MULTIFACTORIAL ANALYSIS FOR PREDICTING CHRONIC RHINOSINUSITIS RECURRENCE AFTER FUNCTIONAL ENDOSCOPIC SURGERY USING MACHINE LEARNING COMBINATION METHODS

Authors:

Abstract:

Chronic rhinosinusitis represents a major healthcare burden with recurrence rates after functional endoscopic sinus surgery ranging from 6 % to 65 %. Machine learning approaches offer superior predictive capabilities compared to traditional statistical methods. This retrospective study analyzed 426 CRS patients who underwent functional endoscopic sinus surgery during 2019–2025. Seven machine learning algorithms were applied, and an ensemble model was developed. A simplified clinical risk score was created based on the most significant predictors for routine clinical use. Recurrence occurred in 157 patients (36.9 %) during 32.8±9.4 months follow-up. The ensemble model demonstrated the highest performance with AUC=0.94 and accuracy =89.2 %. Key predictors included previous surgery (OR=3.24), olfactory cleft obstruction ≥2 points (OR=2.87), blood eosinophilia ≥6 % (OR=2.34), and Lund-Mackay index ≥16 (OR=1.89). The simplified clinical risk score showed acceptable predictive ability (AUC=0.89) for routine practice. A two-tier prediction approach combining high-accuracy ML models for specialized centers and simplified clinical scores for routine practice can optimize personalized treatment strategies.

Keywords:

chronic rhinosinusitis machine learning prediction recurrence ensemble methods

References:

1. Bondarenko SV, Dubina SO, Serbin SI, Samoylenko OV, Stetsuk YeV, Rud MV, et al. Craniotopographic Anatomical Individual Variability and Variants of the Structure of the Dura Mater Superior Sagittal Sinus of the Skull Vault in People of Mature Age, World of Medicine and Biology, №1(91), 2025, pp. 150-154. DOI 10.26724/2079-8334-2025-1-91-150-154.
2. Caulley L, Thavorn K, Rudmik L, Cameron C, Kilty SJ. Direct costs of adult chronic rhinosinusitis by using 4 methods of estimation: Results of the US Medical Expenditure Panel Survey. J Allergy Clin Immunol. 2015; 136(6): 1517-1522. doi: 10.1016/j.jaci.2015.08.037.
3. Dovhych SV, Dieieva YuV Improving the Clinical Effectiveness of Paranasal Sinus X-ray Examination in Diagnosing Acute Rhinosinusitis Using Convolutional Neural Networks, Otolaryngology, №3(6), 2023, pp. 2-10. DOI 10.37219/2528-8253-2023-3-02
4. Fokkens WJ, Lund VJ, Hopkins C, Hellings PW, Kern R, Reitsma S, et al. European Position Paper on Rhinosinusitis and Nasal Polyps 2020. Rhinology. 2020; 58(Suppl S29): 1-464. doi: 10.4193/Rhin20.600.
5. Fokkens WJ, Viskens AS, Backer V, Conti D, De Corso E, Gevaert P, et al. EPOS/EUFOREA update on indication and evaluation of Biologics in Chronic Rhinosinusitis with Nasal Polyps 2023. Rhinology. 2023; 61(3): 194-202. doi: 10.4193/Rhin22.489.
6. Huang P, Yang J, Zhao D, Ran T, Luo Y, Yang D, et al. Machine Learning-Based Prediction of Early Complications Following Surgery for Intestinal Obstruction: Multicenter Retrospective Study. J Med Internet Res. 2025; 27: e68354. doi: 10.2196/68354.
7. Kato A, Peters AT, Stevens WW, Schleimer RP, Tan BK. Endotypes of chronic rhinosinusitis: Relationships to disease phenotypes, pathogenesis, clinical findings, and treatment approaches. Allergy. 2022; 77(3): 812-826. doi: 10.1111/all.15074.
8. Liu GS, Fereydooni S, Lee MC, Paranjape S, Hung J, Kwon S, et al. Scoping review of deep learning research illuminates artificial intelligence chasm in otolaryngology-head and neck surgery. NPJ Digit Med. 2025; 8: 13. doi: 10.1038/s41746-025-01693-0.
9. Liu Y-Y, Jiang S-P, Wang Y-B. Artificial intelligence optimizes the standardized diagnosis and treatment of chronic sinusitis. Front Physiol. 2025; 16: 1522090. doi: 10.3389/fphys.2025.1522090.
10. Martin-Jimenez D, Moreno-Luna R, Callejon-Leblic A, del Cuvillo A, Ebert CS Jr, Maza-Solano J, et al. Long-Term Clinical Outcomes in Patients with Chronic Rhinosinusitis with Nasal Polyps Associated with Expanded Types of Endoscopic Sinus Surgery. J Clin Med. 2024; 13(3): 866. doi: 10.3390/jcm13030866.
11. Min HK, Lee S, Kim S, Son Y, Park J, Kim HJ, et al. Global Incidence and Prevalence of Chronic Rhinosinusitis: A Systematic Review and Meta-Analysis. Clin Exp Allergy. 2025; 55(1): 121-135. doi: 10.1111/cea.14592.
12. Orlandi RR, Kingdom TT, Smith TL, Bleier B, DeConde A, Luong AU, et al. International consensus statement on allergy and rhinology: rhinosinusitis 2021. Int Forum Allergy Rhinol. 2021; 11(3): 213-739. doi: 10.1002/alr.22741.
13. Sedaghat AR, Kuan EC, Scadding GK. Epidemiology of Chronic Rhinosinusitis: Prevalence and Risk Factors. J Allergy Clin Immunol Pract. 2022; 10(6): 1395-1403. doi: 10.1016/j.jaip.2022.02.020.
14. Sinha P, Tharakan T, Payne S, Piccirillo JF. Balloon sinus dilation versus functional endoscopic sinus surgery for chronic rhinosinusitis: Systematic review and meta-analysis. Ann Otol Rhinol Laryngol. 2022; 131(10): 1087-1097. doi: 10.1177/00034894221104939.
15. Tran T, Staibano P, Snidvongs K, Nguyen TBV, Sommer DD. Extent of Endoscopic Sinus Surgery in Chronic Rhinosinusitis: A Systematic Review and Meta-Analysis. Curr Allergy Asthma Rep. 2024; 24(9): 505-520. doi: 10.1007/s11882-024-01175-5.

Publication:

«World of Medicine and Biology» Vol. 21 No. 94 (2025) , с. 117-121
УДК 616.216-002.2-089.87-037

DOI:

https://doi.org/10.26724/2079-8334-2025-4-94-117-121