GSGenevieve Jayne Sippel

Genevieve Jayne Sippel

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Genevieve Jayne Sippel has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Computer-vision based recognition of cervical spine stabilization during trauma resuscitation

    by Mary S. Kim, Sifan Yuan, Genevieve J. Sippel, Aaron H. Mun, Dylan W. Arkowitz, Ivan Marsic, Randall S. Burd

  • Open Access

    To Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events

    by Angela Mastrianni, Mary Suhyun Kim, Travis M Sullivan, Genevieve Jayne Sippel, Randall S Burd, Krzysztof Z. Gajos, Aleksandra Sarcevic

    AI-enabled decision-support systems aim to help medical providers rapidly make decisions with limited information during medical emergencies. A critical challenge in developing these systems is supporting providers in interpreting the system output to make optimal treatment decisions. In this study, we designed and evaluated an AI-enabled decision-support system to aid providers in treating patients with traumatic injuries. We first conducted user research with physicians to identify and design information types and AI outputs for a decision-support display. We then conducted an online experiment with 35 medical providers from six health systems to evaluate two human-AI interaction strategies: (1) AI information synthesis and (2) AI information and recommendations. We found that providers were more likely to make correct decisions when AI information and recommendations were provided compared to receiving no AI support. We also identified two socio-technical barriers to providing AI recommendations during time-critical medical events: (1) an accuracy-time trade-off in providing recommendations and (2) polarizing perceptions of recommendations between providers. We discuss three implications for developing AI-enabled decision support used in time-critical events, contributing to the limited research on human-AI interaction in this context.


  • Open Access

    To Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events

    by Angela Mastrianni, Mary Suhyun Kim, Travis M. Sullivan, Genevieve Jayne Sippel, Randall S. Burd, Krzysztof Z. Gajos, Aleksandra Sarcevic

    AI-enabled decision-support systems aim to help medical providers rapidly make decisions with limited information during medical emergencies. A critical challenge in developing these systems is supporting providers in interpreting the system output to make optimal treatment decisions. In this study, we designed and evaluated an AI-enabled decision-support system to aid providers in treating patients with traumatic injuries. We first conducted user research with physicians to identify and design information types and AI outputs for a decision-support display. We then conducted an online experiment with 35 medical providers from six health systems to evaluate two human-AI interaction strategies: (1) AI information synthesis and (2) AI information and recommendations. We found that providers were more likely to make correct decisions when AI information and recommendations were provided compared to receiving no AI support. We also identified two socio-technical barriers to providing AI recommendations during time-critical medical events: (1) an accuracy-time trade-off in providing recommendations and (2) polarizing perceptions of recommendations between providers. We discuss three implications for developing AI-enabled decision support used in time-critical events, contributing to the limited research on human-AI interaction in this context.

  • Development of an algorithm for adjudicating actionable hemorrhage in pediatric trauma patients

    by Mary S. Kim, Genevieve J. Ba Sippel, Travis M. Sullivan, Nathan J. Alcasid, Steffanie J. Bs Rodgers, Kristine L. Griffin, Aaron H. Bs Mun, Andrea M. Gochi, Aaron R. Md Jensen, Julie C. Leonard, et al.

    BACKGROUND Bleeding is the leading cause of preventable death in trauma. Early identification of hemorrhage improves patient outcomes. Current triage tools for predicting hemorrhage rely on transfusion receipt as a surrogate outcome, indicating that blood was needed. This outcome does not account for misclassification of patients who receive prompt hemorrhage control procedure (HCP) without transfusion, patients who die before transfusion receipt, or those who receive unnecessary transfusion. Objective criteria that do not rely on transfusion receipt alone are needed to more accurately determine actionable hemorrhage and the appropriateness of transfusions in pediatric trauma patients. METHODS We defined actionable hemorrhage within 6 hours of emergency department arrival as (1) actual or (2) estimated pretransfusion hemoglobin Export


  • Human intention recognition for trauma resuscitation: An interpretable deep learning approach for medical process data

    by Keyi Li, Mary S. Kim, Wenjin Zhang, Sen Yang, Genevieve J. Sippel, Aleksandra Sarcevic, Randall S. Burd, Ivan Marsic


  • Comparative analysis of personal protective equipment nonadherence detection: computer vision versus human observers

    by Mary S Kim, Beomseok Park, Genevieve J Sippel, Aaron H Mun, Wanzhao Yang, Kathleen H McCarthy, Emely Fernandez, Marius George Linguraru, Aleksandra Sarcevic, Ivan Marsic, et al.

    Human monitoring of personal protective equipment (PPE) adherence among healthcare providers has several limitations, including the need for additional personnel during staff shortages and decreased vigilance during prolonged tasks. To address these challenges, we developed an automated computer vision system for monitoring PPE adherence in healthcare settings. We assessed the system performance against human observers detecting nonadherence in a video surveillance experiment. The automated system was trained to detect 15 classes of eyewear, masks, gloves, and gowns using an object detector and tracker. To assess how the system performs compared to human observers in detecting nonadherence, we designed a video surveillance experiment under 2 conditions: variations in video durations (20, 40, and 60 seconds) and the number of individuals in the videos (3 versus 6). Twelve nurses participated as human observers. Performance was assessed based on the number of detections of nonadherence. Human observers detected fewer instances of nonadherence than the system (parameter estimate −0.3, 95% CI −0.4 to −0.2, P < .001). Human observers detected more nonadherence during longer video durations (parameter estimate 0.7, 95% CI 0.4-1.0, P < .001). The system achieved a sensitivity of 0.86, specificity of 1, and Matthew’s correlation coefficient of 0.82 for detecting PPE nonadherence. An automated system simultaneously tracks multiple objects and individuals. The system performance is also independent of observation duration, an improvement over human monitoring. The automated system presents a potential solution for scalable monitoring of hospital-wide infection control practices and improving PPE usage in healthcare settings.


  • Development and Validation of a Bayesian Network Predicting Intubation Following Hospital Arrival Among Injured Children

    by Travis M. Sullivan, Mary S. Kim, Genevieve J. Sippel, Waverly V. Gestrich-Thompson, Caroline G. Melhado, Kristine L. Griffin, Suzanne M. Moody, Rajan K. Thakkar, Meera Kotagal, Aaron R. Jensen, et al.


  • Factors associated with correction of personal protective equipment nonadherence in a multidisciplinary emergency department setting: A retrospective video review

    by Mary S. Kim, Aleksandra Sarcevic, Genevieve J. Sippel, Kathleen H. McCarthy, Eleanor A. Wood, Carmen Riley, Aaron H. Mun, Karen J. O’cOnnell, Peter T. LaPuma, Randall S. Burd


  • Strategies to Obtain and Deliver Blood Products Into Critically Injured Children

    by Travis M. Sullivan, Genevieve J. Ba Sippel, Waverly V. Bs Gestrich-Thompson, Randall S. Burd

    Objectives: Timely transfusion is associated with improved survival and a reduction in in-hospital morbidity. The benefits of early hemorrhagic shock recognition may be limited by barriers to accessing blood products and their timely administration. We examined how pediatric trauma programs obtain blood products, the types of rapid infusion models used, and the metrics tracked to improve transfusion process efficiency in their emergency department (ED). Methods: We developed and distributed a self-report survey to members of the Pediatric Trauma Society. The survey consisted of 6 initial questions, including the respondent's role and institution, whether a blood storage refrigerator was present in their ED, the rapid infuser model used to transfuse critically injured children in their ED, if their program tracked 4 transfusion process metrics, and if a video recording system was present in the trauma bay. Based on these responses, additional questions were prompted with an option for a free-text response. Results: We received 137 responses from 77 institutions. Most pediatric trauma programs have a blood storage refrigerator in the ED (n = 46, 59.7%) and use a Belmont rapid infuser to transfuse critically injured children (n = 45, 58.4%). The American College of Surgeons Level 1 designated trauma programs, or state-based equivalents, and “pediatric” trauma programs were more likely to have video recording systems for performance improvement review compared with lower designated trauma programs and “combined pediatric and adult” trauma programs, respectively. Conclusions: Strategies to improve the timely acquisition and infusion of blood products to critically injured children are underreported. This study examined the current practices that pediatric trauma programs use to transfuse critically injured children and may provide a resource for trauma programs to cite for transfusion-related quality improvement.