Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric

Olasehinde Olayemi Oladimeji; Olayemi Olufunke Catherine; Adetunmbi Adebayo Olusola

doi:doi:10.11648/j.ijiis.20200905.11

| Peer-Reviewed

Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric

Olasehinde Olayemi Oladimeji, Olayemi Olufunke Catherine, Adetunmbi Adebayo Olusola

Published in International Journal of Intelligent Information Systems (Volume 9, Issue 5)

Received: 10 September 2020 Accepted: 5 October 2020 Published: 4 November 2020

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Lower Respiratory Tract Infections (LRTIs) are the second and third causes of pediatric patients' death in Nigeria and the United States of America. It is observed from several reviewed literature that the LRTIs accounted for more than a million children morbidity and mortality yearly due to lack of prompt diagnosis or no diagnosis due to a shortage of medical experts and medical facilities in our localities. Intense research is ongoing on applying machine learning (ML) to its clinical diagnosis and reducing its spread in pediatric patients. In this research, K-Nearest Neighbor (KNN), C4.5 Decision Tree, and Naive Bayes' ML algorithms were used to develop three base diagnosis models with Correlation, consistency, and information gain selected feature of the LRTI dataset, Multiple Model Trees (MMT) Meta algorithm is used to combine and improve the diagnoses of all the base models using stacked ensemble. The preliminary diagnosis findings using base models have established that the information gained feature extraction method performed much better than the other two. It, therefore, suffix that the results from this should be used for further processing. All the models built with the reduced feature set recorded improved diagnoses accuracy more than the model built with the whole feature set. The MMT stacked ensemble models recorded an improvement on the diagnosis of LRTIs in Peadiatric, it recorded the highest diagnostic accuracies improvement of 12.80%, 13.52%, and 12.37%, and lowest diagnostic accuracies improvement of 6.37%, 5.22%, and 6.09% with the MMT stacked ensemble models of the Consistency, the Correlation, and the information gain reduced selected feature set respectively. These experimental results show the potential for this approach to deliver a reliable and improved diagnosis of LRTIs. It is recommended to be used to diagnose LRTIs in primary health care centers to reduce its mortality rate.

Published in	International Journal of Intelligent Information Systems (Volume 9, Issue 5)
DOI	10.11648/j.ijiis.20200905.11
Page(s)	44-55
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), 2020. Published by Science Publishing Group

Keywords

Machine Learning Algorithm, Diagnosis, Stacked Ensemble, Infection, Diagnosis Accuracy, Incorrect Diagnosis Rate

References

[1]	P. V. Dasaraju, C. Liu. "Infections of the Respiratory System". In: S. Baron, editor. Medical Microbiology. 4th edition. Galveston (TX): University of Texas Medical Branch at Galveston; 1996. Chapter 93. Available from: https://www.ncbi.nlm.nih.gov/books/NBK8142/ (Accessed: 26th July 2020).
[2]	J. E. Crowe. "Viral Pneumonia. Kendig's Disorders of the Respiratory Tract in Children, 433–440. 2006. https://doi.org/10.1016/B978-0-7216-3695-5.50030-4.
[3]	G. Worrall. "Acute bronchitis." Canadian family physician Medecin de Famille canadien, 54 (2), 238–239. 2008.
[4]	K. Øymar, H. O. Skjerven, I. B. Mikalsen. "Acute bronchiolitis in infants, a review." Scandinavian journal of trauma, resuscitation, and emergency medicine, 22 (23). 2014. https://doi.org/10.1186/1757-7241-22-23
[5]	S. A. Madhi, K. P. Klugman. "Acute Respiratory Infections." In: D. T. Jamison, R. G. Feachem, M. W. Makgoba, editors. Disease and Mortality in Sub-Saharan Africa. 2nd edition. Washington (DC): 2006. Chapter 11. Available from: https://www.ncbi.nlm.nih.gov/books/NBK2283/
[6]	C. O. Oyejide, K. Osinusi, "Acute Respiratory Tract Infection in Children in Idikan Community, Ibadan, Nigeria: Severity, Risk Factors, and Frequency of Occurrence, Reviews of Infectious Diseases," Volume 12, Issue Supplement_8, Pages S1042–SI046, https://doi.org/10.1093/clinids/12.Supplement_8.S1042, 1990.
[7]	R. Loddenkemper, G. J. Gibson, Y. Sibille. "Respiratory health and disease in Europe: the new European Lung White Book. European Respiratory"; European Respiratory Journal. 42: 559-563; DOI: 10.1183/09031936.00105513, 2013.
[8]	A. D. Achary, K. S. Prasanna and S. Nail “Acute Respiratory Infections in Children: A Community Based Longitudinal Study in South India.” Indian Journal of Public Health 47 (1): 1-13. 2003.
[9]	T. Wardlaw, D. You, H. Newby, D. Anthony and M. Chopra “Child Survival: a Message of Hope but a call for Renewed Commitment in UNICEF report." Reprod Health".10 – 64. https://doi.org/10.1186/1742-4755-10-64. 2013.
[10]	Yoo, Illhoi, P. Alafaireet, M. Marinov, K. Pena-Hernandez, R. Gopidi, J. Chang, L. Hua. Data mining in healthcare and biomedicine: a survey of the literature. Journal of medical systems 36 (4) 2431-2448. 2012.
[11]	S. Apoorva, R. Pallavi, P. Kajal, S. R. Rai. "Health Analytics Using Machine Learning: A Survey." International Journal of Innovative Research in Computer and Communication Engineering Vol. 5, Issue 4, DOI: 10.15680/IJIRCCE.2017.05040116650,2017.
[12]	H. Ameri, S. Alizadeh, E. Akhond Application of data mining techniques in clinical decision making: A literature review and classification. In: Akhond Zadeh Noughabi E, Raahemi B, Albadvi A, Far BH. Handbook of research on data science for effective healthcare practice and administration. IGI Global; 257-295. 2017. DOI: 10.4018/978-1-5225-2515-8.ch012.
[13]	J, Ban, M. Gagliano, J. Pham, B. Tang, H. Kashif, “Applications of Machine Learning in Medical Diagnosis." Available from: https://www.researchgate.net/publication/321151498_Applications_of_Machine_Learning_in_Medical_Diagnosis, 2017. [Accessed Dec 05, 2019].
[14]	Xu, J., Xue, K., & Zhang, K. "Current Status and Future Trends of Clinical Diagnoses via Image-Based Deep Learning." Theranostics, 9 (25), 7556–7565. https://doi.org/10.7150/thno.38065, 2019
[15]	K. UmaMaheswari, A. Valarmathi, J. Jasmine., "Effective Diagnosis of Heart Disease through Stacking Approach. Advances in Natural and Applied Sciences". 11 (9); Pages: 323-328. 2017.
[16]	A. Oguntimilehin, O. Adetunmbi, I. Osho “Towards Achieving Optimal Performance using Stacked Generalization Algorithm: A Case Study of Clinical Diagnosis of Malaria Fever” The International Arab Journal of Information Technology, Vol. 16, No. 6. 2019.
[17]	O. C. Olayemi, O. S. Adewale, O. O Olasehinde, B. A. Ojokoh, A. O. Adetunmbi. "Application of Machine Learning to the Diagnosis of Lower Respiratory Tract Infections in Paediatric Patients." i-manager’s Journal on Pattern Recognition, 5 (2), 21-29, https://doi.org/10.26634/jpr.5.2.15538, 2018
[18]	M. Jan, A. A. Awan, M. S. Khalid, S. Nisar, "Ensemble Approach for Developing a Smart Heart Disease Prediction System using Classification Algorithms." Research Reports in Clinical Cardiology, 9: 33-45, 2018.
[19]	R. J. McDonough, "Utilizing Data Mining Techniques and Ensemble Learning to Predict Development of Surgical Site Infections in Gynecologic Cancer Patients" Graduate Dissertations and Theses. 33. https://orb.binghamton.edu/dissertation_and_theses/33, 2018.
[20]	J. R. Quinlan," C4.5: Programs for Machine Learning." San Francisco: Morgan Kaufmann. Publishers, Inc., https://dl.acm.org/doi/book/10.5555/152181, 2003
[21]	O. O. Olasehinde, O. C. Olayemi, B. K. Alese. " Multiple Model Tree Meta Algorithms Improvement of Network Intrusion Detection Predictions Accuracy" International Journal for Information Security Research (IJISR), Volume 9, Issue 3, https://infonomics-society.org/wp-content/uploads/Multiple-Model-Tree-Meta-Algorithms-Improvement-of-Network-Intrusion-Detection.pdf, 2019.
[22]	A. Kaveh, S. M. Amze-Ziabari, T. Bakhshpoori. M5' Algorithm for Shear Strength Prediction of HSC Slender Beams without Web Reinforcement. IJMO 7 (1), 2017. DOI: 10.1617/s11527-015-0752-x.
[23]	H. Duggal and P. Singh, "Comparative Study of the Performance of M5-Rules Algorithm with Different Algorithms," Journal of Software Engineering and Applications, 5 (4) 270-276. doi: 10.4236/jsea.2012.54032.2012.
[24]	P. Yildirim, "Filter-Based Feature Selection Methods for Prediction of Risks in Hepatitis Disease." International Journal of Machine Learning and Computing 5 (4): 258 – 263, 2015.
[25]	O. O. Olasehinde, B. K. Alese, A. O Adetunmbi, Performance Evaluation of Bayesian Classifier on Filter-Based Feature Selection Techniques, International Journal of Computer Science and Telecommunications 9 (7) (2018) 24-30.
[26]	Z. Shichao, L. Xuelong, Z. Ming, Z. Xjaofeng, C. Debo, "Learning K for KNN Classification," ACM Transactions on Intelligent Systems and Technology, https://doi.org/10.1145/2990508, January 2017.
[27]	C. Gaurav “All about Naive Bayes "Towards Data Science," A Medium publication sharing concepts, ideas, and codes https://towardsdatascience.com/all-about-naive-bayes-8e13cef044cf, 2018. (Accessed on 6th June 2020).
[28]	B. N. Lakshmi, T. S. Indumathi, R. N. Ravi, "A study on C4.5 Decision Tree Classification Algorithm for Risk Predictions during Pregnancy", International Conference on Emerging Trends in Engineering, Science and Technology (ICETEST - 2015), Procedia Technology. (24) 1542-1549, 2016.
[29]	E. Frank, Y. Wang, S. Inglis, G. Holmes, I. H. Witten. Using Model Trees for Classification. Machine Learning, (32): 63-76, 1998.

Cite This Article

Plain Text BibTeX RIS

APA Style

Olasehinde Olayemi Oladimeji, Olayemi Olufunke Catherine, Adetunmbi Adebayo Olusola. (2020). Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric. International Journal of Intelligent Information Systems, 9(5), 44-55. https://doi.org/10.11648/j.ijiis.20200905.11

Copy | Download

ACS Style

Olasehinde Olayemi Oladimeji; Olayemi Olufunke Catherine; Adetunmbi Adebayo Olusola. Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric. Int. J. Intell. Inf. Syst. 2020, 9(5), 44-55. doi: 10.11648/j.ijiis.20200905.11

Copy | Download

AMA Style

Olasehinde Olayemi Oladimeji, Olayemi Olufunke Catherine, Adetunmbi Adebayo Olusola. Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric. Int J Intell Inf Syst. 2020;9(5):44-55. doi: 10.11648/j.ijiis.20200905.11

Copy | Download

@article{10.11648/j.ijiis.20200905.11,
  author = {Olasehinde Olayemi Oladimeji and Olayemi Olufunke Catherine and Adetunmbi Adebayo Olusola},
  title = {Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric},
  journal = {International Journal of Intelligent Information Systems},
  volume = {9},
  number = {5},
  pages = {44-55},
  doi = {10.11648/j.ijiis.20200905.11},
  url = {https://doi.org/10.11648/j.ijiis.20200905.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijiis.20200905.11},
  abstract = {Lower Respiratory Tract Infections (LRTIs) are the second and third causes of pediatric patients' death in Nigeria and the United States of America. It is observed from several reviewed literature that the LRTIs accounted for more than a million children morbidity and mortality yearly due to lack of prompt diagnosis or no diagnosis due to a shortage of medical experts and medical facilities in our localities. Intense research is ongoing on applying machine learning (ML) to its clinical diagnosis and reducing its spread in pediatric patients. In this research, K-Nearest Neighbor (KNN), C4.5 Decision Tree, and Naive Bayes' ML algorithms were used to develop three base diagnosis models with Correlation, consistency, and information gain selected feature of the LRTI dataset, Multiple Model Trees (MMT) Meta algorithm is used to combine and improve the diagnoses of all the base models using stacked ensemble. The preliminary diagnosis findings using base models have established that the information gained feature extraction method performed much better than the other two. It, therefore, suffix that the results from this should be used for further processing. All the models built with the reduced feature set recorded improved diagnoses accuracy more than the model built with the whole feature set. The MMT stacked ensemble models recorded an improvement on the diagnosis of LRTIs in Peadiatric, it recorded the highest diagnostic accuracies improvement of 12.80%, 13.52%, and 12.37%, and lowest diagnostic accuracies improvement of 6.37%, 5.22%, and 6.09% with the MMT stacked ensemble models of the Consistency, the Correlation, and the information gain reduced selected feature set respectively. These experimental results show the potential for this approach to deliver a reliable and improved diagnosis of LRTIs. It is recommended to be used to diagnose LRTIs in primary health care centers to reduce its mortality rate.},
 year = {2020}
}

Copy | Download

TY  - JOUR
T1  - Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric
AU  - Olasehinde Olayemi Oladimeji
AU  - Olayemi Olufunke Catherine
AU  - Adetunmbi Adebayo Olusola
Y1  - 2020/11/04
PY  - 2020
N1  - https://doi.org/10.11648/j.ijiis.20200905.11
DO  - 10.11648/j.ijiis.20200905.11
T2  - International Journal of Intelligent Information Systems
JF  - International Journal of Intelligent Information Systems
JO  - International Journal of Intelligent Information Systems
SP  - 44
EP  - 55
PB  - Science Publishing Group
SN  - 2328-7683
UR  - https://doi.org/10.11648/j.ijiis.20200905.11
AB  - Lower Respiratory Tract Infections (LRTIs) are the second and third causes of pediatric patients' death in Nigeria and the United States of America. It is observed from several reviewed literature that the LRTIs accounted for more than a million children morbidity and mortality yearly due to lack of prompt diagnosis or no diagnosis due to a shortage of medical experts and medical facilities in our localities. Intense research is ongoing on applying machine learning (ML) to its clinical diagnosis and reducing its spread in pediatric patients. In this research, K-Nearest Neighbor (KNN), C4.5 Decision Tree, and Naive Bayes' ML algorithms were used to develop three base diagnosis models with Correlation, consistency, and information gain selected feature of the LRTI dataset, Multiple Model Trees (MMT) Meta algorithm is used to combine and improve the diagnoses of all the base models using stacked ensemble. The preliminary diagnosis findings using base models have established that the information gained feature extraction method performed much better than the other two. It, therefore, suffix that the results from this should be used for further processing. All the models built with the reduced feature set recorded improved diagnoses accuracy more than the model built with the whole feature set. The MMT stacked ensemble models recorded an improvement on the diagnosis of LRTIs in Peadiatric, it recorded the highest diagnostic accuracies improvement of 12.80%, 13.52%, and 12.37%, and lowest diagnostic accuracies improvement of 6.37%, 5.22%, and 6.09% with the MMT stacked ensemble models of the Consistency, the Correlation, and the information gain reduced selected feature set respectively. These experimental results show the potential for this approach to deliver a reliable and improved diagnosis of LRTIs. It is recommended to be used to diagnose LRTIs in primary health care centers to reduce its mortality rate.
VL  - 9
IS  - 5
ER  -

Copy | Download

Author Information

Olasehinde Olayemi Oladimeji

Department of Computer Science, Federal Polytechnic, Ile Oluji, Nigeria
Olayemi Olufunke Catherine

Department of Computer Science, Joseph Ayo Babalola University, Ikeji-Arakeji, Nigeria
Adetunmbi Adebayo Olusola

Department of Computer Science, Federal University of Technology, Akure, Nigeria

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Olasehinde Olayemi Oladimeji, Olayemi Olufunke Catherine, Adetunmbi Adebayo Olusola. (2020). Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric. International Journal of Intelligent Information Systems, 9(5), 44-55. https://doi.org/10.11648/j.ijiis.20200905.11

Copy | Download

ACS Style

Olasehinde Olayemi Oladimeji; Olayemi Olufunke Catherine; Adetunmbi Adebayo Olusola. Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric. Int. J. Intell. Inf. Syst. 2020, 9(5), 44-55. doi: 10.11648/j.ijiis.20200905.11

Copy | Download

AMA Style

Olasehinde Olayemi Oladimeji, Olayemi Olufunke Catherine, Adetunmbi Adebayo Olusola. Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric. Int J Intell Inf Syst. 2020;9(5):44-55. doi: 10.11648/j.ijiis.20200905.11

Copy | Download

@article{10.11648/j.ijiis.20200905.11,
  author = {Olasehinde Olayemi Oladimeji and Olayemi Olufunke Catherine and Adetunmbi Adebayo Olusola},
  title = {Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric},
  journal = {International Journal of Intelligent Information Systems},
  volume = {9},
  number = {5},
  pages = {44-55},
  doi = {10.11648/j.ijiis.20200905.11},
  url = {https://doi.org/10.11648/j.ijiis.20200905.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijiis.20200905.11},
  abstract = {Lower Respiratory Tract Infections (LRTIs) are the second and third causes of pediatric patients' death in Nigeria and the United States of America. It is observed from several reviewed literature that the LRTIs accounted for more than a million children morbidity and mortality yearly due to lack of prompt diagnosis or no diagnosis due to a shortage of medical experts and medical facilities in our localities. Intense research is ongoing on applying machine learning (ML) to its clinical diagnosis and reducing its spread in pediatric patients. In this research, K-Nearest Neighbor (KNN), C4.5 Decision Tree, and Naive Bayes' ML algorithms were used to develop three base diagnosis models with Correlation, consistency, and information gain selected feature of the LRTI dataset, Multiple Model Trees (MMT) Meta algorithm is used to combine and improve the diagnoses of all the base models using stacked ensemble. The preliminary diagnosis findings using base models have established that the information gained feature extraction method performed much better than the other two. It, therefore, suffix that the results from this should be used for further processing. All the models built with the reduced feature set recorded improved diagnoses accuracy more than the model built with the whole feature set. The MMT stacked ensemble models recorded an improvement on the diagnosis of LRTIs in Peadiatric, it recorded the highest diagnostic accuracies improvement of 12.80%, 13.52%, and 12.37%, and lowest diagnostic accuracies improvement of 6.37%, 5.22%, and 6.09% with the MMT stacked ensemble models of the Consistency, the Correlation, and the information gain reduced selected feature set respectively. These experimental results show the potential for this approach to deliver a reliable and improved diagnosis of LRTIs. It is recommended to be used to diagnose LRTIs in primary health care centers to reduce its mortality rate.},
 year = {2020}
}

Copy | Download

TY  - JOUR
T1  - Stacked Ensemble Improvement of the Lower Respiratory Tract Infection Diagnoses in Peadiatric
AU  - Olasehinde Olayemi Oladimeji
AU  - Olayemi Olufunke Catherine
AU  - Adetunmbi Adebayo Olusola
Y1  - 2020/11/04
PY  - 2020
N1  - https://doi.org/10.11648/j.ijiis.20200905.11
DO  - 10.11648/j.ijiis.20200905.11
T2  - International Journal of Intelligent Information Systems
JF  - International Journal of Intelligent Information Systems
JO  - International Journal of Intelligent Information Systems
SP  - 44
EP  - 55
PB  - Science Publishing Group
SN  - 2328-7683
UR  - https://doi.org/10.11648/j.ijiis.20200905.11
AB  - Lower Respiratory Tract Infections (LRTIs) are the second and third causes of pediatric patients' death in Nigeria and the United States of America. It is observed from several reviewed literature that the LRTIs accounted for more than a million children morbidity and mortality yearly due to lack of prompt diagnosis or no diagnosis due to a shortage of medical experts and medical facilities in our localities. Intense research is ongoing on applying machine learning (ML) to its clinical diagnosis and reducing its spread in pediatric patients. In this research, K-Nearest Neighbor (KNN), C4.5 Decision Tree, and Naive Bayes' ML algorithms were used to develop three base diagnosis models with Correlation, consistency, and information gain selected feature of the LRTI dataset, Multiple Model Trees (MMT) Meta algorithm is used to combine and improve the diagnoses of all the base models using stacked ensemble. The preliminary diagnosis findings using base models have established that the information gained feature extraction method performed much better than the other two. It, therefore, suffix that the results from this should be used for further processing. All the models built with the reduced feature set recorded improved diagnoses accuracy more than the model built with the whole feature set. The MMT stacked ensemble models recorded an improvement on the diagnosis of LRTIs in Peadiatric, it recorded the highest diagnostic accuracies improvement of 12.80%, 13.52%, and 12.37%, and lowest diagnostic accuracies improvement of 6.37%, 5.22%, and 6.09% with the MMT stacked ensemble models of the Consistency, the Correlation, and the information gain reduced selected feature set respectively. These experimental results show the potential for this approach to deliver a reliable and improved diagnosis of LRTIs. It is recommended to be used to diagnose LRTIs in primary health care centers to reduce its mortality rate.
VL  - 9
IS  - 5
ER  -

Copy | Download