Artificial Intelligence-Driven Prognosis of Respiratory Mechanics: Forecasting Tissue Hysteresivity Using Long Short-Term Memory and Continuous Sensor Data
Author:
Othman Ghada Ben1ORCID, Ynineb Amani R.1ORCID, Yumuk Erhan12ORCID, Farbakhsh Hamed1ORCID, Muresan Cristina3ORCID, Birs Isabela Roxana13ORCID, De Raeve Alexandra4ORCID, Copot Cosmin4ORCID, Ionescu Clara M.13ORCID, Copot Dana13ORCID
Affiliation:
1. Department of Electromechanics, System and Metal Engineering, Ghent University, Tech Lane Science Park 125, 9052 Ghent, Belgium 2. Department of Control and Automation Engineering, Istanbul Technical University, Maslak, Istanbul 34469, Turkey 3. Department of Automation, Technical University Cluj-Napoca, Memorandumului Street 20, 400114 Cluj, Romania 4. Fashion, Textiles and Innovation Lab (FTILab+), HOGENT University of Applied Science and Arts, Buchtenstraat 11, 9051 Ghent, Belgium
Abstract
Tissue hysteresivity is an important marker for determining the onset and progression of respiratory diseases, calculated from forced oscillation lung function test data. This study aims to reduce the number and duration of required measurements by combining multivariate data from various sensing devices. We propose using the Forced Oscillation Technique (FOT) lung function test in both a low-frequency prototype and the commercial RESMON device, combined with continuous monitoring from the Equivital (EQV) LifeMonitor and processed by artificial intelligence (AI) algorithms. While AI and deep learning have been employed in various aspects of respiratory system analysis, such as predicting lung tissue displacement and respiratory failure, the prediction or forecasting of tissue hysteresivity remains largely unexplored in the literature. In this work, the Long Short-Term Memory (LSTM) model is used in two ways: (1) to estimate the hysteresivity coefficient η using heart rate (HR) data collected continuously by the EQV sensor, and (2) to forecast η values by first predicting the heart rate from electrocardiogram (ECG) data. Our methodology involves a rigorous two-hour measurement protocol, with synchronized data collection from the EQV, FOT, and RESMON devices. Our results demonstrate that LSTM networks can accurately estimate the tissue hysteresivity parameter η, achieving an R2 of 0.851 and a mean squared error (MSE) of 0.296 for estimation, and forecast η with an R2 of 0.883 and an MSE of 0.528, while significantly reducing the number of required measurements by a factor of three (i.e., from ten to three) for the patient. We conclude that our novel approach minimizes patient effort by reducing the measurement time and the overall ambulatory time and costs while highlighting the potential of artificial intelligence methods in respiratory monitoring.
Funder
Ghent University special research Romanian Ministry of Research, Innovation, and Digitization Flanders Research Foundation
Reference42 articles.
1. Andreozzi, E., Gargiulo, G.D., Esposito, D., and Bifulco, P. (2021). A novel broadband forcecardiography sensor for simultaneous monitoring of respiration, infrasonic cardiac vibrations and heart sounds. Front. Physiol., 12. 2. Adaptive excitation signals for low-frequency forced oscillation technique measurements in patients;Busschots;IEEE Trans. Instrum. Meas.,2021 3. Application of the forced oscillation technique in diagnosing and monitoring of asthma in preschool children;Dymek;Adv. Respir. Med.,2019 4. Bhattarai, P., Myers, S., Chia, C., Weber, H.C., Young, S., Williams, A.D., and Sohal, S.S. (2020). Clinical application of forced oscillation technique (FOT) in early detection of airway changes in smokers. J. Clin. Med., 9. 5. Ghita, M., Copot, D., Ghita, M., Derom, E., and Ionescu, C. (2019). Low Frequency Forced Oscillation Lung Function Test Can Distinguish Dynamic Tissue Non-linearity in COPD Patients. Front. Physiol., 10.
|
|