Artificial intelligence-based quality control of hand hygiene for hospital-acquired infection_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

YANG Xuchen ¹ , LI Jingwen ² , ZHANG Wan ¹ , FENG Shasha ¹ , ZENG Min ¹ , SHI Jianan ¹ , CHEN Youqiong ¹ , ZHENG Tao ¹ ,  YAO Xun ^1,3

1. Information Center, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China;
2. Medical Artificial Intelligence Lab, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China;
3. Medical Artificial Intelligence Research Laboratory, West China Hospital, Sichuan University, 610041, P. R. China;

Corresponding?author：

YAO Xun, Email: yaoxun@scu.edu.cn

Keywords：

Healthcare-associated infection control; artificial intelligence; hand hygiene; quality control; video recognition; behavior monitoring; operating room; UniFormerV2

DOI：

10.7507/1007-4848.202510019

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To explore an artificial intelligence (AI)-based method for automated hand hygiene monitoring and to compare the effectiveness of three algorithms (UniFormerV2, TDN, C3D) in recognizing hand hygiene steps in surgical settings, thereby aiding hospital infection control. Methods From April to October 2024, we non-invasively collected 641 video recordings of healthcare staff performing hand hygiene at four-bay scrub sinks in two tertiary hospitals using overhead HD cameras. The dataset was annotated by five trained experts for model training and validation. Results Following training on 385 samples, internal validation (n=119) showed the C3D model achieved 81% accuracy, 87% recall, and an 83% F1-score. The TDN model achieved 93%, 91%, and 92% for the same metrics. The UniFormerV2 model outperformed both, with an accuracy, recall, and F1-score of 93%—an improvement of over 10 percentage points compared to traditional CNNs (TDN, C3D). It also achieved an 84% accuracy in external validation, demonstrating strong generalization. Conclusion The UniFormerV2 model is more accurate than CNN-based models for hand hygiene step recognition and shows robust performance in external validation. It presents a viable tool for healthcare facilities to enhance hand hygiene management, ultimately improving medical quality and patient safety.

Citation： YANG Xuchen, LI Jingwen, ZHANG Wan, FENG Shasha, ZENG Min, SHI Jianan, CHEN Youqiong, ZHENG Tao, YAO Xun. Artificial intelligence-based quality control of hand hygiene for hospital-acquired infection. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2026, 33(2): 241-247. doi: 10.7507/1007-4848.202510019 Copy

1.	Kong A, Botero Suarez CS, Rahamatalli B, et al. Hand hygiene and hospital-acquired infections during COVID-19 increased vigilance: one hospital's experience. HCA Healthc J Med, 2021, 2(5): 379-384.
2.	Ward MA, Schweizer ML, Polgreen PM, et al. Automated and electronically assisted hand hygiene monitoring systems: a systematic review. Am J Infect Control, 2014, 42(5): 472-478.
3.	Jernigan JA. The impact of hospital-acquired infections on hospital costs. Infect Control Hosp Epidemiol, 1995, 16(1): 1-7.
4.	World Health Organization. WHO guidelines on hand hygiene in health care: a global challenge for the improvement of practices. Geneva: World Health Organization, 2009.
5.	World Health Organization. WHO guidelines on hand hygiene in health care: first global patient safety challenge clean care is safer care. Geneva: World Health Organization, 2009.
6.	Lotfinejad N, Peters A, Tartari E, et al. Hand hygiene in health care: 20 years of ongoing advances and perspectives. Lancet Infect Dis, 2021, 21(8): e209-e221.
7.	de Kraker MEA, Stewardson AJ, Harbarth S, et al. Implementation of hand hygiene in health-care facilities: a global survey based on the WHO multimodal hand hygiene improvement strategy. Lancet Infect Dis, 2021, 21(12): e204-e214.
8.	Wang C, Tian Z, Chen S, et al. Electronic monitoring systems for hand hygiene: a systematic review. J Med Internet Res, 2021, 23(11): e27880.
9.	Sunkesula VCK, Knights J, Fetherstonhaugh D, et al. Comparison of hand hygiene monitoring using the 5 moments observation and electronic counting device. Am J Infect Control, 2015, 43(4): e55-e60.
10.	Doll ME. Electronic hand hygiene monitoring systems: not worth the costs? Antimicrob Steward Healthc Epidemiol, 2022, 2: e44.
11.	Iversen AM, M?ller JK, Siegel H, et al. Clinical evaluation of an electronic hand hygiene monitoring system. Am J Infect Control, 2023, 51(3): 324-330.
12.	Haque A, Guo M, Alahi A, et al. Towards vision-based smart hospitals: a system for tracking and monitoring hand hygiene compliance. In: Proceedings of the Machine Learning for Healthcare Conference. 2017: 75-87.
13.	Yeung S, Alahi A, Haque A, et al. Vision-based hand hygiene monitoring in hospitals. Proc AMIA Symp, 2016: 1258-1266.
14.	Qian X, Yang L, Darius C, et al. Implementing an electronic hand hygiene system improved compliance in the intensive care unit. Am J Infect Control, 2021, 49(12): 1535-1542.
15.	Boyce JM, Laughman JA, Ader MH, et al. Impact of an automated hand hygiene monitoring system and additional promotional activities on hand hygiene performance rates and healthcare-associated infections. Infection Control & Hospital Epidemiology, 2019, 40 (7).
16.	Wu JY, Lin YC, Lee SY, et al. IoT-based hand hygiene compliance monitoring system and validation of its effectiveness in hospital environments. Glob Chall, 2024, 8(12): 2400124.
17.	Matterson G, Browne K, Russo PL, et al. Evaluating the accuracy of an automatic counting system to detect dispensing of hand hygiene product. Infect Dis Health, 2025, 30(1): 39-45.
18.	Haque A, Singh A, Kwan J, et al. Automatic detection of hand hygiene using computer vision technology. J Am Med Inform Assoc, 2020, 27(8): 1316-1322.
19.	Kim M, Choi J, Jo JY, et al. Video-based automatic hand hygiene detection for operating rooms using 3D convolutional neural networks. J Clin Monit Comput, 2024, 38(3): 83.
20.	Huang W, Huang J, Wang G, et al. A pilot study of deep Learning models for camera based hand hygiene monitoring in ICU. Annu Int Conf IEEE Eng Med Biol Soc. 2023: 1-5.
21.	Nirmal I, Hu W, Hassan M, et al. Improving mmWave based hand hygiene monitoring through beam steering and combining techniques. arXiv preprint arXiv: 2503.16764. 2025.
22.	Ju S, Reibman AR. Shadow augmentation for handwashing action recognition: from synthetic to real datasets. arXiv, 2024: 2410.03984.
23.	Pineles L, Robinson G, Morgan DJ. New Strategies to Monitor Healthcare Workers’ Hand Hygiene Compliance. Current Treatment Options in Infectious Diseases, 2017, 9(1): 11-17.
24.	Gould D. Should automated electronic hand-hygiene monitoring systems be used in real-world settings? A systematic review. J Hosp Infect, 2024, 146: 1-10.
25.	Cotia ALF, Leija H, Mendoza J, et al. Integration of an electronic hand hygiene auditing system with electronic health records and machine learning models can enhance infection control. Am J Infect Control, 2025, 53(1): 6-12.
26.	Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2015: 4489-4497.
27.	Wang L, Tong Z, Ji B, et al. TDN: temporal difference networks for efficient action recognition. arXiv preprint arXiv: 2012.10071. 2020.
28.	Li K, Wang Y, He Y, et al. UniFormerV2: spatiotemporal learning by arming image ViTs with video UniFormer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2023: 15305-15315.
29.	石銳, 鄭兵, 姚巡, 等. “華西黌醫”大模型構建與應用. 中國胸心血管外科臨床雜志, 2025, 32(5): 587-593.Shi R, Zheng B, Yao X, et al. Construction and application of the "Huaxi Hongyi" large medical model. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(5): 587-593.
30.	周小芹, 劉慧珍, 王婷, 等. 基于大語言模型的臨床預測模型研究報告指南(TRIPOD-LLM)解讀. 中國胸心血管外科臨床雜志, 2025, 32(7): 940-946.Zhou XQ, Liu HZ, Wang T, et al. Interpretation of the TRIPOD-LLM reporting guideline for studies using large language models. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(7): 940-946.

1. Kong A, Botero Suarez CS, Rahamatalli B, et al. Hand hygiene and hospital-acquired infections during COVID-19 increased vigilance: one hospital's experience. HCA Healthc J Med, 2021, 2(5): 379-384.
2. Ward MA, Schweizer ML, Polgreen PM, et al. Automated and electronically assisted hand hygiene monitoring systems: a systematic review. Am J Infect Control, 2014, 42(5): 472-478.
3. Jernigan JA. The impact of hospital-acquired infections on hospital costs. Infect Control Hosp Epidemiol, 1995, 16(1): 1-7.
4. World Health Organization. WHO guidelines on hand hygiene in health care: a global challenge for the improvement of practices. Geneva: World Health Organization, 2009.
5. World Health Organization. WHO guidelines on hand hygiene in health care: first global patient safety challenge clean care is safer care. Geneva: World Health Organization, 2009.
6. Lotfinejad N, Peters A, Tartari E, et al. Hand hygiene in health care: 20 years of ongoing advances and perspectives. Lancet Infect Dis, 2021, 21(8): e209-e221.
7. de Kraker MEA, Stewardson AJ, Harbarth S, et al. Implementation of hand hygiene in health-care facilities: a global survey based on the WHO multimodal hand hygiene improvement strategy. Lancet Infect Dis, 2021, 21(12): e204-e214.
8. Wang C, Tian Z, Chen S, et al. Electronic monitoring systems for hand hygiene: a systematic review. J Med Internet Res, 2021, 23(11): e27880.
9. Sunkesula VCK, Knights J, Fetherstonhaugh D, et al. Comparison of hand hygiene monitoring using the 5 moments observation and electronic counting device. Am J Infect Control, 2015, 43(4): e55-e60.
10. Doll ME. Electronic hand hygiene monitoring systems: not worth the costs? Antimicrob Steward Healthc Epidemiol, 2022, 2: e44.
11. Iversen AM, M?ller JK, Siegel H, et al. Clinical evaluation of an electronic hand hygiene monitoring system. Am J Infect Control, 2023, 51(3): 324-330.
12. Haque A, Guo M, Alahi A, et al. Towards vision-based smart hospitals: a system for tracking and monitoring hand hygiene compliance. In: Proceedings of the Machine Learning for Healthcare Conference. 2017: 75-87.
13. Yeung S, Alahi A, Haque A, et al. Vision-based hand hygiene monitoring in hospitals. Proc AMIA Symp, 2016: 1258-1266.
14. Qian X, Yang L, Darius C, et al. Implementing an electronic hand hygiene system improved compliance in the intensive care unit. Am J Infect Control, 2021, 49(12): 1535-1542.
15. Boyce JM, Laughman JA, Ader MH, et al. Impact of an automated hand hygiene monitoring system and additional promotional activities on hand hygiene performance rates and healthcare-associated infections. Infection Control & Hospital Epidemiology, 2019, 40 (7).
16. Wu JY, Lin YC, Lee SY, et al. IoT-based hand hygiene compliance monitoring system and validation of its effectiveness in hospital environments. Glob Chall, 2024, 8(12): 2400124.
17. Matterson G, Browne K, Russo PL, et al. Evaluating the accuracy of an automatic counting system to detect dispensing of hand hygiene product. Infect Dis Health, 2025, 30(1): 39-45.
18. Haque A, Singh A, Kwan J, et al. Automatic detection of hand hygiene using computer vision technology. J Am Med Inform Assoc, 2020, 27(8): 1316-1322.
19. Kim M, Choi J, Jo JY, et al. Video-based automatic hand hygiene detection for operating rooms using 3D convolutional neural networks. J Clin Monit Comput, 2024, 38(3): 83.
20. Huang W, Huang J, Wang G, et al. A pilot study of deep Learning models for camera based hand hygiene monitoring in ICU. Annu Int Conf IEEE Eng Med Biol Soc. 2023: 1-5.
21. Nirmal I, Hu W, Hassan M, et al. Improving mmWave based hand hygiene monitoring through beam steering and combining techniques. arXiv preprint arXiv: 2503.16764. 2025.
22. Ju S, Reibman AR. Shadow augmentation for handwashing action recognition: from synthetic to real datasets. arXiv, 2024: 2410.03984.
23. Pineles L, Robinson G, Morgan DJ. New Strategies to Monitor Healthcare Workers’ Hand Hygiene Compliance. Current Treatment Options in Infectious Diseases, 2017, 9(1): 11-17.
24. Gould D. Should automated electronic hand-hygiene monitoring systems be used in real-world settings? A systematic review. J Hosp Infect, 2024, 146: 1-10.
25. Cotia ALF, Leija H, Mendoza J, et al. Integration of an electronic hand hygiene auditing system with electronic health records and machine learning models can enhance infection control. Am J Infect Control, 2025, 53(1): 6-12.
26. Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2015: 4489-4497.
27. Wang L, Tong Z, Ji B, et al. TDN: temporal difference networks for efficient action recognition. arXiv preprint arXiv: 2012.10071. 2020.
28. Li K, Wang Y, He Y, et al. UniFormerV2: spatiotemporal learning by arming image ViTs with video UniFormer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2023: 15305-15315.
29. 石銳, 鄭兵, 姚巡, 等. “華西黌醫”大模型構建與應用. 中國胸心血管外科臨床雜志, 2025, 32(5): 587-593.Shi R, Zheng B, Yao X, et al. Construction and application of the "Huaxi Hongyi" large medical model. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(5): 587-593.
30. 周小芹, 劉慧珍, 王婷, 等. 基于大語言模型的臨床預測模型研究報告指南(TRIPOD-LLM)解讀. 中國胸心血管外科臨床雜志, 2025, 32(7): 940-946.Zhou XQ, Liu HZ, Wang T, et al. Interpretation of the TRIPOD-LLM reporting guideline for studies using large language models. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(7): 940-946.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Artificial intelligence-based quality control of hand hygiene for hospital-acquired infection

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content