Calculation of Mortality Risks of Covid-19 Patients with Machine Learning Algorithms

Yıl 2022, , 994 - 1011, 22.08.2022

Mehmet Aziz Çakmak , Mehmet Emin Kurt , Cuma Çakmak

https://doi.org/10.21076/vizyoner.1074212

Cited By: 2

Öz

The aim of the study is to calculate the mortality risk of patients diagnosed with Covid-19 using Machine Learning algorithms. In the study, demographic and clinical data of patients admitted to the health facility with the diagnosis of Covid-19 in Atlanta, Georgia, which are published as open access on the web, are used. The mortality risk of the patients is calculated using Machine Learning algorithms called Decision Tree, Random Forest and Adaptive Boost based on the data. It is observed that the demographic and clinical findings of the patients are effective on mortality risks and that the Machine Learning-based prediction modeling created in this direction can be applied with high reliability (Acc=83.5). With the findings obtained, high-reliability classification models can be created using Machine Learning methods and decision support modules can be created that can guide clinicians and health professionals in patient prioritization in line with the calculation of mortality risks of patients. By creating web-based modules, a scientific basis is established for health authorities, clinicians and hospital managers to make effective and efficient preparations for bed occupancy planning. Unnecessary health expenditures and patients who are likely to have a relatively mild illness can be prevented from receiving unnecessary treatment.

Anahtar Kelimeler

Machine Learning Algorithms/Covid-19, Mortality Risk, Clinical Data, Clinicians

Makine Öğrenmesi Algoritmaları ile Covid-19 Hastalarının Mortalite Risklerinin Hesaplanması

Öz

Bu çalışmanın amacı, Makine Öğrenmesi algoritmalarıyla Covid-19 tanılı hastaların mortalite riskinin hesaplanmasıdır. Bu çalışmada, web üzerinde açık erişimli olarak yayınlanan Atlanta, Georgia’da Covid-19 tanısı alarak sağlık tesisine yatan hastaların demografik ve klinik verileri kullanılmıştır. Bu veriler üzerinden Karar Ağacı, Rastsal Orman ve Adaptive Boost olarak adlandırılan Makine Öğrenmesi algoritmaları kullanılarak hastaların mortalite riski hesaplanmıştır. Hastaların demografik ve klinik bulgularının mortalite riskleri üzerinde etkili olduğu ve bu doğrultuda oluşturulan Makine Öğrenmesi tabanlı tahmin modellemesinin yüksek güvenirlikle (Acc=83,5) uygulanabileceği görülmüştür. Elde edilen bulgularla birlikte Makine Öğrenmesi yöntemleri kullanılarak yüksek düzeyde güvenilir sınıflandırma modellemeleri oluşturulup hastaların mortalite risklerinin hesaplanması doğrultusunda klinisyenler ve sağlık profesyonellerine hasta önceliklendirme konusunda kılavuz olabilecek karar destek modülleri oluşturulabilmektedir. Web tabanlı modüller oluşturularak sağlık otoritelerine, klinisyenlere ve hastane yöneticilerine yatak doluluğu planlaması açısından etkin ve verimli hazırlık yapabilmeleri açısından bilimsel dayanak oluşturulmaktadır. Gereksiz sağlık harcamalarının ve hastalığı görece hafif geçirme ihtimali olan hastaların gereksiz tedavi almaları önlenebilecektir.

Anahtar Kelimeler

Makine Öğrenmesi Algoritmaları, Covid-19, Mortalite Riski, Klinik Veriler, Klinisyenler

Kaynakça

• Ahmad, I. ve Asad, S. M. (2020). Predictions of coronavirus COVID-19 distinct cases in Pakistan through an artificial neural network. Epidemiology & Infection, 148(e222), 1-10.
• Alaa, A. M., Bolton, T., Di Angelantonio, E., Rudd, J. ve van der Schaar, M. (2019). Cardiovascular disease risk prediction using automated machine learning: A prospective study of 423,604 UK Biobank participants. PloS one, 14(5), 1-17.
• Alballa, N. ve Al-Turaiki, I. (2021). Machine learning approaches in COVID-19 diagnosis, mortality, and severity risk prediction: A review. Informatics in Medicine Unlocked, 24(2021), 1-17.
• Altschul, D. J., Unda, S. R., Benton, J., Ramos, R., Mehler, M. ve Eskandar, E. (2021). Mortality incidence, sociodemographic and clinical data in COVID-19 patients. Figshare, Dataset. https://doi.org/10.6084/m9.figshare.12685475.v1
• Ayaz, M. (2021). Makine öğrenmesi algoritmaları ile covid-19 hastalarının belirlenmesi [Yüksek Lisans Tezi]. Pamukkale Üniversitesi.
• Breiman, L., Friedman, J. H., Olshen, R. A., ve Stone, C. J. (2017). Classification and regression trees. Routledge.
• Brijain, M., Patel, R., Kushik, M. R. ve Rana, K. (2014). A survey on decision tree algorithm for classification.
• Connor, C. W. (2019). Artificial Intelligence and Machine Learning in Anesthesiology. Anesthesiology, 131(6), 1346–1359.
• DeGregory, K. W., Kuiper, P., DeSilvio, T., Pleuss, J. D., Miller, R., Roginski, J. W., Fisher, C. B., Harness, D., Viswanath, S., Heymsfield, S. B., Dungan, I. ve Thomas, D. M. (2018). A review of machine learning in obesity. Obesity reviews: An official journal of the International Association for the Study of Obesity, 19(5), 668–685.
• Deo, R. C. (2015). Machine Learning in Medicine. Circulation, 132(20), 1920–1930.
• Henwood, A. F. (2020). Coronavirus disinfection in histopathology. Journal of histotechnology, 43(2), 102-104.
• Jaskari, J., Myllärinen, J., Leskinen, M., Rad, A. B., Hollmén, J., Andersson, S. ve Särkkä, S. (2020). Machine learning methods for neonatal mortality and morbidity classification. IEEE Access, 8, 123347-123358.
• Kilic, A., Goyal, A., Miller, J. K., Gleason, T. G. ve Dubrawksi, A. (2021). Performance of a machine learning algorithm in predicting outcomes of aortic valve replacement. The Annals of Thoracic Surgery, 111(2), 503-510.
• Kim, M. J. (2021). Building a Cardiovascular Disease Prediction Model for Smartwatch Users Using Machine Learning: Based on the Korea National Health and Nutrition Examination Survey. Biosensors, 11(7), 228.
• Li, W. T., Ma, J., Shende, N., Castaneda, G., Chakladar, J., Tsai, J. C., Apostol, L., Honda, C. O., Xu, J., Wong, L. M., Zhang, T., Lee, A., Gnanasekar, A., Honda, T. K., Kuo, S. Z., Yu, M. A., Chang, E. Y., Rajasekaran, M. R. ve Ongkeko, W. M. (2020). Using machine learning of clinical data to diagnose COVID-19: a systematic review and meta-analysis. BMC Medical Informatics and Decision Making, 20(1), 247.
• Matsuo, K., Aihara, H., Nakai, T., Morishita, A., Tohma, Y. ve Kohmura, E. (2020). Machine learning to predict in-hospital morbidity and mortality after traumatic brain injury. Journal of neurotrauma, 37(1), 202-210.
• McAvaney, B. J., Covey, C., Joussaume, S., Kattsov, V., Kitoh, A., Ogana, W. ve Zhao, Z. C. (2001). Model evaluation. In Climate Change 2001: The scientific basis. Contribution of WG1 to the Third Assessment Report of the IPCC (TAR) (s. 471-523). Cambridge University Press.
• Moulaei, K., Shanbehzadeh, M., Mohammadi-Taghiabad, Z. ve Kazemi-Arpanahi, H. (2022). Comparing machine learning algorithms for predicting COVID-19 mortality. BMC Medical Informatics and Decision Making, 22(1), 2.
• Muhiyaddin, R., Abd-Alrazaq, A. A., Househ, M., Alam, T.ve Shah, Z. (2020). The Impact of Clinical Decision Support Systems (CDSS) on Physicians: A Scoping Review. Studies in Health Technology and Informatics, 272, 470–473.
• National Health Commission of the PRC. (2021). Features, transmission, symptoms and mortality rate. http://en.nhc.gov.cn/2020-03/01/c_77162.htm adresinden 9 Kasım 2021 tarihinde alınmıştır.
• Oh, J., Yun, K., Maoz, U., Kim, T. S. ve Chae, J. H. (2019). Identifying depression in the National Health and Nutrition Examination Survey data using a deep learning algorithm. Journal of Affective Disorders, 257, 623–631.
• Pollard, S., Bansback, N. ve Bryan, S. (2015). Physician attitudes toward shared decision making: A systematic review. Patient Education and Counseling, 98(9), 1046–1057.
• Rosenstock, I. M. (2005). Why people use health services. The Milbank Quarterly, 83(4),1-32.
• Saber, H., Somai, M., Rajah, G. B., Scalzo, F. ve Liebeskind, D. S. (2019). Predictive analytics and machine learning in stroke and neurovascular medicine. Neurological Research, 41(8), 681–690.
• Sapra, A., Malik, A. ve Bhandari, P. (2021). Vital sign assessment. StatPearls Publishing.
• Sreepadmanabh, M., Sahu, A. K. ve Chande, A. (2020). COVID-19: Advances in diagnostic tools, treatment strategies, and vaccine development. Journal of biosciences, 45(1), 148. https://doi.org/10.1007/s12038-020-00114-6
• Şahin, Ö. S., Üçer, M., Özaydın, B.ve Doğan, I. (2018). Nöroşirürji’de yapay zekâ ve insan zekası. Türk Nöroşirürji Dergsi, 28(3), 277-283.
• Vens, C., Struyf, J., Schietgat, L., Džeroski, S. ve Blockeel, H. (2008). Decision trees for hierarchical multi-label classification. Machine learning, 73(2), 185-214.
• Visa, S., Ramsay, B., Ralescu, A. L. ve Van Der Knaap, E. (2011). Confusion matrix-based feature selection. MAICS, 710, 120-127.
• Wang, P., Zheng, X., Li, J.ve Zhu, B. (2020). Prediction of epidemic trends in COVID-19 with logistic model and machine learning technics. Chaos, Solitons & Fractals, 139, 110058.
• Wirth, R. ve Hipp, J. (2000, April). CRISP-DM: Towards a standard process model for data mining. Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining (s. 29-40).
• World Health Organization. (2022). https://www.who.int/data adresinden 22 Şubat 2022 tarihinde alınmıştır.
• Wu, C. C., Yeh, W. C., Hsu, W. D., Islam, M. M., Nguyen, P. A. A., Poly, T. N., ... ve Li, Y. C. J. (2019). Prediction of fatty liver disease using machine learning algorithms. Computer Methods and Programs in Biomedicine, 170, 23-29.
• Zhang, Y., Coecke, B.ve Chen, M. (2019). On the cost of interactions in interactive visual machine learning. 2019 IEEE workshop on EValuation of Interactive VisuAl Machine Learning systems (Eviva-ML). IEEE.
• Zheng, Y., Zhu, Y., Ji, M., Wang, R., Liu, X., Zhang, M., Liu, J., Zhang, X., Qib, C.H., Fang, L. ve Ma, S. (2020). A learning-based model to evaluate hospitalization priority in COVID-19 pandemics. Patterns, 1(6),1-10.