Abstract
Tourniquets are commonly used devices for hemorrhage control; however, their effectiveness is reduced in anatomical junctions such as the neck and inguinal region. Junctional tourniquets specifically require precise placement to be effective. This precision can be enabled with ultrasound technology to help locate and occlude the major vessels in the junctional regions properly. However, interpretation of ultrasound requires highly skilled personnel, who may not necessarily be available in emergency situations. To overcome this hurdle, we have developed two ultrasound-enabled, AI-driven junctional tourniquet prototypes. AI models can aid in guiding the end-user to the correct location and determine occlusion during and after pressure application. Proof-of-concept functionality of the developed prototypes integrated with AI models was successfully tested in a durable, ultrasound-compatible femoral tissue phantom and compared against commercially available tourniquet devices. Overall, time to occlusion was comparable between the tourniquet prototype designs and traditional junctional tourniquets, while each AI model achieved high performance metrics for this application. As such, the combination of AI and ultrasound can prove to be a viable solution to prevent further hemorrhaging at the point of injury.
Data availability
The datasets presented in this article are not readily available because they have been collected and maintained in a government-controlled database that is located at the U.S. Army Institute of Surgical Research. As such, data can be made available through the development of a business agreement with the corresponding author. Requests for the datasets should be directed to Dr. Eric J. Snider, eric.j.snider3.civ@health.mil.
References
Jones, A. R., Miller, J. & Brown, M. Epidemiology of trauma-related hemorrhage and time to definitive care across North America: making the case for bleeding control education. Prehospital Disaster Med. 38(6), 780–783 (2023).
Eastridge, B. J., Holcomb, J. B. & Shackelford, S. Outcomes of traumatic hemorrhagic shock and the epidemiology of preventable death from injury. Transfus. (Paris). 59, 1423–1428 (2019).
Picard, C. Hemorrhage control, a fundamental skill: A review of direct pressure, dressings, wound packing and bandages for life-saving. Can. J. Emerg. Nurs. 40, 26–28 (2017).
Patel, T. H. et al. A U.S. Army forward surgical team’s experience in operation Iraqi freedom. J. Trauma. Acute Care Surg. 57, 201 (2004).
Eilertsen, K. A., Winberg, M., Jeppesen, E., Hval, G. & Wisborg, T. Prehospital tourniquets in civilians: a systematic review. Prehospital Disaster Med. 36, 86–94 (2021).
Beekley, A. C. et al. Prehospital tourniquet use in operation Iraqi freedom: effect on hemorrhage control and outcomes. J. Trauma. 64, 28–37 (2008).
Goolsby, C. et al. Stop the bleed education consortium: education program content and delivery recommendations. J. Trauma. Acute Care Surg. 84, 205 (2018).
van Oostendorp, S. E., Tan, E. C. T. H. & Geeraedts, L. M. G. Prehospital control of life-threatening truncal and junctional haemorrhage is the ultimate challenge in optimizing trauma care; a review of treatment options and their applicability in the civilian trauma setting. Scand. J. Trauma. Resusc. Emerg. Med. 24, 110 (2016).
Winstanley, M., Smith, J. E. & Wright, C. Catastrophic haemorrhage in military major trauma patients: a retrospective database analysis of haemostatic agents used on the battlefield. J. R Army Med. Corps. 165, 405–409 (2019).
Spiegel, S. & Baker, A. M. EMS junctional hemorrhage control. In StatPearls (StatPearls Publishing, 2024).
Smith, S. et al. The effectiveness of junctional tourniquets: A systematic review and meta-analysis. J. Trauma. Acute Care Surg. 86, 532–539 (2019).
Humphries, R., Naumann, D. N. & Ahmed, Z. Use of haemostatic devices for the control of junctional and abdominal traumatic haemorrhage: A systematic review. Trauma. Care. 2, 23–34 (2022).
Kragh, J. F. et al. Performance of junctional tourniquets in normal human volunteers. Prehosp Emerg. Care. 19, 391–398 (2015).
Chen, J. et al. Testing of junctional tourniquets by medics of the Israeli defense force in control of simulated groin hemorrhage. J. Spec. Oper. Med. Peer Rev. J. SOF Med. Prof. 16, 36–42 (2016).
Kragh, J. F. et al. Junctional tourniquet training experience. J. Spec. Oper. Med. Peer Rev. J. SOF Med. Prof. 15, 20–30 (2015).
Schauer, S. G., April, M. D., Fisher, A. D., Cunningham, C. W. & Gurney, J. M. Junctional tourniquet use during combat operations in afghanistan: the prehospital trauma registry experience. J. Spec. Oper. Med. Peer Rev. J. SOF Med. Prof. 18, 71–74 (2018).
Flecha, I., Naylor, J. F., Schauer, S. G., Curtis, R. A. & Cunningham, C. W. Combat lifesaver-trained, first-responder application of junctional tourniquets: a prospective, randomized, crossover trial. Mil Med. Res. 5, 31 (2018).
Kaymak, Ş. et al. Results of combat medic junctional tourniquet training: a prospective, single-blind, randomized, cross-over study. Turk. J. Trauma. Emerg. Surg. 30, 20–26 (2024).
Gaspary, M. J. et al. Comparison of three junctional tourniquets using a randomized trial design. Prehosp Emerg. Care. 23, 187–194 (2019).
Weiser, G. LST-A novel junctional tourniquet: A study of feasibility and effectiveness. Chin. J. Traumatol. https://doi.org/10.1016/j.cjtee.2025.04.004 (2025).
Drew, B., Bennett, B. L. & Littlejohn, L. Application of current hemorrhage control techniques for backcountry care: part One, tourniquets and hemorrhage control adjuncts. Wilderness Environ. Med. 26, 236–245 (2015).
Agarwal, R., Niezgoda, J., Niezgoda, J., Madetipati, N. & Gopalakrishnan, S. Advances in hemostatic wound dressings: clinical implications and insight. Adv. Skin. Wound Care. 35, 113 (2022).
Bonanno, A. M., Graham, T. L., Wilson, L. N. & Ross, J. D. Novel use of XSTAT 30 for mitigation of lethal non-compressible torso hemorrhage in swine. PLOS ONE. 15, e0241906 (2020).
Kheirabadi, B. S., Scherer, M. R., Estep, J. S., Dubick, M. A. & Holcomb, J. B. Determination of efficacy of new hemostatic dressings in a model of extremity arterial hemorrhage in swine. J. Trauma. 67, 450–459 (2009).
Pikman Gavriely, R. et al. Manual pressure points technique for massive hemorrhage Control-A prospective human volunteer study. Prehosp Emerg. Care. 27, 586–591 (2023).
Garrick, B., Hillis, G., LaRavia, L., Lyon, M. & Gordon, R. 330 effectiveness of common femoral artery compression in elimination of popliteal blood flow. Ann. Emerg. Med. 68, S126–S127 (2016).
Avital, G. et al. Toward Smart, automated junctional Tourniquets—AI models to interpret vessel occlusion at physiological pressure points. Bioengineering 11, 109 (2024).
Dicle, O. Artificial intelligence in diagnostic ultrasonography. Diagn. Interv Radiol. https://doi.org/10.4274/dir.2022.211260 (2023).
Cho, J., Lee, S. & Yi, J. Ultrasound Standard Liver Section Classification Independent of Imaging Device. in 19th International Conference on Ubiquitous Information Management and Communication (IMCOM) 1–8 (2025). 1–8 (2025). (2025). https://doi.org/10.1109/IMCOM64595.2025.10857488
Zhou, Y. T., Yang, T. Y., Han, X. H. & Piao, J. C. Thyroid-DETR: thyroid nodule detection model with transformer in ultrasound images. Biomed. Signal. Process. Control. 98, 106762 (2024).
Bassiouny, R., Mohamed, A., Umapathy, K. & Khan, N. An interpretable neonatal lung ultrasound feature extraction and lung sliding detection system using object detectors. IEEE J. Transl Eng. Health Med. 12, 119–128 (2024).
Hernandez Torres, S. I. et al. Real-Time deployment of ultrasound image interpretation AI models for emergency medicine triage using a swine model. Technologies 13, 29 (2025).
Noordin, S., McEwen, J. A., Kragh, J. F., Eisen, A. & Masri, B. A. Surgical tourniquets in orthopaedics. J. Bone Joint Surg. Am. 91, 2958–2967 (2009).
Kainz, B. et al. Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning. Npj Digit. Med. 4, 1–18 (2021).
Park, S. et al. Artificial intelligence-based evaluation of carotid artery compressibility via point-of-care ultrasound in determining the return of spontaneous circulation during cardiopulmonary resuscitation. Resuscitation 202, 110302 (2024).
Mujkic, R., Haller, K. & Kollmann, C. Energy consumption of ultrasound devices during routine applications and opportunities to save energy and costs. Eur. Radiol. https://doi.org/10.1007/s00330-025-11822-8 (2025).
Wadhwa, M., Choudhury, T., Raj, G. & Patni, J. C. Comparison of YOLOv8 and Detectron2 on Crowd Counting techniques. in 7th International Symposium on Innovative Approaches in Smart Technologies (ISAS) 1–6 (2023). 1–6 (2023). (2023). https://doi.org/10.1109/ISAS60782.2023.10391466
Tan, M., Pang, R., Le, Q. V. & EfficientDet Scalable and efficient object detection. Preprint at (2020). https://doi.org/10.48550/arXiv.1911.09070
Tian, Y., Ye, Q. & Doermann, D. YOLOv12: attention-centric real-time object detectors. Preprint at (2025). https://doi.org/10.48550/arXiv.2502.12524
Guo, Z., Ding, C., Hu, X. & Rudin, C. A supervised machine learning semantic segmentation approach for detecting artifacts in plethysmography signals from wearables. Physiol. Meas. 42, 125003 (2021).
Holland, L., Torres, H., Snider, E. J. & S. I. & Using AI segmentation models to improve foreign body detection and triage from ultrasound images. Bioengineering 11, 128 (2024).
Hatamizadeh, A. et al. Unetr: Transformers for 3d medical image segmentation. in Proceedings of the IEEE/CVF winter conference on applications of computer vision 574–584 (2022).
Hernandez-Torres, S. I., Boice, E. N. & Snider, E. J. Using an ultrasound tissue Phantom model for hybrid training of deep learning models for shrapnel detection. J. Imaging. 8, 270 (2022).
CAE Healthcare. FAST Exam Ultrasound Training Model - Medical Skills Trainers. (2022). https://medicalskillstrainers.cae.com/fast-exam-ultrasound-training-model/p
Mitsuhashi, N. et al. BodyParts3D: 3D structure database for anatomical concepts. Nucleic Acids Res. 37, D782–D785 (2009).
Jocher, G., Chaurasia, A. & Qiu J. Ultralytics (2023). YOLOv8.
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J. & Zisserman, A. The Pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303–338 (2010).
Acknowledgements
The authors acknowledge MAJ Guy Avital of the Israeli Defense Force for his advice and subject matter expertise on this research effort. The authors also acknowledge David Berard for initial assistance in the BaTS prototype design and flow loop setup.
Funding
This work was funded by the United States Department of Defense Domestic Preparedness Support Initiative. This project was supported in part by an appointment to the Science Education Programs at National Institutes of Health (NIH), administered by ORAU through the U.S. Department of Energy Oak Ridge Institute for Science and Education (T.W., B.A., J.C., I.M., and M.L.).
Author information
Authors and Affiliations
Contributions
S.H.T. and E.J.S. conceptualize the initial idea; Prototype devices were design and fabricated by T.W., I.M., B.A., J.P.C.; Ultrasound images were captured and curated by S.H.T., T.W., I.M., C.B., and E.J.S.; AI model development was performed by S.H.T., T.W., and E.J.S.; Prototype testing and characterization was conducted by S.H.T., T.W., I.M., C.B., B.A., and M.L.; Data analysis and figure generation was by S.H.T., T.W., I.M., J.P.C., and E.J.S.; All authors wrote the manuscript test and reviewed the manuscript.
Corresponding author
Ethics declarations
Competing interests
Eric J. Snider is an inventor on a filed patent application owned by the U.S. Army related to the automated junctional tourniquet technology (filed October 24, 2024). The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Disclaimer
The views expressed in this Article are those of the authors and do not reflect the official policy or position of the U.S. Army Medical Department, Department of the Army, DoD, or the U.S. Government.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Hernandez Torres, S.I., Winter, T., Mejia, I. et al. Smart, automated junctional tourniquets leveraging AI-driven ultrasound guidance. Sci Rep (2026). https://doi.org/10.1038/s41598-026-37467-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-37467-1
