Abstract
During mechanical ventilation, a common problem known as patient-ventilator asynchrony (PVA) occurs when there is a mismatch between the needs of the patient’s breathing and the breath cycle delivered by the ventilator. PVA is problematic because it can be associated with adverse effects such as discomfort for the patient, increased work of breathing, longer mechanical ventilation duration and ventilator-induced lung injury. An automated means of early PVA detection and classification could lead to improved health outcomes and help reduce the impact of PVA on hospital resources. This paper presents a machine learning framework to detect PVA events using only the first half second of data after the start of a PVA event. When trained on more than 5000 PVA events sampled from 25 subjects, our logistic classifier achieves a sensitivity (specificity) of 99.81% (99.72%) for detecting PVA events. We then present a system capable of early classification of Ineffective Effort (IE) and Double Trigger (DT) events, which achieves a sensitivity (specificity) of 63.73% (92.88%). By demonstrating the feasibility of early PVA event detection and classification, our findings suggest that more effective intervention processes could be possible, including automated interventions with different response strategies for different PVA event types.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Murias, G., Lucangelo, U., Blanch, L.: Patient-ventilator asynchrony. Curr. Opin. Crit. Care 22(1), 53–59 (2016). https://doi.org/10.1097/MCC.0000000000000270
Chang, D.W.: Clinical Application of Mechanical Ventilation. Cengage Learning (2013)
Daugherty, E.L., Branson, R., Rubinson, L.: Mass casualty respiratory failure. Curr. Opin. Crit. Care 13(1), 51–56 (2007)
Ge, H., et al.: Lung mechanics of mechanically ventilated patients with COVID-19: analytics with high-granularity ventilator waveform data. Front. Med. 7, 541 (2020)
Sassoon, C.S., Foster, G.T.: Patient-ventilator asynchrony. Curr. Opin. Crit. Care 7(1), 28–33 (2001). https://doi.org/10.1097/00075198-200102000-00005
Epstein, S.K.: How often does patient-ventilator asynchrony occur and what are the consequences? Respir. Care 56(1), 25–38 (2011). https://doi.org/10.4187/respcare.01009
Wrigge, H., Girrbach, F., Hempel, G.: Detection of patient-ventilator asynchrony should be improved: and then what? J. Thorac. Dis. 8(12), E1661–E1664 (2016). https://doi.org/10.21037/jtd.2016.12.101
Arellano, D.H.: Identifying patient-ventilator asynchrony using waveform analysis. Palliat. Med. Care: Open Access 4(4), 1–4 (2017). https://doi.org/10.15226/2374-8362/4/4/00147
Fulcher, B.D., Jones, N.S.: Highly comparative feature-based time-series classification. IEEE Trans. Knowl. Data Eng. 26(12), 3026–3037 (2014). https://doi.org/10.1109/tkde.2014.2316504
Mulqueeny, Q., Ceriana, P., Carlucci, A., Fanfulla, F., Delmastro, M., Nava, S.: Automatic detection of ineffective triggering and double triggering during mechanical ventilation. Intensive Care Med. 33(11), 2014–2018 (2007). https://doi.org/10.1007/s00134-007-0767-z
Chen, C.-W., Lin, W.-C., Hsu, C.-H., Cheng, K.-S., Lo, C.-S.: Detecting ineffective triggering in the expiratory phase in mechanically ventilated patients based on airway flow and pressure deflection: Feasibility of using a computer algorithm*. Crit. Care Med. 36(2), 455–461 (2008). https://doi.org/10.1097/01.ccm.0000299734.34469.d9
Cuvelier, A., Achour, L., Rabarimanantsoa, H., Letellier, C., Muir, J.-F., Fauroux, B.: A noninvasive method to identify ineffective triggering in patients with noninvasive pressure support ventilation. Respiration 80(3), 198–206 (2010). https://doi.org/10.1159/000264606
Yu, K.H., Beam, A.L., Kohane, I.S.: Artificial intelligence in healthcare. Nat. Biomed. Eng. 2(10), 719–731 (2018). https://doi.org/10.1038/s41551-018-0305-z
Gholami, B., et al.: Replicating human expertise of mechanical ventilation waveform analysis in detecting patient-ventilator cycling asynchrony using machine learning. Comput. Biol. Med. 97, 137–144 (2018). https://doi.org/10.1016/j.compbiomed.2018.04.016
Rehm, G., et al.: Creation of a robust and generalizable machine learning classifier for patient ventilator asynchrony. Methods Inf. Med. 57(04), 208–219 (2018). https://doi.org/10.3414/me17-02-0012
Zhang, L., et al.: Detection of patient-ventilator asynchrony from mechanical ventilation waveforms using a two-layer long short-term memory neural network. Comput. Biol. Med. 120, 103721 (2020). https://doi.org/10.1016/j.compbiomed.2020.103721
Ching, T., et al.: Opportunities and obstacles for deep learning in biology and medicine: 2019 update (2019)
Quinn, T.P., Jacobs, S., Senadeera, M., Le, V., Coghlan, S.: The three ghosts of medical AI: can the black-box present deliver? Artif. Intell. Med. 124, 102158 (2021). https://doi.org/10.1016/j.artmed.2021.102158
Mulqueeny, Q., et al.: Automated detection of asynchrony in patient-ventilator interaction. In: 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 5324–5327. IEEE, September 2009
Wang, C., Aickelin, U., Luo, L., Ristanoski, G.: Patient-ventilator asynchrony detection via similarity search methods. In: ICMHI 2021 Proceeding, vol. 13, no. 1, pp. 15–20. ACM Press (2021). https://doi.org/10.12720/jait.13.1.15-20
Fulcher, B.D., Little, M.A., Jones, N.S.: Highly comparative time-series analysis: the empirical structure of time series and their methods. J. R. Soc. Interface 10(83), 20130048 (2013). https://doi.org/10.1098/rsif.2013.0048
Hannan, L.M., et al.: Randomised controlled trial of polysomnographic titration of noninvasive ventilation. Eur. Respiratory J. 53(5), 1802118 (2019). https://doi.org/10.1183/13993003.02118-2018
Thille, A.W., Rodriguez, P., Cabello, B., Lellouche, F., Brochard, L.: Patient-ventilator asynchrony during assisted mechanical ventilation. Intensive Care Med. 32(10), 1515–1522 (2006). https://doi.org/10.1007/s00134-006-0301-8
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edn. Springer, New York (2009). https://doi.org/10.1007/978-0-387-84858-7
De Wit, M., Miller, K.B., Green, D.A., Ostman, H.E., Gennings, C., Epstein, S.K.: Ineffective triggering predicts increased duration of mechanical ventilation*. Crit. Care Med. 37(10), 2740–2745 (2009). https://doi.org/10.1097/ccm.0b013e3181a98a05
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Appendix - Description of Signals
Appendix - Description of Signals
Signal name | Description |
|---|---|
Oximetry | Blood oxygen levels, displayed as a percentage |
PtcCO2 | Transcutaneous carbon dioxide |
Leak - Tx | Air leakage from NIV mask |
Pos | Body position sensor: back-supine, front-prone, sides-left and right |
Light | Environmental light sensor (lights “on” or “off”) |
Pmask | NIV mask pressure signal |
Thor | Breathing effort detected by respiratory belt placed over thoracic region |
Abdo | Breathing effort detected by respiratory belt placed over abdominal region |
Flow - Tx | Airflow through nasal prongs |
DB Meter | Decibel meter to detect snoring |
ECG+ECG- | Cardiac activity and heart rate |
EMGs+- EMGs- | Electromyogram - electrodes placed on both sides of the jaw (bilateral masseter muscles) to detect clenching of the jaw (bruxism) during sleep |
E1 | Picks up eye muscle movement (E1 and E2). Electrode placed on outer corner of left eye |
E2 | Electrode placed on outer corner of right eye |
F4-M1 | Electrode placed on right side of head over the frontal area. Note: M1 refers to reference electrode placed over left mastoid bone area behind the left ear |
C4-M1 | Electrode placed on right side of the head, centrally |
O2-M1 | Electrode place on right side of the head, towards the lower back |
dEMG+-dEMG- | Electromyogram - electrodes placed over diaphragm area |
atEMG/L_T3-atEMG | Electromyogram - electrodes placed on left anterior tibialis muscle on the shin to detect periodic limb movement (PLM) during sleep |
atEMG/R_T4-atEMG | Electromyogram-electrodes placed on right anterior tibialis muscle on the shin to detect PLM during sleep |
Nasal pressure | Pressure signal derived from nasal prongs |
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, E., Ristanoski, G., Aickelin, U., Berlowitz, D., Howard, M. (2022). Early Detection and Classification of Patient-Ventilator Asynchrony Using Machine Learning. In: Michalowski, M., Abidi, S.S.R., Abidi, S. (eds) Artificial Intelligence in Medicine. AIME 2022. Lecture Notes in Computer Science(), vol 13263. Springer, Cham. https://doi.org/10.1007/978-3-031-09342-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-09342-5_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09341-8
Online ISBN: 978-3-031-09342-5
eBook Packages: Computer ScienceComputer Science (R0)