SOM Clustering of OECD Countries for COVID-19 Indicators and Related Socio-economic Indicators

Öz

The coronavirus disease is one of the most severe public health problems globally. Governments need policies to better cope with the disease, so policymakers analyze the country's indicators related to the pandemic to make proper decisions. The study aims to cluster OECD (Organisation for Economic Co-operation and Development) countries using COVID-19, health, socioeconomic, and environmental indicators. A self-organizing map (SOM) clustering method, an unsupervised artificial neural network (ANN) method and a hierarchical clustering method are used. The data comprises 38 OECD countries, and 16 different variables are selected. As a result, the countries are grouped into 3 clusters. Cluster 1 contains 33 countries, the USA is Cluster 2, and Cluster 3 has 4 countries, including Turkey. COVID-19 mortality is highly related to mortality from chronic respiratory diseases. In addition, environmental indicators show differences in clusters.

Anahtar Kelimeler

• COVID-19
• OECD countries
• Kohonen SOM
• clustering

Kaynakça

1. Abdullah, D., Susilo, S, Ahmar A.S., et al., 2022. The application of K-means clustering for province clustering in Indonesia of the risk of the COVID-19 pandemic based on COVID-19 data. Quality and Quantity 56(3). Springer Netherlands: 1283–1291. DOI: 10.1007/s11135-021-01176-w.
2. Arunachalam, D., Kumar, N., 2018. Benefit-based consumer segmentation and performance evaluation of clustering approaches: An evidence of data-driven decision-making. Expert Systems with Applications 111. Elsevier Ltd: 11–34. DOI: 10.1016/j.eswa.2018.03.007.
3. Aydin N and Yurdakul G., 2020. Assessing countries’ performances against COVID-19 via WSIDEA and machine learning algorithms. Applied Soft Computing Journal 97. Elsevier B.V.: 106792. DOI: 10.1016/j.asoc.2020.106792.
4. Bergquist, S., Otten, T., Sarich, N., 2020. COVID-19 pandemic in the United States. Health Policy and Technology 9(4). Elsevier Ltd: 623–638. DOI: 10.1016/j.hlpt.2020.08.007.
5. Bollyky, T.J., Castro, E., Aravkin, A.Y., et al., 2023. Assessing COVID-19 pandemic policies and behaviours and their economic and educational trade-offs across US states from Jan 1, 2020, to July 31, 2022: an observational analysis. The Lancet 401(10385). The Authors. Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license: 1341–1360. DOI: 10.1016/S0140-6736(23)00461-0.
6. Boluwade, A., 2020. Regionalizing Partitioning Africa’s Coronavirus (COVID-19) Fatalities Using Environmental Factors and Underlying Health Conditions for Social-economic Impacts. 2nd Novel Intelligent and Leading Emerging Sciences Conference, NILES 2020: 439–443. DOI: 10.1109/NILES50944.2020.9257875.
7. Bruwer, J., Prayag, G., Disegna, M., 2018. Why wine tourists visit cellar doors: Segmenting motivation and destination image. International Journal of Tourism Research 20(3): 355–366. DOI: 10.1002/jtr.2187.
8. Calderón-Larrañaga, A., Dekhtyar, S., Vetrano, D.L., et al., 2020. COVID-19: risk accumulation among biologically and socially vulnerable older populations. Ageing Research Reviews 63(May). DOI: 10.1016/j.arr.2020.101149.

9. Cardoso, E.H.S., Silva, M.S., Da, Júnior, FEDAF, et al., 2020. Characterizing the Impact of Social Inequality on COVID-19 Propagation in Developing Countries. IEEE Access 8: 172563–172580. DOI: 10.1109/ACCESS.2020.3024910.
10. Carrillo-Larco, R.M., Castillo-Cara, M., 2020. Using country-level variables to classify countries according to the number of confirmed COVID-19 cases: An unsupervised machine learning approach. Wellcome Open Research 5: 56. DOI: 10.12688/wellcomeopenres.15819.1.
11. Coccia, M., 2021. High health expenditures and low exposure of population to air pollution as critical factors that can reduce fatality rate in COVID-19 pandemic crisis: a global analysis. Environmental Research 199(January). Elsevier Inc.: 111339. DOI: 10.1016/j.envres.2021.111339.
12. Davies, D.L., Bouldin, D.W., 1979. A Cluster Separation Measure. IEEE Transactions on Pattern Analysis and Machine Intelligence (2): 224–227.
13. Gebhard, C., Regitz-Zagrosek, V., Neuhauser, H.K., et al., 2020. Impact of sex and gender on COVID-19 outcomes in Europe. Biology of Sex Differences 11(1). Biology of Sex Differences: 1–13. DOI: 10.1186/s13293-020-00304-9.
14. Gohari, K., Kazemnejad, A., Sheidaei, A., et al., 2022. Clustering of countries according to the COVID-19 incidence and mortality rates. BMC Public Health 22(1). BioMed Central: 1–12. DOI: 10.1186/s12889-022-13086-z.
15. Haykin, S., 2008. Neural Networks and Learning Machines. DOI: 978-0131471399.
16. Huiyan, S.B., Gelfand, A.E., Chris, L., et al., 2008. Interpreting self-organizing maps through space–time data models. The Annals of Applied Statistics 2(4): 1194–1216. DOI: 10.1214/08-AOAS174.
17. Hussein, H.A., Abdulazeez, A.M., 2021. Covid-19 Pandemic Datasets Based on Machine Learning Clustering Algorithms: A Review. Journal Of Archaeology Of Egypt/Egyptology 18(4): 2672–2700. Available at: https://archives.palarch.nl/index.php/jae/article/download/6703/6488.
18. Imtyaz, A., Abid Haleem, Javaid, M., 2020. Analysing governmental response to the COVID-19 pandemic. Journal of Oral Biology and Craniofacial Research 10(4). Elsevier: 504–513. DOI: 10.1016/j.jobcr.2020.08.005.
19. Islam, N., Lacey, B., Shabnam, S., et al., 2021. Social inequality and the syndemic of chronic disease and COVID-19: County-level analysis in the USA. Journal of Epidemiology and Community Health 75(6): 496–500. DOI: 10.1136/jech-2020-215626.
20. Khan, J.R., Awan, N., Islam, M.M., et al., 2020. Healthcare Capacity, Health Expenditure, and Civil Society as Predictors of COVID-19 Case Fatalities: A Global Analysis. Frontiers in Public Health 8(July): 1–10. DOI: 10.3389/fpubh.2020.00347.
21. Kohonen, T., 1982. Self-organized formation of topologically correct feature maps. Biological Cybernetics 43(1): 59–69. DOI: 10.1007/BF00337288.
22. Kohonen, T., 2013. Essentials of the self-organizing map. Neural Networks 37. Elsevier Ltd: 52–65. DOI: 10.1016/j.neunet.2012.09.018.
23. Kumru, S., Yiğit, P., Hayran, O., 2022. Demography, inequalities and Global Health Security Index as correlates of COVID-19 morbidity and mortality. International Journal of Health Planning and Management 37(2): 944–962. DOI: 10.1002/hpm.3384.
24. Levin, A.T., Owusu-Boaitey, N., Pugh, S., et al., 2022. Assessing the burden of COVID-19 in developing countries: Systematic review, meta-Analysis and public policy implications. BMJ Global Health 7(5): 1–17. DOI: 10.1136/bmjgh-2022-008477.
25. Mahmoudi, M.R., Baleanu, D., Mansor, Z., et al., 2020. Fuzzy clustering method to compare the spread rate of Covid-19 in the high risks countries. Chaos, Solitons and Fractals 140. Elsevier Ltd: 1–9. DOI: 10.1016/j.chaos.2020.110230.
26. Micah, A.E., Cogswell, I.E., Cunningham, B., et al., 2021. Tracking development assistance for health and for COVID-19: a review of development assistance, government, out-of-pocket, and other private spending on health for 204 countries and territories, 1990–2050. The Lancet 398(10308): 1317–1343. DOI: 10.1016/S0140-6736(21)01258-7.
27. OECD, 2023. OECD Statistics. Available at: https://stats.oecd.org/ (accessed 11 July 2023).
28. Our World in Data (2023) Data, Coronavirus Pandemic (COVID-19) - Statistics and Research - Our World in. Available at: https://ourworldindata.org/explorers/coronavirus (accessed 8 July 2023).
29. Rizvi, S.A., Umair, M., Cheema, M.A., 2021. Clustering of countries for COVID-19 cases based on disease prevalence, health systems and environmental indicators. Chaos, Solitons and Fractals 151. Elsevier Ltd: 111240. DOI: 10.1016/j.chaos.2021.111240.
30. Rousseeuw, P.J., 1987. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics 20(C): 53–65. DOI: 10.1016/0377-0427(87)90125-7.
31. Sadeghi, B., Cheung, R.C.Y., Hanbury, M., 2021. Using hierarchical clustering analysis to evaluate COVID-19 pandemic preparedness and performance in 180 countries in 2020. BMJ Open 11(11): 1–11. DOI: 10.1136/bmjopen-2021-049844.
32. Shuai, Y., Jiang, C., Su, X., et al., 2020. A Hybrid Clustering Model for Analyzing COVID-19 National Prevention and Control Strategy. 2020 IEEE 6th International Conference on Control Science and Systems Engineering, ICCSSE 2020: 68–71. DOI: 10.1109/ICCSSE50399.2020.9171941.
33. Siddiqui, M.K., Morales-Menendez, R., Gupta, P.K., et al., 2020. Correlation between temperature and COVID-19 (suspected, confirmed and death) cases based on machine learning analysis. Journal of Pure and Applied Microbiology 14(May): 1017–1024. DOI: 10.22207/JPAM.14.SPL1.40.
34. The World Bank, 2023. The World Bank Data.
35. Vesanto, J., Alhoniemi, E., 2000. Clustering of self-organizing map. IEEE TRANSACTIONS ON NEURAL NETWORKS 11(3): 586–600.
36. Wehrens, M.R., 2018. Package ‘ kohonen .’
37. WEO Groups and Aggregates Information, 2023. World Economic Outlook Database - Groups and Aggregates. Available at: https://www.imf.org/en/Publications/WEO/weo-database/2023/April/groups-and-aggregates (accessed 12 August 2023).
38. WHO, 2020. The top 10 causes of death. Available at: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death (accessed 28 December 2023).
39. WHO, 2023a. Coronavirus disease (COVID-19) pandemic. Available at: https://www.who.int/europe/emergencies/situations/covid-19 (accessed 10 August 2023).
40. WHO, 2023b. WHO Coronavirus (COVID-19) Dashboard.
41. Wolf, M.J., Emerson, J.W., Esty, D.C., et al., 2022. Environmental Performance Index. DOI: 10.1002/9781118445112.stat03789.
42. Worldometer, 2023. COVID - Coronavirus Statistics - Worldometer. Available at: https://www.worldometers.info/coronavirus/ (accessed 10 August 2023).
43. Zarikas, V., Poulopoulos, S.G., Gareiou, Z., et al., 2020. Clustering analysis of countries using the COVID-19 cases dataset. Data in Brief 31. Elsevier Inc.: 105787. DOI: 10.1016/j.dib.2020.105787.