An Apparatus for the Simulation of Breathing Disorders: Physically Meaningful Generation of Surrogate Data

09/14/2021 ∙ by Harry J. Davies, et al. ∙ 0

Whilst debilitating breathing disorders, such as chronic obstructive pulmonary disease (COPD), are rapidly increasing in prevalence, we witness a continued integration of artificial intelligence into healthcare. While this promises improved detection and monitoring of breathing disorders, AI techniques are "data hungry" which highlights the importance of generating physically meaningful surrogate data. Such domain knowledge aware surrogates would enable both an improved understanding of respiratory waveform changes with different breathing disorders and different severities, and enhance the training of machine learning algorithms. To this end, we introduce an apparatus comprising of PVC tubes and 3D printed parts as a simple yet effective method of simulating both obstructive and restrictive respiratory waveforms in healthy subjects. Independent control over both inspiratory and expiratory resistances allows for the simulation of obstructive breathing disorders through the whole spectrum of FEV1/FVC spirometry ratios (used to classify COPD), ranging from healthy values to values seen in severe chronic obstructive pulmonary disease. Moreover, waveform characteristics of breathing disorders, such as a change in inspiratory duty cycle or peak flow are also observed in the waveforms resulting from use of the artificial breathing disorder simulation apparatus. Overall, the proposed apparatus provides us with a simple, effective and physically meaningful way to generate surrogate breathing disorder waveforms, a prerequisite for the use of artificial intelligence in respiratory health.

READ FULL TEXT VIEW PDF
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.

I Introduction

The prevalence of obstructive breathing disorders such as chronic obstructive pulmonary disease (COPD) and asthma are increasing rapidly [12], whilst other breathing disorders such as the restrictive pulmonary fibrosis (PF) continue to suffer from poor clinical outcomes and a lack of treatment options [5]. Therefore, the understanding of breathing mechanics and resulting respiratory waveforms for different breathing disorders is paramount for the classification of breathing disorders, both in terms of screening and in terms of identifying severity. To this end, we propose an apparatus for the artificial simulation of breathing disorders through healthy subjects, both for obstructive and restrictive respiratory diseases and reliably generating the whole spectrum range of disease severities.

I-a Changes to breathing with obstruction and restriction

Chronic obstructive pulmonary disease (COPD) is caused by an increased inflammatory response in the lungs which leads to obstructed airflow [10]. Chronic obstructive pulmonary disease encompasses both emphysema, defined by a breakdown in the elastic structure of the alveolar walls [8] and bronchitis, defined by increased mucus secretion in the lungs [3]. When we expire, the airways narrow due to reduced pressure, and thus if airway obstruction exists it is exaggerated during expiration. This explains why patients with COPD generally take longer to breath out than breathe in, and can generate higher inspiratory peak flows than expiratory peak flows. The COPD can be diagnosed with a spirometry test, which measures the ratio of volume during forced expiration in one second (FEV1), against forced vital capacity (FVC), whereby COPD is defined as an FEV1/FVC<0.7 [7]. More severe cases of COPD are generally reflected in lower FEV1/FVC ratios. The increased effects of obstruction during expiration also lead to a decreased inspiration time (TI) in comparison with the overall breathing time (TTOT) as it takes longer to breathe out. The ratio TI/TTOT, known as the inspiratory duty cycle, is lower in patients with COPD [9] [11].

An example of a restrictive lung disease is pulmonary fibrosis (scaring of the lungs). In this case, there is no obstruction of airways, but a restriction that applies equally to both inspiration and expiration. Whilst diagnosis of pulmonary fibrosis requires a multidisciplinary approach, such as the use of CT scans [5], spirometry tests will generally show healthy FEV1/FVC ratios, but lower peak flows for both inspiration and expiration as well as a greatly reduced vital lung capacity.

Fig. 1: Block diagram for the proposed breathing disorder simulation apparatus. (a) The mouth input. (b) One-way valves in different directions for inspiration and expiration, comprised of a light PVC ball, a cone shaped funnel with a hole that is slightly smaller in diameter than the ball, and a fine mesh with allows air through but not the ball. (c) Tubes for both inspiration and expiration which can be easily swapped out for tubes of different diameter, allowing for independent control of resistances to inspiration and expiration. (d) A digital flow meter to record spirometry waveforms.

I-B Artificial changes to breathing resistance

Previously, resistance to breathing has been considered both to measure the strength and endurance of lungs in subjects, and also as a potential avenue to train lungs for increases in strength and endurance. A portable apparatus for collecting respiratory gas was designed in the early 1970s, comprising of tubes with 32mm diameter (giving negligible resistance to breathing) and a one-way valve so that gas could be stored when breathing out, but new air would be breathed in [1]. This apparatus was adapted in the mid to late 1970s by replacing the 32mm inspiratory tube with different smaller tube diameters (14mm, 11mm or 8mm), and breathing under different inspiratory resistances was examined in endurance athletes [2]. A similar apparatus with four different inspiratory tube sizes was used to investigate the lung strength of a group of British coal miners over the age of 45 [6]. More recently, resistance has been applied to both inspiration and expiration through masks that have multiple inspiratory and expiratory valves, with the desire to train lungs for increased strength and endurance [4].

Different from the existing set-ups, the apparatus presented in this paper is capable of providing different resistances to both inspiration and expiration independently, with the aim of simulating the respiratory waveforms of different breathing disorders.

The simulation of breathing disorders through healthy subjects has the following benefits:

  • Ability to collect vast amounts data by expanding the subject pool to include healthy individuals;

  • Full control over breathing resistances for both inspiration and expiration;

  • Multiple breathing disorders of different severities can be investigated on the same healthy individual, thus keeping individual physiological differences constant;

  • A controlled environment makes it easier to investigate how other physiological measures vary with resistance to breathing;

  • A physically meaningful way to generate surrogate breathing disorder waveform data for both training and testing machine learning models.

Fig. 2: Exemplar recordings from a single subject. (a) FEV1/FVC values calculated for different expiratory tube diameters, highlighting the area in red as FEV1/FVC<0.7 (COPD ratios). (b) A normal breathing recording with an 8mm diameter inspiratory tube and an 8mm diameter expiratory tube. (c) A normal breathing recording with an 8mm diameter inspiratory tube and a 3mm diameter expiratory tube. This resembles a typical inspiratory duty cycle seen in severe cases of COPD.

Ii Apparatus Design

The apparatus consists of 3D printed parts and PVC tubes. It has a single input tube which a subject breathes in and out of. This is connected to two one-way valves facing in opposite directions to switch the airflow path depending on inspiration and expiration. The valves consist of light PVC ball in a 3D printed cone shaped funnel with a hole slightly smaller than the diameter of the ball. Securing the ball in the funnel is a fine mesh in which air can pass through but the ball cannot. Depending on the orientation of the valve, either positive or negative airflow will seal the hole with the ball, thus preventing air from passing through. It is important that the ball is light so that it will move easily to the hole under low pressures.

Connected to the inspiratory valve is an inspiratory tube which can be varied in diameter, as is the case with the expiratory valve and expiratory tube. The largest tube diameter is 25mm, which is considered as very low resistance to breathing. The smallest tube diameter used is 3mm, which provides very challenging resistance to breathing. To minimise the resistance of the whole apparatus, 3D printed parts also have an internal diameter of 25mm. Both the inspiratory and expiratory tubes are then connected to an output tube which leads into a SFM3200 digital flow meter by Sensiron (Stäfa, Switzerland) to record the breathing flow. The entire apparatus is shown in Fig. 1. The digital flow meter was connected to an Arduino Uno by Arduino (Somerville, MA, USA), which sampled flow values at a sampling frequency of 20Hz and displayed them on a computer monitor.

Trial recordings were performed on 8 subjects (4 male, 4 female) aged 18-25 years, and included normal breathing under different resistances, as well as breathing in and out as hard as possible for both FEV1/FVC measurements and peak expiratory and inspiratory flow measurements.

The recordings were performed under the Imperial College London ethics committee approval JRCO 20IC6414, and all subjects gave full informed consent.

Iii Results

The apparatus was able to achieve a wide range of FEV1/FVC ratios across all subjects, with an example of the varying ratios in an individual shown in Fig. 2 (a) in which the maximum FEV1/FVC achieved is 0.92 with the 25mm diameter tube, and the minimum is 0.09 with the 3mm diameter tube. Example waveforms presented in Fig. 2 (b) and (c) detail how both flow and expiration varies with an increased expiratory resistance in comparison with inspiratory resistance, with an inspiratory duty cycle of TI/TTOT = 0.46 when resistance to inspiration and expiration is the same, but a mean duty cycle of TI/TTOT = 0.32 when the inspiratory tube is 8mm diameter and the expiratory tube is 3mm diameter.

Iv Conclusion

We have demonstrated a simple yet effective method of simulating both obstructive and restrictive respiratory waveforms in healthy subjects with the use of a tube-based apparatus. Independent control over both in inspiratory and expiratory resistances allows for the simulation respiratory waveforms corresponding to obstructive breathing disorders with a wide range of FEV1/FVC ratios, from healthy values through to values seen in severe chronic obstructive pulmonary disease. Moreover, restrictive breathing disorder waveforms can also be simulated by the increased resistance applied equally to both inspiration and expiration. Notably, this makes it possible for multiple breathing disorders at a range of severities to be investigated in the same individual, allowing the waveform differences due to different tube resistances to be isolated whilst individual physiological differences are kept constant. Importantly, this apparatus provides us with a physically meaningful way to generate surrogate breathing disorder waveforms for testing and training machine learning models for classification of breathing disorders. Finally, this apparatus could serve the educational purpose of illuminating the difficulties that patients with breathing disorders face, both for public health awareness and as a persuasive argument against behaviours which increase the risk of breathing disorders such as smoking.

Acknowledgment

This work was supported by the Racing Foundation grant 285/2018, MURI/EPSRC grant EP/P008461, and the Dementia Research Institute at Imperial College London.

References

  • [1] J. Daniels (1971-07) Portable respiratory gas collection equipment. Journal of Applied Physiology 31 (1), pp. 164–167. Cited by: §I-B.
  • [2] R. H. Dressendorfer, C. E. Wade, and E. M. Bernauer (1977) Combined effects of breathing resistance and hyperoxia on aerobic work tolerance. Journal of Applied Physiology 42 (3), pp. 444–448. External Links: Document Cited by: §I-B.
  • [3] B. E. Heard, V. Khatchatourov, H. Otto, N. V. Putov, and L. Sobin (1979) The morphology of emphysema, chronic bronchitis, and bronchiectasis: definition, nomenclature, and classification.. Journal of Clinical Pathology 32 (9), pp. 882. External Links: Document, Link Cited by: §I-A.
  • [4] S. Kido, Y. Nakajima, T. Miyasaka, Y. Maeda, T. Tanaka, W. Yu, H. Maruoka, and K. Takayanagi (2013-05) Effects of Combined Training with Breathing Resistance and Sustained Physical Exertion to Improve Endurance Capacity and Respiratory Muscle Function in Healthy Young Adults. Journal of Physical Therapy Science 25 (5), pp. 605–610. External Links: Document, ISSN 0915-5287 Cited by: §I-B.
  • [5] T. E. King, A. Pardo, and M. Selman (2011-12) Idiopathic pulmonary fibrosis. The Lancet 378 (9807), pp. 1949–1961. External Links: Document, ISSN 0140-6736 Cited by: §I-A, §I.
  • [6] R. G. Love, D. C. Muir, K. F. Sweetland, R. A. Bentley, and O. G. Griffin (1977-05) Acceptable levels for the breathing resistance of respiratory apparatus: results for men over the age of 45.. Occupational and Environmental Medicine 34 (2), pp. 126–129. External Links: Document, ISSN 1351-0711 Cited by: §I-B.
  • [7] M. Roman-Rodriguez and A. Kaplan (2021) GOLD 2021 Strategy Report: Implications for Asthma–COPD Overlap. International Journal of Chronic Obstructive Pulmonary Disease 16, pp. 1709. External Links: Document, Link Cited by: §I-A.
  • [8] W. M. Thurlbeck and N. L. Müller (1994) Emphysema: definition, imaging, and quantification.. American Journal of Roentgenology 163 (5), pp. 1017–1025. Note: PMID: 7976869 External Links: Document, Link Cited by: §I-A.
  • [9] M. J. Tobin, T. S. Chadha, G. Jenouri, S. J. Birch, H. B. Gazeroglu, and M. A. Sackner (1983) Breathing Patterns: 2. Diseased Subjects. Chest 84 (3), pp. 286–294. External Links: Document, ISSN 0012-3692 Cited by: §I-A.
  • [10] G. Viegi, F. Pistelli, D. L. Sherrill, S. Maio, S. Baldacci, and L. Carrozzi (2007-11) Definition, epidemiology and natural history of COPD. Vol. 30, European Respiratory Society. External Links: Document, ISSN 09031936 Cited by: §I-A.
  • [11] H. Wilkens, B. Weingard, A. Lo Mauro, E. Schena, A. Pedotti, G. W. Sybrecht, and A. Aliverti (2010) Breathing pattern and chest wall volumes during exercise in patients with cystic fibrosis, pulmonary fibrosis and COPD before and after lung transplantation. Thorax 65 (9), pp. 808–814. External Links: Document, ISSN 14683296 Cited by: §I-A.
  • [12] M. Xie, X. Liu, X. Cao, M. Guo, and X. Li (2020-02) Trends in prevalence and incidence of chronic respiratory diseases from 1990 to 2017. Respiratory Research 21 (1), pp. 49. External Links: Document, ISSN 1465993X Cited by: §I.