COVID-19 Crisis Management: Global Appraisal using Two-Stage DEA and Ensemble Learning Algorithms

Document Type : Article

Authors

Faculty of Industrial and Mechanical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran

Abstract

Due to the rapid growth of COVID-19 data, this paper investigated an integrated approach for performance evaluation of countries at any time of the COVID-19 pandemic. First, the strategies implemented in countries were summarized in three systems: prevention, infection detection, and medical. Then, the input-output of the systems was identified. In Phase 1, after variable selection (tests, total cases, active cases, recovered cases, and deaths), data were collected for 100 countries with the highest infected cases by June 21, 2021. Then, mathematical modeling of two-stage data envelopment analysis with desirable-undesirable variables was performed using three basic ideas: independent, connected, and relational. By solving the relational model, the efficiency scores of the countries were obtained, and they were categorized into four classes based on these results. In Phase 2, 80% of the data were considered as training samples to generate a machine learning model via ensemble methods (i.e., Bag, Adaptive Boost, and Random Under-Sampling Boost). In Phase 3, the class of test samples was predicted using the optimal ensemble model. The results showed that in a small dataset, the Bag algorithm had 95% accuracy in predicting the class of test samples.

Keywords


  1. References: 

    1. World Health Organization, Novel Coronavirus (2019-nCoV) (SITUATION REPORT-1), Reported January 20, 2020, URL https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200121-sitrep-1-2019-ncov.pdf
    2. Coronaviridae Study Group. “The species Severe acute respiratory syndrome-related coronavirus: classifying 2019-nCoV and naming it SARS-CoV-2”, Nature microbiology, 5(4), p.536 (2020).
    3. World Health Organization, Novel Coronavirus (2019-nCoV) (Situation Report –22), Reported February 11, 2020, URL https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200211-sitrep-22-ncov.pdf
    4. World Health Organization, WHO Coronavirus (COVID-19) Dashboard, Updated June 21, 2021, URL https://covid19.who.int/
    5. Johns Hopkins University, COVID-19 Dashboard by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University (JHU), Updated June 21, 2021, URL https://coronavirus.jhu.edu/map.html/
    6. Worldometers, Reported Cases and Deaths by Country or Territory. Updated 16:17 GMT June 21, 2021, Accessed June 21, 2021, https://www.worldometers.info/coronavirus/
    7. Jacobsen, K.H. “Will COVID-19 generate global preparedness?”, Lancet (London, England), 395(10229), p.1013 (2020).
    8. Wang, P., Zheng, X., Li, J., et al. “Prediction of epidemic trends in COVID-19 with logistic model and machine learning technics”, Chaos, Solitons & Fractals, 139, p.110058 (2020).
    9. Farooq, J. and Bazaz, M.A. “A novel adaptive deep learning model of Covid-19 with focus on mortality reduction strategies”, Chaos, Solitons & Fractals, 138, p.110148 (2020).
    10. Rafiq, D., Batool, A. and Bazaz, M.A. “Three months of COVID‐19: A systematic review and meta‐analysis”, Reviews in medical virology, 30(4), p.e2113 (2020).
    11. Charnes, A., Cooper, W.W. and Rhodes, E. “Measuring the efficiency of decision making units”, European journal of operational research, 2(6), pp.429-444 (1978).
    12. Alinezhad, A., Makui, A. and Mavi, R.K. “An inverse DEA model for inputs/outputs estimation with respect to decision maker’s preferences: The case of Refah bank of IRAN”, Mathematical Sciences, 1(1-2), pp.61-70 (2007).
    13. Alinezhad, A., Sarrafha, K. and Amini, A. “Sensitivity analysis of SAW technique: The impact of changing the decision making matrix elements on the final ranking of alternatives”, Iranian Journal of Operations Research, 5(1), pp.82-94 (2014).
    14. Sarrafha, K., Kazemi, A. and Alinezhad, A. “A multi-objective evolutionary approach for integrated production-distribution planning problem in a supply chain network”, Journal of Optimization in Industrial Engineering, 7(14), pp.89-102 (2014).
    15. Khalili, J. and Alinezhad, A. “Performance evaluation in green supply chain using BSC, DEA and data mining”, International journal of supply and operations management, 5(2), pp.182-191 (2018).
    16. Alinezhad, A. and Khalili, J., MAUT Method. New methods and applications in multiple attribute decision making (MADM), Springer, Cham, pp. 127–131 (2019).
    17. Amini, A. Alinezhad, A. and Yazdipoor, F., “A TOPSIS, VIKOR and DEA integrated evaluation method with belief structure under uncertainty to rank alternatives”, International Journal of Advanced Operations Management, 11(3), pp. 171-188 (2019).
    18. Vaezi, E. “Performance Measurement in the Health Care Sector: a Leader-Follower Network DEA Model based on Double Frontier Analysis”, Scientia Iranica, (2020).
    19. Esmaeeli, J., Amiri, M. and Taghizadeh, H. “A new approach in the DEA technique for measurement of productivity of decision-making units through efficiency and effectiveness”, Scientia Iranica, (2021).
    20. Sadat Rezaei, M. and Haeri, A. “A heuristic method for choosing 'virtual best' DMUs to enhance the discrimination power of the augmented DEA model”, Scientia Iranica, 28(4), pp. 2400-2418. (2021).
    21. Emrouznejad, A. and Yang, G.L. “A survey and analysis of the first 40 years of scholarly literature in DEA: 1978–2016”, Socio-economic planning sciences, 61, pp.4-8 (2018).
    22. Kao, C. “Network data envelopment analysis”, International Series in Operations Research & Management Science, 10, pp.978-3 (2017).
    23. Zhu, N., Zhu, C. and Emrouznejad, A. “A combined machine learning algorithms and DEA method for measuring and predicting the efficiency of Chinese manufacturing listed companies”, Journal of Management Science and Engineering, (2020).
    24. Agrawal, T. “Hyperparameter Optimization in Machine Learning”, Apress, (2021).
    25. Misiunas, N., Oztekin, A., Chen, Y., et al. “DEANN: A healthcare analytic methodology of data envelopment analysis and artificial neural networks for the prediction of organ recipient functional status”, Omega, 58, pp.46-54 (2016).
    26. De Clercq, D., Wen, Z. and Fei, F. “Determinants of efficiency in anaerobic bio-waste co-digestion facilities: A data envelopment analysis and gradient boosting approach”, Applied Energy, 253, p.113570 (2019).
    27. Liu, L. and Zhan, X. “Analysis of financing efficiency of Chinese agricultural listed companies based on machine learning”, Complexity, (2019).
    28. Mirmozaffari, M., Boskabadi, A., Azeem, G., et al. “Machine learning clustering algorithms based on the DEA optimization approach for banking system in developing countries”, European Journal of Engineering and Technology Research, 5(6), pp.651-658 (2020).
    29. Rebai, S., Yahia, F.B. and Essid, H. “A graphically based machine learning approach to predict secondary schools performance in Tunisia”, Socio-Economic Planning Sciences, 70, p.100724 (2020).
    30. Salehi, V., Veitch, B. and Musharraf, M. “Measuring and improving adaptive capacity in resilient systems by means of an integrated DEA-Machine learning approach”, Applied ergonomics, 82, p.102975 (2020).
    31. Gupta, A., Kohli, M. and Malhotra, N. “Classification based on Data Envelopment Analysis and supervised learning: A case study on energy performance of residential buildings”, In 2016 IEEE 1st international conference on power electronics, intelligent control and energy systems (ICPEICES), pp. 1-5 (2016).
    32. Nandy, A. and Singh, P.K. “Farm efficiency estimation using a hybrid approach of machine-learning and data envelopment analysis: Evidence from rural eastern India”, Journal of Cleaner Production, 267, p.122106 (2020).
    33. Emrouznejad, A. and Shale, E. “A combined neural network and DEA for measuring efficiency of large scale datasets”, Computers & Industrial Engineering, 56(1), pp.249-254 (2009).
    34. Murphy, K.P. “Machine learning: a probabilistic perspective”, MIT press, (2012).
    35. Loey, M., Manogaran, G., Taha, M.H.N., et al. “A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic”, Measurement, 167, p.108288 (2021).
    36. Ordu, M., Kirli Akin, H. and Demir, E. “Healthcare systems and Covid19: Lessons to be learnt from efficient countries”, The International Journal of Health Planning and Management, (2021).
    37. Mariano, E., Torres, B., Almeida, M., et al. “Brazilian states in the context of COVID-19 pandemic: an index proposition using Network Data Envelopment Analysis”, IEEE Latin America Transactions, 19(6), pp.917-924 (2021).
    38. Nepomuceno, T.C., Silva, W., Nepomuceno, K.T., et al. “A DEA-based complexity of needs approach for hospital beds evacuation during the COVID-19 outbreak”, Journal of healthcare engineering, (2020).
    39. Yeasmin, S., Banik, R., Hossain, S., et al. “Impact of COVID-19 pandemic on the mental health of children in Bangladesh: A cross-sectional study”, Children and youth services review, 117, p.105277 (2020).
    40. Ahamad, M.M., Aktar, S., Rashed-Al-Mahfuz, M., et al. “A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients”, Expert systems with applications, 160, p.113661 (2020).
    41. Malki, Z., Atlam, E.S., Hassanien, A.E., et al. “Association between weather data and COVID-19 pandemic predicting mortality rate: Machine learning approaches”, Chaos, Solitons & Fractals, 138, p.110137 (2020).
    42. Sonbhadra, S.K., Agarwal, S. and Nagabhushan, P. “Target specific mining of COVID-19 scholarly articles using one-class approach”, Chaos, Solitons & Fractals, 140, p.110155 (2020).
    43. Mahmoudi, M.R., Baleanu, D., Mansor, Z., et al. “Fuzzy clustering method to compare the spread rate of Covid-19 in the high risks countries”, Chaos, Solitons & Fractals, 140, p.110230 (2020).
    44. Imtyaz, A., Haleem, A. and Javaid, M. “Analysing governmental response to the COVID-19 pandemic”, Journal of Oral Biology and Craniofacial Research, 10(4), pp.504-513 (2020).
    45. Guerrero, M.D., Vanderloo, L.M., Rhodes, R.E., et al. “Canadian children's and youth's adherence to the 24-h movement guidelines during the COVID-19 pandemic: A decision tree analysis”, Journal of sport and health science, 9(4), pp.313-321 (2020).
    46. Mei, Y., Weinberg, S.E., Zhao, L., et al. “Risk stratification of hospitalized COVID-19 patients through comparative studies of laboratory results with influenza”, E-Clinical Medicine, 26, p.100475 (2020).
    47. Aydin, N. and Yurdakul, G. “Assessing countries’ performances against COVID-19 via WSIDEA and machine learning algorithms”, Applied Soft Computing, 97, p.106792 (2020).
    48. Institute for Health Metrics and Evaluation, COVID-19 Projections, 2021. URL https://covid19.healthdata.org/
    49. Liu, W.B., Meng, W., Li, X.X., et al. “DEA models with undesirable inputs and outputs”, Annals of Operations Research, 173(1), pp.177-194 (2010).
    50. Färe, R. and Grosskopf, S. “Modeling undesirable factors in efficiency evaluation: comment”, European Journal of Operational Research, 157(1), pp.242-245 (2004).
    51. Kiani Mavi, R. Makui, A. Fazli, S., et al. “A forecasting method in data envelopment analysis with group decision making”, International Journal of Applied Management Science. 2 (2), pp. 152-168 (2010).
    52. Färe, R. and Grosskopf, S. “Productivity and intermediate products: A frontier approach”, Economics letters, 50(1), pp.65-70 (1996).
    53. Kao, C. “Efficiency decomposition in network data envelopment analysis: A relational model”, European journal of operational research, 192(3), pp.949-962 (2009).
    54. Kumar, A. and Mayank, J., Ensemble Learning for AI Developers, New Delhi, India: Springer, (2020).
    55. Zhou, Z.H., Ensemble methods: foundations and algorithms, Chapman and Hall/CRC, (2019).
    56. Alfaro, E., Gámez, M. and García, N., Ensemble classification methods with applications in R, John Wiley & Sons, (2018).
    57. Zhang, C. and Ma, Y., Ensemble machine learning: methods and applications, Springer Science & Business Media, (2012).
    58. Breiman, L. “Bagging predictors”, Machine learning, 24(2), pp.123-140 (1996).
    59. Freund, Y. and Schapire, R.E. “Experiments with a new boosting algorithm”, in icml, 96, pp. 148-156 (1996).
    60. Seiffert, C., Khoshgoftaar, T.M., Van Hulse, J., et al. “RUSBoost: Improving classification performance when training data is skewed”, 19th International Conference on Pattern Recognition, pp. 1-4, (2008).
    61. Sarkis, J., Preparing your data for DEA. In Modeling data irregularities and structural complexities in data envelopment analysis, Springer, Boston, MA, pp. 305-320 (2007).
    62. The Math Works, Inc., MATLAB, version R2019b, URL https://de.mathworks.com/
    63. Tabachnick, B. G., Fidell, L. S. and Ullman, J. B., Using multivariate statistics, 5. Boston, MA: Pearson, (2007).
    64. Cousineau, D. and Chartier, S. “Outliers detection and treatment: a review”, International Journal of Psychological Research, 3(1), pp.58-67 (2010).
    65. Kalkan, Ö. K., Yusuf, K. and Kelecioğlu, H. “Evaluating performance of missing data imputation methods in IRT analyses”, International Journal of Assessment Tools in Education, 5(3), pp.403-416 (2018).