COVID Geliştirme Duyarlılığını Tahmin Etmek için Makine Öğrenimi Modellerinin Geliştirilmesi

Öz

COVID-19 genomiklerinin karmaşıklıklarını çözmek son derece önemli bir sorundur. Virüsün genetik yapısında meydana gelen mutasyonlar, ilerlemesini ve semptomatolojisini doğal olarak öngörülemez kılmaktadır. Özellikle, “Uzun COVID” terimi, COVID-19’un kalıcı sonuçlarını belirtmek için ortaya çıkmış olup, etiyolojisini anlamak için yoğun çabaları tetiklemiştir. Devam eden çalışmalar, Uzun COVID’i ve belirleyicilerini titizlikle araştırmaktadır. Yapay zekâ (YZ) ve makine öğrenimi (MO) bu amaçla vazgeçilmez varlıklar olarak ortaya çıkmış olup, COVID-19 krizi ortamında hastalık duyarlılığını açıklığa kavuşturma ve öngörme konusunda dikkate değer etkinlik sergilemektedirler. Bu çerçevede, çabamız, Uzun COVID’in başlangıç olasılığını öngörmek için MO metodolojilerini kullanmaya yöneliktir. Bu amaçla, birden fazla MO modeli titizlikle eğitilmiştir. Ampirik bulgular, en yetkin modelin Uzun COVID’in meydana gelme olasılığını tahmin etmede takdir edilecek bir doğruluk oranı olan %80’e ulaştığını ortaya koymaktadır.

Anahtar Kelimeler

• Sınıflandırma
• özellik mühendisliği
• özellik seçimi
• makine öğrenimi

Development of Machine Learning Models to Predict the Susceptibility of Developing COVID

Öz

Abstract: Unraveling the intricacies of COVID-19 genomics is a very important problem. The mutations occurring within the virus’s genetic makeup render its progression and symptomatology inherently unpredictable. Notably, the term "Long COVID" has surfaced to delineate the enduring repercussions of COVID-19, prompting concerted efforts to comprehend its etiology. Ongoing studies are meticulously investigating Long COVID and its determinants. Artificial intelligence (AI) and machine learning (ML) have emerged as indispensable assets in this pursuit, demonstrating remarkable efficacy in elucidating underlying factors and forecasting disease susceptibility amidst the COVID-19 crisis. Within this framework, our endeavor aims to harness ML methodologies to prognosticate the likelihood of Long COVID onset. Multiple ML models have been meticulously trained for this purpose. The empirical findings reveal that the most proficient model attains a commendable accuracy rate of 80% in predicting Long COVID occurrence.

Anahtar Kelimeler

• Classification
• feature engineering
• feature selection
• machine learning.

Kaynakça

1. Ahsan M. M., Luna S. A., Siddique Z. Machine-learning-based disease diagnosis: A comprehensive review. In Healthcare, 2022, 10: 541.
2. Silva Andrade B, Siqueira S, de Assis Soares WR, de Souza Rangel F, Santos NO, dos Santos Freitas A, Ribeiro da Silveira P, Tiwari S, ve diğerleri. Long-COVID and post-COVID health complications: an up-to-date review on clinical conditions and their possible molecular mechanisms. Viruses, 2021; 13(4): 700.
3. https://portal.challenge.gov/public/previews/
4. Raveendran AV, Jayadevan R, Sashidharan S. Long COVID: An overview. Diabetes Metab Syndr 2021; 15(3): 869-875.
5. Syeda HB, Syed M, Sexton KW, Syed S, Begum S, Syed F, Prior F, Yu Jr F. Role of machine learning techniques to tackle the COVID-19 crisis: systematic review. JMIR Med Inform 2021; 9(1): 23811.
6. https://covid.cd2h.org/enclave
7. Dwivedi AK. Performance evaluation of different machine learning techniques for prediction of heart disease. Neural Comput & Applic 2018; 29(10): 685-693.
8. Kwekha-Rashid AS, Abduljabbar HN, Alhayani B. Coronavirus disease (COVID-19) cases analysis using machine-learning applications. Appl Nanosci 2021.1-13.

9. Alimadadi A, Aryal S, Manandhar I, Munroe PB, Joe B, Cheng X. Artificial intelligence and machine learning to fight COVID-19. Physiological genomics, 2020; 52(4): 200-202.
10. Burdick H, Lam C, Mataraso S, Siefkas A, Braden G, Dellinger RP, McCoy A, Vincent JL, ve diğerleri. Prediction of respiratory decompensation in Covid-19 patients using machine learning: The READY trial. Comput Biol and Med 2020; 124: 103949.
11. Arvind V, Kim JS, Cho BH, Geng E, Cho SK. Development of a machine learning algorithm to predict intubation among hospitalized patients with COVID-19. J Crit Care, 2021; 62:.25-30.
12. Haendel MA, Chute CG, Bennett TD, Eichmann DA, Guinney J, Kibbe WA, Payne PR, Pfaff ER, Robinson, PN, Saltz JH and Spratt H, The National COVID Cohort Collaborative (N3C): rationale, design, infrastructure, and deployment. Journal of the American Medical Informatics Association, 2021, 28(3): 427-443.
13. Vishwanathan, SVM, Murty MN, May. SSVM: a simple SVM algorithm. In Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN’02, 2002, 3: 2393-2398.
14. Kleinbaum, DG, Dietz K, Gail M, Klein, M. and Klein, M., Logistic regression, 2002, New York: Springer-Verlag.
15. Rokach L and Maimon O. Decision trees. Data mining and knowledge discovery handbook, 2005.
16. Hosmer Jr DW, Lemeshow S, Sturdivant RX. Applied logistic regression. Wiley; 2013.
17. Joachims T. Making large-scale SVM learning practical. SFB 475: Komplexitätsreduktion Multivariaten Datenstrukturen, Univ. Dortmund, Dortmund, Tech. Rep. 1998.
18. Quinlan JR. Induction of decision trees. Mach Learn. 1986, 1(1):81–106.
19. Cruz JA, Wishart DS. Applications of machine learning in cancer prediction and prognosis. Cancer Informat. 2006, 2:59–77.
20. Uddin S, Khan A, Hossain ME and Moni MA, 2019. Comparing different supervised machine learning algorithms for disease prediction. BMC medical informatics and decision making, 19(1):1-16.
21. Aneja S, Lal S. International Conference on Parallel, Distributed and Grid Computing (PDGC) 2014. Effective asthma disease prediction using naive Bayes—Neural network fusion technique.
22. Ahmad LG, Eshlaghy A, Poorebrahimi A, Ebrahimi M, Razavi A. Using three machine learning techniques for predicting breast cancer recurrence. J Health Med Inform. 2013, 4(124):3.
23. Chen M, Hao Y, Hwang K, Wang L, Wang L. Disease prediction by machine learning over big data from healthcare communities. IEEE Access. 2017, 5:8869–8879.
24. Yang J, Yao D, Zhan X, Zhan X. International Symposium on Bioinformatics Research and Applications. 2014. Predicting disease risks using feature selection based on random forest and support vector machine.