Mary Suhyun Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mary Suhyun Kim has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Randall S. Burd
Division of Trauma and Burn Surgery, Children’s National Hospital, Washington, D.C.
15 shared publications - Aleksandra Sarcevic
Drexel University, Philadelphia, PA, USA
10 shared publications - Genevieve Jayne Sippel
Division of Trauma and Burn Surgery, Children's National Hospital, Washington, DC, USA
8 shared publications - Aaron H. Mun
Division of Trauma and Burn Surgery, Children’s National Hospital, Washington, DC, USA
7 shared publications - Ivan Marsic
Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, USA
7 shared publications - Travis M. Sullivan
Children's National Hospital, Washington, DC, USA
5 shared publications
Latest Publications
- Open Access
- 16 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 8 (1) , 1-25
Automatic Detection of Physiological Attributes from Verbal Communication during Time-Critical Medical Events
In this study, we present a proof-of-concept system exploring the feasibility of automatically capturing physiological values during the primary survey phase of trauma resuscitation—a complex, time-sensitive evaluation of severely injured patients. We developed and evaluated a speech-driven activity recognition system designed to detect and extract key physiological parameters (e.g., age, manual blood pressure, Glasgow Coma Scale) from spoken clinical dialogue in real-time. By using audio recordings from actual trauma resuscitation cases, our system performs streaming inference to identify verbalized measurements associated with primary survey activities. Experimental results show that our approach can recognize seven attributes with an average accuracy of 72% in a challenging clinical environment with acceptable latency. We present this work as an initial feasibility demonstration rather than a deployment-ready system, highlighting both the opportunities and the remaining challenges of automating documentation in fast-paced emergency environments.
- 16 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 8 (1) , 1-25
Open AccessAutomatic Detection of Physiological Attributes from Verbal Communication during Time-Critical Medical Events
In this study, we present a proof-of-concept system exploring the feasibility of automatically capturing physiological values during the primary survey phase of trauma resuscitation—a complex, time-sensitive evaluation of severely injured patients. We developed and evaluated a speech-driven activity recognition system designed to detect and extract key physiological parameters (e.g., age, manual blood pressure, Glasgow Coma Scale) from spoken clinical dialogue in real-time. By using audio recordings from actual trauma resuscitation cases, our system performs streaming inference to identify verbalized measurements associated with primary survey activities. Experimental results show that our approach can recognize seven attributes with an average accuracy of 72% in a challenging clinical environment with acceptable latency. We present this work as an initial feasibility demonstration rather than a deployment-ready system, highlighting both the opportunities and the remaining challenges of automating documentation in fast-paced emergency environments.
- Open Access
- 18 April 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 268
Multi-view real-time detection of patient arrival in trauma resuscitation using computer vision
- 18 April 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 268
Open AccessMulti-view real-time detection of patient arrival in trauma resuscitation using computer vision
- 24 March 2026
- Published by Wolters Kluwer Health in Journal of Trauma and Acute Care Surgery
- Vol. 101 (3) , 415-422
Consensus-based criteria for actionable hemorrhage in pediatric trauma: A Delphi study
BACKGROUND: Blood transfusion and hemorrhage control procedures can be unreliable surrogates for bleeding requiring intervention in children. Some receive unnecessary blood transfusions or lack intraoperative findings for hemorrhage, while others die before an intervention occurs. Standardized criteria for adjudicating the presence of actionable hemorrhage are needed. We aimed to define expert consensus criteria for retrospectively identifying actionable hemorrhage within 6 hours of emergency department (ED) arrival. METHODS: Experts from six specialties involved in pediatric trauma care participated in a modified Delphi study. Panelists were prompted to consider “actionable hemorrhage” as “severe bleeding or injuries at risk of progression to class III or IV shock without prompt intervention.” In Round 1, panelists answered five free-response questions identifying criteria for actionable hemorrhage, including indicators for transfusion and hemorrhage control procedures, postmortem findings, and other relevant factors. Responses were consolidated and rated on a five-point strength-of-indication scale in subsequent rounds. Consensus was defined a priori as ≥70% agreement among panelists. Stability of consensus ( p >0.05) between rounds was assessed using the Wilcoxon Signed-Rank Test. RESULTS: Three Delphi rounds were required to achieve a stable consensus. Twenty-nine of 32 participating panelists participated in all three rounds. Thirteen statements achieved stable consensus as strong indicators of actionable hemorrhage. Criteria with the highest agreement included partial/total resection of intrathoracic/abdominal bleeding solid organs (96.4%), hemoglobinJ Trauma Acute Care Surg . 2026;00:00-00. Copyright © 2026 Wolters Kluwer Health, Inc. All rights reserved.) LEVEL OF EVIDENCE: Diagnostic Test/Criteria; Level III.
- 24 March 2026
- Published by Wolters Kluwer Health in Journal of Trauma and Acute Care Surgery
- Vol. 101 (3) , 415-422
Consensus-based criteria for actionable hemorrhage in pediatric trauma: A Delphi study
BACKGROUND: Blood transfusion and hemorrhage control procedures can be unreliable surrogates for bleeding requiring intervention in children. Some receive unnecessary blood transfusions or lack intraoperative findings for hemorrhage, while others die before an intervention occurs. Standardized criteria for adjudicating the presence of actionable hemorrhage are needed. We aimed to define expert consensus criteria for retrospectively identifying actionable hemorrhage within 6 hours of emergency department (ED) arrival. METHODS: Experts from six specialties involved in pediatric trauma care participated in a modified Delphi study. Panelists were prompted to consider “actionable hemorrhage” as “severe bleeding or injuries at risk of progression to class III or IV shock without prompt intervention.” In Round 1, panelists answered five free-response questions identifying criteria for actionable hemorrhage, including indicators for transfusion and hemorrhage control procedures, postmortem findings, and other relevant factors. Responses were consolidated and rated on a five-point strength-of-indication scale in subsequent rounds. Consensus was defined a priori as ≥70% agreement among panelists. Stability of consensus ( p >0.05) between rounds was assessed using the Wilcoxon Signed-Rank Test. RESULTS: Three Delphi rounds were required to achieve a stable consensus. Twenty-nine of 32 participating panelists participated in all three rounds. Thirteen statements achieved stable consensus as strong indicators of actionable hemorrhage. Criteria with the highest agreement included partial/total resection of intrathoracic/abdominal bleeding solid organs (96.4%), hemoglobinJ Trauma Acute Care Surg . 2026;00:00-00. Copyright © 2026 Wolters Kluwer Health, Inc. All rights reserved.) LEVEL OF EVIDENCE: Diagnostic Test/Criteria; Level III.
- Open Access
- 11 February 2026
- Published by Elsevier in SSRN Electronic Journal
ReSSL: Boosting Semi-Supervised Learning with Reconstruction-Aware Masked Autoencoders
Foundation vision models show remarkable performance across various tasks but often require domain-specific adaptation to achieve optimal results. However, fine-tuning these models is challenging due to the high cost of obtaining labeled data, particularly in specialized domains like medical imaging. Semi-supervised learning (SSL) addresses this challenge by leveraging limited labeled data to generate pseudo-labels for unlabeled data. Existing SSL methods rely on confidence-based thresholding, which biases training towards high-confidence samples while neglecting uncertain ones, leading to suboptimal generalization.To overcome this limitation, we propose \algo, an SSL booster that enhances representation learning by incorporating Masked Autoencoder (MAE)-based reconstruction loss and Supplementary MixUp (SMU). Unlike traditional MAE-based pretraining followed by fine-tuning, our method jointly optimizes reconstruction and classification, learning from all data and ensuring feature alignment with the target task (i.e., classification). To avoid overfitting issues of MixUp in SSLs, we propose SMU that balances original and MixUp-augmented data. This approach also addressed the challenge of determining the optimal transition point for augmentation.Our approach achieves state-of-the-art performance on multiple SSL benchmarks, including 97.5\% accuracy on Euro-SAT with 2 labeled samples per class and 74.6\% accuracy on R2PPE recognition with 20 labeled samples per class. These results show that \algo effectively improves SSL by leveraging all available unlabeled data, reducing reliance on confidence thresholds, and enhancing generalization through joint optimization of MAE and classification objectives.
- 11 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessReSSL: Boosting Semi-Supervised Learning with Reconstruction-Aware Masked Autoencoders
Foundation vision models show remarkable performance across various tasks but often require domain-specific adaptation to achieve optimal results. However, fine-tuning these models is challenging due to the high cost of obtaining labeled data, particularly in specialized domains like medical imaging. Semi-supervised learning (SSL) addresses this challenge by leveraging limited labeled data to generate pseudo-labels for unlabeled data. Existing SSL methods rely on confidence-based thresholding, which biases training towards high-confidence samples while neglecting uncertain ones, leading to suboptimal generalization.To overcome this limitation, we propose \algo, an SSL booster that enhances representation learning by incorporating Masked Autoencoder (MAE)-based reconstruction loss and Supplementary MixUp (SMU). Unlike traditional MAE-based pretraining followed by fine-tuning, our method jointly optimizes reconstruction and classification, learning from all data and ensuring feature alignment with the target task (i.e., classification). To avoid overfitting issues of MixUp in SSLs, we propose SMU that balances original and MixUp-augmented data. This approach also addressed the challenge of determining the optimal transition point for augmentation.Our approach achieves state-of-the-art performance on multiple SSL benchmarks, including 97.5\% accuracy on Euro-SAT with 2 labeled samples per class and 74.6\% accuracy on R2PPE recognition with 20 labeled samples per class. These results show that \algo effectively improves SSL by leveraging all available unlabeled data, reducing reliance on confidence thresholds, and enhancing generalization through joint optimization of MAE and classification objectives.
- Open Access
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-33
To Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events
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.
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-33
Open AccessTo Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events
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.
- 28 August 2025
- Published by Elsevier in American Journal of Infection Control
- Vol. 53 (12) , 1325-1329
Timing and type of personal protective equipment adherence lapses in pediatric trauma resuscitation: A retrospective video study
- 28 August 2025
- Published by Elsevier in American Journal of Infection Control
- Vol. 53 (12) , 1325-1329
Timing and type of personal protective equipment adherence lapses in pediatric trauma resuscitation: A retrospective video study
- Open Access
- 4 July 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 3473-3489
Understanding Personal Protective Equipment Use in Interdisciplinary Medical Settings: Design Explorations for Just-in-Time Compliance Alerts
We examine the use of personal protective equipment (PPE) in two interdisciplinary medical settings to inform the design of just-in-time alerts and reminders for correcting PPE noncompliance. We reviewed videos of 26 pediatric resuscitations occurring over the course of the COVID-19 pandemic at an urban pediatric teaching hospital. Through video review, we identified causes for PPE noncompliance, activities that were frequently performed without PPE, instances in which PPE was intentionally removed, and mechanisms by which healthcare providers corrected PPE noncompliance. We also interviewed 18 registered nurses working in the hospital’s emergency department (ED) and intensive care unit (ICU) to better understand observed PPE behaviors and practices. Our results suggest that alert design will require considering the urgency of correcting PPE noncompliance against the urgency of tasks being performed. We discuss our findings through the lens of the COM-B framework and conclude by exploring design opportunities for just-in-time alerts and reminders for prompting PPE noncompliance corrections in dynamic medical work.
- 4 July 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 3473-3489
Open AccessUnderstanding Personal Protective Equipment Use in Interdisciplinary Medical Settings: Design Explorations for Just-in-Time Compliance Alerts
We examine the use of personal protective equipment (PPE) in two interdisciplinary medical settings to inform the design of just-in-time alerts and reminders for correcting PPE noncompliance. We reviewed videos of 26 pediatric resuscitations occurring over the course of the COVID-19 pandemic at an urban pediatric teaching hospital. Through video review, we identified causes for PPE noncompliance, activities that were frequently performed without PPE, instances in which PPE was intentionally removed, and mechanisms by which healthcare providers corrected PPE noncompliance. We also interviewed 18 registered nurses working in the hospital’s emergency department (ED) and intensive care unit (ICU) to better understand observed PPE behaviors and practices. Our results suggest that alert design will require considering the urgency of correcting PPE noncompliance against the urgency of tasks being performed. We discuss our findings through the lens of the COM-B framework and conclude by exploring design opportunities for just-in-time alerts and reminders for prompting PPE noncompliance corrections in dynamic medical work.
- Open Access
To Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events
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 AccessTo Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events
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.
- 3 March 2025
- Published by Wolters Kluwer Health in Journal of Trauma and Acute Care Surgery
- Vol. 99 (3) , 364-372
Development of an algorithm for adjudicating actionable hemorrhage in pediatric trauma patients
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
- 3 March 2025
- Published by Wolters Kluwer Health in Journal of Trauma and Acute Care Surgery
- Vol. 99 (3) , 364-372
Development of an algorithm for adjudicating actionable hemorrhage in pediatric trauma patients
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