Development and validation of a machine learning and Internet of Medical Things-based model for ICU ventilator alarm management_Chinese Journal of Evidence-Based Medicine

Authors：

WANG Xiaomin ^1,2 , CHEN Zhu ³ , ZHANG Heng ⁴ , JIANG Xin ² , LIU Qilin ² ,  HUANG Jin ²

1. Department of Respiratory Care, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
2. Innovation Institute for Integration of Medicine and Engineering, Med-X Center for Manufacturing, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
3. Department of Medical Engineering Division, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
4. College of Electrical Engineering, Sichuan University, Chengdu 610065, P. R. China;

Corresponding author：

HUANG Jin, Email: michael_huangjin@163.com

Keywords：

Mechanical ventilation; Alarm management; Machine learning; Internet of medical things; Intensive care unit

DOI：

10.7507/1672-2531.202411199

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To explore the development and application of a novel ventilator alarm management model in critically ill patients receiving invasive mechanical ventilation (MV) in the intensive care unit (ICU) using machine learning (ML) and Internet of Medical Things (IoMT). The study aims to identify alarms’ intervention requirements. Methods A retrospective cohort study and ML analysis were conducted, including adult patients receiving invasive MV in the ICU at West China Hospital from February 10, 2024, to July 22, 2024. A total of 76 ventilator alarm-related parameters were collected through the IoMT system. Feature selection was performed using a stratified approach, and six ML algorithms were applied: Gaussian Naive Bayes, K-Nearest Neighbors, Linear Discriminant Analysis, Support Vector Machine, Categorical Boosting (CatBoost), and Logistic Regression. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC). Results A total of 107 patients and their associated ventilator alarm records were included. Thirteen highly relevant features were selected from the 76 parameters for model training through stratified feature selection. The CatBoost model demonstrated the best predictive performance, with an AUC-ROC of 0.984 7 and an accuracy of 0.912 3 in the training set. External validation of the CatBoost model yielded an AUC-ROC of 0.805 4. Conclusion The CatBoost-based ML model successfully constructed in this study has high accuracy and reliability in predicting the ventilator alarms in ICU patients, providing an effective tool for ventilator alarm management. The CatBoost-based ML method exhibited remarkable efficacy in predicting the necessity of ventilator intervention in critically ill ICU patients. Further large-scale multicenter studies are recommended to validate its clinical application value and promote model optimization and implementation.

Citation： WANG Xiaomin, CHEN Zhu, ZHANG Heng, JIANG Xin, LIU Qilin, HUANG Jin. Development and validation of a machine learning and Internet of Medical Things-based model for ICU ventilator alarm management. Chinese Journal of Evidence-Based Medicine, 2025, 25(4): 387-394. doi: 10.7507/1672-2531.202411199 Copy

1.	McMullen SM, Meade M, Rose L, et al. Partial ventilatory support modalities in acute lung injury and acute respiratory distress syndrome-a systematic review. PLoS One, 2012, 7(8): e40190.
2.	Azoulay E. Intensive care medicine: onwards and upwards. Intensive Care Med, 2019, 45(1): 106-107.
3.	Kelly FE, Fong K, Hirsch N, et al. Intensive care medicine is 60 years old: the history and future of the intensive care unit. Clin Med (Lond), 2014, 14(4): 376-379.
4.	Pelosi P, Ball L, Barbas CSV, et al. Personalized mechanical ventilation in acute respiratory distress syndrome. Crit Care, 2021, 25(1): 250.
5.	Hayhurst C. Right alert, right time: developing clinically meaningful, actionable alarm notifications. Biomed Instrum Technol, 2020, 54(1): 12-20.
6.	Graham KC, Cvach M. Monitor alarm fatigue: standardizing use of physiological monitors and decreasing nuisance alarms. Am J Crit Care, 2010, 19(1): 28-34.
7.	Bonafide CP, Lin R, Zander M, et al. Association between exposure to nonactionable physiologic monitor alarms and response time in a children's hospital. J Hosp Med, 2015, 10(6): 345-351.
8.	Chambrin MC, Ravaux P, Calvelo-Aros D, et al. Multicentric study of monitoring alarms in the adult intensive care unit (ICU): a descriptive analysis. Intensive Care Med, 1999, 25(12): 1360-1366.
9.	Lawless ST. Crying wolf: false alarms in a pediatric intensive care unit. Crit Care Med, 1994, 22(6): 981-985.
10.	Siebig S, Kuhls S, Imhoff M, et al. Intensive care unit alarms--how many do we need? Crit Care Med, 2010, 38(2): 451-456.
11.	Tsien CL, Fackler JC. Poor prognosis for existing monitors in the intensive care unit. Crit Care Med, 1997, 25(4): 614-619.
12.	Johnson KR, Hagadorn JI, Sink DW. Alarm safety and alarm fatigue. Clin Perinatol, 2017, 44(3): 713-728.
13.	Jones K. Alarm fatigue a top patient safety hazard. CMAJ, 2014, 186(3): 178.
14.	Ruskin KJ, Hueske-Kraus D. Alarm fatigue: impacts on patient safety. Curr Opin Anaesthesiol, 2015, 28(6): 685-690.
15.	Ali TM, Alharbi MF. AF among nurses working in neonatal and paediatric intensive care units: a cross-sectional study. Healthcare (Basel), 2024, 12(16): 1574.
16.	Cvach M. Monitor alarm fatigue: an integrative review. Biomed Instrum Technol, 2012, 46(4): 268-277.
17.	Winters BD, Slota JM, Bilimoria KY. Safety culture as a patient safety practice for alarm fatigue. JAMA, 2021, 326(12): 1207-1208.
18.	Sowan A. Effective dealing with alarm fatigue in the intensive care unit. Intensive Crit Care Nurs, 2024, 80: 103559.
19.	Cvach MM, Stokes JE, Manzoor SH, et al. Ventilator alarms in intensive care units: frequency, duration, priority, and relationship to ventilator parameters. Anesth Analg, 2020, 130(1): e9-e13.
20.	Pham JC, Williams TL, Sparnon EM, et al. Ventilator-related adverse events: a taxonomy and findings from 3 incident reporting systems. Respir Care, 2016, 61(5): 621-631.
21.	Scott JB. The conundrum of mechanical ventilation alarms. Respir Care, 2021, 66(4): 699-700.
22.	Walsh BK, Waugh JB. Alarm strategies and surveillance for mechanical ventilation. Respir Care, 2020, 65(6): 820-831.
23.	唐雷, 钟世镇. 人工智能及其在医学领域中的应用. 中国实用妇科与产科杂志, 2024, 40(9): 876-878.
24.	Haug CJ, Drazen JM. Artificial intelligence and machine learning in clinical medicine, 2023. N Engl J Med, 2023, 388(13): 1201-1208.
25.	Hever G, Cohen L, O'Connor MF, et al. Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU. J Clin Monit Comput, 2020, 34(2): 339-352.
26.	Au-Yeung WM, Sahani AK, Isselbacher EM, et al. Reduction of false alarms in the intensive care unit using an optimized machine learning based approach. NPJ Digit Med, 2019, 2: 86.
27.	González-Nóvoa JA, Busto L, Rodríguez-Andina JJ, et al. Using explainable machine learning to improve intensive care unit alarm systems. Sensors (Basel), 2021, 21(21): 7125.
28.	Gupta A, Katarya R. Social media based surveillance systems for healthcare using machine learning: a systematic review. J Biomed Inform, 2020, 108: 103500.
29.	Sanchez-Pinto LN, Luo Y, Churpek MM. Big data and data science in critical care. Chest, 2018, 154(5): 1239-1248.
30.	何施谦, 郭尹浩, 杨帆, 等. 围术期不同吸入氧浓度与术后肺部并发症的研究进展. 河北医药, 2024, 46(7): 1070-1074, 1079.
31.	王小芳, 吴跃明, 潘柳华. 呼气末正压和吸氧浓度调整对稳定期ARDS机械通气患者炎性肺损伤的改善作用. 现代实用医学, 2024, 36(4): 473-476.
32.	Beloncle FM, Richard JC, Merdji H, et al. Advanced respiratory mechanics assessment in mechanically ventilated obese and non-obese patients with or without acute respiratory distress syndrome. Crit Care, 2023, 27(1): 343.
33.	Marini JJ, Rocco PRM, Gattinoni L. Static and dynamic contributors to ventilator-induced lung injury in clinical practice. pressure, energy, and power. Am J Respir Crit Care Med, 2020, 201(7): 767-774.
34.	Tawfik P, Syed MKH, Elmufdi FS, et al. Static and dynamic measurements of compliance and driving pressure: a pilot study. Front Physiol, 2022, 13: 773010.
35.	Johnston BW, Barrett-Jolley R, Krige A, et al. Heart rate variability: measurement and emerging use in critical care medicine. J Intensive Care Soc, 2020, 21(2): 148-157.
36.	Weinstein TB, Rogers CB, Uppal A, et al. Ventilator alarm trends in a medical ICU. Chest, 2022, 162(4): A1465.
37.	Cheifetz IM. Cardiorespiratory interactions: the relationship between mechanical ventilation and hemodynamics. Respir Care, 2014, 59(12): 1937-1945.
38.	张伟, 刘新. 间歇性时间序列数据多目标决策挖掘算法设计. 计算机仿真, 2024, 41(10): 291-295, 300.

1. McMullen SM, Meade M, Rose L, et al. Partial ventilatory support modalities in acute lung injury and acute respiratory distress syndrome-a systematic review. PLoS One, 2012, 7(8): e40190.
2. Azoulay E. Intensive care medicine: onwards and upwards. Intensive Care Med, 2019, 45(1): 106-107.
3. Kelly FE, Fong K, Hirsch N, et al. Intensive care medicine is 60 years old: the history and future of the intensive care unit. Clin Med (Lond), 2014, 14(4): 376-379.
4. Pelosi P, Ball L, Barbas CSV, et al. Personalized mechanical ventilation in acute respiratory distress syndrome. Crit Care, 2021, 25(1): 250.
5. Hayhurst C. Right alert, right time: developing clinically meaningful, actionable alarm notifications. Biomed Instrum Technol, 2020, 54(1): 12-20.
6. Graham KC, Cvach M. Monitor alarm fatigue: standardizing use of physiological monitors and decreasing nuisance alarms. Am J Crit Care, 2010, 19(1): 28-34.
7. Bonafide CP, Lin R, Zander M, et al. Association between exposure to nonactionable physiologic monitor alarms and response time in a children's hospital. J Hosp Med, 2015, 10(6): 345-351.
8. Chambrin MC, Ravaux P, Calvelo-Aros D, et al. Multicentric study of monitoring alarms in the adult intensive care unit (ICU): a descriptive analysis. Intensive Care Med, 1999, 25(12): 1360-1366.
9. Lawless ST. Crying wolf: false alarms in a pediatric intensive care unit. Crit Care Med, 1994, 22(6): 981-985.
10. Siebig S, Kuhls S, Imhoff M, et al. Intensive care unit alarms--how many do we need? Crit Care Med, 2010, 38(2): 451-456.
11. Tsien CL, Fackler JC. Poor prognosis for existing monitors in the intensive care unit. Crit Care Med, 1997, 25(4): 614-619.
12. Johnson KR, Hagadorn JI, Sink DW. Alarm safety and alarm fatigue. Clin Perinatol, 2017, 44(3): 713-728.
13. Jones K. Alarm fatigue a top patient safety hazard. CMAJ, 2014, 186(3): 178.
14. Ruskin KJ, Hueske-Kraus D. Alarm fatigue: impacts on patient safety. Curr Opin Anaesthesiol, 2015, 28(6): 685-690.
15. Ali TM, Alharbi MF. AF among nurses working in neonatal and paediatric intensive care units: a cross-sectional study. Healthcare (Basel), 2024, 12(16): 1574.
16. Cvach M. Monitor alarm fatigue: an integrative review. Biomed Instrum Technol, 2012, 46(4): 268-277.
17. Winters BD, Slota JM, Bilimoria KY. Safety culture as a patient safety practice for alarm fatigue. JAMA, 2021, 326(12): 1207-1208.
18. Sowan A. Effective dealing with alarm fatigue in the intensive care unit. Intensive Crit Care Nurs, 2024, 80: 103559.
19. Cvach MM, Stokes JE, Manzoor SH, et al. Ventilator alarms in intensive care units: frequency, duration, priority, and relationship to ventilator parameters. Anesth Analg, 2020, 130(1): e9-e13.
20. Pham JC, Williams TL, Sparnon EM, et al. Ventilator-related adverse events: a taxonomy and findings from 3 incident reporting systems. Respir Care, 2016, 61(5): 621-631.
21. Scott JB. The conundrum of mechanical ventilation alarms. Respir Care, 2021, 66(4): 699-700.
22. Walsh BK, Waugh JB. Alarm strategies and surveillance for mechanical ventilation. Respir Care, 2020, 65(6): 820-831.
23. 唐雷, 钟世镇. 人工智能及其在医学领域中的应用. 中国实用妇科与产科杂志, 2024, 40(9): 876-878.
24. Haug CJ, Drazen JM. Artificial intelligence and machine learning in clinical medicine, 2023. N Engl J Med, 2023, 388(13): 1201-1208.
25. Hever G, Cohen L, O'Connor MF, et al. Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU. J Clin Monit Comput, 2020, 34(2): 339-352.
26. Au-Yeung WM, Sahani AK, Isselbacher EM, et al. Reduction of false alarms in the intensive care unit using an optimized machine learning based approach. NPJ Digit Med, 2019, 2: 86.
27. González-Nóvoa JA, Busto L, Rodríguez-Andina JJ, et al. Using explainable machine learning to improve intensive care unit alarm systems. Sensors (Basel), 2021, 21(21): 7125.
28. Gupta A, Katarya R. Social media based surveillance systems for healthcare using machine learning: a systematic review. J Biomed Inform, 2020, 108: 103500.
29. Sanchez-Pinto LN, Luo Y, Churpek MM. Big data and data science in critical care. Chest, 2018, 154(5): 1239-1248.
30. 何施谦, 郭尹浩, 杨帆, 等. 围术期不同吸入氧浓度与术后肺部并发症的研究进展. 河北医药, 2024, 46(7): 1070-1074, 1079.
31. 王小芳, 吴跃明, 潘柳华. 呼气末正压和吸氧浓度调整对稳定期ARDS机械通气患者炎性肺损伤的改善作用. 现代实用医学, 2024, 36(4): 473-476.
32. Beloncle FM, Richard JC, Merdji H, et al. Advanced respiratory mechanics assessment in mechanically ventilated obese and non-obese patients with or without acute respiratory distress syndrome. Crit Care, 2023, 27(1): 343.
33. Marini JJ, Rocco PRM, Gattinoni L. Static and dynamic contributors to ventilator-induced lung injury in clinical practice. pressure, energy, and power. Am J Respir Crit Care Med, 2020, 201(7): 767-774.
34. Tawfik P, Syed MKH, Elmufdi FS, et al. Static and dynamic measurements of compliance and driving pressure: a pilot study. Front Physiol, 2022, 13: 773010.
35. Johnston BW, Barrett-Jolley R, Krige A, et al. Heart rate variability: measurement and emerging use in critical care medicine. J Intensive Care Soc, 2020, 21(2): 148-157.
36. Weinstein TB, Rogers CB, Uppal A, et al. Ventilator alarm trends in a medical ICU. Chest, 2022, 162(4): A1465.
37. Cheifetz IM. Cardiorespiratory interactions: the relationship between mechanical ventilation and hemodynamics. Respir Care, 2014, 59(12): 1937-1945.
38. 张伟, 刘新. 间歇性时间序列数据多目标决策挖掘算法设计. 计算机仿真, 2024, 41(10): 291-295, 300.

Chinese Journal of Evidence-Based Medicine

Development and validation of a machine learning and Internet of Medical Things-based model for ICU ventilator alarm management

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content