Approaching Automated COPD Treatment Based on Markov Decision Process
2023 IEEE 64th International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS 2023): Proceedings 2023
Dmitrijs Bļizņuks, Jurijs Čižovs, Davis Freimanis, Dana Zarina, Artis Svaza

This paper presents an innovative approach to automate the treatment of sleep apnea and Chronic Obstructive Pulmonary Disease (COPD) through the application of Continuous Positive Airway Pressure (CPAP) and/or Bilevel Positive Airway Pressure (BiPAP) machines. Recognizing the constraints posed by moderate to severe cases that demand round-the-clock healthcare professional supervision, this study aims to increase the utility and availability of PAP machines by automating the treatment process. We introduce a hypothesis centering around conceptualizing the treatment process as a Markov Decision Process (MDP). Traditionally, the construction of an MDP graph requires environmental interaction. However, in this specific context, where the environment pertains to patient treatment, we propose a method to construct the graph drawing from expert knowledge and treatment records of a select group of patients. This model fosters an environment for future enhancement and refinement of apnea/COPD treatment. Ultimately, the goal is to streamline the treatment process, accelerating patient condition normalization, and reducing the necessity for numerous interventions. This proposed automated approach has potential implications for enhancing patient care and optimizing health care resources. © 2023 IEEE.


Keywords
Apnea; Continuous Positive Airway Pressure; Markov Decision Process; Treatment Automation
DOI
10.1109/ITMS59786.2023.10317773
Hyperlink
https://ieeexplore.ieee.org/document/10317773

Bļizņuks, D., Čižovs, J., Freimanis, D., Zarina, D., Svaza, A. Approaching Automated COPD Treatment Based on Markov Decision Process. In: 2023 IEEE 64th International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS 2023): Proceedings, Latvia, Riga, 5-6 October, 2023. Piscataway: IEEE, 2023, pp.1-10. ISBN 979-8-3503-7030-0. e-ISBN 979-8-3503-7029-4. ISSN 2771-6953. e-ISSN 2771-6937. Available from: doi:10.1109/ITMS59786.2023.10317773

Publication language
English (en)
The Scientific Library of the Riga Technical University.
E-mail: uzzinas@rtu.lv; Phone: +371 28399196