Keywords
Upper Respiratory Tract Infections
Weather Data
How to Cite
Abstract
Upper Respiratory Tract Infections (URTIs) are a global health issue, affecting myriad individuals and encompassing infections of the nose, sinuses, pharynx, or larynx. The diverse symptoms and varying severity of URTIs, coupled with their potential to be influenced by meteorological factors, underscore the importance of understanding the interplay between weather conditions and URTI incidence. This research, conducted in the Pamukova District from December 15, 2020, to December 31, 2022, delves into this relationship by integrating weather data from Meteoblue and patient data from the Pamukova Family Medicine Center. The comprehensive data cleaning, harmonization, and preprocessing considered the 3 or 5 preceding days in alignment with the URTI incubation period. Utilizing the Catboost machine learning model on two separate datasets, the study revealed enhanced performance with a 5-day data frame. The model yielded 67 true positives, 24 true negatives, 8 false positives, and 22 false negatives, resulting in an F1-score of 0.6154, an accuracy of 75.21%, precision and recall values of 0.75 and 0.5217, respectively, and an AUC value of approximately 0.7768. These results emphasize the critical role of an extended temporal frame in understanding the connection between environmental factors and URTI incidence, offering substantial insights for the development of targeted public health interventions in the Pamukova District.
References
Bentéjac, C., A. Csörgő, and G. Martínez-Muñoz, 2021. A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review 54: 1937–1967.
Chelgani, S. C., H. Nasiri, A. Tohry, and H. Heidari, 2023. Modeling industrial hydrocyclone operational variables by SHAP-CatBoost – a “conscious lab” approach. Powder Technology 420: 118416.
Chen, X., L. Huang, Q. Li, M. Wu, L. Lin, et al., 2021. Exposure to environmental tobacco smoke during pregnancy and infancy increased the risk of upper respiratory tract infections in infants: A birth cohort study in Wuhan, China. Indoor Air 31: 673–681.
Derbyshire, E. J. and P. C. Calder, 2021. Respiratory tract infections and antibiotic resistance: A protective role for vitamin D? Frontiers in Nutrition 8: 652469.
D’Amato, M., A. Molino, G. Calabrese, L. Cecchi, I. Annesi-Maesano, et al., 2018. The impact of cold on the respiratory tract and its consequences to respiratory health. Clinical and Translational Allergy 8: 1–8.
Eccles, R. and J. Wilkinson, 2015. Exposure to cold and acute upper respiratory tract infection. Rhinology 53: 99–106.
Falagas, M. E., G. Theocharis, A. Spanos, L. A. Vlara, E. A. Issaris, et al., 2008. Effect of meteorological variables on the incidence of respiratory tract infections. Respiratory Medicine 102: 733–737.
Jhuo, S.-L., M.-T. Hsieh, T.-C. Weng, M.-J. Chen, C.-M. Yang, et al., 2019. Trend prediction of influenza and the associated pneumonia in Taiwan using machine learning. In 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp. 1–2, IEEE.
Kannangara, K. P. M., W. Zhou, Z. Ding, and Z. Hong, 2022. Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method. Journal of Rock Mechanics and Geotechnical Engineering 14: 1052–1063.
Kavzoglu, T. and A. Teke, 2022. Predictive performances of ensemble machine learning algorithms in landslide susceptibility mapping using random forest, extreme gradient boosting (XGBoost) and natural gradient boosting (NGBoost). Arabian Journal for Science and Engineering 47: 7367–7385.
Kern, C., K. Kortüm, M. Müller, F. Raabe, W. J. Mayer, et al., 2016. Correlation between weather and incidence of selected ophthalmological diagnoses: A database analysis. Clinical Ophthalmology 10: 1587–1592.
Kolawole, O. M. and O. O. Idris, 2020. Erythromycin resistance in bacterial isolates from patients with respiratory tract infections in Ikere-Ekiti, Nigeria. Annals of Science and Technology 5: 49–57.
Lim, J. T., K. B. Tan, J. Abisheganaden, and B. L. Dickens, 2023. Forecasting upper respiratory tract infection burden using high-dimensional time series data and forecast combinations. PLOS Computational Biology 19: e1010892.
Mäkinen, T. M., R. Juvonen, J. Jokelainen, T. H. Harju, A. Peitso, et al., 2009. Cold temperature and low humidity are associated with increased occurrence of respiratory tract infections. Respiratory Medicine 103: 456–462.
Mansour, M., T. B. Donmez, M. Kutlu, and C. Freeman, 2023. Respiratory diseases prediction from a novel chaotic system. Chaos Theory and Applications 5: 20–26.
Prokhorenkova, L., G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, 2018.
CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems 31.
Santhanam, N., H. E. Kim, D. Ruegamer, A. Bender, S. Muthers, et al., 2024. Machine learning-based forecasting of daily acute ischemic stroke admissions using weather data. medRxiv, 2024–07.
Stolz, D., E. Papakonstantinou, L. Grize, D. Schilter, W. Strobel, et al., 2019. Time-course of upper respiratory tract viral infection and COPD exacerbation. European Respiratory Journal 54.
Tu, J., K. Inthavong, G. Ahmadi, et al., 2013. The human respiratory system. In Computational Fluid and Particle Dynamics in the Human Respiratory System, pp. 19–44.
Yang, J., X. Xu, X. Ma, Z. Wang, Q. You, et al., 2023. Application of machine learning to predict hospital visits for respiratory diseases using meteorological and air pollution factors in Linyi, China. Environmental Science and Pollution Research 30: 88431–88443.
Zeru, T., H. Berihu, G. Buruh, and H. Gebrehiwot, 2020. Magnitude and factors associated with upper respiratory tract infection among under-five children in public health institutions of Aksum town, Tigray, Northern Ethiopia: An institutional-based cross-sectional study. Pan African Medical Journal 36.
Zou, Z., C. Cheng, and S. Shen, 2021. The complex nonlinear coupling causal patterns between PM2.5 and meteorological factors in Tibetan Plateau: A case study in Xining. IEEE Access 9: 150373–150382.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.