Rule Mining about the Relationship between Climatic Factors and the Number of Patients in a Hospital Using Classification Based on Multidimensional Association Rule Mining

Document Type : Research Paper

Authors

1 PhD Candidate, Department of Industrial Management, Faculty of Economic & Administrative Sciences, Ferdowsi University of Mashhad, Mashhad, Iran.

2 Associate Prof., Department of Industrial Management, Faculty of Economic & Administrative Sciences, Ferdowsi University of Mashhad, Mashhad, Iran.

3 Assistant Prof., Department of Industrial Management, Faculty of Economic & Administrative Sciences, Ferdowsi University of Mashhad, Mashhad, Iran.

4 Associate Prof., Department of Artificial Intelligence, Faculty of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.

Abstract

Objective: There are many climatic factors affecting the number of patients in hospitals which generally tend to make a Non-optimal use of their facilities and human resources.This research is aimed at discovering hidden knowledge between climatic factors and the number of hospital patients using data mining techniques.
Methods: In this study, the relationship between climatic factors and the number of patients in Dr. Sheikh specialized pediatric hospital of Mashhad is investigated by classification based on multidimensional association rule mining. The number of patients in the nephrology, hematology, emergency and PICU department of this hospital have been considered separately, and consequently the relationship between the number of patients and the climatic factors such as air temperature, relative humidity, wind speed, air pressure and air pollution have been analyzed. This research has analyzed data gathered through a 19 month period and has been obtained by referring to the documents. In this research for feature selection, all subsets of climatic factors are searched and the effect of all subsets on the number of patients are evaluated using linear regression. Also for rule mining is used classification based on multidimensional association rule mining which is based on known Apriori algorithm.
Results: The results show different patterns that indicate the relationship between the number of patients in the hospital departments with the climatic factors.
Conclusion: This study is able to help analyze the relationship between the climatic factors and the number of patients in the hospital. Also, the rules will help managers make optimal planning for hospital resources according to the different number of patients.

Keywords

References

 Abbasi Ranjbar, Z. (2006). Prevalence of Asthma Symptoms in Children. Jounal ofr guilan university medical science, 14 (56), 1-9. (in Persian)
Adham, D., Mahdavi, A., Mehrtak, M., Ebrahimi, K., & Azari, A. (2016). Assessment of Human Resource Allocation in General University Hospitals in the Cities of East Azerbaijan Province. Journal of health, 6 (5), 507-516. (in Persian)
AL-Hamodi, A., Songfeng, L., & AL-Salhi, Y. (2016). An enhanced frequent pattern growth based on mapreduce for mining association rules. International Journal of Data Mining & Knowledge Management Process (IJDKP), 6(2), 19-28.
 Alwidian, J., Bassam, H., & Obeid, N. (2018). WCBA: Weighted classification based on association rules algorithm for breast cancer disease. Applied Soft Computing, 62, 536–549.
Assari, R., Modarresi, M., Haghjou Javanmard, SH., Lahijanzadeh, A., Poursafa, P., Sadeghian, B., & Kelishadi, R. (2010). Evaluation of relationship between air pollution level and serum thrombomudolin and tissue factor in selected sample from 10 to 18 years old adolescents in Isfahan. Journal of Isfahan medical science, 28 (109), 425-436. 
(in Persian)
Bhatt, U., & Pratik, P. (2014). A Recent Overview: Rare Association Rule Mining. International Journal of Computer Applications, 107(8), 1-4.
Borah, A., & Nath, B. (2018). Identifying Risk Factors for Adverse Diseases using Dynamic Rare Association Rule Mining. Expert systems with applications, 113, 1-62.
Cano, A., Zafra, A., & Ventura, S. (2013). An interpretable classification rule mining algorithm. Information Sciences, 240, 1-20.
D’souza, R. M., Hall, G., & Becker, N. G. (2007). Climatic factors associated with hospitalizations for rotavirus diarrhoea in children under 5 years of age. Epidemiol, 136, 56-64.
Dash, M., & Liu, H. (2003). Consistency-based search in feature selection. Artificial Intelligence, 151(1), 155-176.
Dougherty, J., Kohavi, V., & Sahami, M. (1995). Supervised and Unsupervised Discretization of Continuous Features. Proceedings of the Twelfth International Conference on Machine Learning. Tahoe City, California, USA.
Farajzadeh, M., & Hydari, A. (2013). A. Relationship between Climate changes with Children's Infectious Diseases in Bandar Abbas, Iran. Hakim health system research journal, 16 (1), 72-79. (in Persian)
Hadi, W., Aburub, F., & Alhawari., S. (2016). A new fast associative classification algorithm for detecting phishing websites. Applied Soft Computing, 48, 729–734.
HervásaL, A., & Marcos, G. (2015). Can meteorological factors forecast asthma exacerbation in a paediatric population? Allergologia et Immunopathologia, 43 (1), 32-36.
Hu, L., Hu, Y., Tsai, C., Wang, J., & Huang, M. (2016). Building an associative classifier with multiple minimum supports. Speringer plus, 5, 1-19.
Ivančević, V., Tǔsek, I., Jasmina, J., Kneˇzevi´, M., Elheshk, S., & Lukovi, I. (2015). Using association rule mining to identify riskfactors for early childhood caries. Computer Methods and Programs in Biomedicine, 122(2), 175-181.
Javed, K., Babri, A., & Saeed, M. (2012). Feature Selection Based on Class-Dependent Densities for High-Dimensional Binary Data. IEEE Transactions on Knowledge and Data Engineering, 24(3), 465-477.
Karimipour, F., & Kananisadat, Y. (2015). Investigating the Relation between Prevalence of Asthmatic Allergy with the Characteristics of the Environment Using Fuzzy Association Rule Mining. Journal of Geomatics Science and Technology, 4 (3), 117-130. (in Persian)
Kim, SH., Kim, JS., Jin, MH., Jin, C., & Lee, JH. (2017).The effects of weather on pediatric seizure: A single-center retrospectivestudy (2005–2015). life-sciences literature, 609, 535-540.
Koh, Y. & Nathan, R. (2010). Rare Association Rule Mining and Knowledge Discovery: Technologies for infrequent and critical event detection , New Zland, Information Science Reffrence.
Liu, B., Hsu, W., & Ma, Y. (1998). Integrating Classification and Association Rule Mining, KDD’98 Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, New York, USA.
Martína, MR. & Bayleb, MS. (2018). Impact of air pollution in paediatric consultations in Primary Health Care. Ecological study, Pollution and paediatric consultations in Primary Health Care, 89 (2), 80-85.
Mireku, N., Wang, Y., Ager, J., Reddy, R.C., & Baptist, AP. (2009). Changes in weather and the effects on pediatric asthma exacerbations. Annals of Allergy, Asthma & Immunology, 103: 221-224.
Mohammadi, J., Azar, A., & Zareei Matin, H. (2005). Designing a Model of Manpower Planning for Educational Hospitals in Ahwaz. Daneshvar Raftar, 12 (11), 79-90. . (in Persian)
Nahar , J., Tasadduq, I., Tickle, k., Yi-Ping Phoebe, Ch. (2013). Association rule mining to detect factors which contribute to heart disease in males and females. Expert Systems with Applications, 40, 1086–1093.
Neshat, N., & Mahlooji, H. (2010). Predictive Process Control Using Artificial Neural Networks (ANNs) and A Combined Method of Regression Analysis and ANNs. Journal of Industrial Management, 1 (2), 153-170. (in Persian)
North, M. (2012). Data Mining for the Masses. Washington, Global Text Project.
Onozuka, D., & Hashizume, M. (2011). The influence of temperature and humidity on the incidence of hand, foot, and mouth disease in Japan Science of the Total Environment. Science of the Total Environment, 410, 119-125.
Ordonez, C. (2006). Association Rule Discovery With the Train and Test Approach for Heart Disease Prediction. IEEE Transactions on Information Technology in Biomedicine, 10(2), 334- 343.
Ordonez, C., Omiecinski, E., de Braal, L., Santana, C., Ezquerra, N., Taboada, J., Cooke, D., rawczynska, E., & Garcia, E. (2001). Mining Constrained Association Rules to Predict Heart Disease. Proceedings 2001 IEEE International Conference on Data Mining. San Jose, USA.
Rahal, I., Dongmei, R., Weihua, W., & Perrizo, W. (2004). Mining Confident Minimal Rules with Fixed-Consequents. In Proceedings OF THE 16TH IEEE International Conference ON Tools With Artificial Intelligence. IEEE Computer Society. Washington.
Reif, M., & Shafait, F. (2014). Efficient feature size reduction via predictive forward selection. Pattern Recognition, 47(4):1664-1673.
Shariatpanahi, S P., Habibi, D., Rafiei, M., Ghandi, Y., & Anvari, M. (2018). Determination of Relations between Systolic Blood Pressure and Heart Attack in Patients with Type 2 Diabetes with Association Rules. Journal of Arak University Medicla Science, 20 (12), 44-50. (in Persian)
Sridevi, R., & Ramaraj, E. (2013). A General Survey on Multidimensional And Quantitative Association Rule Mining Algorithms. International Journal of Engineering Research and Applications, 3(4), 1442-1448.
Taghizadeh Yazdi, M., Mirshojaeian Hosseini, H., Asgharizadeh, E., &  SHakouri Ganjavi, H. (2015). Relative Performance of Statistical and Fuzzy Regression Models in Estimation of Gasoline Demand in Iran. Journal of Industrial Management, 7 (1), 1-19. (in Persian)
 Tauler, E., Llorens-Terol, J., Mur, A., & Leal, C. (1985). Asthma and Environmental Factors. Pediatric Research 19, 1120-1129.
 Thabtah, F. )2007(. A review of associative classification mining. The Knowledge Engineering Review, 22(1), 37-65.
 Toti, G., Vilalta, V., Lindner, P., Lefer, B., Macias, C., & Price, D. (2016). Analysis of correlation between pediatric asthma exacerbation andexposure to pollutant mixtures with association rule mining. Artificial Intelligence in Medicine, 74, 44-52.
Wedyan, S. )2014(. Review and Comparison of Associative Classification Data Mining Approaches. International Journal of Industrial and Manufacturing Engineering, 8(1), 34-45.
Weng, Ch. )2011(. Mining fuzzy specific rare itemsets for education data. Knowledge-Based Systems, 24, 697-708.
Weng, Ch.) 2016(. Identifying association rules of specific later-marketed products, Applied Soft Computing, 38,528-529.
Zahng, Ch. & Zhang, SH. (2007). AssociationRule Mining Models and Algorithms. Springer-Verlag Berlin Heidelberg NewYork.
Zucco, Ch. ) 2019(. Data Mining in Bioinformatics. Reference Module in Life Sciences, 1, 328-335.
Industrial Management Journal
Volume 11, Issue 4
2019
Pages 575-599

Files

Share

How to cite

Statistics