Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Deniz Taşkıran has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Interobserver Agreement Between Artificial Intelligence, Radiologist, and Gynecologist in Hysterosalpingography Interpretation: A Retrospective Comparative Study

    by Deniz Taşkıran, Serdar Aslan, Salih Kolsuz, Mesut Alçı, Esra Yazgan Yiğitbaş

    Background: Infertility is a common reproductive health disorder that affects roughly 10–15% of couples during their reproductive period. Hysterosalpingography (HSG) is a widely utilized imaging modality for assessing uterine cavity morphology and fallopian tube patency and continues to play a central role in infertility investigations. Nevertheless, the interpretation of HSG findings may vary according to the experience and expertise of the evaluator, potentially leading to inconsistencies in clinical decision-making. Although artificial intelligence (AI) has demonstrated considerable potential in medical image analysis across various specialties, evidence regarding its application in the interpretation of HSG examinations remains scarce. Therefore, this study aimed to evaluate the level of agreement among radiologists, gynecologists, and an AI-based system in the assessment of identical HSG images. Methods: In this retrospective study, a total of 1443 HSG images obtained from 414 women who underwent hysterosalpingography as part of an infertility evaluation between January 2021 and January 2025 were reviewed. Cases with incomplete clinical records or suboptimal image quality were excluded from the analysis. All examinations were independently assessed by an experienced radiologist, a gynecologist specializing in infertility management, and a multimodal artificial intelligence system based on ChatGPT-5, with each evaluator blinded to the assessments of the others and to the patients’ clinical information. Image interpretation included the evaluation of contrast distribution, peritoneal spill, uterine cavity findings, tubal patency, and overall HSG impression, which were categorized according to predefined diagnostic criteria. The primary outcome was the degree of interobserver agreement among the evaluators. Agreement analyses were performed using Cohen’s kappa (κ) and Gwet’s AC1 coefficients. Analyses were conducted using IBM SPSS Statistics (version 30.0; IBM Corp., Armonk, NY, USA) and R statistical software (version 4.4.0; R Foundation for Statistical Computing, Vienna, Austria). Statistical significance was set at p < 0.05 (two-sided). Results: A total of 1443 HSG images obtained from 414 women were included in the final analysis. The mean age of the study population was 30.97 ± 5.59 years, and primary infertility accounted for 87.9% of cases. The average number of images acquired per examination was 3.49 ± 1.05. According to Cohen’s kappa analysis, the highest levels of agreement were observed for the assessment of image artifacts and contrast medium distribution. Agreement between the AI system and the radiologist was particularly strong for contrast medium distribution (κ = 0.757). For the overall interpretation of HSG findings, AI demonstrated substantial agreement with the radiologist (κ = 0.637), exceeding the level of agreement observed between the radiologist and the gynecologist (κ = 0.363). In contrast, concordance involving AI was lower for the evaluation of uterine abnormalities, intrauterine filling defects, and tubal patency. When agreement was reassessed using Gwet’s AC1 statistic, concordance coefficients were consistently higher than the corresponding kappa values across all evaluator pairs. Near-perfect agreement between AI and the radiologist was identified for contrast medium distribution (AC1 = 0.954), peritoneal spill (AC1 = 0.893), and patterns of peritoneal contrast passage (AC1 = 0.841). Procedures performed under local anesthesia yielded a significantly greater number of images than those conducted under general anesthesia (3.86 ± 0.86 vs. 3.08 ± 1.10, p < 0.001). No significant associations were detected between abnormal HSG findings and either infertility type or anesthetic technique. In multivariable analysis, the use of general anesthesia was independently associated with a lower image count, whereas the presence of tubal pathology emerged as an independent predictor of acquiring a greater number of images during the examination. Conclusions: Our findings indicate that AI-assisted interpretation of HSG images has the potential to complement expert assessment, showing substantial concordance in several key diagnostic domains. While the technology appears promising as a decision-support tool in infertility evaluation, further research and refinement are warranted, particularly regarding the assessment of tubal and uterine pathologies.

  • A RARE CASE OF APPARENTLY SPONTANEOUS SKULL DEPRESSION INCIDENTALLY DETECTED IN A NEWBORN FOLLOWING CESAREAN SECTION

    by Deniz Taşkıran, Fidel Ceren Yavuzyilmaz

    In the neonatal period, cranial bones are thin and flexible, with open sutures. While this allows for protection during birth, it also increases the risk of skull depressions. These depressions may result from birth trauma, spontaneous causes, or medical interventions. However, cases without clear risk factors are rare. A term newborn, delivered via emergency cesarean section at 37 weeks due to cephalopelvic disproportion, was found to have a 1 cm depression in the parietal bone. Imaging revealed no fracture lines, and the appearance was consistent with a ping-pong skull depression, likely occurring in utero. Neurological examination was normal. The infant was given vitamin D and followed with conservative management. At one-month follow-up, partial resolution of the depression was observed. Continued clinical and neurological monitoring was planned. Cranial depressions in newborns do not always require surgical intervention. In selected cases, conservative treatment can lead to spontaneous improvement.

  • Open Access

    Reproductive and obstetric outcomes after complete and partial hydatidiform mole: A single-center retrospective cohort study

    by Orhan Ay, Fethiye Şahin, Pelin Bahçeci, Deniz Taşkıran, Ali Acar

    Aim: To evaluate the reproductive and obstetric outcomes after complete hydatidiform mole (CHM) and partial hydatidiform mole (PHM) in a tertiary referral center. Materials and Methods: This retrospective cohort included 90 women with histologically confirmed molar pregnancy (65 CHM and 25 PHM) who were managed between 2015 and 2024. Cases with ectopic localization, uncertain diagnosis, missing essential data, or insufficient follow-up were excluded. Women with uterine preservation, no permanent contraception, reproductive age, and adequate follow-up were defined as the subgroup with potential for subsequent pregnancy and were included in the reproductive outcome analysis. Postmolar gestational trophoblastic neoplasia (GTN), occurrence of at least one subsequent pregnancy, outcomes of the first postmolar pregnancy, and obstetric outcomes of the first live birth were compared between CHM and PHM. Results: Among women with potential for subsequent pregnancy (43 CHM and 14 PHM), at least one subsequent pregnancy occurred in 22 (51.2%) and 8 (57.1%) women, respectively (p=0.697). When only the first subsequent pregnancy was considered, live birth, miscarriage, and recurrent molar pregnancy rates did not differ significantly between CHM and PHM groups (live birth: 63.6% vs 87.5%, p=0.374; miscarriage: 18.2% vs 12.5%, p=1.000; recurrent mole: 18.2% vs 0%, p=0.550). Obstetric outcomes of the first subsequent live birth were also comparable between groups, including gestational age at delivery (p=0.336), birthweight (p=0.924), Apgar scores (all p>0.05), and mode of delivery (p=1.000); all deliveries occurred at term. Fetal growth restriction, preeclampsia, uterine atony, and oligohydramnios did not differ significantly between groups (all p>0.05). No cases of preterm premature rupture of membranes (PPROM), premature rupture of membranes (PROM), placenta previa, placenta accreta spectrum, or placental abruption were observed. Conclusion: In this single-center cohort, fertility potential and obstetric outcomes appeared generally favorable after both CHM and PHM. However, subgroup comparisons should be interpreted cautiously, as the limited sample size, particularly in the PHM group, may have reduced the statistical power to detect meaningful between-group differences.

  • Comparison of outpatient versus inpatient management after early stabilization in preterm prelabor rupture of membranes <34 weeks: Maternal safety, latency, and neonatal outcomes

    by Orhan Ay, Fethiye Şahin, Pelin Bahçeci, Deniz Taşkıran, Kazım Gezginç

    Objective: This study compared outpatient/home follow‐up after initial stabilization with inpatient management in singleton pregnancies with preterm prelabor rupture of membranes (PPROM) before 34 + 0 weeks of gestation, focusing on maternal safety, neonatal outcomes, latency, and healthcare utilization. Materials and Methods: In this single‐center retrospective cohort, singleton PPROM cases managed between January 2020 and December 2024 were evaluated. After stabilization, patients were classified as outpatient/home or inpatient. The primary outcome was neonatal intensive care unit (NICU) admission. Inverse probability of treatment weighting (IPTW) was used to reduce selection bias, and latency was assessed with landmark Kaplan–Meier analyses. Results: A total of 239 cases were analyzed (inpatient, n = 173; outpatient/home, n = 66). NICU admission was lower in the outpatient/home group (unadjusted risk ratio [RR] 0.56; IPTW RR 0.59, P = 0.007). The outpatient/home group had higher gestational age at delivery (median 36 vs. 31 weeks), shorter NICU stay (IPTW median difference, −4 days), and greater birth weight (IPTW median difference, +980 g). Placental abruption was more frequent in the outpatient/home group (IPTW RR 2.48). Landmark analyses showed markedly longer additional latency in the outpatient/home group (after 48 h: 43 vs. 3 days; after 7 days: 38 vs. 5 days; log‐rank P < 0.001). Conclusion: In carefully selected, initially stable PPROM cases before 34 weeks, outpatient/home management was associated with longer latency and lower NICU utilization. However, these findings should be interpreted cautiously because more stable patients might have been preferentially selected for outpatient follow‐up. With careful selection and close surveillance, outpatient/home management might be a reasonable alternative to reduce inpatient resource use.

  • Open Access

    Comparison of obstetric, maternal, and neonatal outcomes between preterm prelabor rupture of membranes at 34 + 0–36 + 6 weeks and term prelabor rupture of membranes at ≥ 37 weeks

    by Orhan Ay, Pelin Bahçeci, Deniz Taşkıran, Kazım Gezginç

    To compare preterm prelabor rupture of membranes (PPROM) at 34 + 0-36 + 6 weeks with term prelabor rupture of membranes at ≥ 37 weeks in terms of obstetric outcomes, maternal morbidity, and short-term neonatal outcomes. This retrospective cohort study included 646 singleton pregnancies diagnosed with PROM at 34 + 0 weeks or later in a tertiary care center between January 1, 2018 and July 30, 2025. Cases were grouped as PPROM at 34 + 0-36 + 6 weeks (n = 334) and term PROM at ≥ 37 weeks (n = 312). Maternal, obstetric, and neonatal outcomes were compared. Logistic regression was used to identify factors associated with NICU admission and the respiratory neonatal morbidity composite. Compared with term PROM, the 34 + 0-36 + 6 weeks PPROM group had longer antibiotic use, higher rates of tocolysis and antenatal corticosteroid administration and longer latency. Infectious maternal morbidity did not differ significantly between groups. However, PPROM at 34 + 0-36 + 6 weeks was associated with lower birth weight, a higher rate of NICU admission (25.7% vs. 6.7%, p < 0.001), and a higher rate of the respiratory neonatal morbidity composite (14.5% vs. 3.5%, p < 0.001). In multivariable analysis, PPROM at 34 + 0-36 + 6 weeks remained independently associated with NICU admission (aOR 5.05, 95% CI 2.90-8.76) and respiratory neonatal morbidity composite (aOR 5.91, 95% CI 2.82-12.37). PPROM at 34 + 0-36 + 6 weeks appears to be a distinct clinical entity rather than simply an earlier form of term PROM. Despite similar maternal infectious morbidity, its substantially higher neonatal morbidity burden supports individualized management and consideration of expectant management in carefully selected cases.

  • Open Access

    Clinical predictors of symptom and quality-of-life improvement with antimuscarinics in overactive bladder: a 12-month prospective cohort study in Türkiye

    by Mesut Alci, Deniz Taskiran, Bahar Ozdemir

    Antimuscarinic therapy is a first-line pharmacological treatment for overactive bladder (OAB), but individual response is highly variable. This study aimed


  • A Cross‐Sectional Study on Healthcare Workers' Knowledge and Attitudes Regarding Menstrual Cup Use in Turkey

    by Deniz Taşkıran

    Objective: Misconceptions surrounding menstrual bleeding and its management persist among the general population, often rooted in cultural norms and upbringing. However, such misconceptions can also be observed among healthcare professionals, who are expected to serve as advocates for public health. This study aimed to assess the knowledge and awareness of healthcare professionals in Turkey regarding menstrual cup use and associated topics. Patients and Methods: This cross‐sectional study was conducted between July 25 and August 10, 2025, using a self‐administered online questionnaire via Google Forms. The target population included female healthcare workers employed in various healthcare institutions across Turkey who voluntarily agreed to participate. A total of 309 participants were included through a simple random sampling method based on their institutions of employment. The data were collected using structured questionnaires completed by the participants. Results: Only 6.8% of participants reported ever using a menstrual cup. During menstruation, 97.7% of respondents reported using sanitary pads, whereas 5.2% reported using menstrual cups. Among menstrual cup users, 34.9% expressed satisfaction with the product, while 51.2% were uncertain. Additionally, 62.2% reported no problems during use, 55% stated they felt comfortable, and 60% believed menstrual cups to be environmentally friendly. Overall awareness of menstrual cups among healthcare professionals was low. Most users were physicians and had learned about menstrual cups primarily through social media and peers. Those who used menstrual cups reported lower expenditures on menstrual hygiene products. Conclusion: There is a clear need to improve awareness and knowledge about menstrual cup use among healthcare professionals. Enhancing educational efforts and providing accurate information may empower healthcare workers to offer better guidance and promote sustainable menstrual hygiene practices.

  • Open Access

    Can Albumin/Lymphocyte Ratio and MPV /Lymphocyte Ratio Serve as New Inflammatory Biomarkers in Patients With Hyperemesis Gravidarum?

    by Deniz Taşkıran, Orhan Ay

    Objective: This study aimed to evaluate the diagnostic utility of the albumin/lymphocyte ratio (ALR) and mean platelet volume/lymphocyte ratio (MPVLR) novel inflammatory markers not previously studied in hyperemesis gravidarum (HG) as potential biomarkers in patients diagnosed with HG. Patients and Methods: A total of 68 first‐trimester pregnant women with clinically diagnosed HG and 78 healthy pregnant controls were included. Systemic inflammatory markers including neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), albumin/fibrinogen ratio (AFR), fibrinogen/lymphocyte ratio (FLR), magnesium/lymphocyte ratio (MgLR), ALR, MPVLR, and systemic immune‐inflammation index (SII) were calculated and compared between the two groups. Results: Lymphocyte counts and ketonuria levels were significantly higher in the HG group. Conversely, ALR and MPVLR values were significantly lower in the HG group. MPVLR was identified as a potential diagnostic marker for HG with a cutoff value of 4.569, yielding a sensitivity of 54.4% and specificity of 44.9%. ALR demonstrated a cutoff value of 22.853 with a sensitivity of 61.8% and specificity of 38.5%. Conclusions: In contrast to the previous literature, PLR and NLR levels were not elevated in HG patients. However, ALR and MPVLR previously unexamined in this population were significantly lower, suggesting a potential role in HG pathophysiology. The findings underscore the complexity and dynamic nature of inflammatory responses in HG, warranting further investigation.