Tuğçe Şençelikel

Tuğçe Şençelikel

Auto-generated profile, based on publicly available information

Tuğçe Şençelikel

Department of Biostatistics, Ankara Medipol University, Ankara 06570, Turkey

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2025 in Life
Verified
Journal Article
Open access
PDF file
TÖTugce Öznacar
Tugce Öznacar
TGTunç Güler
Tunç Güler
Objectives: Ovarian cancer continues to be one of the most prevalent gynecological cancers diagnosed. Early detection is highly critical for increasing survival chances. This research aims to assess the feature extraction process from various machine learning techniques for better modelling of ovarian cancer and the selection process in ovarian cancer analysis. By eliminating irrelevant features, this approach could guide clinicians towards more accurate results and optimize diagnostic precision. Methods: This study included both patients with and without ovarian cancer, creating a dataset containing 50 independent variables/features. Eight machine learning algorithms: Random Forest, XGBoost, CatBoost, Decision Tree, K-Nearest Neighbors, Naive Bayes, Gradient Boosting, and Support Vector Machine, were evaluated alongside four feature selection techniques: Boruta, PCA, RFE, and MI. Metrics performance has been evaluated to obtain the best possible combination for diagnosis. Results: These results were obtained using these methods with a significantly reduced number of features. Random Forest and CatBoost’s performances demonstrated significant differences in contrast to other algorithms (respectively, AUC 0.94% and 0.95%). On the other hand, feature selection methods such as Boruta and RFE consistently reflected higher AUC and accuracy scores than the others. Conclusions: This study highlights the importance of choosing appropriate machine learning algorithms and feature selection techniques for ovarian cancer diagnosis. Boruta and RFE showed high accuracy. By reducing the number of features from 50 to the most relevant ones, clinicians can make more precise diagnoses, enhance patient outcomes, and reduce unnecessary tests.

16 June 2021 in Journal of Burn Care & Research
Verified
Journal Article
Closed access
PDF file
EKEmre Karakaya
Emre Karakaya
AAAydincan Akdur
Aydincan Akdur
ESEbru Ayvazoğlu Soy
Ebru Ayvazoğlu Soy
CACoşkun Araz
Coşkun Araz
AAAlev Ok Atilgan
Alev Ok Atilgan
MHMehmet Haberal
Mehmet Haberal
Burns are one of the most severe traumas, causing coagulative destruction of the skin. The use of various products that accelerate wound healing in patients with burns may affect rates of patient survival and reduce complications. We studied the effects of subcutaneous ozone injection on second-degree burn wounds in animal model. For this study, 72 Sprague-Dawley male rats were divided randomly into the following three groups: control group , silver sulfadiazine group, and ozone group; each group was then divided randomly into two subgroups (day 7 or day 14 examination and sacrifice). Superficial partial thickness burns were created on the lower back. In the control group, subcutaneous 0.9% serum saline was injected daily into the burn area. In the silver sulfadiazine group, burns were dressed daily with silver sulfadiazine. In the ozone group, subcutaneous ozone was injected daily into the burn area. We performed tissue hydroxyproline level measurements and histopathological evaluations. When groups were compared in terms of weight change, no significant difference was found between day 7 and day 14. With regard to tissue hydroxyproline levels the ozone group had significantly higher levels on both day 7 and day 14 (P < .001). In histopathological evaluations, we determined that wound healing in the ozone group was significantly higher than in the other groups. We found that subcutaneous ozone therapy was more effective than silver sulfadiazine in the healing process of second-degree burn wounds and could be safely used in the treatment of burn wounds.

3 July 2022 in Journal of Psychosomatic Obstetrics & Gynecology
Verified
Journal Article
Closed access
SOSabri Berkem Okten
Sabri Berkem Okten
AGAnil Gunduz
Anil Gunduz
TÖTugce Öznacar
Tugce Öznacar
GDGuldeniz Desteli
Guldeniz Desteli
EGElvan Basak Usta Gunduz
Elvan Basak Usta Gunduz
TBTevfik Berk Bildacı
Tevfik Berk Bildacı
Purpose The aim of this study is to understand the motives behind CS requests in nulliparous women in their late pregnancy better and to investigate if specific personality traits affect the maternal decision on mode of delivery. Material and Method This prospective study was conducted with 70 healthy, nulliparous parturient with singleton pregnancies. Women at their 28-32. weeks of gestation were asked to fill a socio-demographic data form and the questionnaires; Personality Belief Questionnaire - Short Form (PBQ-SF) and The Childbirth Attitudes Questionnaire (CAQ). After delivery, all the results of pre-filled questionnaires and women's mode of delivery were analyzed and compared. Results There were significant differences in personality types; dependent (p = 0.033), passive-aggressive (p = 0.031), obsessive-compulsive (p = 0.001), antisocial (p = 0.014), narcissistic (p = 0.014) and borderline (p = 0.014) between vaginal delivery and CS groups. The CAQ scores of the mothers who requested CS were significantly higher (p:0.007). Weak but significant positive relation was found between total CAQ scores and avoidant (p = 0.022), dependent (p = 0.034), passive-aggressive (p = 0.040), narcissistic (p = 0,006), schizoid (p = 0.007), paranoid (p = 0.007) and borderline (p = 0.007) personality types. Conclusion This is the first study that investigates the relationship between mode of delivery and personality traits according to the Diagnostic and Statistical Manual of Mental Disorders (DSM) and cognitive behavioral perspective in the literature. These personality traits can be carried at a level that is not clinically significant to create an obvious pathology, yet they might play a role as the motives behind the apparent reasons for women who request CS. Understanding women's motives and attitudes for childbirth during their pregnancy may help healthcare providers to tailor women's approach to childbirth to avoid unnecessary CS.

1 March 2025 in Brain Sciences
Verified
Journal Article
Open access
PDF file
TÖTugce Öznacar
Tugce Öznacar
IAİpek Pınar Aral
İpek Pınar Aral
HZHatice Yağmur Zengin
Hatice Yağmur Zengin
YTYılmaz Tezcan
Yılmaz Tezcan
Objectives: Accurate survival prediction for brain metastasis patients undergoing stereotactic radiotherapy (SRT) is crucial for personalized treatment planning and improving patient outcomes. This study aimed to develop a machine learning model to estimate survival times, providing clinicians with a reliable tool for making informed decisions based on individual patient characteristics. The goal was to compare the performance of multiple algorithms and identify the most effective model for clinical use. Methods: We applied a hybrid machine learning approach to predict survival in brain metastasis patients treated with SRT, utilizing real-world data. Four algorithms—XGBoost, CatBoost, Random Forest, and Gradient Boosting—were compared within a meta-model framework to identify the most accurate for survival prediction. Model performance was evaluated using metrics such as MSE, MAE, MAPE, and C index. Results: XGBoost outperformed all other algorithms, achieving an MSE of 0.14%, MAE of 0.10%, and MAPE of 0.093%, with a high C-index of 100%. CatBoost showed reasonable performance, while Gradient Boosting had higher error rates (MSE of 6.99%, MAE of 21.04%, MAPE of 19.29%). Random Forest performed the weakest, with the highest MSE (14.39%), MAE (30.23%), and MAPE (33.58%). Conclusion: Inputting relevant clinical variables into the model enables clinicians to obtain highly accurate survival predictions for patients with brain metastasis. This enhances clinical decision making by providing a more precise understanding of expected outcomes. The XGBoost-based hybrid model showed exceptional accuracy in predicting survival for brain metastasis patients after SRT, offering valuable support for clinical decision making. Integrating machine learning into clinical practice can improve treatment planning and personalize care for these patients.

2 September 2021 in Cureus
Verified
Journal Article
Open access
MTMuberra Turan
Muberra Turan
FSFisun Sozen
Fisun Sozen
MEMuzaffer G. Eminsoy
Muzaffer G. Eminsoy
TÖTugce Öznacar
Tugce Öznacar
AKAltug Kut
Altug Kut
EOErgun Oksuz
Ergun Oksuz
We aimed to investigate the effectiveness of physician-performed diagnostic clinical breast examination (DCBE) for the diagnosis of breast cancer in clinical practice and to determine the rates of breast cancer diagnosed with DCBE compared to the results of breast ultrasonography (US), mammography (MG), and histopathology. In the retrospective cohort study, the files of female patients diagnosed with breast cancer and admitted to the general surgery outpatient clinics of a university hospital over a 10-year period (2011-2021) were examined. Patients with complete DCBE findings in their files were identified and analyzed (n = 1,091). The examinations of the patients were performed by general surgery specialists with 5-22 years of experience and by radiologists with 4-15 years of experience. The mean age of breast cancer diagnosis of the patients was 55.1 ± 13.5 years. While the sensitivity of DCBE was found to be 88.9%, MG sensitivity was 89.8% and breast US sensitivity was 95.1%. Cancer was detected by MG, breast US, and DCBE in 47.9% (n = 523), by breast US and DCBE in 38.9% (n = 424), by MG and breast US in 5.6% (n = 61), by DCBE alone in 3.6% (n = 39), by MG and DCBE in 2.4% (n = 26), and by breast US alone in 1.6% (n = 18). Early-stage breast cancer (p = 0.00) consisted of 73.2% (n = 383) of cancers detected with DCBE, breast US and MG, 74.6% (n = 316) of cancers detected with DCBE and breast US, 93.4% of cancers detected with breast US and MG (n = 57), 92.3% (n = 24) of cancers detected with DCBE and MG, 94.4% (n = 17) of cancers detected with breast US alone, and 69.2% of cancers detected with DCBE alone (n = 27). CBE still maintains its importance in societies where screening participation and awareness of breast cancer are low. A breast cancer diagnosis is often done after a complaint of a palpable mass in the breast, and only then are more advanced-stage breast cancers are seen. CBE is among the important diagnostic methods preventing breast cancer from being overlooked, especially in places where health resources are limited.

1 August 2019 in Anatomy
Verified
Journal Article
Open access
PDF file
HÖHale Öktem
Hale Öktem
CPCan Peli̇n
Can Peli̇n
AKAyla Kürkçüoğlu
Ayla Kürkçüoğlu
MIMerve İzCi̇
Merve İzCi̇
TÖTugce Öznacar
Tugce Öznacar
Objectives: Ballet dancers require a high level of control on their muscles in order to perform various dance figures. Special ballet moves require adaptive changes in order to maintain posture while performing classical ballet dance. The aim of the present study was to evaluate the differences in body postures and range of motion in certain joints between female classical ballet students and female non-dancer students. Methods: Fifty nine female university students participated in the study; 30 were studying classical ballet at Hacettepe University Ankara State Conservatory and 29 were studying at Baflkent University with no professional dancing history. Students in both groups were compared by conducting a body posture analysis anteriorly, laterally and posteriorly with the symmetrigraf chart. Range of motion of the joints was measured using a goniometer and distances were measured using an anthropometer. Results: Ballet education was a factor in the development of hallux valgus and genu varum deformities (p0.05). The median values of body flexion and hyperextension showed statistically significant differences between the two groups (p<0.001). Conclusion: Postural defects caused by the adaptive changes that occur during ballet training can be assessed easily by using a symmetrigraph. It is also possible to evaluate the degree of the deformities that can develop by time.