Wos İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/11727/4807

Browse

Filters

2019 - 201912020 - 20211

Settings

Has files: NoSubject: search.filters.subject.tuberculosis

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Automated Tuberculosis Detection Using Pre-Trained CNN and SVM
    (2021) Oltu, Burcu; Guney, Selda; Dengiz, Berna; Agildere, Muhtesem
    Tuberculosis (TB) is a dreadfully contagious and life-threatening disease if left untreated. Therefore, early and accurate diagnosis is critical for treatment. Today, invasive, expensive, or time-consuming tests are performed for diagnosis. Unfortunately, accurate TB diagnosis is still a major challenge. In the proposed study, a decision support system that can automatically separate normal and TB chest X-ray (CXR) images is presented for objective and accurate diagnosis. In the presented methodology, first various data augmentation methods were applied to the data set, then pre-trained networks (VGG16, MobileNet), were employed as feature extractors from augmented CXR's. Afterward, the extracted features for all images were fed into a support vector machine classifier. In training process, 5-fold cross-validation was applied. As a result of this classification, it was concluded that TB can be diagnosed with an accuracy of 96,6% and an area under the ROC curve (AUC) of 0,99.
  • No Thumbnail Available
    Item
    Relative risk of tuberculosis in patients with rheumatic diseases managed with anti-tumour necrosis factor-alpha therapy: A nationwide cohort study
    (2019) Aydin, Volkan; Akici, Ahmet; Isil, Fatma; Aksoy, Mesil; Aydin, Mehtap; Gursoz, Hakki; 30763469
    What is known and objective Anti-tumour necrosis factor-alpha (anti-TNF-alpha) therapy is known to raise the risk of granulomatous infections, leading to development of risk management strategies at national or global level. This study aimed to determine the relative risk (RR) of tuberculosis (TB) due to anti-TNF-alpha usage in patients with rheumatologic diseases (RDs) in a nationwide basis. Method This retrospective cohort study included patients with rheumatoid arthritis (RA), ankylosing spondylitis, juvenile idiopathic arthritis or psoriatic arthritis (PsA) that treated with or without anti-TNF-alpha agents, as registered in the national prescription information system between years 2013 and 2015. Two-year RR of TB after anti-TNF-alpha therapy initiation was calculated in this RD population, including main subgroups. Results and discussion The study cohort included 413 500 RD patients, where anti-TNF-alpha(+) arm (n = 2117) had mean age of 41.9 +/- 13.4 years and male distribution of 54.3%. Four patients among anti-TNF-alpha users developed TB compared to 128 patients in anti-TNF-alpha-naive group (189 vs 31 cases per 100 000 patients, respectively), yielding a 2-year RR of 6.07 (95% CI, 2.25-16.42) with an attributable risk of 0.16%. These RRs (95% CI), which were particularly pronounced, were 5.39 (1.69-7.17) in men, 6.12 (2.26-16.55) in adults, and 5.70 (1.41-23.08) in RA and 13.46 (1.58-114.40) in PsA patients. There was no difference between the anti-TNF-alpha users who developed and undeveloped TB regarding drug utilization characteristics, except significantly less immunosuppressive drug exposure in TB patients. What is new and conclusion This study is the first prescription-based nationwide study to suggest an elevated RR of TB in a comparably younger population with a broad spectrum of RDs managed with any approved anti-TNF-alpha drug in Turkey.