Evaluation of COVID-19 mortality using machine learning regression methods based on health system indicators

Year 2024, Volume: 42 Issue: 6, 1797 - 1805, 09.12.2024

Canan Bulut , Tuğba Sönal , Dilek Kolca , Fatih Tarlak

Abstract

In the global health crisis caused by the COVID-19 pandemic, countries have faced significant challenges in combating the outbreak in terms of healthcare systems and economies. Evaluating the performance of healthcare systems in dealing with pandemics has become a priority for policymakers, healthcare providers, and the public alike. Assessing the performance of healthcare systems during the pandemic is crucial for preparedness and improvements in similar situations in the future. By identifying complex patterns and relationships, machine learning algorithms aim to uncover the relationship between healthcare system indicators and deaths due to the COVID-19 pandemic, using large and intricate datasets. These algorithms utilize various datasets containing demographic information and medical factors to reveal hidden relationships between various variables and disease severity. The objective of this study is to predict COVID-19 death rates for 27 OECD (Organisation for Economic Cooperation and Development) countries spanning the period from 2006 to 2019 using various machine learning regression methods. Health-care system indicators, comprising accessibility, healthcare financing, and healthcare workforce, have been aggregated into three dimensions. The dataset includes COVID-19 death counts per a million-population due to the pandemic. Random forest regression, neural network regression, and Gaussian process regression were employed to forecast COVID-19 death rates, and the predictive capabilities of machine learning regression methods were evaluated using k-fold cross validation. The suitability of the algorithms was assessed using statistical measures such as the coefficient of determination (R²) and root mean square error (RMSE). A high R² value and a low RMSE indicate that Gaussian process regression (GPR) can effectively predict COVID-19 death rates, taking various health indicators into account. Machine learning regression methods have revolutionized our understanding of COVID-19 death rates. Through prediction models, machine learning has empowered healthcare professionals with the ability to forecast death risks for individual patients, guiding decision-making processes and resource allocation. According to the research findings, to enhance the performance of healthcare systems in coping with global pandemics, there is a need to prioritize community-based healthcare services, adopt a social policy approach, encourage the use of advanced technology, ensure the trust of the public and healthcare workers, enhance social support opportunities, emphasize the importance of measures by leaders, and support global governance. Additionally, flexible supply chain plans for the procurement of personal protective equipment have been identified as necessary.

Keywords

COVID-19, Health Indicator, Prediction, Machine Learning

References

• REFERENCES
• [1] Basler MJ, Basler RC. Understanding power system stability. IEEE Trans Ind Appl 2008;44:463–474.
• [2] Kundur P. Power System Stability and Control. New York, USA: McGraw Hill;1994.
• [3] Law KT, Godfrey NR. Robust co-ordinated AVR-PSS design. IEEE Trans Power Syst 1994;9:1218–1225.
• [4] Bourl√®s HC, Houry MP. Robust continuous speed governor control for small-signal and transient stability. IEEE Trans Power Syst 1997;12:129–135. https://doi.org/10.1109/59.574932
• [5] Dudgeon GJW, Dysko A, O'Reilly J, McDonald JR. The effective role of AVR and PSS in power systems: Frequency response analysis. IEEE Trans Power Syst 2007;22:1986–1994.
• [6] Wei SZ, Huang Y. Synchronous motor-generator pair to enhance small signal and transient stability of power system with high penetration of renewable energy. IEEE Access 2017;5:11505–11512.
• [7] Xiang JH, Ma J. Distributed power control for transient stability of multimachine power systems. IEEE J Emerg Sel Top Circuits Syst 2017;7:383–392.
• [8] Khayyatzadeh M, Khayyatzadeh R. Sub-synchronous resonance damping using high penetration PV plant. Mech Syst Signal Process 2017;84:431–444.
• [9] Varma RK, Varma S. SSR mitigation with a new control of PV solar farm as STATCOM (PV-STATCOM). IEEE Trans Sustain Energy 2017;8:1473–1483.
• [10] Varma RK, Varma H. PV solar system control as STATCOM (PV-STATCOM) for power oscillation damping. IEEE Trans Sustain Energy 2019;10:1793–1803.
• [11] Wang LL, Prokhorov AV, Mokhlis H, Huat CK. Modal control design of damping controllers for thyristor-controlled series capacitor to stabilize common-mode torsional oscillations of a series- capacitor compensated power system. IEEE Trans Ind Appl 2019;55:2327–2336.
• [12] Gupta SK, Gupta AK, Kumar N. Damping subsynchronous resonance in power systems. IEE Proc Gener Transm Distrib 2002;149:679–688.
• [13] Gupta SK, Kumar N, Gupta AK. Controlled series compensation in coordination with double order SVS auxiliary controller and induction M/C for repressing the torsional oscillations in power systems. Available at: www.elsevier.com/locate/epsr Last Accessed Date: 22.11.2024.
• [14] Hingorani NG, Gyugyi L, El-Hawary ME. Understanding FACTS: concepts and technology of flexible AC transmission systems. New York: IEEE Press; 2000.
• [15] Wang LC, Kuan BL, Prokhorov AV. Stability improvement of a two-area power system connected with an integrated onshore and offshore wind farm using a STATCOM. IEEE Trans Ind Appl 2017;53:867–877.
• [16] Bakhshi MH, Rabiee A. Fuzzy based damping controller for TCSC using local measurements to enhance transient stability of power systems. Int J Electr Power Energy Syst 2017;85:12–21.
• [17] Kiran SHD, Subramani C. Performance of two modified optimization techniques for power system voltage stability problems. Alex Eng J 2016;55:2525–2530.
• [18] Inkollu SR, Reddy VR. Optimal setting of FACTS devices for voltage stability improvement using PSO adaptive GSA hybrid algorithm. Eng Sci Technol Int J 2016;19:1166–1176.
• [19] Safari AA, Golkar MA. Controller design of STATCOM for power system stability improvement using honey bee mating optimization. J Appl Res Technol 2013;11:144–155.
• [20] Yao JW, Li J, Liu R, Zhang H. Sub-synchronous resonance damping control for series-compensated DFIG-based wind farm with improved particle swarm optimization algorithm. IEEE Trans Energy Convers 2019;34:849–859.
• [21] Bamba S, Gupta SK. Sub-synchronous resonance mitigation in series-compensated power systems using a GWO-based optimal controller. In: India International Conference on Power Electronics, IICPE. IEEE Computer Society; 2023.
• [22] Kumar R, Singh R, Ashfaq H. Stability enhancement of multi-machine power systems using ant colony optimization-based static synchronous compensator. Comput Electr Eng 2020;83.
• [23] Yousuf V, Ahmad A. Optimal design and application of fuzzy logic equipped control in STATCOM to abate SSR oscillations. Int J Circuit Theory Appl 2021;49:4070–4087.
• [24] Moradi-Shahrbabak Z. Proposed sub-synchronous resonance damping controller for large-scale wind farms. IET Renew Power Gener 2023;17:3209–3220.
• [25] Padiyar KR, Prabhu N. Analysis of SSR with three-level twelve-pulse VSC-based interline power-flow controller. IEEE Trans Power Deliv 2007;22:1688–1695.
• [26] Farmer RG. Second benchmark model for computer simulation of subsynchronous resonance. IEEE Power Eng Rev 1985;PER-5:34.
• [27] Second benchmark model for computer simulation of subsynchronous resonance. IEEE Subsynchronous Resonance Working Group. 1985.
• [28] Sharma PR, Gupta SK, Yadav P, Sharma PR. Optimal location of UPFC in power system using multi-objective GAPSO hybrid algorithm. Int J Ser Eng Sci 2016;2:26–45.
• [29] Minaxi, Saini S. Frequency control using different optimization techniques of a standalone PV-wind-diesel with BESS hybrid system. IEEJ Trans Power Energy 2023;143:218–225.
• [30] Wadhwa K, Gupta SK. A novel black widow optimized controller approach for automatic generation control in modern hybrid power systems. Int J Electr Electron Res 2023;11:819–825.
• [31] Wadhwa K, Gupta SK. Integrating capacitive energy storage (CES) into existing power system to manage frequency deviation. Int J Intell Syst Appl Eng 2024;12:737–734.
• [32] Mirjalili S, Mirjalili SM, Lewis A. Grey wolf optimizer. Adv Eng Softw 2014;69:46–61.
• [33] Prasad CE, Vadhera S. Mitigation of sub synchronous resonance using STATCOM controlled by PID and FL controllers. In: 2014 IEEE 6th India International Conference on Power Electronics (IICPE). IEEE; 2014. p. 1–5.