Yazar "Kaya, Mehmet Onur" seçeneğine göre listele
Listeleniyor 1 - 4 / 4
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Assessment of COVID-19-Related Genes Through Associative Classification Techniques(Duzce Univ, Fac Medicine, 2022) Cicek, Ipek Balikci; Kaya, Mehmet Onur; Colak, CemilObjective: This study aims to classify COVID-19 by applying the associative classification method on the gene data set consisting of open access COVID-19 negative and positive patients and revealing the disease relationship with these genes by identifying the genes that cause COVID-19. Methods: In the study, an associative classification model was applied to the gene data set of patients with and without open access COVID-19. In this open-access data set used, 15979 genes are belonging to 234 individuals. Out of 234 people, 141 (60.3%) were COVID-19 negative and 93 (39.7%) were COVID-19 positives. In this study, LASSO, one of the feature selection methods, was performed to choose the relevant predictors. The models' performance was evaluated with accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score. Results: According to the study findings, the performance metrics from the associative classification model were accuracy of 92.70%, balanced accuracy of 91.80%, the sensitivity of 87.10%, the specificity of 96.50%, the positive predictive value of 94.20%, the negative predictive value of 91.90%, and F1-score of 90.50%. Conclusions: The proposed associative classification model achieved very high performances in classifying COVID-19. The extracted association rules related to the genes can help diagnose and treat the disease.Öğe Comparison of Performance of Deep Survival and Cox Proportional Hazard Models: an Application on the Lung Cancer Dataset(2022) Akbaş, Kübra Elif; Kaya, Mehmet Onur; Çiçek, İpek Balıkçı; Çolak, CemilThe goal of this study is to compare the performance of the deep survival model and the Cox regression model in an open-access Lung cancer dataset consisting of survi vors and dead patients. In the study, it is applied to an open access dataset named "Lung Cancer Data" to compare the performances of the CPH and deepsurv models. The performance of the models is evaluated by C-index, AUC, and Brier score. The concordance index of the deep survival model is 0.64296, the Brier score was 0.128921, and the AUC was 0.6835. With the Cox regression model, the concordance index is calculated as 0.61445, brier score 0.1667, and AUC 0.5832. According to the Con cordance index, brier score, and AUC criteria, the deep survival model performed better than the cox regression model. DeepSurv's forecasting, modeling, and predictive capabilities pave the path for future deep neural network and survival analysis research. DeepSurv has the potential to supplement traditional survival analysis methods and become the standard method for medical doctors to examine and offer individualized treatment alternatives with more research.Öğe The correlation between delirium subtypes and treatment efficacy and biochemical parameters: A preliminary study(2019) Gurok, Mehmet Gurkan; Kazgan, Asli; Kaya, Mehmet Onur; Atmaca, MuradAim: Delirium is one of the most important emergency cases in geriatric patient population with high morbidity and mortality rates. In clinical practice, three delirium types are defined as hyperactive, hypoactive and mixed according to the psychomotor activity and the level of wakefulness. In the present study, the purpose was to examine the treatment response of the subtypes of delirium and its relation with possible biochemical parameters.Material and Methods: Thirty patients, who were diagnosed with delirium and who were hospitalized for treatment were included in the present study. Following the classification of the patients according to the subtypes of delirium, they were evaluated before the treatment and on the 7th day of the treatment. In both interviews, the Delirium Rating Scale (DRS), Richmond Agitation and Sedation Scale (RASS), and Memorial Delirium Rating Scale (MDRS) were applied to the patients. In addition, the biochemical parameters that were required for the patients in relevant clinics were recorded.Results: Delirium patients consisted of a total of 30 patients. The patients of all three subtypes of delirium responded to the treatment scores at significant levels in terms of scale scores. However, when the Hyperactive, Hypoactive and Mixed subtypes were evaluated in terms of the difference of change on the 1st and 7th days of the treatment separately, it was determined that the difference of change values were significantly higher in the hyperactive type in terms of RASS, DRS and MDRS (p=0.004; p=0.002; p=0.001, respectively). Conclusions: As a result, the findings of the present study showed that patients who are diagnosed with delirium might show different treatment responses according to motor subtypes. Further studies are required to be conducted with bigger sampling groups.Keywords: Delirium; treatment efficacy; biochemical parameters.Öğe Prostat spesifik antijeni yardımı ile prostat kanserinin değişik yapay sinir ağı modelleri ile tahmini(İnönü Üniversitesi Sağlık Bilimleri Dergisi, 2013) Kaya, Mehmet Onur; Çolak, Cemil; Özdemir, EnverBu çalışmada, prostat spesifik antijeni (PSA) değerlerinin yardımıyla prostat kanseri olan ve prostat kanseri olmayan vakaların yapay sinir ağları (YSA) modelleri yardımıyla tahmin edilmesi amaçlanmıştır. Çalışma, geriye yönelik veri toplama yöntemi ile 203 erkek bireye ait olup, Fırat Üniversitesi Tıp Fakültesi Üroloji Anabilim Dalı Polikliniği’nden sağlanmıştır. Prostat kanserinin oluşumuna ilişkin PSA tipleri ve prostat kanserinin tanısında kullanılan değişkenler incelenmiştir. YSA, değişik öğrenme algoritmaları kullanılarak eğitilmiştir. Girdi katmanında 9 işlem elamanı kullanılmıştır. Çıktı katmanındaki değişken ise PSA değerlerine göre prostat kanser olup olmaması idi. Değişik YSA modelleri ve öğrenme algoritmaları denenerek, en iyi sonuç elde edilmeye çalışılmıştır. YSA modelleri, ileri beslemeli geriye yayılımlı ağ kullanılarak tahminde bulunulmuştur. Çalışmadaki YSA modellerinde, en iyi açıklayıcılık katsayısı (R 2) ve en küçük hata kareleri ortalaması (MSE) sırasıyla; 0.75 ve 0.07 olarak bulunmuştur. Yapılan çalışmada değişik YSA modellerinin, PSA’nın yardımı ile prostat kanserinin tahmin edilmesinde daha etkili ve ümit verici sonuçlar verebildiği belirlenmiştir. Böylece İleriye yönelik klinik tanı sürecinde kullanılabilir olduğu görülmüştür.
