Biological Data

Association Rule Mining Reveals IgG–Symptom Relationships in COVID-19 Patients: Insights for Personalized Medicine

Document Type : Original Article

Author

Department of Radiology, Kurdistan University of Medical Sciences, Sanandaj, Iran

Abstract

The COVID-19 pandemic has underscored the variability in immune responses and symptom presentations due to SARS-CoV-2, with Immunoglobulin G (IgG) levels critical for long-term immunity. This study explores the relationship between IgG levels and COVID-19 symptoms using association rule mining (ARM) to address a research gap. A cross-sectional study was conducted during the third wave of COVID-19 in western Iran, enrolling 237 RT-PCR-confirmed patients, excluding those with autoimmune conditions or recent infections. Data on demographics, IgG levels (measured via ELISA), and symptoms (e.g., fever, cough, loss of smell) were analyzed using the ORANGE software for machine learning with the Apriori algorithm, applying 90% confidence, 0.001 support, and lift > 1 thresholds. Significant associations emerged: low IgG levels correlated with milder symptoms (e.g., absence of cough, tiredness), moderate IgG with intermediate symptoms (e.g., loss of smell without fever), and high IgG with severe clusters (e.g., fever, cough). Younger females (20-40 years) and blood group A were linked to higher IgG, while older patients (>65 years) with blood group O and Rh-negative status showed lower IgG. Confidence reached 100%, with lift values up to 3.607. These findings enhance understanding of immune response dynamics, offering insights for personalized diagnostics, treatment, and long COVID management. ARM application highlights its potential for diagnostic modeling in infectious diseases, improving public health preparedness.

Keywords

AbdulLateef, O., Sanmargaraja, S., Oni, O., Anavhe, P., & Mewomo, C.M. (2024). An association rule mining model for the application of construction technologies during COVID-19. International Journal of Construction Management, 24(4), 443-453. https://doi.org/10.1080/15623599.2023.2212420
Abril, A.G., Alejandre, J., Mariscal, A., Alserawan, L., Rabella, N., Roman, E., Lopez-Contreras, J., Navarro, F., Serrano, E., Nomdedeu, J.F., & Vidal, S. (2024). Titers of IgG and IgA against SARS-CoV-2 proteins and their association with symptoms in mild COVID-19 infection. Scientific reports, 14(1), 12725. https://doi.org/10.1038/s41598-024-59634-y
Ahmed, T., Hasan, S.T., Akter, A., Tauheed, I., Akhtar, M., Rahman, S.I.A., Bhuiyan, T.R., Ahmed, T., Qadri, F., & Chowdhury, F. (2023). Determining clinical biomarkers to predict long-term SARS-CoV-2 antibody response among COVID-19 patients in Bangladesh. Frontiers in Medicine, 10, 1111037. https://doi.org/10.3389/fmed.2023.1111037
Alathari, M.J.A., Al Mashhadany, Y., Bakar, A.A.A., Mokhtar, M.H.H., Zan, M.S.D.B., & Arsad, N. (2024). COVID-19 IgG antibodies detection based on CNN-bilstm algorithm combined with fiber-optic dataset. Journal of Virological Methods, 330, 115011. https://doi.org/10.1016/j.jviromet.2024.115011
Alimohamadi, Y., Sepandi, M., Taghdir, M., & Hosamirudsari, H. (2020). Determine the most common clinical symptoms in COVID-19 patients: A systematic review and meta-analysis. Journal of Preventive Medicine and Hygiene, 61(3), E304-E312. https://doi.org/10.15167/2421-4248/jpmh2020.61.3.1530
Altuna, M., Sánchez-Saudinós, M.B., & Lleó, A. (2021). Cognitive symptoms after COVID-19. Neurology perspectives, 1, S16-S24. https://doi.org/10.1016/j.neurop.2021.10.005
Amjadi, M.F., O’Connell, S.E., Armbrust, T., Mergaert, A.M., Narpala, S.R., Halfmann, P.J., Bashar, S. J., Glover, C.R., Heffron, A.S., Taylor, A., Flach, B., O’Connor, D.H., Kawaoka, Y., McDermott, A.B., Sethi, A.K., & Shelef, M.A. (2021). Specific COVID-19 symptoms correlate with high antibody levels against SARS-CoV-2. Immunohorizons, 5(6), 466-476. https://doi.org/10.4049/immunohorizons.2100022
Bastos, M.L., Tavaziva, G., Abidi, S.K., Campbell, J.R., Haraoui, L.P., Johnston, J.C., Lan, Z., Law, S., MacLean, E., Trajman, A., Menzies, D., Benedetti, A., & Khan, F.A. (2020). Diagnostic accuracy of serological tests for covid-19: systematic review and meta-analysis. BMJ, 370, m2516. https://doi.org/10.1136/bmj.m2516
Binswanger, I.A., Palmer-Toy, D.E., Barrow, J.C., Narwaney, K.J., Bruxvoort, K.J., Kraus, C.R., Lyons, J.A., Lam, J.A., & Glanz, J.M. (2024). Assessing the association between antibody status and symptoms of long COVID: A multisite study. PloS One, 19(6), e0304262. https://doi.org/10.1371/journal.pone.0304262
de Oliveira, M.I., Aciole, M.R., Neves, P.A.F., Silva, V.P.O.E., Silva, M.P.O.E., de Lorena, V.M.B., & de Araújo, P.S.R. (2024). A stronger antibody response in increased disease severity of SARS-CoV-2. BMC Infectious Diseases, 24, 1-17. https://doi.org/10.1186/s12879-023-08923-4
Dehghani, M., & Yazdanparast, Z. (2023). Discovering the symptom patterns of COVID-19 from recovered and deceased patients using Apriori association rule mining. Informatics in Medicine Unlocked, 42, 101351. https://doi.org/10.1016/j.imu.2023.101351
Demšar, J., Curk, T., Erjavec, A., Gorup, Č., Hočevar, T., Milutinovič, M., Možina, M., Polajnar, M., Toplak, M., Starič, A., Štajdohar, M., Umek, L., Žagar, L., Žbontar, J., Žitnik, M., & Zupan, B. (2013). Orange: data mining toolbox in Python. Journal of Machine Learning Research, 14, 2349-2353.
Elkin, M.E., & Zhu, X. (2022). A machine learning study of COVID-19 serology and molecular tests and predictions. Smart Health, 26, 100331. https://doi.org/10.1016/j.smhl.2022.100331
Fajgenbaum, D.C., & June, C.H. (2020). Cytokine storm. New England Journal of Medicine, 383(23), 2255-2273. https://doi.org/10.1056/NEJMra2026131
Faul, F., Erdfelder, E., Lang, A.G., & Buchner, A. (2007). G* Power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behavior Research Methods, 39(2), 175-191. https://doi.org/10.3758/BF03193146
Franchini, M., Maggi, F., & Focosi, D. (2024). ABO blood group-related mechanism of infection of SARS-CoV-2: an overview of systematic reviews. Clinical Chemistry and Laboratory Medicine, 62(3), 396-401. https://doi.org/10.1515/cclm-2023-0825
Ghaderi, H., Elahimanesh, F., Roshani, D., Hosseini Nasab, A., Nikkhoo, B., Mohammadi, A., Hessami, S., & Ghaznavi, H. (2024). Seroprevalence of anti-SARS-CoV-2 IgG antibodies across ABO blood groups and Rh Factor. Microbes and Infectious Diseases, 14, 1-10. https://doi.org/10.21608/mid.2024.303954.2075 
Hormaty, S., Seiwan, A.N., Rasheed, B.H., Parvaz, H., Gharahzadeh, A., & Ghaznavi, H. (2025). A review on biomarker-enhanced machine learning for early diagnosis and outcome prediction in ovarian cancer management. Cancer Medicine, 14(17), e71224. https://doi.org/10.1002/cam4.71224
Hudu, S.A., Alshrari, A.S., Abu-Shoura, E.A.J.I., Osman, A., & Jimoh, A.O. (2025). A critical review of the prospect of integrating artificial intelligence in infectious disease diagnosis and prognosis. Interdisciplinary Perspectives on Infectious Diseases, 2025, 6816002. https://doi.org/10.1155/ipid/6816002 
Jia, X., Zhang, P., Tian, Y., Wang, J., Zeng, H., Wang, J., Liu, J., Chen, Z., Zhang, L., He, H., He, K., & Liu, Y. (2021). Clinical significance of an IgM and IgG test for diagnosis of highly suspected COVID-19. Frontiers in Medicine, 8, 569266. https://doi.org/10.3389/fmed.2021.569266
Khudhur, S.D., & Khudhur, D.D. (2022). IgG-IgM antibodies-based infection time detection of COVID-19 using machine learning models. TELKOMNIKA (Telecommunication Computing Electronics and Control), 20(2), 340-347. https://doi.org/10.12928/TELKOMNIKA.v20i2.21649
Klein, S.L., & Flanagan, K.L. (2016). Sex differences in immune responses. Nature Reviews Immunology, 16(10), 626-638. https://doi.org/10.1038/nri.2016.90
Kurano, M., Ohmiya, H., Kishi, Y., Okada, J., Nakano, Y., Yokoyama, R., Qian, C., Xia, F., He, F., Zheng, L., Yu, Y., Jubishi, D., Okamoto, K., Moriya, K., Kodama, T., & Yatomi, Y. (2022). Measurement of SARS-CoV-2 antibody titers improves the prediction accuracy of COVID-19 maximum severity by machine learning in non-vaccinated patients. Frontiers in Immunology, 13, 811952. https://doi.org/10.3389/fimmu.2022.811952
Lakshmi, K.S., & Vadivu, G. (2017). Extracting association rules from medical health records using multi-criteria decision analysis. Procedia Computer Science, 115, 290-295. https://doi.org/10.1016/j.procs.2017.09.137
Lucas, C., Wong, P., Klein, J., Castro, T.B.R., Silva, J., Sundaram, M., Ellingson, M.K., Mao, T., Oh, J.E., Israelow, B., Takahashi, T., Tokuyama, M., Lu, P., Venkataraman, A., Park, A., Mohanty, S., Wang, H., Wyllie, A.L., Vogels, C.B.F., . . . Iwasaki, A. (2020). Longitudinal analyses reveal immunological misfiring in severe COVID-19. Nature, 584(7821), 463-469. https://doi.org/10.1038/s41586-020-2588-y
Marklund, E., Leach, S., Axelsson, H., Nyström, K., Norder, H., Bemark, M., Angeletti, D., Lundgren, A., Nilsson, S., Andersson, L.M., Yilmaz, A., Lindh, M., Liljeqvist, J.Å., & Gisslén, M. (2020). Serum-IgG responses to SARS-CoV-2 after mild and severe COVID-19 infection and analysis of IgG non-responders. PloS One, 15(10), e0241104. https://doi.org/10.1371/journal.pone.0241104
Matharaarachchi, S., Domaratzki, M., Katz, A., & Muthukumarana, S. (2022). Discovering long COVID symptom patterns: association rule mining and sentiment analysis in social media tweets. JMIR Formative Research, 6(9), e37984. https://doi.org/10.2196/37984
Mutter, S., Hall, M., & Frank, E. (2004). Using classification to evaluate the output of confidence-based association rule mining. In G.I. Webb & X. Yu (Eds.), Proceedings of the 17th Australian Joint Conference on Artificial Intelligence, 538-549. Springer. https://doi.org/10.1007/978-3-540-30549-1-47
Nikolich-Žugich, J. (2018). The twilight of immunity: emerging concepts in aging of the immune system. Nature Immunology, 19(1), 10-19.  https://doi.org/10.1038/s41590-017-0006-x
Park, S.E. (2020). Epidemiology, virology, and clinical features of severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2; Coronavirus Disease-19). Clinical and Experimental Pediatrics, 63(4), 119-124. https://doi.org/10.3345/cep.2020.00493
Riazi, K., Ly, M., Barty, R., Callum, J., Arnold, D.M., Heddle, N.M., Down, D.G., Sidhu, D., & Li, N. (2023). An unsupervised learning approach to identify immunoglobulin utilization patterns using electronic health records. Transfusion, 63(12), 2234-2247. https://doi.org/10.1111/trf.17585
Silva, F.A.F.D., Brito, B.B.D., Santos, M.L.C., Marques, H.S., Silva Júnior, R.T.D., Carvalho, L.S.D., Vieira, E.S., Oliveira, M.V., & Melo, F.F.D. (2020). COVID-19 gastrointestinal manifestations: A systematic review. Revista da Sociedade Brasileira de Medicina Tropical, 53, e20200714. https://doi.org/10.1590/0037-8682-0714-2020
Singh, A., Singh, D., Upreti, K., Sharma, V., Rathore, B.S., & Raikwal, J. (2023). Investigating New Patterns in Symptoms of COVID-19 Patients by Association Rule Mining (ARM). Journal of Mobile Multimedia, 19(1), 1-28. https://doi.org/10.13052/jmm1550-4646.1911
Sobhani, S., Aryan, R., Kalantari, E., Soltani, S., Malek, N., Pirzadeh, P., Yarahmadi, A., & Aghaee, A. (2021). Association between clinical characteristics and laboratory findings with outcome of hospitalized COVID‐19 patients: A report from northeast Iran. Interdisciplinary Perspectives on Infectious Diseases, 2021, 5552138. https://doi.org/10.1155/2021/5552138
Sogandi, F. (2024). Identifying diseases symptoms and general rules using supervised and unsupervised machine learning. Scientific Reports, 14, 17956. https://doi.org/10.1038/s41598-024-69029-8
Sołkiewicz, K., Kokot, I., Dymicka-Piekarska, V., Dorf, J., & Kratz, E.M. (2024). Are changes in serum IgG glycosylation related to the severe course of SARS-CoV-2 infection and recovery process? In search of new diagnostic and prognostic biomarkers. Journal of Inflammation Research, 17, 1413-1427. https://doi.org/10.2147/JIR.S439005
Sun, C., Xue, M., Yang, M., Zhu, L., Zhao, Y., Lv, X., Lin, Y., Ma, D., Shen, X., Cheng, Y., Xuan, H., Jia, X., Li, T., & Han, L. (2021). Early prediction of severe COVID-19 in patients by a novel immune-related predictive model. Msphere, 6(5), e00752-21. https://doi.org/10.1128/mSphere.00752-21
Tandan, M., Acharya, Y., Pokharel, S., & Timilsina, M. (2021). Discovering symptom patterns of COVID-19 patients using association rule mining. Computers in Biology and Medicine, 131, 104249. https://doi.org/10.1016/j.compbiomed.2021.104249
Vojdani, A., Almulla, A.F., Zhou, B., Al-Hakeim, H.K., & Maes, M. (2024). Reactivation of herpesvirus type 6 and IgA/IgM-mediated responses to activin-A underpin long COVID, including affective symptoms and chronic fatigue syndrome. Acta Neuropsychiatrica, 36(3), 172-184. https://doi.org/10.1017/neu.2024.10
Xu, J., Chen, J., Wen, F., Liu, K., & Chen, Y. (2024). Detection methods and dynamic characteristics of specific antibodies in patients with COVID-19: A review of the early literature. Heliyon, 10(3), e24580. https://doi.org/10.1016/j.heliyon.2024.e24580
Ye, H., Gan, X., Zhou, W., Gao, Y., Mei, Z., Zheng, Q., Luo, X., Yuan, C., & Wu, Y. (2024). Symptom clusters and symptom networks of symptom experiences in patients with SARS-CoV-2 infection. Heliyon, 10(22), e40497. https://doi.org/10.1016/j.heliyon.2024.e40497
Zakur, Y., & Flaih, L. (2023). Apriori algorithm and hybrid Apriori algorithm in the data mining: A comprehensive review. E3S Web of Conferences, 448, 02021. https://doi.org/10.1051/e3sconf/202344802021
Zhang, C., & Zhang, S. (2002). Association rule mining: models and algorithms. Springer. https://doi.org/10.1007/3-540-46027-6
Zhuang, Z., Qi, Y., Yao, Y., & Yu, Y. (2023). A predictive model for disease severity among COVID-19 elderly patients based on IgG subtypes and machine learning. Frontiers in Immunology, 14, 1286380. https://doi.org/10.3389/fimmu.2023.1286380
 
 
Biological Data
Volume 1, Issue 1 - Serial Number 1
June 2026
Pages 1-19
  • Receive Date: 23 February 2026
  • Revise Date: 22 March 2026
  • Accept Date: 09 April 2026
  • First Publish Date: 01 June 2026