SJSudha Jayaraman

Sudha Jayaraman

*This is an algorithmically generated author record based on publicly available information.

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


Sudha Jayaraman has a total of 243 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Barriers and Priorities for Strengthening Prehospital Trauma Care in Hawassa, Ethiopia

    by Fayrouz Abu-Hamdan, Dalal Abuaqel, Tomas Tesfasilassie, Taye Gari, Belay Mellese, Haben Taafesse, Zemedkun Motera Wirtu, Emnet Tesfaye Shimber, Sudha Jayaraman, Syed Nabeel Zafar, et al.

  • Open Access

    The Promise of Ambient AI Technology in Medical Education: Opportunities and Guardrails

    by Shirin Shafazand, Umar Bowers, Sudha Jayaraman

    Ambient AI technologies, commonly known as AI scribes, are transforming clinical practice by autonomously capturing patient-provider conversations and structuring them into clinical notes. Short-term studies suggest that ambient AI can significantly reduce documentation time and improve job satisfaction. However, as health care systems accelerate the adoption of these tools, the medical education community must seek to answer unresolved questions regarding their full impact on learners. The inevitable integration of ambient AI in teaching hospitals presents both transformative opportunities and significant challenges for medical education. This viewpoint discusses the potential benefits and risks of ambient AI in both undergraduate and graduate medical education and considers its impact on learning and clinical skills acquisition. Robust research studies are urgently needed to navigate this new frontier and ensure that the integration of ambient AI in the clinical learning environment ultimately enriches, rather than diminishes, the practice of medicine.

  • Open Access

    A Conceptual Model for Ambient AI Adoption: Perspectives From Academia and Industry

    by Joshua Biro, Jesse M Pines, Sudha Jayaraman, Vamsi Chagari, Raj Ratwani

    Ambient AI technologies are increasingly marketed as solutions to reduce clinician burden and improve care efficiency; however, real-world performance varies widely across clinical settings. Health care provider organizations face challenges in determining which aspects of ambient AI performance matter most and how to obtain meaningful information about those aspects from vendors or through internal evaluation. This article presents a shared mental model to guide health system leaders in conceptualizing ambient AI performance across 3 interdependent dimensions: technical, interface, and system level. For each dimension, we outline the types of information relevant to assessment; what vendors should reasonably be expected to provide; and how health care provider organizations can conduct their own evaluations to contextualize, verify, or supplement vendor claims. By integrating both vendor and health system perspectives, this work offers a grounded, practical structure to support organizations of all sizes in understanding and making informed decisions about ambient AI technologies.

  • Open Access

    A Novel Mobile Health Software Platform to Improve Emergency Medical Systems: 912Rwanda

    by Teresa M Bell, Jean Marie Uwitonze, Jeanne D'Arc Nyinawankusi, Rebecca Maine, Andrea Nicole Davis, Jean Habanabakize, Mediatrice Niyonsaba, Aurore Nishimwe, Melissa H. Watt, Rob Rickard, et al.

    Emergency care is essential to health systems, yet many low- and middle-income countries (LMICs) lack well-organised pre-hospital systems. The Ministry of Health of Rwanda created an emergency medical system in the capital city of Kigali in 2007, which is led by the Service d’Aide Médicale Urgente (SAMU) ambulance team. Based on a long-standing collaboration with SAMU, we developed, tested and implemented 912Rwanda, a mobile health software platform to integrate and improve communication between callers, dispatch staff, ambulance teams, and receiving facilities. We evaluated the reliability, fidelity, and usability of the 912Rwanda platform over 15 months since its full implementation in December 2023 during which the platform has been used in 9,293 completed incidents, with > 97% reliability and 99.99% uptime. Usability improved across all domains, including ease of use, effort, and demand, as measured by two scales. Our experience provides a robust and scalable example of mobile health technologies for LMICs as they develop essential emergency infrastructure in their settings.

  • Open Access

    Safety of Patient-Facing Agentic AI: a Consensus Framework for Risk Assessment and Mitigation (Preprint)

    by Sudha Jayaraman, Arooshi Kumar, Erin Palm, Melanie Fernando, Chethan Sarabu, Michael Choma, Kevin Wang, Vishnu Ravi, Maritza Suarez, Peter McCaffrey, et al.

    UNSTRUCTURED Deploying agentic AI systems without adequate plans for human supervision raises serious concerns about patient safety, privacy, and equity. To address this gap, a group of experts across industry, academic and clinical informatics interested in AI and safety convened a voice AI taskforce to discuss and develop consensus on the impact of agentic AI in healthcare. Through this collaboration, we developed a consensus framework to determine potential risks and plan mitigation efforts based on potential clinical use cases to aid health care delivery organizations assess, implement and evaluate AI agents to meet their needs. Based on five diverse use case examples, we identified common themes of risk at the level of the agent, data, patient and clinician as well as the mitigation strategies needed to address them. Agent-level risks include robust transcription validation, knowledge-grounded responses, mandatory conversation checklists, demographic bias testing, and red-teamed escalation triggers. At the data level, secure identity verification, high‑quality data, interoperable standards and rigorous governance form the foundation of safety. Patient‑level risks include equitable access, patient suitability and clear escalation paths. Finally, clinician-level risks include alert prioritization, defined liability frameworks, workflow-integrated outputs, and preserved clinical override authority. Robust symptom recognition and a thoughtful precision–recall balance are also essential aspects to consider. These guardrails, supported by multidisciplinary oversight and continuous evaluation, can enable AI agents to contribute to patient care without compromising safety, privacy or equity. This framework aims to address the uncertainties in risks to patient safety that should be considered by healthcare delivery organizations to safely apply these technologies to address healthcare needs.


  • Open Access

    Core Components for Emergency Medical Dispatch Systems: An International Delphi Consensus Study

    by Katinka Weber, Willem Stassen, Sudha Jayaraman, Maria Lisa Odland, Aurore Nishimwe, Indrakantha Welgama, Lee Wallis, Agnieszka Ignatowicz, Justine P Davies

    Introduction: Emergency Medical Dispatch Systems (EMDS) can reduce delays in accessing emergency care by providing structured communication, triage, and coordination. However, such systems remain absent or underdeveloped in most low- or middle-income countries (LMICs). This study aimed to establish international consensus on essential EMDS components to inform global guidance. Methods: We convened a multidisciplinary expert group to draft a preliminary list of essential components for three EMDS levels reflecting resource availability and system maturity. We then conducted a three-round Delphi with international experts to reach consensus on core EMDS components. Components which had ≥75% agreement were included, those with ≥75% disagreement were excluded. Components not achieving consensus by Round 3 were removed. Results were analysed overall and stratified by respondents’ country income level. A subsequent online expert meeting resolved inconsistencies and finalised the component list. Results: The expert group generated 111 components for each of three EMDS levels (Foundational, Emerging, and Established) spanning 11 operational domains. Of the 68 experts invited to the Delphi, 43 participated in Round 1 and 30 in Round 3. Across all Delphi rounds, 289 components reached consensus for inclusion. The consensus resulted in a final list of 227 components (63 Foundational, 84 Emerging, and 80 Established). Consensus agreement clustered around core EMDS domains including communication, structured call-taking and prioritisation, advice-giving, resource dispatch and tracking, and foundational governance and data functions, whereas items showing either non-consensus or consensus disagreement were typically technology-dependent or context-specific. Conclusions: This international consensus offers guidance for EMDS development across diverse resource settings and provides a scalable roadmap to strengthen emergency care systems.

  • Surgeons at the Policy Table

    by Denis A. Foretia, Sudha P. Jayaraman, Michael S. Nussbaum

  • Open Access

    Validation of a mobile application for prehospital transport time data collection in Kigali, Rwanda

    by Teresa Bell, Jean Marie Uwitonze, Michael Oravic, Rebecca Maine, Jeanne D’ARc Nyinawankusi, Andrea N. Davis, Jean Nepomuscene Sindikubwabo, Robert Rickard, Melissa H. Watt, Justine Davies, et al.

    Emergency medical services (EMS) are critical for patient outcomes during emergencies. Organised EMS systems that can promptly locate patients, deliver on-


  • Open Access

    Data quality and associations over 4 years of use of WHO’s Clinical Registry - Trauma Module, in Rwanda

    by Indrakantha P Welgama, Jean Nepomuscene Ntezimana, Irene Bagahirwa, Venantie Umuhoza, Fabrice Iradukunda, Daniel Lange, Leila Ghalichi, Sudha Jayaraman, Kathryn Chu, Aurore Nishimwe, et al.

    Objective: Poor quality of injury care causes avoidable death and disability. Quality data is integral to care-quality improvement. We assessed longitudinal data quality of the Trauma Module (TM) of WHO’s Clinical Registry in Rwanda, towards understanding data collection challenges in low resourced settings. Methods: Retrospective analysis of TM data between its implementation in August 2019 and July 2023. We describe trends in overall TM case and variable missingness and their associations with availability of funding and formal training. Variable missingness is also described by each of the 7 domains of the TM. Findings: The TM was initiated in 4 hospitals in August 2019 and expanded to 6 in June 2021. Between implementation and July 2023, 13,513 cases were entered. Annual numbers of cases varied per hospital (maximum of 2051, minimum of 259). Case missingness ranged from 60% to 66% across all hospitals. The median annual variable missingness varied between hospitals from 28% to 41%. Over the whole period, across all hospitals, median missingness was 39.63% (IQR 0.65 – 82.46); 12 variables had 100% missingness and 15 variables, 0% missingness. Variable missingness depending on TM domain; highest in “In-ward care & Facility disposition” (77.30%) and “EU disposition” (51.67%). Data collection was dependent on external funding; when funding ceased in 2023, case and variable missingness increased to 100%. Short term increases in data collection were noted following periodic formal trainings. Conclusions: Although TM sustainment in Rwanda relied on external funding, even with funding and training, data quality was variable.


  • Open Access

    A Conceptual Model for Ambient AI Adoption: Perspectives from Academia and Industry (Preprint)

    by Josh Biro, Jesse M. Pines, Sudha Jayaraman, Vamsi Chagari, Raj Ratwani

    UNSTRUCTURED Ambient AI technologies are increasingly marketed as solutions to reduce clinician burden and improve care efficiency, yet real-world performance varies widely across clinical settings. Healthcare provider organizations face challenges in determining which aspects of ambient AI performance matter most and how to obtain meaningful information about those aspects from vendors or through internal evaluation. This article presents a shared mental model to guide health system leaders in conceptualizing ambient AI performance across three interdependent dimensions: technical, interface, and system-level. For each dimension, we outline the types of information relevant to assessment, what vendors should reasonably be expected to provide, and how healthcare provider organizations can conduct their own evaluations to contextualize, verify, or supplement vendor claims. By integrating both vendor and health-system perspectives, this work offers a grounded, practical structure to support organizations of all sizes in understanding and making informed decisions about ambient AI technologies.