person bedside nurse workflow and 25 in the virtual discharge workflow. The highest Risk Priority Number identified in the in-person workflow was 210, assigned to the failure mode of a nurse being interrupted during the After Visit Summary review. Virtual discharge workflows consistently produced lower Risk Priority Numbers: missed patient questions scored 150 in person versus 60 virtually, and failure to escalate concerns scored 120 in person versus 45 virtually. Virtual Registered Nurse workflows saved bedside nurses approximately 40 minutes per patient's discharge; target recommendations for each identified failure mode were developed. CONCLUSIONS FMEA provides an effective framework for identifying and mitigating discharge process failures. Virtual discharge workflows demonstrate superior safety profiles and efficiency compared to traditional in-person methods. Integrating Virtual Registered Nurses reduces bedside nursing workload, improves consistency in patient education, and supports workforce sustainability amid ongoing nursing shortages CLINICALTRIAL Not applicable
- Open Access
- 15 April 2026
- Published by JMIR Publications Inc. in JMIR AI
Challenges and Opportunities for AI Tools in Healthcare: A Systematic Review from a Quadruple Aim Perspective. (Preprint)
- 15 April 2026
- Published by JMIR Publications Inc. in JMIR AI
Open AccessChallenges and Opportunities for AI Tools in Healthcare: A Systematic Review from a Quadruple Aim Perspective. (Preprint)
- Open Access
- 15 April 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Challenges and Opportunities for AI Tools in Healthcare:A Systematic Review from a Quadruple Aim Perspective (Preprint)
BACKGROUND Artificial intelligence (AI) has become one of the most transformative forces in modern medicine, promising enhanced diagnostic accuracy, predictive analytics, and greater operational efficiency across clinical settings. However, despite remarkable technical progress, translating AI systems from pilot projects to sustainable clinical use has been inconsistent. Many implementations remain confined to prototypes or local trials, while evidence about long-term value and equity is fragmented. The Quadruple Aim, improving patient experience, population health, cost efficiency, and provider well-being, offers a comprehensive framework for assessing whether AI truly advances the mission of value-based care. OBJECTIVE This systematic review synthesizes evidence from 34 peer-reviewed publications (2019–2026) to identify key challenges and opportunities in implementing AI tools in healthcare and to interpret findings through the Quadruple Aim framework. METHODS In accordance with PRISMA 2020 guidelines, a systematic search was conducted across PubMed, Scopus, and Web of Science. The initial search yielded 652 records. After removing 277 duplicates, 375 unique studies were screened by title and abstract, of which 283 were excluded for failing to meet the inclusion criteria. Following full-text assessment, 34 studies met all inclusion criteria. Data were extracted using a structured framework and synthesized thematically. Findings were mapped onto the four dimensions of the Quadruple Aim. RESULTS Of the 34 included studies, the most prevalent implementation barriers were workflow disruption and usability challenges (74%), trust and explainability limitations (71%), data quality and interoperability failures (68%), clinician knowledge and training gaps (62%), and regulatory uncertainty (53%). Key opportunities included predictive analytics and early warning systems (56%), stakeholder engagement and co-design (53%), workflow optimization and automation (50%), and patient engagement and access (44%). Mapping findings to the Quadruple Aim revealed that 23 studies addressed provider well-being, 22 addressed cost and system efficiency, 21 addressed patient experience, and 20 addressed population health. CONCLUSIONS Evidence from 34 peer-reviewed publications underscores both optimism and caution regarding AI’s role in healthcare. While most studies confirm AI’s potential to enhance quality, safety, and efficiency, barriers related to governance, transparency, workforce readiness, and equitable design continue to impede scale-up. Sustainable success requires aligning AI strategies with the Quadruple Aim through robust data governance, inclusive co-design, investment in digital-health literacy, and rigorous economic evaluation.
- 15 April 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessChallenges and Opportunities for AI Tools in Healthcare:A Systematic Review from a Quadruple Aim Perspective (Preprint)
BACKGROUND Artificial intelligence (AI) has become one of the most transformative forces in modern medicine, promising enhanced diagnostic accuracy, predictive analytics, and greater operational efficiency across clinical settings. However, despite remarkable technical progress, translating AI systems from pilot projects to sustainable clinical use has been inconsistent. Many implementations remain confined to prototypes or local trials, while evidence about long-term value and equity is fragmented. The Quadruple Aim, improving patient experience, population health, cost efficiency, and provider well-being, offers a comprehensive framework for assessing whether AI truly advances the mission of value-based care. OBJECTIVE This systematic review synthesizes evidence from 34 peer-reviewed publications (2019–2026) to identify key challenges and opportunities in implementing AI tools in healthcare and to interpret findings through the Quadruple Aim framework. METHODS In accordance with PRISMA 2020 guidelines, a systematic search was conducted across PubMed, Scopus, and Web of Science. The initial search yielded 652 records. After removing 277 duplicates, 375 unique studies were screened by title and abstract, of which 283 were excluded for failing to meet the inclusion criteria. Following full-text assessment, 34 studies met all inclusion criteria. Data were extracted using a structured framework and synthesized thematically. Findings were mapped onto the four dimensions of the Quadruple Aim. RESULTS Of the 34 included studies, the most prevalent implementation barriers were workflow disruption and usability challenges (74%), trust and explainability limitations (71%), data quality and interoperability failures (68%), clinician knowledge and training gaps (62%), and regulatory uncertainty (53%). Key opportunities included predictive analytics and early warning systems (56%), stakeholder engagement and co-design (53%), workflow optimization and automation (50%), and patient engagement and access (44%). Mapping findings to the Quadruple Aim revealed that 23 studies addressed provider well-being, 22 addressed cost and system efficiency, 21 addressed patient experience, and 20 addressed population health. CONCLUSIONS Evidence from 34 peer-reviewed publications underscores both optimism and caution regarding AI’s role in healthcare. While most studies confirm AI’s potential to enhance quality, safety, and efficiency, barriers related to governance, transparency, workforce readiness, and equitable design continue to impede scale-up. Sustainable success requires aligning AI strategies with the Quadruple Aim through robust data governance, inclusive co-design, investment in digital-health literacy, and rigorous economic evaluation.