Volume 9, Issue 4 (2025)
Manage Strat Health Syst 2025, 9(4): 314-328 |
Back to browse issues page
Ethics code: IR.IAU.YAZD.REC.1401.034
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Fallah Tafti H, Esteghlal A, Al-Modaresi S A, Beheshtipour Z, Mirhosseini S M. Forecasting the Demand of Medical Tourists in Yazd Using Artificial Neural Network. Manage Strat Health Syst 2025; 9 (4) :314-328
URL: http://mshsj.ssu.ac.ir/article-1-792-en.html
URL: http://mshsj.ssu.ac.ir/article-1-792-en.html
Hamidreza Fallah Tafti 
, Ahmad Esteghlal * , Seyed Ali Al-Modaresi , Zohreh Beheshtipour , Seyed Majid Mirhosseini
, Ahmad Esteghlal * , Seyed Ali Al-Modaresi , Zohreh Beheshtipour , Seyed Majid Mirhosseini
Assistant Professor, Department of Architecture and Urban Planning, Yazd Branch, Islamic Azad University, Yazd, Iran
Abstract: (277 Views)
Background: Medical tourism is one of the newest types of tourism and predicting the demand of medical tourists for a society is one of the most important prerequisites of the tourism industry to provide the necessary infrastructure so that we can maximize the future of this income-generating industry. Therefore, in order to better develop the medical tourism industry, the purpose of this research is to predict the demand of medical tourists in Yazd using artificial neural network.
Methods: The present quantitative study was conducted in the summer and fall of 2023. Field study method was used to collect data. The statistical population of this study was medical tourists referring to 4 government hospitals in Yazd city during 2015-2022. In this study, medical indicators of hospitals in question and other medical indicators of Yazd city, such as the number of patient admission beds, the number of pharmacies, the number of health centers, etc., were examined with respect to the spread of the coronavirus disease from late 2019 to late 2021. The effective indicators in this study were first identified and using the proposed artificial neural network model, the number of medical tourists for the next year in Yazd city was predicted. For further investigation, time series methods were also used.
Results: Using the conducted surveys, the number of medical tourists entering Yazd city was predicted in different months of 2023. Moreover, to check the accuracy of predictions in the artificial neural network, the prediction was also done with the time series model. The results of this study revealed that the error rate of training data in artificial neural network and time series model was 0.000618 and 0.011131, respectively, as well as 0.013346 and 0.0531902 for test data, respectively, indicating the superiority of the proposed method.
Conclusion: By taking advantage of the forecast of the demand for medical tourists, it is possible to attract more tourists by providing the necessary and real infrastructures for medical tourists and homogenizing the current and required urban facilities, which will lead to an increase in income and economic and social development of the city.
Methods: The present quantitative study was conducted in the summer and fall of 2023. Field study method was used to collect data. The statistical population of this study was medical tourists referring to 4 government hospitals in Yazd city during 2015-2022. In this study, medical indicators of hospitals in question and other medical indicators of Yazd city, such as the number of patient admission beds, the number of pharmacies, the number of health centers, etc., were examined with respect to the spread of the coronavirus disease from late 2019 to late 2021. The effective indicators in this study were first identified and using the proposed artificial neural network model, the number of medical tourists for the next year in Yazd city was predicted. For further investigation, time series methods were also used.
Results: Using the conducted surveys, the number of medical tourists entering Yazd city was predicted in different months of 2023. Moreover, to check the accuracy of predictions in the artificial neural network, the prediction was also done with the time series model. The results of this study revealed that the error rate of training data in artificial neural network and time series model was 0.000618 and 0.011131, respectively, as well as 0.013346 and 0.0531902 for test data, respectively, indicating the superiority of the proposed method.
Conclusion: By taking advantage of the forecast of the demand for medical tourists, it is possible to attract more tourists by providing the necessary and real infrastructures for medical tourists and homogenizing the current and required urban facilities, which will lead to an increase in income and economic and social development of the city.
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
