{
    "article_id": 1460,
    "public_id": "d0e7fe2e-b132-4ac5-8cf5-707dfbbb2162",
    "internal_identifier": null,
    "source_identifier": "90:9",
    "status": "published",
    "type": "research_article",
    "title": "Ailevi Akdeniz Ateşi'nde Kolşisin Tedavisinin Makine Öğrenmesi Analizi",
    "title_secondary": null,
    "abstract": "Bu çalışma, Ailevi Akdeniz Ateşi (AAA) hastalığına özgü bir veri setini analiz etmek için K-means kümeleme ve Kruskal-Wallis istatistiksel testini kullanan kapsamlı bir araştırmadır. Çalışmanın ana hedefi, AAA hastalarının kolşisin tedavi yanıtlarını etkileyen klinik ve demografik özellikleri belirlemektir. Toplamda 144 hasta kaydı içeren veri seti, demografik bilgiler, klinik semptomlar ve genetik varyantlar gibi 15 farklı özelliği barındırmaktadır. Özellik seçimi için ANOVA F-değerini temel alan SelectKBest algoritması kullanılmış ve \"atak süresi\", \"ateş\" ve \"TİT protein\" en fazla bilgi taşıyan üç özellik olarak seçilmiştir. Bu özellikler üzerinde K-means kümeleme algoritması uygulanmış ve yaklaşık olarak %70.14 doğruluk oranı elde edilmiştir. Ayrıca, Kruskal-Wallis testi ile de bu özelliklerin kolşisin tedavi yanıtları açısından istatistiksel olarak anlamlı farklılıklar gösterdiği tespit edilmiştir. Çalışma, klinisyenlere AAA hastalarına daha etkili ve kişiselleştirilmiş tedavi protokolleri önerme olanağı sağlama potansiyeli ile dikkat çekmektedir. Bu araştırma, daha geniş kapsamlı çalışmalar için önemli bir temel oluşturmaktadır.",
    "language": "tr",
    "english_title": "Machine Learning Analysis of Colchicine Treatment in Familial Mediterranean Fever",
    "english_abstract": "This study is a comprehensive investigation using K-means clustering and Kruskal-Wallis statistical tests to analyze a dataset specific to Familial Mediterranean Fever (FMF). The main objective of the study is to identify the clinical and demographic characteristics that influence colchicine treatment responses in FMF patients. The dataset, containing a total of 144 patient records, includes 15 different characteristics such as demographic information, clinical symptoms, and genetic variants. The SelectKBest algorithm, based on ANOVA F-values, was used for characteristic selection, and \"attack duration,\" \"fever,\" and \"UTI protein\" were selected as the three characteristics carrying the most information. The K-means clustering algorithm was applied to these characteristics, and an accuracy rate of approximately 70.14% was obtained. Furthermore, the Kruskal-Wallis test revealed that these characteristics showed statistically significant differences in terms of colchicine treatment responses. The study is noteworthy for its potential to enable clinicians to recommend more effective and personalized treatment protocols for AAA patients. This research provides an important foundation for broader studies.",
    "doi": "10.36287/setsci.6.1.017",
    "doi_url": "https://doi.org/10.36287/setsci.6.1.017",
    "resource_url": "https://www.set-science.com/a/d0e7fe2e-b132-4ac5-8cf5-707dfbbb2162",
    "pdf_url": "https://www.set-science.com/a/d0e7fe2e-b132-4ac5-8cf5-707dfbbb2162/pdf",
    "og_image": "https://www.set-science.com/assets/img/og-card-v2.png",
    "authors": [
        {
            "public_id": "4d56b628-313f-47ab-a8c9-27cbda90d928",
            "given": "Muhammet İkbal",
            "family": "Yıldız",
            "full": "Muhammet İkbal Yıldız",
            "literal": null,
            "orcid": null,
            "orcid_url": null,
            "email": "muh.ikbalyildiz@gmail.com",
            "corresponding": true,
            "sequence": "first",
            "affiliations": [
                {
                    "name": "Bilecik Şeyh Edebali Üniversitesi",
                    "department": null,
                    "country": null,
                    "country_code": null,
                    "ror": null,
                    "ror_url": null
                }
            ]
        },
        {
            "public_id": "8a7518d9-c5ea-42f3-902a-18a1709532f9",
            "given": "Salim",
            "family": "Ceyhan",
            "full": "Salim Ceyhan",
            "literal": null,
            "orcid": null,
            "orcid_url": null,
            "email": "salim.ceyhan@bilecik.edu.tr",
            "corresponding": false,
            "sequence": "additional",
            "affiliations": [
                {
                    "name": "Bilecik Şeyh Edebali Üniversitesi",
                    "department": null,
                    "country": null,
                    "country_code": null,
                    "ror": null,
                    "ror_url": null
                }
            ]
        }
    ],
    "keywords": [
        "Makine Öğrenmesi",
        "K-means Kümeleme",
        "Ailevi Akdeniz Ateşi",
        "Kolşisin Tedavisi",
        "Sağlıkta Veri Madenciliği"
    ],
    "translations": [
        {
            "language": "en",
            "title": "Machine Learning Analysis of Colchicine Treatment in Familial Mediterranean Fever",
            "abstract": "This study is a comprehensive investigation using K-means clustering and Kruskal-Wallis statistical tests to analyze a dataset specific to Familial Mediterranean Fever (FMF). The main objective of the study is to identify the clinical and demographic characteristics that influence colchicine treatment responses in FMF patients. The dataset, containing a total of 144 patient records, includes 15 different characteristics such as demographic information, clinical symptoms, and genetic variants. The SelectKBest algorithm, based on ANOVA F-values, was used for characteristic selection, and \"attack duration,\" \"fever,\" and \"UTI protein\" were selected as the three characteristics carrying the most information. The K-means clustering algorithm was applied to these characteristics, and an accuracy rate of approximately 70.14% was obtained. Furthermore, the Kruskal-Wallis test revealed that these characteristics showed statistically significant differences in terms of colchicine treatment responses. The study is noteworthy for its potential to enable clinicians to recommend more effective and personalized treatment protocols for AAA patients. This research provides an important foundation for broader studies.",
            "keywords": [
                "Machine Learning",
                "K-means Clustering",
                "Familial Mediterranean Fever",
                "Colchicine Treatment",
                "Data Mining in Healthcare"
            ]
        }
    ],
    "subjects": [],
    "subject_names": [],
    "published_date": "2023-12-29",
    "published_year": "2023",
    "received_date": null,
    "accepted_date": null,
    "volume": "15",
    "issue": null,
    "page_first": "40",
    "page_last": "44",
    "article_number": null,
    "conference": {
        "short_name": "BMYZ2023",
        "full_title": "Cognitive Models and Artificial Intelligence Conference",
        "name": "Cognitive Models and Artificial Intelligence Conference",
        "acronym": "BMYZ2023",
        "location": "Ankara, Türkiye",
        "start_date": "2023-10-26",
        "end_date": null,
        "public_id": "dc3a47c3-f4b3-4059-b610-f99aca33d7a0"
    },
    "proceedings": {
        "title": "Cognitive Models and Artificial Intelligence Conference",
        "series_title": "SETSCI Conference Proceedings",
        "publisher": "SET Technology",
        "isbn": "978-605-69925-7-5",
        "eisbn": null,
        "issn": null,
        "eissn": "2687-5527",
        "doi": null,
        "doi_prefix": "10.36287",
        "slug": "setsci-volume-15-2023-legacy-90",
        "public_id": "33fc699d-0ab3-4057-b2e0-644dc89f900d",
        "url": "https://www.set-science.com/p/setsci-volume-15-2023-legacy-90"
    },
    "license": {
        "name": "CC BY 4.0",
        "url": "https://creativecommons.org/licenses/by/4.0/",
        "code": "CC-BY-4.0",
        "open_access": true
    },
    "copyright": {
        "holder": "SET Technology",
        "year": "2023"
    },
    "funding_statement": null,
    "funders": [],
    "references": [
        {
            "order": 1,
            "raw": "M. Tunca, Familial Mediterranean Fever (FMF) in Turkey: Results of a Nationwide Multicenter Study, Medicine, 84(1): p 1-11, 2005. \r\n\r\nP. Mansueto, A. Seidita, M.  Chiavetta, D. Genoves, A. Giuliano, W. Priano, A. Carroccio, A. Casuccio, E. Amodio, Familial Mediterranean Fever and Diet: A Narrative Review of the Scientific Literature, Nutrients, 14, 3216, 2022. \r\n\r\nS. Üstebay, D. Ü. Üstebay, Y. Yılmaz, Ailevi Akdeniz Ateşi. Journal of Academic research in medicine, 2015.\r\n\r\nD. Zemer, A. Livneh, Y. L. Danon, M. Pras, E. Sohar, Long-term colchicine treatment in children with familial Mediterranean fever, Arthritis Rheum, 34: 973-7, 1991.\r\n\r\nR. C. Goldstein, A.D. Schwabe, Prophylactic colchicine therapy in familial Mediterranean fever. A controlled, double-blind study, Ann Intern Med, 81: 792-4, 1974.\r\n\r\nV. J. Parvaneh, R. Shiari, Treatment of Colchicine-Resistant Familial Mediterranean Fever With Anakinra. Arch Pediatr Infect Dis, 3(3): e21664, 2015.\r\n\r\nO. Adato, R. Brenner, A. Levy et al, Determining the origin of different variants associated with familial mediterranean fever by machine-learning, Sci Rep, 12, 15206 (2022).\r\n\r\nE. Sohar, J. Gafni, M. Pras, H. Heller, Familial Mediterranean fever. A survey of 470 cases and review of the literatüre, Am J Med, 43:227–53. doi:10.1016/0002-9343(67)90167-2, 1967.\r\n\r\nS. Ozgocmen, O. Akgul, Anti-TNF agents in familial Mediterranean fever: report of three cases and review of the literature. Mod Rheuma\ttol 2011; 21: 684-90.\r\n\r\nİ. Sarı, M. Birlik, T. Kaşifoğlu, Familial Mediterranean fever: An updated review, Eur. J. Rheumatol, 1: 21-33, 2014.\r\n\r\nI. Guyon, A. Elisseeff, An Introduction to Variable and Feature Selection, Journal of Machine Learning Research. 3 1157-1182, 2003.\r\n\r\nW. H. Kruskal, W. A. Wallis, Use of ranks in one-criterion variance analysis. Journal of the American Statistical Association, 47(260), 583-621, 1952.\t\r\n\r\nM. Hollander, D.A A. Wolfe, E. Chicken, Nonparametric statistical methods. John Wiley & Sons, 2013.",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        }
    ],
    "statements": {
        "acknowledgements": null,
        "conflict_of_interest": null,
        "data_availability": null,
        "ai_disclosure": null
    },
    "credit": [],
    "history": {
        "published": "2023-12-29"
    }
}