Asthma Diagnosis Indispensable Tool based on Support Vector Machines
DOI:
https://doi.org/10.30732/ijbbb.20160101005Keywords:
Asthma, SVM, Lung, Machine learningAbstract
Asthma is a lung disease and incurable in nature. It can be only controlled by the proper medication after the correct diagnosis. In the absence of the correct diagnosis, it is very difficult to detect the different stages of asthma. In this study, for the riddance of misdiagnosis problem, expertise, knowledge has been translated into the machine learning and designed a tool for the diagnosis of Asthma. The experts’ knowledge and assessments on these four symptoms have been translated as input into Support vector machine (SVM) based on machine learning approaches. And the severity of Asthma has been diagnosed as an output. This tool has been developed in Microsoft Visual Studio 2010 with four input parameters Forced vital capacity (FVC), Forced Expiratory Volume in the first, second, Forced expiratory volume (FEV) (FEV1) (viz. FVC, and PERF) and one output in the form of severity. The efficacy of this tool is approximately 78.11%. This tool possibly will be useful for newer practitioners as well as researchers working in this area. The underlying technology for this tool is machine learning approach based on Support Vector Machine.
References
2. A.S. Buist, Mary A. M., William M. V., Suzanne G., Peter B., David M M., Ana M B M., Sean D S., Todd A L., Kevin B W., Robert L J., Guy B M., Amund G., Ewa N. Collaborative Research Group. (). International variation in the prevalence of COPD (the BOLD Study): a population-based prevalence study. The Lancet, 2007, 370(9589), 741-750.
3. Stanley F. M., Medical emergencies in the dental office. Elsevier Health Sciences, 2014.
4. C J.C. Burges, A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, 2(2), 121-167
5. D. Chicco Support Vector Machines in Bioinformatics: a Survey Technical Report. (2012).
6. A.Patel, J. Choubey, S. K. Gupta, M. K. Verma , R. Prasad, Q. Rahman, Decision Support System for the Diagnosis of Asthma Severity Using Fuzzy Logic, Vol. 1,(2012),14-16.
7. El-Naqa, Y.Yang, M. N. Wernick, N. P. Galatsanos, A support vector machine approach for detection of microcalcifications. Medical Imaging, IEEE Transactions on, 2002, 21(12), 1552-1563.
8. J. K. L. Walker, M. Kraft and J. T. Fisher, Assessment of murine lung mechanics outcome measures: alignment with those made in asthmatics. Frontiers in physiology, 2012, 3.
9. L.J. Janssen, E.E. Daniel, I.W. Rodger, Airway smooth muscle cells: Structure and function. Asthma: Basic Mechanisms and Clinical Management, 1998, 90-112.
10. N. G. Polson, S L. Scott, Data augmentation for support vector machines. Bayesian Analysis, 2011, 6(1), 1-23.
11. S. R. Gunn, Support vector machines for classification and regressionists technical report, 1998, 14.
12. Gang L., MLBCD: a machine learning tool for big clinical data. Health Information Science and Systems, 2015, 3.
13. Kwetishe J. D., Performance Evaluation of Machine Learning Algorithms in Post-operative Life Expectancy in the Lung Cancer Patients. 2015. arXiv preprint arXiv:1504.04646.
14. XuanLong N., Ling H., and Anthony D. J., Support vector machines, data reduction, and approximate kernel matrices. In Machine Learning and Knowledge Discovery in Databases 2008, 137-153.
15. World Health Organization (WHO), 2008, http://www.who.int/mediacentre/factsheets/fs307/en/
Downloads
Published
How to Cite
Issue
Section
License
The Copyright Notice will appear in About the Journal. It should describe for readers and authors whether the copyright holder is the author, journal, or a third party. It should include additional licensing agreements (e.g. CREATIVE COMMONS licenses) that grant rights to readers (see EXAMPLES), and it should provide the means for securing permissions, if necessary, for the use of the journal's content
