Çocukluk Alerjilerinde Veri Kesme Yöntemiyle Yeni Bir Hibrit Sınıflandırma Çerçevesi

Year 2024, Volume: 12 Issue: 3, 1371 - 1388, 31.07.2024

Pınar Karadayı Ataş

https://doi.org/10.29130/dubited.1353771

Abstract

Çocukluk alerjileri, özellikle de gıda alerjileri giderek artmaktadır. Çocukların sağlığı ve refahı üzerindeki büyük etkileri dünya çapındaki halk sağlığı yetkililerinin ilgisini çekmektedir. Bu kalıpların da geçerli olduğu Türkiye'de çocukluk çağı alerjilerinin artan prevalansı, etkili sınıflandırma ve yönetim seçeneklerine olan ihtiyacın aciliyetini artırmaktadır. Bu çalışma, yeni bir hibrit sınıflandırma metodolojisi sunarak, basit sınıflandırma algoritmalarının yüksek doğruluk elde etmedeki eksikliklerini gidermektedir. Araştırma, Destek Vektör Makinesi ve Karar Ağacı sınıflandırıcılarını birleştirerek üç farklı tahmin modelinin oluşturulduğu yeni bir yöntem yaratmaktadır. Çalışmamızda kullanılan bu yöntem, yanlış sınıflandırılan örnekleri sadece gürültü olarak değil, potansiyel olarak kullanışlı bilgi kaynakları olarak ele alarak sınıflandırma sürecini geliştirir. Bu örnek filtreleme tabanlı hibrit sınıflandırma algoritması, nispeten yüksek doğruluk elde ederken öğrenme çıktılarını yorumlamanın basitliğini korur. Alerji veri seti üzerinde yapılan kapsamlı deneyler, bu hibrit yaklaşımın etkinliğini 0,906'lık etkileyici bir doğrulukla göstermektedir. Bu, temel algoritmaların yanı sıra daha önce önerilen klasik sınıflandırma algoritmalarından da büyük ölçüde daha iyi performans sergilemektedir. Deneysel çıktıların tıp uzmanları için önemli sonuçları vardır. Bu çalışma çocukluk çağı alerji sınıflandırmasına yeni bir çözüm sunarak literatüre değerli bir katkı sağlayabilir.

Keywords

Çocukluk alerjileri, Hibrit sınıflandırma, Makine öğrenmesi

A New Hybrid Classification Framework in Childhoods Allergies with Dataset Slicing Method

Abstract

Childhood allergies, particularly food allergies, are growing more frequent. Their major influence on children's health and well-being has piqued the interest of worldwide public health officials. The increased prevalence of childhood allergies in Turkey, where these patterns are also relevant, adds urgency to the need for effective classification and management options. This study addresses the shortcomings of simple classification algorithms in obtaining high accuracy by presenting a novel hybrid classification methodology. The research creates a novel method where three different prediction models are built by combining Support Vector Machine and Decision Tree classifiers. This method improves the classification process by taking into account instances that have been incorrectly classified as possible sources of useful information instead of just being noise. This instance filtering-based hybrid classification algorithm that is used in this study maintains the simplicity of interpreting learning outcomes while achieving comparatively high accuracy. Extensive experiments on the allergy dataset show the effectiveness of this hybrid approach, with an impressive accuracy of 0.906. This greatly outperforms the fundamental classification algorithms. The experimental outputs have important implications for medical professionals. This study might add a valuable contribution to the literature by giving a fresh solution to childhood allergy classification.

Keywords

Childhood allergies, Hybrid classification, Machine learning

References

• [1] R. S. Gupta et al., “The public health impact of parent-reported childhood food allergies in the United States,” Pediatrics, vol. 142, no. 6, p. e20181235, 2018.
• [2] S. M. Jones and A. W. Burks, “Food allergy,” New England Journal of Medicine, vol. 377, no. 12, pp. 1168–1176, 2017.
• [3] A. Elghoudi and H. Narchi, “Food allergy in children—the current status and the way forward,” World Journal of Clinical Pediatrics, vol. 11, no. 3, p. 253, 2022.
• [4] C. Westwell‐Roper et al., “Food‐allergy‐specific anxiety and distress in parents of children with food allergy: A systematic review,” Pediatric Allergy and Immunology, vol. 33, no. 1, p. e13695, 2022.
• [5] E. Jensen‐Jarolim et al., “State‐of‐the‐art in marketed adjuvants and formulations in allergen immunotherapy: a position paper of the European Academy of Allergy and Clinical Immunology (EAACI),” Allergy, vol. 75, no. 4, pp. 746–760, 2020.
• [6] P. Bégin et al., “CSACI guidelines for the ethical, evidence-based and patient-oriented clinical practice of oral immunotherapy in IgE-mediated food allergy,” Allergy, Asthma & Clinical Immunology, vol. 16, pp. 1–45, 2020.
• [7] S. Clark, J. Espinola, S. A. Rudders, A. Banerji, and C. A. Camargo, “Frequency of US emergency department visits for food-related acute allergic reactions,” Journal of allergy and clinical immunology, vol. 127, no. 3, pp. 682–683, 2011.
• [8] R. Pawankar et al., “Asia Pacific Association of Allergy Asthma and Clinical Immunology White Paper 2020 on climate change, air pollution, and biodiversity in Asia-Pacific and impact on allergic diseases,” Asia Pacific Allergy, vol. 10, no. 1, 2020.
• [9] C. J. Haug and J. M. Drazen, “Artificial intelligence and machine learning in clinical medicine, 2023,” New England Journal of Medicine, vol. 388, no. 13, pp. 1201–1208, 2023.
• [10] A. Ktona, A. Mitre, D. Shehu, and D. Xhaja, “Support Allergic Patients, using Models Found by Machine Learning Algorithms, to Improve their Quality of Life.,” International Journal of Intelligent Systems and Applications in Engineering, vol. 10, no. 4, pp. 512–517, 2022.
• [11] K. Kamphorst, A. Lopez-Rincon, A. M. Vlieger, J. Garssen, E. van’t Riet, and R. M. van Elburg, “Predictive factors for allergy at 4–6 years of age based on machine learning: A pilot study,” PharmaNutrition, vol. 23, p. 100326, 2023.
• [12] E. M. Moreno et al., “Usefulness of an artificial neural network in the prediction of β-lactam allergy,” The Journal of Allergy and Clinical Immunology: In Practice, vol. 8, no. 9, pp. 2974–2982, 2020.
• [13] J. J. Wu et al., “Predictors of nonresponse to dupilumab in patients with atopic dermatitis: a machine learning analysis,” Annals of Allergy, Asthma & Immunology, vol. 129, no. 3, pp. 354–359, 2022.
• [14] D. Di Bona, F. Spataro, P. Carlucci, G. Paoletti, and G. W. Canonica, “Severe asthma and personalized approach in the choice of biologic,” Current Opinion in Allergy and Clinical Immunology, vol. 22, no. 4, pp. 268–275, 2022.
• [15] Y. Kuniyoshi, H. Tokutake, N. Takahashi, A. Kamura, S. Yasuda, and M. Tashiro, “Machine learning approach and oral food challenge with heated egg,” Pediatric Allergy and Immunology, vol. 32, no. 4, pp. 776–778, 2021.
• [16] P. Bhardwaj, A. Tyagi, S. Tyagi, J. Antão, and Q. Deng, “Machine learning model for classification of predominantly allergic and non-allergic asthma among preschool children with asthma hospitalization,” Journal of Asthma, vol. 60, no. 3, pp. 487–495, 2023.
• [17] I. S. Randhawa, K. Groshenkov, and G. Sigalov, “Food anaphylaxis diagnostic marker compilation in machine learning design and validation,” Plos one, vol. 18, no. 4, p. e0283141, 2023.
• [18] M. G. Yousif, F. G. Al-Amran, A. M. Sadeq, and N. G. Yousif, “The Impact of COVID-19 on Cardiovascular Health: Insights from Hematological Changes, Allergy Prevalence, and Predictive Modeling,” Medical Advances and Innovations Journal, vol. 1, no. 1, p. 10, 2023.
• [19] K. Goto et al., “Novel machine learning method allerStat identifies statistically significant allergen-specific patterns in protein sequences,” Journal of Biological Chemistry, vol. 299, no. 6, 2023.
• [20] J. Zhang et al., “Prediction of oral food challenge outcomes via ensemble learning,” Informatics in Medicine Unlocked, vol. 36, p. 101142, 2023.
• [21] M. A. Tosca, R. Olcese, C. Trincianti, M. Naso, I. Schiavetti, and G. Ciprandi, “Children with cow’s milk allergy: prediction of oral immunotherapy response in clinical practice,” Allergo Journal International, pp. 1–2, 2023.
• [22] G. Martinroche et al., “Creating a French Dataset for artificial intelligence-assisted allergy diagnosis using semantic attributes and allergen multiplex technology,” Journal of Allergy and Clinical Immunology, vol. 151, no. 2, p. AB318, 2023.
• [23] B. J. Patchett et al., “Allergic Polysensitization Clusters: Newly Recognized Severity Marker in Urban Asthmatic Adults,” International Archives of Allergy and Immunology, vol. 184, no. 3, pp. 261–272, 2023.
• [24] S. Grinek et al., “Epitope-specific IgE at 1 year of age can predict peanut allergy status at 5 years,” International Archives of Allergy and Immunology, vol. 184, no. 3, pp. 273–278, 2023.
• [25] R. H. Ekpo, V. C. Osamor, A. A. Azeta, E. Ikeakanam, and B. O. Amos, “Machine learning classification approach for asthma prediction models in children,” Health and Technology, vol. 13, no. 1, pp. 1–10, 2023.
• [26] V. Malizia et al., “Endotyping allergic rhinitis in children: A machine learning approach,” Pediatric Allergy and Immunology, vol. 33, pp. 18–21, 2022.
• [27] V. R. Allugunti, “A machine learning model for skin disease classification using convolution neural network,” International Journal of Computing, Programming and Database Management, vol. 3, no. 1, pp. 141–147, 2022.
• [28] M. H. Shamji et al., “EAACI guidelines on environmental science in allergic diseases and asthma–Leveraging artificial intelligence and machine learning to develop a causality model in exposomics,” Allergy, 2023.
• [29] M. Nedyalkova, M. Vasighi, A. Azmoon, L. Naneva, and V. Simeonov, “Sequence-Based Prediction of Plant Allergenic Proteins: Machine Learning Classification Approach,” ACS omega, vol. 8, no. 4, pp. 3698–3704, 2023.
• [30] D. A. Hill, R. W. Grundmeier, G. Ram, and J. M. Spergel, “The epidemiologic characteristics of healthcare provider-diagnosed eczema, asthma, allergic rhinitis, and food allergy in children: a retrospective cohort study,” BMC pediatrics, vol. 16, no. 1, pp. 1–8, 2016.
• [31] D. Valero-Carreras, J. Alcaraz, and M. Landete, “Comparing two SVM models through different metrics based on the confusion matrix,” Computers & Operations Research, vol. 152, p. 106131, 2023.
• [32] X. Han, X. Zhu, W. Pedrycz, and Z. Li, “A three-way classification with fuzzy decision trees,” Applied Soft Computing, vol. 132, p. 109788, 2023.
• [33] M. A. Azam, A. Shahzadi, A. Khalid, S. M. Anwar, and U. Naeem, “Smartphone based human breath analysis from respiratory sounds,” presented at the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 2018, pp. 445–448.
• [34] P. Tinschert et al., “Nocturnal cough and sleep quality to assess asthma control and predict attacks,” Journal of asthma and allergy, pp. 669–678, 2020.
• [35] L. Tenero, M. Sandri, M. Piazza, G. Paiola, M. Zaffanello, and G. Piacentini, “Electronic nose in discrimination of children with uncontrolled asthma,” Journal of Breath Research, vol. 14, no. 4, p. 046003, 2020.
• [36] R. X. A. Pramono, S. A. Imtiaz, and E. Rodriguez-Villegas, “Automatic cough detection in acoustic signal using spectral features,” presented at the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 2019, pp. 7153–7156.
• [37] A. T. Purnomo, D.-B. Lin, T. Adiprabowo, and W. F. Hendria, “Non-contact monitoring and classification of breathing pattern for the supervision of people infected by COVID-19,” Sensors, vol. 21, no. 9, p. 3172, 2021.