PREDICTING LONG-TERM COVID-19 SYMPTOMS USING MACHINE LEARNING: A CASE STUDY IN KURDISTAN REGION OF IRAQ

AVEEN KAKAMEN  MUSTAFA; IBRAHIM ISMAEL  HAMARASH

doi:10.26682/csjuod.2023.26.2.54

AVEEN KAKAMEN MUSTAFA *Computer Science, University of Kurdistan Hewler. Kurdistan Region - Iraq
IBRAHIM ISMAEL HAMARASH **Computer Engineering, Salahaddin University-Erbil, University of Kurdistan Hewler, Kurdistan Region - Iraq

DOI: https://doi.org/10.26682/csjuod.2023.26.2.54

Keywords: Long-Term, COVID 19, Pandemic, Machine Learning, Deep Learning, Healthcare Systems, Tenser Flow ,keras

Abstract

The COVID-19 pandemic has introduced substantial challenges to individuals, communities, and healthcare systems worldwide. While initial responses primarily addressed the acute impact of the virus, emerging evidence highlights a noteworthy portion of individuals grappling with persistent symptoms even after recuperating from the acute phase. This research delves into the domain of algorithms and their application to the context of COVID-19. Specifically, we employ Machine Learning (ML) techniques to formulate a robust model for assessing the likelihood of enduring long-term COVID-19 symptoms among individuals in the recovery phase. Our investigation revolves around a comprehensive dataset drawn from 3,500 patients residing in the Kurdistan Region of Iraq, all of whom had previously contracted COVID-19. Employing a combination of hospital records and direct/mobile interviews, we systematically capture information pertaining to six prevalent long-term symptoms. Rigorous preprocessing techniques are then applied to the collected data, ensuring standardization and mitigating any inherent inconsistencies or biases. To achieve our objective, we harness the capabilities of the TensorFlow and Keras libraries, leveraging a deep learning algorithm. This algorithm plays a pivotal role in predicting the probability of sustained COVID-19 symptoms among recovered patients. This endeavor demonstrates the potential of deep learning, especially when harnessed within a well-structured dataset and coupled with adept preprocessing methodologies. Consequently, our findings underscore the viability of utilizing deep learning algorithms as potent tools for forecasting the propensity of long-term symptom manifestation in individuals previously diagnosed with COVID-19.

Downloads

Download data is not yet available.

References

H. Zhang et al., “Data-driven identification of post-acute SARS-CoV-2 infection subphenotypes,” Nat Med, vol. 29, no. 1, pp. 226–235, Jan. 2023, doi: 10.1038/s41591-022-02116-3.
P. Z. Chen, N. Bobrovitz, Z. Premji, M. Koopmans, D. N. Fisman, and F. X. Gu, “SARS-COV-2 shedding dynamics across the respiratory tract, sex, and disease severity for adult and pediatric COVID-19,” Elife, vol. 10, Aug. 2021, doi: 10.7554/eLife.70458.
M. Heightman et al., “Post-COVID-19 assessment in a specialist clinical service: A 12-month, single-centre, prospective study in 1325 individuals,” BMJ Open Respir Res, vol. 8, no. 1, Nov. 2021, doi: 10.1136/bmjresp-2021-001041.
J. Dong et al., “Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care,” Crit Care, vol. 25, no. 1, Dec. 2021, doi: 10.1186/s13054-021-03724-0.
T. Aishwarya and V. Ravi Kumar, “Machine Learning and Deep Learning Approaches to Analyze and Detect COVID-19: A Review,” SN Computer Science, vol. 2, no. 3. Springer, May 01, 2021. doi: 10.1007/s42979-021-00605-9.
S. Lopez-Leon et al., “More than 50 long-term effects of COVID-19: a systematic review and meta-analysis,” Sci Rep, vol. 11, no. 1, Dec. 2021, doi: 10.1038/s41598-021-95565-8.
N. DeLuca et al., “Experiences with COVID-19 case investigation and contact tracing: A qualitative analysis,” SSM - Qualitative Research in Health, vol. 3, Jun. 2023, doi: 10.1016/j.ssmqr.2023.100244.
Adel Abdel Moneim, Marwa A Radwan, and Ahmed I Yousef, “COVID-19 and cardiovascular disease: manifestations, pathophysiology, vaccination, and long-term implication,” Jul. 2022.
D. Assaf et al., “Utilization of machine-learning models to accurately predict the risk for critical COVID-19,” Intern Emerg Med, vol. 15, no. 8, pp. 1435–1443, Nov. 2020, doi: 10.1007/s11739-020-02475-0.
T. Chakraborty, R. F. Jamal, G. Battineni, K. V. Teja, C. M. Marto, and G. Spagnuolo, “A review of prolonged post-covid-19 symptoms and their implications on dental management,” International Journal of Environmental Research and Public Health, vol. 18, no. 10. MDPI, May 02, 2021. doi: 10.3390/ijerph18105131.
H. Göker et al., “The effects of blood group types on the risk of COVID-19 infection and its clinical outcome,” Turk J Med Sci, vol. 50, no. 4, pp. 679–683, 2020, doi: 10.3906/sag-2005-395.
E. A. Troyer, J. N. Kohn, and S. Hong, “Are we facing a crashing wave of neuropsychiatric sequelae of COVID-19? Neuropsychiatric symptoms and potential immunologic mechanisms,” Brain, Behavior, and Immunity, vol. 87. Academic Press Inc., pp. 34–39, Jul. 01, 2020. doi: 10.1016/j.bbi.2020.04.027.
A. Pavli, M. Theodoridou, and H. C. Maltezou, “Post-COVID Syndrome: Incidence, Clinical Spectrum, and Challenges for Primary Healthcare Professionals,” Archives of Medical Research, vol. 52, no. 6. Elsevier Inc., pp. 575–581, Aug. 01, 2021. doi: 10.1016/j.arcmed.2021.03.010.
L. E. Boulware et al., “Combating Structural Inequities — Diversity, Equity, and Inclusion in Clinical and Translational Research,” New England Journal of Medicine, vol. 386, no. 3, pp. 201–203, Jan. 2022, doi: 10.1056/nejmp2112233.
N. Subramanian, O. Elharrouss, S. Al-Maadeed, and M. Chowdhury, “A review of deep learning-based detection methods for COVID-19,” Computers in Biology and Medicine, vol. 143. Elsevier Ltd, Apr. 01, 2022. doi: 10.1016/j.compbiomed.2022.105233.
R. Karthikeyan, et al., “A fractional order model for the novel coronavirus (COVID-19) outbreak”, Nonlinear Dynamics, 24 June 2020. doi.org/10.1007/s11071-020-05757-6.
B. A. S. Al-rimy, M. A. Maarof, and S. Z. M. Shaid, “Ransomware threat success factors, taxonomy, and countermeasures: A survey and research directions,” Comput Secur, vol. 74, pp. 144–166, May 2018, doi: 10.1016/J.COSE.2018.01.001.