Ivan Marsic
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
Ivan Marsic has a total of 95 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.
33 shared publications - Aleksandra Sarcevic
Drexel University, Philadelphia, PA, USA
15 shared publications Shuhong Chen
Multimedia Image Processing Lab, Electrical and Computer Engineering Department, Rutgers University, Piscataway, NJ, USA
12 shared publications- Xinyu Li
Multimedia Image Processing Lab, Electrical and Computer Engineering Department, Rutgers University, Piscataway, NJ, USA
10 shared publications - Richard A. Farneth
Children's National Medical Center, Washington, DC, USA
9 shared publications - Mary Suhyun Kim
Children's National Hospital, Washington D.C., District of Columbia, USA
7 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.
- 25 August 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 272
TextAidAR: Text-driven domain knowledge for fine-grained medical activity recognition
- 25 August 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 272
TextAidAR: Text-driven domain knowledge for fine-grained medical activity recognition
- 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
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Bounding Boxes in Practice: Design and Early Evaluation of a Video-Based PPE Compliance Monitoring Application for Time-Critical Care
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessBounding Boxes in Practice: Design and Early Evaluation of a Video-Based PPE Compliance Monitoring Application for Time-Critical Care
- 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
- 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.
- 31 December 2024
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 161, 104767
Human intention recognition for trauma resuscitation: An interpretable deep learning approach for medical process data
- 31 December 2024
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 161, 104767
Human intention recognition for trauma resuscitation: An interpretable deep learning approach for medical process data
- Open Access
- 21 December 2024
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 251
ASELMAR: Active and semi-supervised learning-based framework to reduce multi-labeling efforts for activity recognition
- 21 December 2024
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 251
Open AccessASELMAR: Active and semi-supervised learning-based framework to reduce multi-labeling efforts for activity recognition
- Open Access
- 12 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (9) , 1-31
ProcessGAN: Generating Privacy-Preserving Time-Aware Process Data with Conditional Generative Adversarial Nets
Process data constructed from event logs provides valuable insights into procedural dynamics over time. The confidential information in process data, together with the data’s intricate nature, makes the datasets not sharable and challenging to collect. Consequently, research is limited using process data and analytics in the process mining domain. In this study, we introduced a synthetic process data generation task to address the limitation of sharable process data. We introduced a generative adversarial network, called ProcessGAN, to generate process data with activity sequences and corresponding timestamps. ProcessGAN consists of a transformer-based network as the generator, and a time-aware self-attention network as the discriminator. It can generate privacy-preserving process data from random noise. ProcessGAN considers the duration of the process and time intervals between activities to generate realistic activity sequences with timestamps. We evaluated ProcessGAN on five real-world datasets, two that are public and three collected in medical domains that are private. To evaluate the synthetic data, in addition to statistical metrics, we trained a supervised model to score the synthetic processes. We also used process mining to discover workflows for synthetic medical processes and had domain experts evaluate the clinical applicability of the synthetic workflows. ProcessGAN outperformed the existing generative models in generating complex processes with valid parallel pathways. The synthetic process data generated by ProcessGAN better represented the long-range dependencies between activities, a feature relevant to complicated medical and other processes. The timestamps generated by the ProcessGAN model showed similar distributions with the authentic timestamps. In addition, we trained a transformer-based network to generate synthetic contexts (e.g., patient demographics) that were associated with the synthetic processes. The synthetic contexts generated by our model outperformed the baseline models, with the distributions similar to the authentic contexts. We conclude that ProcessGAN can generate sharable synthetic process data indistinguishable from authentic data. Our source code is available in https://github.com/raaachli/ProcessGAN .
- 12 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (9) , 1-31
Open AccessProcessGAN: Generating Privacy-Preserving Time-Aware Process Data with Conditional Generative Adversarial Nets
Process data constructed from event logs provides valuable insights into procedural dynamics over time. The confidential information in process data, together with the data’s intricate nature, makes the datasets not sharable and challenging to collect. Consequently, research is limited using process data and analytics in the process mining domain. In this study, we introduced a synthetic process data generation task to address the limitation of sharable process data. We introduced a generative adversarial network, called ProcessGAN, to generate process data with activity sequences and corresponding timestamps. ProcessGAN consists of a transformer-based network as the generator, and a time-aware self-attention network as the discriminator. It can generate privacy-preserving process data from random noise. ProcessGAN considers the duration of the process and time intervals between activities to generate realistic activity sequences with timestamps. We evaluated ProcessGAN on five real-world datasets, two that are public and three collected in medical domains that are private. To evaluate the synthetic data, in addition to statistical metrics, we trained a supervised model to score the synthetic processes. We also used process mining to discover workflows for synthetic medical processes and had domain experts evaluate the clinical applicability of the synthetic workflows. ProcessGAN outperformed the existing generative models in generating complex processes with valid parallel pathways. The synthetic process data generated by ProcessGAN better represented the long-range dependencies between activities, a feature relevant to complicated medical and other processes. The timestamps generated by the ProcessGAN model showed similar distributions with the authentic timestamps. In addition, we trained a transformer-based network to generate synthetic contexts (e.g., patient demographics) that were associated with the synthetic processes. The synthetic contexts generated by our model outperformed the baseline models, with the distributions similar to the authentic contexts. We conclude that ProcessGAN can generate sharable synthetic process data indistinguishable from authentic data. Our source code is available in https://github.com/raaachli/ProcessGAN .