Monitoring Pressure in Controlled Ventilator System under Different Lung Settings

Authors

  • Palak Meena  Department of Information Technology Delhi Technological University, New Delhi, India
  • Palak Sharma  Department of Information Technology Delhi Technological University, New Delhi, India
  • Kapil Sharma  Department of Information Technology Delhi Technological University, New Delhi, India

Keywords:

Mechanical Ventilator System, Sedated Artificial Lung, Time-Series Prediction, Machine Learning, Deep Learning, Air Pressure, Covid-19 Variants.

Abstract

To support the weak human lungs with supply of continuous airway pressure in respiratory system throughout the time when patient is on life-support is quite a daunting and people-driven job. To reduce the stress on few doctors and nurses of saving innumerable lives in the time when the world is grappling with Covid-19 and its new deadly variants after every six months. In order to save patients life developing automated ventilation system is the need of the hour. We collected data from several simulations of test lung under different conditions. After preprocessing this dataset using NLP, cross-validation of train and test set. A range of different Machine Learning and Deep Neural Network Models are tried as they can better generalize across lungs with varying characteristics, we scored these models against several evaluation metrics such as MAE, MSE, RMSE. Lastly, we selected best model to predict the target pressure in the respiratory circuit. Through exhaustive clinical tests and accurate medical advice, it is practically possible to bring these results into practical application in future.

References

  1. PVP1–The People’s Ventilator Project: A fully open, low-cost, pressure-controlled ventilator. Julienne LaChance, Tom J. Zajdel, Manuel Schottdorf, Jonny L. Saunders, Sophie Dvali, Chase Marshall, Lorenzo Seirup, Daniel A. Notterman, Daniel J. Cohen medRxiv 2020.10.02.20206037; DOI: https://doi.org/10.1101/2020.10.02.20206037.
  2. Oruganti Venkata SS, Koenig A, Pidaparti RM. Me- chanical Ventilator Parameter Estimation for Lung Health through Machine Learning. Bioengineering (Basel, Switzerland). 2021 May;8(5). DOI: 10.3390/bioengineer- ing8050060. PMID: 34067153; PMCID: PMC8150272.
  3. Supreeth P. Shashikumar, Gabriel Wardi, Paulina Paul, Morgan Carlile, Laura N. Brenner, Kathryn A. Hib- bert, Crystal M. North, Shibani S. Mukerji, Gregory K. Robbins, Yu-Ping Shao, M. Brandon Westover, Shamim Nemati, Atul Malhotra, Development and Prospective Validation of a Deep Learning Algorithm for Predicting Need for Mechanical Ventilation,Chest,Volume 159, Issue 6,2021
  4. Sanjay S.O., Pidaparti R.M. Graded Particle Swarm Op- timization (GPSO); Proceedings of the 2016 Interna- tional Conference on Robotics: Current Trends and Future Challenges (RCTFC); Thanjavur, India. 19–20 December 2016;
  5. Kulkarni AR, Athavale AM, Sahni A, et alDeep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with Covid- 19BMJ Innovations 2021;7:261-270.
  6. Chen T, Guestrin C. XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; San Francisco, California, USA: Association for Computing Machinery; 2016.
  7. Arvind V, Kim JS, Cho BH, Geng E, Cho SK. De- velopment of a machine learning algorithm to predict intubation among hospitalized patients with COVID-19. Journal of Critical Care. 2021; 62:25–30. https:// doi.org/10.1016/j.jcrc.2020.10.033 PMID: 33238219
  8. Siami-Namini, Sima et al. “The Performance of LSTM and BiLSTM in the Forecasting Time Series.” 2019 IEEE International Conference on Big Data (Big Data) (2019): 3285-3292.
  9. Rehm GB, Kuhn BT, Nguyen J, Anderson NR, Chuah CN, Adams JY. Improving Mechanical Ventilator Clin- ical Decision Support Systems with a Machine Learn- ing Classifier for Determining Ventilator Mode. Stud Health Technol Inform. 2019 Aug 21;264:318-322. doi: 10.3233/SHTI190235. PMID: 31437937
  10. Yu L, Halalau A, Dalal B, Abbas AE, Ivascu F, Amin M, et al. (2021) Machine learning methods to predict mechanical ventilation and mortality in pa- tients with COVID-19. PLoS ONE 16(4): e0249285. https://doi.org/10.1371/journal.pone.0249285
  11. Lin M-Y, Li C-C, Lin P-H, Wang J-L, Chan M-C, Wu C- L and Chao W-C (2021) Explainable Machine Learning to Predict Successful Weaning Among Patients Requiring Prolonged Mechanical Ventilation: A Retrospective Co- hort Study in Central Taiwan. Front. Med. 8:663739. doi: 10.3389/fmed.2021.663739
  12. Jia Y, Kaul C, Lawton T, Murray-Smith R, Habli I. Prediction of weaning from mechanical ventilation us- ing Convolutional Neural Networks. Artif Intell Med. 2021 Jul;117:102087. doi: 10.1016/j.artmed.2021.102087. Epub 2021 May 5. PMID: 34127233.
  13. Chang, W.; Ji, X.; Wang, L.; Liu, H.; Zhang, Y.; Chen, B.; Zhou, S. A Machine-Learning Method of Predicting Vital Capacity Plateau Value for Ventilatory Pump Fail- ure Based on Data Mining. Healthcare 2021, 9, 1306. https://doi.org/10.3390/healthcare9101306
  14. Rehm GB, Kuhn BT, Nguyen J, Anderson NR, Chuah CN, Adams JY. Improving Mechanical Ventilator Clin- ical Decision Support Systems with a Machine Learn- ing Classifier for Determining Ventilator Mode. Stud Health Technol Inform. 2019 Aug 21;264:318-322. doi: 10.3233/SHTI190235. PMID: 31437937.
  15. Strodthoff, Claas Frerichs, Ine´z Weiler, Nor- bert Bergh, Bjo¨rn. (2021). Predicting and simulating effects of PEEP changes with machine learning. 10.1101/2021.01.28.21250212.
  16. Zhang L, Mao K, Duan K, Fang S, Lu Y, Gong Q, Lu F, Jiang Y, Jiang L, Fang W, Zhou X, Wang J, Fang L, Ge H, Pan Q. Detection of patient-ventilator asynchrony from mechanical ventilation waveforms us- ing a two-layer long short-term memory neural net- work. Comput Biol Med. 2020 May; 120:103721. doi: 10.1016/j.compbiomed.2020.103721. Epub 2020 Mar 26. PMID: 32250853
  17. Zhang, K., Karanth, S., Patel, B., Murphy, R., Jiang, X. (2021). Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network. arXiv preprint arXiv:2102.01147.
  18. Oruganti Venkata SS, Koenig A, Pidaparti RM. Me- chanical Ventilator Parameter Estimation for Lung Health through Machine Learning. Bioengineering (Basel). 2021 May 7;8(5):60. doi: 10.3390/bioengineering8050060. PMID: 34067153; PMCID: PMC8150272.
  19. Machine Learning for Mechanical Ventilation Control Daniel Suo, Cyril Zhang, Paula Gradu, Udaya Ghai, Xinyi Chen, Edgar Minasyan, Naman Agarwal, Karan Singh, Julienne LaChance, Tom Zajdel, Manuel Schottdorf, Daniel Cohen, Elad Hazan medRxiv 2021.02.26.21252524; doi: https://doi.org/10.1101/2021.02.26.21252524
  20. Schalekamp, Steven Huisman, Merel Dijk, Rogier Boomsma, Martijn Jorge, Pedro Boer, Wytze Herder, Gerada Bonarius, Marja Groot, Oscar Jong, Eefje Schreuder, Anton Schaefer-Prokop, Cornelia. (2020). Model-based Prediction of Critical Illness in Hospital- ized Patients with COVID-19. Radiology. 298. 202723. 10.1148/radiol.2020202723.
  21. Cvitkovic, Milan. “Supervised Learning on Rela- tional Databases with Graph Neural Networks.” ArXiv abs/2002.02046 (2020): n. pag.
  22. Sathesh, A. ”Computer Vision on IOT Based Patient Preference Management System.” Journal of Trends in Computer Science and Smart Technology 2, no. 2 (2020): 68-77.
  23. Murthy, Shrujana, and C. R. Kavitha. ”A Smart and Secure Framework for IoT Device Based Multimedia Medical Data.” In International Conference On Computa- tional Vision and Bio Inspired Computing, pp. 583-588. Springer, Cham, 2019.
  24. P. Meena, P. Sharma and K. Sharma, ”Optimizing Control of IOT Device using Traditional Machine Learning Mod- els and Deep Neural Networks,” 2022 6th International Conference on Computing Methodologies and Commu- nication (ICCMC), 2022, pp. 445-451, doi: 10.1109/IC- CMC53470.2022.9753943.

International Journal of Scientific Research in Science, Engineering and Technology

Downloads

Published

2023-08-30

Issue

Volume 10, Issue 4, July-August-2023

Section

Research Articles

License

Copyright (c) IJSRSET

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Palak Meena, Palak Sharma, Kapil Sharma "Monitoring Pressure in Controlled Ventilator System under Different Lung Settings" International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 10, Issue 4, pp.98-108, July-August-2023.