IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0211413.html
   My bibliography  Save this article

Correlating exhaled aerosol images to small airway obstructive diseases: A study with dynamic mode decomposition and machine learning

Author

Listed:
  • Jinxiang Xi
  • Weizhong Zhao

Abstract

Background: Exhaled aerosols from lungs have unique patterns, and their variation can be correlated to the underlying lung structure and associated abnormities. However, it is challenging to characterize such aerosol patterns and differentiate their difference because of their complexity. This challenge is even greater for small airway diseases, where the disturbance signals are weak. Objectives and methods: The objective of this study is exploiting different feature extraction algorithms to develop a practical classifier to diagnose obstructive lung diseases using exhaled aerosol images. These include proper orthogonal decomposition (POD), principal component analysis (PCA), dynamic mode decomposition (DMD), and DMD with control (DMDC). Aerosol images were generated via physiology-based simulations in one normal and four diseased airway models in G7-9 bronchioles. The image data were classified using both the support vector machine (SVM) and random forest (RF) algorithms. The effectiveness of different features was evaluated by classification accuracy and misclassification rate. Findings: Results show a significantly higher performance using dynamic feature extractions (DMD and DMDC) than static algorithms (POD and PCA). Adding the control variables to DMD further improved classification accuracy. Comparing the classification methods, RF persistently outperformed SVM for all types of features considered. While the performance of RF constantly increased with the number of features retained, the performance of SVM peaked at 50 and decreased thereafter. The 5-class classification accuracy was 94.8% using the DMDC-RF model and 93.0% using the DMD-RF model, both of which were higher than 87.0% in the previous study that used fractal dimension features. Conclusion: Considering that disease progression is inherently a dynamic process, DMD(C)-based feature extraction preserves temporal information and is preferred over POD and PCA. Compared with hand-crafted features like fractals, feature extraction by DMD and DMDC is automatic and more accurate.

Suggested Citation

  • Jinxiang Xi & Weizhong Zhao, 2019. "Correlating exhaled aerosol images to small airway obstructive diseases: A study with dynamic mode decomposition and machine learning," PLOS ONE, Public Library of Science, vol. 14(1), pages 1-22, January.
  • Handle: RePEc:plo:pone00:0211413
    DOI: 10.1371/journal.pone.0211413
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0211413
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0211413&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0211413?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Hua, Jia-Chen & Roy, Sukesh & McCauley, Joseph L. & Gunaratne, Gemunu H., 2016. "Using dynamic mode decomposition to extract cyclic behavior in the stock market," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 448(C), pages 172-180.
    2. Jinxiang Xi & Weizhong Zhao & Jiayao Eddie Yuan & JongWon Kim & Xiuhua Si & Xiaowei Xu, 2015. "Detecting Lung Diseases from Exhaled Aerosols: Non-Invasive Lung Diagnosis Using Fractal Analysis and SVM Classification," PLOS ONE, Public Library of Science, vol. 10(9), pages 1-19, September.
    3. Jinxiang Xi & Xiuhua A Si & JongWon Kim & Edward Mckee & En-Bing Lin, 2014. "Exhaled Aerosol Pattern Discloses Lung Structural Abnormality: A Sensitivity Study Using Computational Modeling and Fractal Analysis," PLOS ONE, Public Library of Science, vol. 9(8), pages 1-12, August.
    4. Jordan Mann & J. Nathan Kutz, 2016. "Dynamic mode decomposition for financial trading strategies," Quantitative Finance, Taylor & Francis Journals, vol. 16(11), pages 1643-1655, November.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jinxiang Xi & Xiuhua April Si, 2018. "Review of Feature Extraction from Exhaled Aerosol Fingerprints to Diagnose Lung Structural Remolding," Biomedical Journal of Scientific & Technical Research, Biomedical Research Network+, LLC, vol. 11(3), pages 8504-8508, November.
    2. Elmore, Clay T. & Dowling, Alexander W., 2021. "Learning spatiotemporal dynamics in wholesale energy markets with dynamic mode decomposition," Energy, Elsevier, vol. 232(C).
    3. Sijilmassi, Ouafa & López Alonso, José-Manuel & Del Río Sevilla, Aurora & Barrio Asensio, María del Carmen, 2020. "Multifractal analysis of embryonic eye structures from female mice with dietary folic acid deficiency. Part I: Fractal dimension, lacunarity, divergence, and multifractal spectrum," Chaos, Solitons & Fractals, Elsevier, vol. 138(C).
    4. Ausloos, Marcel & Cerqueti, Roy & Bartolacci, Francesca & Castellano, Nicola G., 2018. "SME investment best strategies. Outliers for assessing how to optimize performance," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 509(C), pages 754-765.
    5. Avalos, Edgar & Datta, Amitava & Rosato, Anthony D. & Blackmore, Denis & Sen, Surajit, 2020. "Dynamics in a confined mass–spring chain with 1∕r repulsive potential: Strongly nonlinear regime," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 553(C).
    6. Mohamed Talaat & Xiuhua Si & Jinxiang Xi, 2023. "Datasets of Simulated Exhaled Aerosol Images from Normal and Diseased Lungs with Multi-Level Similarities for Neural Network Training/Testing and Continuous Learning," Data, MDPI, vol. 8(8), pages 1-13, July.
    7. Gyurhan Nedzhibov, 2024. "Delay-Embedding Spatio-Temporal Dynamic Mode Decomposition," Mathematics, MDPI, vol. 12(5), pages 1-18, March.
    8. Jinxiang Xi & Weizhong Zhao & Jiayao Eddie Yuan & JongWon Kim & Xiuhua Si & Xiaowei Xu, 2015. "Detecting Lung Diseases from Exhaled Aerosols: Non-Invasive Lung Diagnosis Using Fractal Analysis and SVM Classification," PLOS ONE, Public Library of Science, vol. 10(9), pages 1-19, September.
    9. Rubén Ibáñez & Emmanuelle Abisset-Chavanne & Amine Ammar & David González & Elías Cueto & Antonio Huerta & Jean Louis Duval & Francisco Chinesta, 2018. "A Multidimensional Data-Driven Sparse Identification Technique: The Sparse Proper Generalized Decomposition," Complexity, Hindawi, vol. 2018, pages 1-11, November.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0211413. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.