Severity classification of chronic obstructive pulmonary disease based on deep learning_Journal of Biomedical Engineering

Authors：

 YING Jun ^1,3 , YANG Ceyuan ² , LI Quanzheng ³ , XUE Wanguo ¹ , LI Tanshi ¹ , CAO Wenzhe ¹

1. General Hospital of PLA, Beijing 100853, P.R.China;
2. NO.422 Hospital of PLA, Zhanjiang 524005, P.R.China;
3. Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA;

Corresponding author：

YING Jun, Email: yingjun301@sina.com

Keywords：

chronic obstructive pulmonary disease; The Global Initiative for Chronic Obstructive Lung Disease classification; machine learning; deep learning; deep belief networks

DOI：

10.7507/1001-5515.201604061

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

In this paper, a deep learning method has been raised to build an automatic classification algorithm of severity of chronic obstructive pulmonary disease. Large sample clinical data as input feature were analyzed for their weights in classification. Through feature selection, model training, parameter optimization and model testing, a classification prediction model based on deep belief network was built to predict severity classification criteria raised by the Global Initiative for Chronic Obstructive Lung Disease (GOLD). We get accuracy over 90% in prediction for two different standardized versions of severity criteria raised in 2007 and 2011 respectively. Moreover, we also got the contribution ranking of different input features through analyzing the model coefficient matrix and confirmed that there was a certain degree of agreement between the more contributive input features and the clinical diagnostic knowledge. The validity of the deep belief network model was proved by this result. This study provides an effective solution for the application of deep learning method in automatic diagnostic decision making.

Citation： YING Jun, YANG Ceyuan, LI Quanzheng, XUE Wanguo, LI Tanshi, CAO Wenzhe. Severity classification of chronic obstructive pulmonary disease based on deep learning. Journal of Biomedical Engineering, 2017, 34(6): 842-849. doi: 10.7507/1001-5515.201604061 Copy

1.	Criner G J, Bourbeau J, Diekemper R L, et al. Prevention of acute exacerbations of COPD: American College of Chest Physicians and Canadian Thoracic Society Guideline. Chest, 2015, 147(4): 894-942.
2.	Torres A, Menéndez R. Mortality in COPD patients with community-acquired pneumonia: Who is the third partner? European Respiratory Journal, 2006, 28(2): 262-263.
3.	O'Reilly J, Jones M M, Parnham J, et al. Management of stable chronic obstructive pulmonary disease in primary and secondary care: summary of updated Nice guidance. BMJ, 2010, 340: c3134.
4.	Gupta, S. Agrawal A, Gopalakrishnan K, Deep learning with limited numerical precision, Computer Science, 2015: 234-241.
5.	Mohamed A, Sainath T N, Dahl G, et al. Deep belief networks using discriminative features for phone recognition, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2011: 5060-5063.
6.	Schmidhuber, J. Deep learning in neural networks: an overview, Neural Networks, 2015, 61: 85.
7.	Glorot X B, Bordes A, Bengio Y. Domain adaptation for large-scale sentiment classification: a deep learning approach//in Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011: 513-520.
8.	Regan E A, Hokanson J E, Murphy J R, et al. Genetic epidemiology of COPD (COPDGene) study design. COPD, 2010, 7(1): 32-43.
9.	Han M K, Muellerova H, Curran-Everett D, et al. Gold 2011 disease severity classification in COPDGene: a prospective cohort study. Lancet Respir Med, 2013, 1(1): 43-50.
10.	Yusen R D. Evolution of the Gold documents for the diagnosis, management, and prevention of chronic obstructive pulmonary disease. Controversies and questions. Am J Respir Crit Care Med, 2013, 188(1): 4-5.
11.	Duda R O, Hart P E, Stork D G, Pattern Classification. John wiley & Sons, 2012: 273-280.
12.	LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444.
13.	Mohamed A, Yu dong, Deng Li. Investigation of full-sequence training of deep belief networks for speech recognition. Interspeech. 2010: 2846-2849.
14.	Kuremoto T, Kimura S, Kobayashi K A. Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing, 2014, 137(SI): 47-56.
15.	Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets. Neural Comput, 2006, 18(7): 1527-1554.
16.	Bengio Y, Lamblin P, Popovici D, Greedy layer-wise training of deep networks, Advances in neural information processing systems, 2006, 19: 153.
17.	Karakida R O, Okada M, Amari S I. Dynamical analysis of contrastive divergence learning:Restricted Boltzmann machines with Gaussian visible units. Neural Networks, 2016, 79(3): 78-87.
18.	Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504-507.
19.	Semwal V B, Mondal K, Nandi G C. Robust and accurate feature selection for humanoid push recovery and classification: deep learning approach. Neural Comput & Appl, 2017, 28(3): 565-574.
20.	Cai Deng, Zhang Chiyuan, He Xiaofei. Unsupervised feature selection for multi-cluster data//in Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, 2010: 333-342.
21.	Carneiro G, Mateus D, Loïc P, et al. Deep learning and data labeling for medical applications, 2016: 231-245.
22.	Lange P, Marott J L, Vestbo J, et al. Prediction of the clinical course of chronic obstructive pulmonary disease, using the new GOLD classification: a study of the general population. Am J Respir Crit Care Med, 2012, 186(10): 975-981.
23.	Burholt V, Nash P. Short form 36 (SF-36) health survey questionnaire: normative data for Wales. J Public Health (Oxf), 2011, 33(4): 587-603.
24.	Hurst J R, Vestbo J, Anzueto A, et al. Susceptibility to exacerbation in chronic obstructive pulmonary disease N Engl J Med, 2010, 363(12): 1128-1138.
25.	Balcells E, Gea J, Ferrer J, et al. Factors affecting the relationship between psychological status and quality of Life in COPD patients. Health Qual Life Outcomes, 2010, 8(108): 108.
26.	Rutgers R S, Postma D, ten H, et al. Ongoing airway inflammation in patients with COPD who do not currently smoke. Thorax, 2000, 55(1): 12-18.

1. Criner G J, Bourbeau J, Diekemper R L, et al. Prevention of acute exacerbations of COPD: American College of Chest Physicians and Canadian Thoracic Society Guideline. Chest, 2015, 147(4): 894-942.
2. Torres A, Menéndez R. Mortality in COPD patients with community-acquired pneumonia: Who is the third partner? European Respiratory Journal, 2006, 28(2): 262-263.
3. O'Reilly J, Jones M M, Parnham J, et al. Management of stable chronic obstructive pulmonary disease in primary and secondary care: summary of updated Nice guidance. BMJ, 2010, 340: c3134.
4. Gupta, S. Agrawal A, Gopalakrishnan K, Deep learning with limited numerical precision, Computer Science, 2015: 234-241.
5. Mohamed A, Sainath T N, Dahl G, et al. Deep belief networks using discriminative features for phone recognition, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2011: 5060-5063.
6. Schmidhuber, J. Deep learning in neural networks: an overview, Neural Networks, 2015, 61: 85.
7. Glorot X B, Bordes A, Bengio Y. Domain adaptation for large-scale sentiment classification: a deep learning approach//in Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011: 513-520.
8. Regan E A, Hokanson J E, Murphy J R, et al. Genetic epidemiology of COPD (COPDGene) study design. COPD, 2010, 7(1): 32-43.
9. Han M K, Muellerova H, Curran-Everett D, et al. Gold 2011 disease severity classification in COPDGene: a prospective cohort study. Lancet Respir Med, 2013, 1(1): 43-50.
10. Yusen R D. Evolution of the Gold documents for the diagnosis, management, and prevention of chronic obstructive pulmonary disease. Controversies and questions. Am J Respir Crit Care Med, 2013, 188(1): 4-5.
11. Duda R O, Hart P E, Stork D G, Pattern Classification. John wiley & Sons, 2012: 273-280.
12. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444.
13. Mohamed A, Yu dong, Deng Li. Investigation of full-sequence training of deep belief networks for speech recognition. Interspeech. 2010: 2846-2849.
14. Kuremoto T, Kimura S, Kobayashi K A. Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing, 2014, 137(SI): 47-56.
15. Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets. Neural Comput, 2006, 18(7): 1527-1554.
16. Bengio Y, Lamblin P, Popovici D, Greedy layer-wise training of deep networks, Advances in neural information processing systems, 2006, 19: 153.
17. Karakida R O, Okada M, Amari S I. Dynamical analysis of contrastive divergence learning:Restricted Boltzmann machines with Gaussian visible units. Neural Networks, 2016, 79(3): 78-87.
18. Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504-507.
19. Semwal V B, Mondal K, Nandi G C. Robust and accurate feature selection for humanoid push recovery and classification: deep learning approach. Neural Comput & Appl, 2017, 28(3): 565-574.
20. Cai Deng, Zhang Chiyuan, He Xiaofei. Unsupervised feature selection for multi-cluster data//in Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, 2010: 333-342.
21. Carneiro G, Mateus D, Loïc P, et al. Deep learning and data labeling for medical applications, 2016: 231-245.
22. Lange P, Marott J L, Vestbo J, et al. Prediction of the clinical course of chronic obstructive pulmonary disease, using the new GOLD classification: a study of the general population. Am J Respir Crit Care Med, 2012, 186(10): 975-981.
23. Burholt V, Nash P. Short form 36 (SF-36) health survey questionnaire: normative data for Wales. J Public Health (Oxf), 2011, 33(4): 587-603.
24. Hurst J R, Vestbo J, Anzueto A, et al. Susceptibility to exacerbation in chronic obstructive pulmonary disease N Engl J Med, 2010, 363(12): 1128-1138.
25. Balcells E, Gea J, Ferrer J, et al. Factors affecting the relationship between psychological status and quality of Life in COPD patients. Health Qual Life Outcomes, 2010, 8(108): 108.
26. Rutgers R S, Postma D, ten H, et al. Ongoing airway inflammation in patients with COPD who do not currently smoke. Thorax, 2000, 55(1): 12-18.

Previous Article
Degree centrality of the functional network in schizophrenia patients
Next Article
Synchronous analysis of corticomuscular coherence based on Gabor wavelet-transfer entropy

Journal of Biomedical Engineering

Severity classification of chronic obstructive pulmonary disease based on deep learning

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content