International Journal of Intelligent Information Systems

| Peer-Reviewed |

Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches

Received: 24 September 2021    Accepted: 21 October 2021    Published: 30 October 2021
Views:       Downloads:

Share This Article

Abstract

The technology of machine learning has been widely applied in several domains and complex medical problems, specifically in chronic obstructive pulmonary disease (COPD). Researchers in the field of respiratory diseases confirm that people who suffer from COPD have high risks when exposed to COVID-19. The most common oncoming COPD exacerbations and COPD symptoms of COVID-19 are congruent. The distinction between COPD exacerbations and COVID-19 with COPD is nearly impossible without testing. This paper proposes a new powerful model for classifying COPD patients with exacerbations and those with COVID-19 using machine learning and deep learning algorithms. The major contribution of this research is the dynamic classification process based on the patient context that can help detect exacerbations or COVID-19 per period. Indeed, Five Machine Learning algorithms are trained, tested and a performant classification model is identified. This prediction model is then associated with a dynamic COPD patient context for monitoring the patient's health status. This model based on the dynamic adaptation mechanism combined with a classification contributes to identifying dynamically COPD exacerbations and COVID-19 symptoms for COPD patients. Indeed, periodically, data on a new patient is injected into the prediction model. At the output of the model, the patient is either classified in the exacerbation category, or classified in the COVID-19 category, or no category. By period. A dynamic dashboard of classified patients is available to help medical staff take appropriate decisions. This approach helps to follow the evolution of COPD patient comorbidities (exacerbation, COVID-19). Finally, classification would allow healthcare stakeholders to provide healthcare service according to the patient’s status. The methodology of research consists of designing and implementing a dynamic model for classifying COPD patients. Since early intervention is associated with improved prognosis, with our solution, healthcare staff can identify COPD patients who are most at risk of developing exacerbation or COVID-19. Consequently, upon admission, this will ensure that these patients receive appropriate care as soon as possible.

DOI 10.11648/j.ijiis.20211005.11
Published in International Journal of Intelligent Information Systems (Volume 10, Issue 5, October 2021)
Page(s) 81-97
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Software Adaptation Mechanism, Deep Learning, Exacerbation, COPD, COVID-19, Prediction

References
[1] Chronic respiratory diseases. Available online: www.who.int/respiratory (accessed on 10-03-2021).
[2] Stiell, I. G.; Perry, J. J.; Clement, C. M.; Brison, R. J.; Rowe, B. H.; Aaron, S. D.; McRae, A. D.; Borgundvaag, B.; Calder, L. A.; Forster, A. J.; et al. Clinical validation of a risk scale for serious outcomes among patients with chronic obstructive pulmonary disease managed in the emergency department. Can. Med Assoc. J. 2018, 190, E1406–E1413, doi: 10.1503/cmaj.180232.
[3] Ajami, H., & Mcheick, H. (2018). Ontology-based model to support ubiquitous healthcare systems for COPD patients. Electronics, 7 (12), 371.
[4] Kouamé, K. M., & Mcheick, H. (2021). An Ontological Approach for Early Detection of Suspected COVID-19 among COPD Patients. Applied System Innovation, 4 (1), 21.
[5] Tal-Singer, R., & Crapo, J. D. (2020). COPD at the time of COVID-19: a COPD Foundation perspective. Chronic Obstructive Pulmonary Diseases: Journal of the COPD Foundation, 7 (2), 73.
[6] Olloquequi, J. (2020). COVID-19 Susceptibility in chronic obstructive pulmonary disease. European journal of clinical investigation, 50 (10), e13382.
[7] Alqahtani, J. S., Oyelade, T., Aldhahir, A. M., Alghamdi, S. M., Almehmadi, M., Alqahtani, A. S.,... & Hurst, J. R. (2020). Prevalence, severity and mortality associated with COPD and smoking in patients with COVID-19: a rapid systematic review and meta-analysis. PloS one, 15 (5), e0233147.
[8] Leung, J. M., Niikura, M., Yang, C. W. T., & Sin, D. D. (2020). COVID-19 and COPD. European Respiratory Journal, 56 (2).
[9] Deslée, G., Zysman, M., Burgel, P. R., Perez, T., Boyer, L., Gonzalez, J., & Roche, N. (2020). Chronic obstructive pulmonary disease and the COVID-19 pandemic: Reciprocal challenges. Respiratory medicine and research, 78, 100764.
[10] Attaway, A. (2020). Management of patients with COPD during the COVID-19 pandemic. Clevel. clin. j. med.
[11] Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K.,... & Dean, J. (2019). A guide to DL in healthcare. Nature medicine, 25 (1), 24-29.
[12] Humphries, S. M., Notary, A. M., Centeno, J. P., Strand, M. J., Crapo, J. D., Silverman, E. K., & Genetic Epidemiology of COPD (COPDGene) Investigators. (2020). DL enables automatic classification of emphysema pattern at CT. Radiology, 294 (2), 434-444.
[13] J. Ying et al., "Classification of Exacerbation Frequency in the COPDGene Cohort Using DL With Deep Belief Networks," in IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 6, pp. 1805-1813, June 2020, doi: 10.1109/JBHI.2016.2642944.
[14] Mohsen, H., El-Dahshan, E. S. A., El-Horbaty, E. S. M., & Salem, A. B. M. (2018). Classification using DL neural networks for brain tumors. Future Computing and Informatics Journal, 3 (1), 68-71.
[15] Altan, G., Kutlu, Y., & Allahverdi, N. (2019). DL on computerized analysis of chronic obstructive pulmonary disease. IEEE journal of biomedical and health informatics, 24 (5), 1344-1350.
[16] Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., & Lungren, M. P. (2018). DL for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practising radiologists. PLoS medicine, 15 (11), e1002686.
[17] Negahdar, M., & Beymer, D. (2019, March). Lung tissue characterization for emphysema differential diagnosis using deep convolutional neural networks. In Medical Imaging 2019: Computer-Aided Diagnosis (Vol. 10950, p. 109503R). International Society for Optics and Photonics.
[18] Wang, Q., Wang, H., Wang, L., & Yu, F. (2020). Diagnosis of Chronic Obstructive Pulmonary Disease Based on Transfer Learning. IEEE Access, 8, 47370-47.
[19] Peng, J., Chen, C., Zhou, M., Xie, X., Zhou, Y., & Luo, C. H. (2020). A machine-learning approach to forecast aggravation risk in patients with acute exacerbation of chronic obstructive pulmonary disease with clinical indicators. Scientific reports, 10 (1), 1-9.
[20] Li, L., Qin, L., Xu, Z., Yin, Y., Wang, X., Kong, B., & Xia, J. (2020). Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology.
[21] Liang, W., Yao, J., Chen, A., Lv, Q., Zanin, M., Liu, J., & He, J. (2020). Early triage of critically ill COVID-19 patients using DL. Nature communications, 11 (1), 1-7.
[22] Nature communications, 11 (1), 1-7. Li, L., Qin, L., Xu, Z., Yin, Y., Wang, X., Kong, B.,... & Xia, J. (2020). Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology.
[23] Fadlullah, Z. M., Tang, F., Mao, B., Kato, N., Akashi, O., Inoue, T., & Mizutani, K. (2017). State-of-the-art DL: Evolving machine intelligence toward tomorrow’s intelligent network traffic control systems. IEEE Communications Surveys & Tutorials, 19 (4), 2432-2455.
[24] Khemphila, A., & Boonjing, V. (2011, August). Heart disease classification using neural network and feature selection. In 2011 21st International Conference on Systems Engineering (pp. 406-409). IEEE.
[25] Bhatia, S., Prakash, P., & Pillai, G. N. (2008, October). SVM based decision support system for heart disease classification with integer-coded genetic algorithm to select critical features. In Proceedings of the world congress on engineering and computer science (pp. 34-38).
[26] Gray, K. R., Aljabar, P., Heckemann, R. A., Hammers, A., Rueckert, D., & Alzheimer's Disease Neuroimaging Initiative. (2013). Random forest-based similarity measures for multi-modal classification of Alzheimer's disease. NeuroImage, 65, 167-175.
[27] Sinha, P., & Sinha, P. (2015). Comparative study of chronic kidney disease prediction using KNN and SVM. International Journal of Engineering Research and Technology, 4 (12), 608-12. To provide personalized care to chronic patients at home. Journal of biomedical informatics, 46 (3), 516-529.
[28] Banu, G. R. (2016). Predicting thyroid disease using linear discriminant analysis (LDA) data mining technique. Commun. Appl. Electron. (CAE), 4, 4-6.
[29] Stekhoven, D. J., & Bühlmann, P. (2012). MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics, 28 (1), 112-118.
[30] Azhagusundari, B., & Thanamani, A. S. (2013). Feature selection based on information gain. International Journal of Innovative Technology and Exploring Engineering (IJITEE), 2 (2), 18-21.
[31] Richhariya, B., Tanveer, M., Rashid, A. H., & Alzheimer’s Disease Neuroimaging Initiative. (2020). Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE). Biomedical Signal Processing and Control, 59, 101903.
[32] Brownlee, J. (2019). Information Gain and Mutual Information for Machine Learning. Preuzeto, 18, 2020.
[33] Python tutoral. Available online: https://data-flair.training/blogs/python-tutorials-home/ (accessed on 21/03/2021).
[34] Brownlee, J. (2016). Machine Learning mastery with python. Machine Learning Mastery Pty Ltd, 527, 100-120.
[35] Alotaibi, A., Shiblee, M., & Alshahrani, A. (2021). Prediction of Severity of COVID-19-Infected Patients Using Machine Learning Techniques. Computers, 10 (3), 31.
[36] Rhee, C. K., Kim, J. W., Yoo, K. H., & Jung, K. S. (2020). Prediction model of COPD acute exacerbation with big data by Machine Learning methods.
[37] Caliendo, M., & Kopeinig, S. (2008). Some practical guidance for the implementation of propensity score matching. Journal of economic surveys, 22 (1), 31-72.
[38] He and E. A. Garcia, Learning from Imbalanced Data, IEEE Transactions on Knowledge and Data Engineering, 21 (2009), No. 9, 1263-1284.
[39] Truica, C. O., & Leordeanu, C. A. (2017). Classification of an imbalanced data set using decision tree algorithms. Univ. Politech. Bucharest Sci. Bull. Ser. C Electr. Eng. Comput. Sci, 79, 69-84.
[40] Brownlee, J. (2020). Imbalanced classification with Python: better metrics, balance skewed classes, cost-sensitive learning. Machine Learning Mastery.
[41] Amalia Luque et al., The impact of class imbalance in classification performance metrics based on the binary confusion matrix, Pattern Recognition, Elsevier, 91 (2019) 216–231.
[42] Alberto Fernández et al., Analysing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approaches, Knowledge-Based Systems, Elsevier, 42 (2013) 97–110.
[43] Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011.
[44] Esteban, Cristobal and Moraza, Javier and Esteban, Cristobal and Sancho, Fernando and Aburto, Myriam and Aramburu, Amaia and Goiria, Begona and Garcia-Loizaga, Amaia and Capelastegui, Alberto,” Machine learning for COPD exacerbation prediction,” European Respiratory Journal, vol. 46, 2015.
[45] Jaap CA Trappenburg, Irene Touwen, Gerdien H de Weert-van Oene, Jean Bourbeau, Evelyn M Monninkhof, Theo JM Verheij, Jan- Willem J Lammers, Augustinus JP Schrijvers, ”Detecting exacerbations using the Clinical COPD Questionnaire,” Health Qual Life Outcomes, vol. 8, no. 102, 2010.
[46] Bertens, L. C. M.; Reitsma, J. B.; Moons, K. G. M.; van, M. Y.; Lammers, J. J.; Broekhuizen, B.; Hoes, A. W.; Ru, tten F. H., ”Development and validation of a model to predict the risk of exacerbations in chronic obstructive pulmonary disease,” Int J Chron Obstruct Pulmon Dis., vol. 8, p. 493499, 2013.
Author Information
  • Computer Science and Mathematics Department, University of Québec, Chicoutimi, Canada

  • Computer Science and Mathematics Department, University of Québec, Chicoutimi, Canada

Cite This Article
  • APA Style

    Konan-Marcelin Kouamé, Hamid Mcheick. (2021). Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches. International Journal of Intelligent Information Systems, 10(5), 81-97. https://doi.org/10.11648/j.ijiis.20211005.11

    Copy | Download

    ACS Style

    Konan-Marcelin Kouamé; Hamid Mcheick. Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches. Int. J. Intell. Inf. Syst. 2021, 10(5), 81-97. doi: 10.11648/j.ijiis.20211005.11

    Copy | Download

    AMA Style

    Konan-Marcelin Kouamé, Hamid Mcheick. Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches. Int J Intell Inf Syst. 2021;10(5):81-97. doi: 10.11648/j.ijiis.20211005.11

    Copy | Download

  • @article{10.11648/j.ijiis.20211005.11,
      author = {Konan-Marcelin Kouamé and Hamid Mcheick},
      title = {Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches},
      journal = {International Journal of Intelligent Information Systems},
      volume = {10},
      number = {5},
      pages = {81-97},
      doi = {10.11648/j.ijiis.20211005.11},
      url = {https://doi.org/10.11648/j.ijiis.20211005.11},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.ijiis.20211005.11},
      abstract = {The technology of machine learning has been widely applied in several domains and complex medical problems, specifically in chronic obstructive pulmonary disease (COPD). Researchers in the field of respiratory diseases confirm that people who suffer from COPD have high risks when exposed to COVID-19. The most common oncoming COPD exacerbations and COPD symptoms of COVID-19 are congruent. The distinction between COPD exacerbations and COVID-19 with COPD is nearly impossible without testing. This paper proposes a new powerful model for classifying COPD patients with exacerbations and those with COVID-19 using machine learning and deep learning algorithms. The major contribution of this research is the dynamic classification process based on the patient context that can help detect exacerbations or COVID-19 per period. Indeed, Five Machine Learning algorithms are trained, tested and a performant classification model is identified. This prediction model is then associated with a dynamic COPD patient context for monitoring the patient's health status. This model based on the dynamic adaptation mechanism combined with a classification contributes to identifying dynamically COPD exacerbations and COVID-19 symptoms for COPD patients. Indeed, periodically, data on a new patient is injected into the prediction model. At the output of the model, the patient is either classified in the exacerbation category, or classified in the COVID-19 category, or no category. By period. A dynamic dashboard of classified patients is available to help medical staff take appropriate decisions. This approach helps to follow the evolution of COPD patient comorbidities (exacerbation, COVID-19). Finally, classification would allow healthcare stakeholders to provide healthcare service according to the patient’s status. The methodology of research consists of designing and implementing a dynamic model for classifying COPD patients. Since early intervention is associated with improved prognosis, with our solution, healthcare staff can identify COPD patients who are most at risk of developing exacerbation or COVID-19. Consequently, upon admission, this will ensure that these patients receive appropriate care as soon as possible.},
     year = {2021}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches
    AU  - Konan-Marcelin Kouamé
    AU  - Hamid Mcheick
    Y1  - 2021/10/30
    PY  - 2021
    N1  - https://doi.org/10.11648/j.ijiis.20211005.11
    DO  - 10.11648/j.ijiis.20211005.11
    T2  - International Journal of Intelligent Information Systems
    JF  - International Journal of Intelligent Information Systems
    JO  - International Journal of Intelligent Information Systems
    SP  - 81
    EP  - 97
    PB  - Science Publishing Group
    SN  - 2328-7683
    UR  - https://doi.org/10.11648/j.ijiis.20211005.11
    AB  - The technology of machine learning has been widely applied in several domains and complex medical problems, specifically in chronic obstructive pulmonary disease (COPD). Researchers in the field of respiratory diseases confirm that people who suffer from COPD have high risks when exposed to COVID-19. The most common oncoming COPD exacerbations and COPD symptoms of COVID-19 are congruent. The distinction between COPD exacerbations and COVID-19 with COPD is nearly impossible without testing. This paper proposes a new powerful model for classifying COPD patients with exacerbations and those with COVID-19 using machine learning and deep learning algorithms. The major contribution of this research is the dynamic classification process based on the patient context that can help detect exacerbations or COVID-19 per period. Indeed, Five Machine Learning algorithms are trained, tested and a performant classification model is identified. This prediction model is then associated with a dynamic COPD patient context for monitoring the patient's health status. This model based on the dynamic adaptation mechanism combined with a classification contributes to identifying dynamically COPD exacerbations and COVID-19 symptoms for COPD patients. Indeed, periodically, data on a new patient is injected into the prediction model. At the output of the model, the patient is either classified in the exacerbation category, or classified in the COVID-19 category, or no category. By period. A dynamic dashboard of classified patients is available to help medical staff take appropriate decisions. This approach helps to follow the evolution of COPD patient comorbidities (exacerbation, COVID-19). Finally, classification would allow healthcare stakeholders to provide healthcare service according to the patient’s status. The methodology of research consists of designing and implementing a dynamic model for classifying COPD patients. Since early intervention is associated with improved prognosis, with our solution, healthcare staff can identify COPD patients who are most at risk of developing exacerbation or COVID-19. Consequently, upon admission, this will ensure that these patients receive appropriate care as soon as possible.
    VL  - 10
    IS  - 5
    ER  - 

    Copy | Download

  • Sections